30 results about "Graph data model" patented technology

The invention relates to the technical field of side slope displacement monitoring, and discloses a side slope displacement monitoring method based on computer vision, which comprises the following steps: step 1, acquiring multi-temporal remote sensing image data of a monitoring area, constructing a time sequence based on a vegetation index, analyzing a disturbance trend of a sub-area, and generating a disturbance risk level map; 2, initial image feature points are extracted based on the slope monitoring image, the feature points are constructed into a graph structure according to the spatial proximity relation, and a graph data model with nodes connected with edges is formed; and step 3, based on the disturbance risk level graph and the graph structure, inputting the graph neural network model to carry out feature point stability modeling. The technical scheme of disturbance risk level map guidance, map neural network stability modeling and feature point stability score screening is adopted, and the technical effect that stable and traceable key feature points can be effectively recognized and screened out under the dynamic disturbance conditions of vegetation disturbance, climate change and the like is achieved.

The invention provides a parameter and data processing correction method and system for power grid energy management, and the method comprises the steps: constructing a double-layer graph data model of a power grid, which comprises an operation state view taking a bus as a node, an asset parameter view taking a power transmission branch as a node, and a topological incidence matrix connecting the two views; inputting the double-layer graph data model into a side node switching convolution encoder, and executing alternate bidirectional feature updating between an operation state view and an asset parameter view through a topological incidence matrix to generate potential feature representation; through decoding reconstruction and feature projection, physical consistency constraint verification and feature decoupling comparative learning are jointly executed, potential feature representation is mapped to a parameter subspace and a measurement subspace which are independent of each other, and contribution degrees of anomaly in the two subspaces are distinguished through comparative learning. Therefore, measuring equipment faults and branch parameter errors are separated and identified. And according to verification and comparison learning results, outputting a distinguishing result of the exception type and a corresponding operation and maintenance decision.

The present application belongs to the technical field of power transmission line structure health monitoring, and discloses a power transmission line tower group structure mechanics response and multi-source remote sensing parameter fusion analysis method based on graph neural network. The method aims at the problems of existing finite element simulation modeling complexity, incomplete sensor monitoring, lack of physical mapping of multi-source remote sensing data and tower mechanics response, acquires and pre-processes tower structure parameters and multi-source remote sensing data, and constructs a tower group graph data model; taking span as a unit, combining conductor mechanics equation to calculate load and unbalanced tension, building a graph neural network model integrated with tower axial force and bending moment bearing capacity physical regularization constraint; after training by historical working condition data, inputting new remote sensing and meteorological data to reconstruct tower group mechanics response field, generating risk early warning according to safety threshold. The present application realizes deep fusion of mechanics mechanism and remote sensing data, quickly and accurately reconstructs tower group mechanics response field, and outputs the results conforming to the structure mechanics balance law, thereby providing technical support for power transmission line health monitoring.

A reasoning implementation method and apparatus based on a labeled property graph data model, and a computer device. Specifically, the reasoning implementation method based on a labeled property graph data model comprises: extracting a keyword included in a user inquiry and a semantic property associated with the keyword (S101); on the basis of the semantic property, converting the user inquiry into a second inquiry (S102); and on the basis of the second inquiry, providing a reasoning answer based on a labeled property graph data model (S103). The reasoning implementation method based on a labeled property graph data model can extend semantics of a labeled property graph model, so as to use the labeled property graph data model to provide more accurate and rational reasoning answers to user inquiries; and the disclosed method is relatively simple and fast to implement.

The application provides a parameter and data processing correction method and system for power grid energy management, comprising constructing a double-layer graph data model of the power grid, including an operating state view taking a bus as a node and an asset parameter view taking a power transmission branch as a node, and a topological correlation matrix connecting the two views; inputting the double-layer graph data model into an edge node switching convolutional encoder, performing alternating bidirectional feature updating between the operating state view and the asset parameter view through the topological correlation matrix, and generating a latent feature representation; through decoding reconstruction and feature projection, jointly performing physical consistency constraint checking and feature decoupling contrast learning, for mapping the latent feature representation to mutually independent parameter and measurement subspaces, and distinguishing the contribution degree of the anomaly in the two subspaces through contrast learning, to separate and identify measurement device faults and branch parameter errors; and outputting the distinguishing result of the anomaly type and the corresponding operation and maintenance decision according to the checking and contrast learning results.

The present application provides a kind of compact sandstone gas reservoir multi-layer combined production capacity prediction method, method includes the following steps: based on the construction of the graph data model including operating variables, static parameters, dynamic data of spearman correlation coefficient, through Internet of Things sensor real-time update node characteristics, adopt dynamic graph mechanism to revise adjacent matrix weight;S2: utilize CNN network model and LSTM network model to extract multi-modal data features, after PCA dimension reduction, input OV-GCN model, realize graph structure modeling in combination with GAT and Transformer, output capacity distribution, water cut and interlayer interference prediction value;S3: the prediction result is input into NSGA-II multi-objective optimization model, with the maximum capacity, cost minimization, interference balance as target, combined with Eclipse numerical simulation verification, generate fracturing parameter Pareto optimal solution set.According to the present application, the information in the well log image, production time series data and structured data can be deeply mined, and the complex correlation between gas reservoir capacity and various data can be accurately captured.

The invention discloses a graph database storage method, device and equipment based on Hash mapping and a medium, a graph database comprises a storage engine, the storage engine comprises a plurality of storage areas which are arranged on a disk and are mutually independent in logic, and the storage areas comprise Hash index areas. The Hash index area comprises a storage file managed by a Hash index structure, and the method comprises the following steps: adding a write-in request for the graph database into a pre-write log queue; analyzing the write-in statement to obtain write-in statement data; inserting to-be-written data into a variable hash table in a memory through log structured merging-hash; and when the table is full of data, writing the storage data into an immutable storage file on the disk layer by layer. According to the embodiment of the invention, the performance is stable and predictable; high write throughput is kept; the efficiency of complex traversal query is greatly improved; efficient storage of the storage structure is achieved, and efficient support of point and edge query and traversal operation under a graph data model is achieved.

The process of generation a knowledge graph for Thai law according to this invention consists of the following steps: data collection, text extraction, data chunking and embedding, ontology design, graph data model ingestion, and integration. A unique feature of the ontology design step is that it creates the structure for representing and linking legal concepts within the knowledge graph. This process includes extracting legal content, defining concepts and developing classes, specifying properties and developing relationships, developing hierarchy, and contextual alignment, all of which are integrated together.

The application provides a data model conversion method and device, equipment and medium, and relates to the technical field of data processing. The method comprises the following steps: determining business data used for constructing a graph data model according to a business scenario; determining a business entity relationship corresponding to the business data according to a relational data model of the business scenario; and constructing the graph data model according to the business entity relationship; wherein a node layer of the graph data model comprises a query layer and a business layer, and the nodes of the graph data model comprise query nodes located in the query layer and business nodes located in the business layer, the query nodes correspond to multiple business query dimensions, and the business nodes correspond to business query data. Thus, the relational data model of the business system is converted into the graph data model, and the query efficiency of data query based on the data model is improved.

The invention relates to a research and development cost collection method, system and device based on an intelligent robot and a medium. According to the method, sensor equipment carried by an intelligent robot autonomously moves in a new material research and development environment, research and development activity data are collected in real time, and the data are uploaded to a research and development project management platform; constructing an attribute graph data model based on data received by the platform, taking a formula version, a sample entity and a test report as nodes, and taking a derivative relationship and a cost allocation weight as edges; backtracking the traversal model from a target sample node by adopting a reverse breadth-first search algorithm to obtain a traversal path and node association relationship, and calculating a cost allocation coefficient in combination with a cost allocation weight so as to accurately allocate the amortization fee and the depreciation fee to formula batch nodes; finally, the labor cost, the depreciation cost and the amortization cost are collected based on the distribution result, accurate collection of the research and development cost in a complex pedigree scene is achieved, the cost allocation error caused by a traditional linear structure is effectively avoided, and the collection accuracy and efficiency are improved.

A computer-implemented method for generating a graph database includes generating a prompt for input to a large language model (LLM) based on user input and stored metadata. The LLM is used to extract graph metadata from the prompt, generate a knowledge graph based on the graph metadata and additional sources of data, and further generate a graph data model including both structured and unstructured data using the knowledge graph. A graph platform is used to generating a graph using the graph data model.

The present application relates to the field of power system informatization technology, in particular to a kind of power grid multi-source heterogeneous data panoramic modeling and dynamic characterization method, mapping rule of SG-CIM model to graph data model is established, combined with the vertex mapping based on hierarchical inheritance, the edge mapping and attribute storage based on class member complexity and the multiple of association relationship, the primary equipment of power grid is abstracted as node, the connection relationship between equipment is abstracted as edge, and the connection point and terminal class are simplified and reconstructed, the unified power grid topology graph model covering equipment node, container node, connection node is constructed;The connection relationship of power grid is dynamically characterized by three types of edges of connection relationship, subordinate relationship, aggregation relationship, and a unified power grid graph data model is established.Compared with the prior art, the present application realizes the standardization integration and cross-business dynamic mapping of power grid heterogeneous data, significantly improves the efficiency and accuracy of power grid topology analysis, and provides a unified and efficient data basis for power grid panoramic business collaboration and intelligent decision-making.

The invention provides a risk disposal method and device based on an exposed surface knowledge graph, equipment and a storage medium, and the method comprises the steps: obtaining the asset information and the configuration information of assets, building the exposed surface knowledge graph through a graph data model according to the asset information and the configuration information, and carrying out the construction of the exposed surface knowledge graph. Association between unified and dispersed data and recorded data can be standardized; on the basis of the preset exposed surface detection rule, the exposed surface knowledge graph is traversed, the target exposed path with the risk is recognized, multi-table association query is not needed, and the analysis response efficiency can be improved; according to the target exposure path, the processing tasks are automatically generated and dispatched, the generation and distribution of the processing tasks do not need manual intervention, the efficiency is improved, and omission is avoided.

This invention belongs to the field of power transmission line structural health monitoring technology, and discloses a method for fusing and analyzing the structural mechanical response of power transmission line tower groups with multi-source remote sensing parameters based on graph neural networks. This method addresses the problems of complex finite element simulation modeling, incomplete sensor monitoring, and lack of physical mapping between multi-source remote sensing data and tower mechanical response in existing methods. It acquires and preprocesses tower structural parameters and multi-source remote sensing data to construct a graph data model of the tower group; calculates loads and unbalanced tensions using span as a unit and combining conductor mechanics equations, and builds a graph neural network model incorporating physical regularization constraints of tower axial force, bending moment, and bearing capacity; trains on historical operating data, inputs new remote sensing and meteorological data to reconstruct the mechanical response field of the tower group, and generates risk warnings based on safety thresholds. This invention achieves deep fusion of mechanical mechanisms and remote sensing data, rapidly and accurately reconstructs the mechanical response field of the tower group, and outputs data conforming to structural mechanical equilibrium laws, providing technical support for power transmission line health monitoring.

The invention provides a comprehensive energy intelligent management and control platform data analysis method and device, equipment and a medium, and belongs to the technical field of data processing, and the method comprises the steps: constructing a graph data model corresponding to each moment according to the operation data of power grid equipment at N moments; according to the graph data model corresponding to each moment, determining fusion space-time sequence features; dynamically predicting the operation data of the power grid equipment after the N moments according to the fused space-time sequence features to obtain a predicted value of the power grid equipment; and determining a power equipment control strategy according to the predicted value of the operation data. According to the comprehensive energy intelligent management and control platform data analysis method and device, the equipment and the medium provided by the invention, accurate prediction and intelligent decision making are realized, and the accuracy of real-time prediction can be improved.

This paper describes a technique for concurrently populating entries in compressed sparse row (CSR) encodings of heterogeneous graph edge types. In an embodiment, the computer obtains a mapping from a relational schema to a graph data model. The relational schema defines a vertex table corresponding to vertex types in the graph data model, and an edge table corresponding to edge types in the graph data model. Each edge type is associated with a source vertex type and a destination vertex type. For each vertex type, a persistent identifier sequence of vertices is obtained. Based on the mapping, for each edge type's CSR representation, a source array is populated, sorted for vertices identical to the persistent identifier sequence of the source vertex type, based on the edge counts originating from the edge type of the source vertex type. For the CSR, the computer populates a destination array in parallel based on the mapping, the destination array containing canonical offsets as sequence positions within the persistent identifier sequence of vertices.

This application discloses a network behavior analysis method, apparatus, electronic device, and storage medium. Based on acquired raw data, the method precisely classifies and judges the metadata and operation commands in the raw data to generate a first row of graph data. The first row of graph data is then stored in a graph-structured manner to generate a second row of graph data. The second row of graph data includes nodes and edges; nodes indicate entity objects in the metadata, and edges indicate operation commands between entity objects in the metadata. The second row of graph data is then identified to obtain abnormal behavior analysis results. Thus, by combining the entity objects and operation commands in the raw data to construct a graph data model, the relationships between entity objects can be better represented. Furthermore, by using graph computing technology and the graph data model to identify abnormal behavior analysis results, the accuracy and efficiency of network abnormal behavior detection can be improved.

The invention discloses an object-oriented power grid topological graph data modeling method and a related device. The method comprises the steps of collecting original data of a power grid structure and original data describing power grid measurement; and according to the original data of the power grid structure and the original data describing power grid measurement, a power grid topological graph instance is constructed based on a node class of a preset power grid graph data model, an edge class of the power grid graph data model and an edge constraint of the power grid graph data model, and the method and the related device can perform graph data model modeling for power grid data.

The invention relates to the technical field of geological modeling and three-dimensional visualization, and discloses a method for generating a three-dimensional geologic body model based on interactive editing of a two-dimensional profile map, and the method comprises the following steps: S1, initialization and data input: receiving reference two-dimensional profile map data, model space positioning data and auxiliary constraint data; s2, preprocessing and standardizing profile data; s3, performing interactive interpolation and connection between profiles; s4, performing external inference and model closing; and S5, outputting and applying the model. Through a three-dimensional visual interaction interface and an interactive editing function, a user is supported to preview a three-dimensional section model in real time in the modeling process, control point adjustment, grid local modification and other operations are carried out on a three-dimensional curved surface generated by interpolation, the model form can be flexibly optimized according to actual geological cognition, and the modeling efficiency is improved. The problem that the model is separated from the actual geological condition due to lack of user participation in the traditional modeling process is avoided, and the fitting degree of the model to geological details is improved.

The invention relates to the technical field of real estate registration businesses, and discloses a real estate registration business modeling method based on graph data, which comprises the following steps: step 1, vertexes, edges, labels, edge types and attributes in the graph data are defined, and the vertexes are used for storing entity objects, are uniquely identified by vertex identifiers, and can have a plurality of labels; the edges are used for connecting the vertexes, are directed edges and pass through the quaternion lt; starting points, edge types, edge sorting values and end points gt; the unique identifier has a unique edge type and an edge sorting value; the labels are composed of predefined attributes and used for describing the vertexes. According to the method, entities such as rights, people, real estate units and real estate registration in real estate registration business are expressed by using point and line relationships, mapping and conversion logic from the relational data model to the graph data model is innovatively constructed, and the problems that the relational data model is low in query efficiency and a graph database is difficult to update based on existing business logic are solved.

The invention relates to a generator excitation system safety early warning method and device based on multi-modal data fusion, and the method comprises the steps: calculating the attention weight of a data node at a current time step and a spatial position based on a preset heterogeneous graph data model, and generating a fusion feature vector containing multi-source data; simulating a multi-physical field interaction process of the generator excitation system under a preset environment condition by using a preset multi-physical field digital twin model, and determining an environment disturbance adaptive compensation action meeting a preset optimal condition; and detecting the fault risk of the generator excitation system by using the knowledge graph so as to trigger the safety early warning of the corresponding level of the generator excitation system according to the fault risk. According to the method, deep fusion of multi-source heterogeneous data is realized, a nonlinear coupling relationship among the data is captured, early warning model parameters are dynamically adjusted according to environmental parameter changes, the influence of environmental interference on an early warning result is reduced, a fault propagation path model is established, and progressive fault occurrence is predicted in advance.

The specification discloses a business scenario data processing method, system and electronic equipment, which is more convenient, fast and efficient for management, query and application of business scenario record data. The method comprises: acquiring business source data and business demand information under a current business scenario; extracting a plurality of demand items and determining the association relationship between the plurality of demand items according to the business demand information; constructing a graph data model according to the plurality of demand items and the association relationship between the plurality of demand items; and processing the business source data based on the graph data model to generate business graph data with a data structure conforming to the graph data model. The system comprises a data information acquisition module, a demand analysis module, a graph data model creation module and a source data processing module. The electronic equipment comprises a memory, a processor and a computer program stored in the memory and executable on the processor to execute the business scenario data processing method.

The application relates to a dynamic modeling method of an electronic chart product, and belongs to the technical field of marine surveying and mapping. The method realizes unified management of the semantic structure of diversified electronic chart products by constructing an extensible concept dictionary and an element catalog; XSD files are generated based on the element catalog, and a relational database structure suitable for a general geographic information platform is automatically created; and visual rendering conforming to the electronic chart standard is realized through graphic expression catalog. The application realizes compatible adaptation of the electronic chart data model and the basic geographic information platform, solves the problems of loss of hierarchical structure, non-standard symbolization, high manual configuration cost and the like in the application of the electronic chart data in the traditional geographic information system, has the advantages of flexible modeling, high automation degree and strong expansibility, and can effectively improve the fusion and sharing of various marine space information.

This document relates to parallel efficient techniques for constructing and maintaining a main memory CSR based graph index in an RDBMS. Techniques for concurrently populating entries in CSR coding of heterogeneous graph edge types are disclosed. A computer obtains a mapping of relationship patterns to a graph data model. The relationship pattern defines a vertex table corresponding to vertex types in the graph data model, and an edge table corresponding to edge types in the graph data model. Each edge type is associated with a source vertex type and a target vertex type. For each vertex type, a persistent sequence of identifiers for the vertices is obtained. Based on the mapping, for the CSR representation of each edge type, a source array is populated, which is based on a count of edges of an edge type originating from the source vertex type, for the same vertex ranking as the persistent identifier sequence of the source vertex type. For the CSR, the computer populates a destination array in parallel based on the mapping, the destination array containing a canonical offset of sequence positions within the sequence of persistent identifiers as vertices.

The invention provides a PCDN management control flow suppression method, device and equipment and a storage medium, relates to the technical field of network communication, and is used for realizing high-precision identification and low-cost and low-accidental-injury precise suppression of PCDN management control flows. The method comprises the following steps: receiving a traffic data set of suspected PCDN users drained from each broadband access server to a centralized broadband access server; constructing a graph data model based on each IP address and a communication session between each IP address in the traffic data set of the suspected PCDN user; performing deep analysis on an interaction mode among nodes in the graph data model by using a graph convolutional network, and identifying a potential PCDN management and control address; performing deep analysis on behavior characteristics of flow generated or associated with each potential PCDN management and control address by using a multi-layer perceptron, and identifying PCDN management and control flow; and performing flow suppression on the PCDN management control flow.

This application relates to a data processing method, apparatus, device, storage medium, and computer program product. The method includes: acquiring characteristic parameters of each power device in a power system; determining a graph data model based on the characteristic parameters, the graph data model including device nodes representing each power device and electrical nodes storing electrical data of each power device; obtaining state parameters of each power device based on the characteristic parameters; dividing the graph data model into multiple sub-graph data models based on the state parameters; identifying target device nodes with abnormal electrical data in each sub-graph data model; identifying other device nodes connected to the target electrical node along with the target device node; obtaining target electrical data of the target device node based on the electrical data of the other device nodes; and obtaining target characteristic parameters of the power system based on the target electrical data. This method can improve the efficiency and accuracy of generating target electrical data in ultra-large-scale power systems.

The embodiment of the invention provides a data processing method and device, equipment, a storage medium and a program product, and relates to the field of big data. The method comprises the following steps: extracting node coupling data from a plurality of nodes based on a preset synchronization strategy; wherein the synchronization strategy is used for indicating data extraction time of different nodes, and the node coupling data comprises an original data set representing a calling or dependency relationship between the nodes; analyzing the node coupling data and the node code library according to a predefined analysis format to obtain uniformly formatted data; performing association analysis on the uniformly formatted data according to a graph data model to obtain graph data for representing a node dependency relationship; according to the graph data, the incidence relation between the nodes is determined, and the incidence relation is used for node fault analysis. According to the method provided by the invention, the mining efficiency and accuracy of the complex node dependency relationship in the distributed system are improved, each node is conveniently and effectively tracked, and how the fault diffuses in the system is understood.

This invention discloses a method for building a multimodal fusion-based fault diagnosis model for power transformers, belonging to the field of fault diagnosis model technology. This method deploys multimodal sensors to synchronously acquire transformer vibration and oscillation wave signals. After preprocessing the signals using Empirical Mode Decomposition (EMD), it jointly models the time-domain, frequency-domain, and oscillation wave parameter features. The core of this invention lies in constructing a graph data model based on physical topology and introducing a cross-modal Transformer network for deep feature fusion to capture the complex correlations between different modes. Furthermore, this method utilizes a variational autoencoder (VAE) to achieve unsupervised diagnosis and data augmentation for unknown faults; by constructing a power transformer fault knowledge graph (KG) and using a TransE model for entity embedding, it achieves accurate fault severity assessment and lifespan prediction of power transformers.

The invention discloses a network information security assessment method and system based on big data analysis, and particularly relates to the technical field of data analysis. The method comprises the following steps: collecting multi-source heterogeneous security data, extracting entity multi-dimensional feature information, and constructing a graph data model containing semantic tags; for the entity confusion problem under the shared identifier, an identity recognition and node splitting strategy based on a probabilistic graph model is adopted, and refined recognition and graph structure reconstruction of entities are achieved; according to the method, path analysis is performed in combination with behavior semantic tags, potential attack chains and abnormal behaviors are effectively identified, a structured security assessment report is finally generated, risk level division is performed on entities and assets, and targeted response suggestions are provided, so that the accuracy of entity identification and the precision of attack path analysis are remarkably improved, the false alarm rate is reduced, and the security assessment efficiency is improved. And the intelligent level and the practicability of the network security evaluation system in a complex environment are enhanced.

The application discloses a kind of equipment health state evaluation methods based on knowledge graph multi-set pooling, belongs to equipment health state evaluation technical field.It includes the following steps:1, equipment health state data model construction;2, knowledge graph multi-set pooling network model construction;3, knowledge graph node dimension feature extraction;4, knowledge graph multi-head attention multi-set pooling;5, training and classification.The present application is aimed at the problem that existing health state evaluation method cannot effectively fuse time feature and space feature, proposes a kind of equipment health evaluation method based on knowledge graph multi-set pooling, utilizes time sequence knowledge graph to carry out deep fusion for equipment component and index information into structured graph data model, and extracts time feature and space feature in it by knowledge graph multi-level pooling, improves the accuracy of health evaluation, provides technical support for realizing equipment predictive maintenance.