Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

52 results about "Graph dynamics" patented technology

Industrial innovation knowledge graph dynamic construction method based on large language model

The invention discloses an industrial innovation knowledge graph dynamic construction method based on a large language model, and belongs to the technical field of data processing. According to the method, multi-source heterogeneous data are integrated, cleaning, format conversion and standardization processing are performed, entities, relationships and attributes are automatically extracted by adopting a large model driven zero sample extraction technology, a high-precision triple library is constructed by combining entity embedding alignment and context anaphora resolution, and a knowledge graph is generated based on a graph database. According to the method, incremental data are captured in real time through a dynamic sensing layer, graph dynamic updating is achieved through an atomization updating mechanism, and data timeliness is guaranteed in combination with timestamps and multi-source verification. According to the method, the knowledge graph construction efficiency and coverage rate are improved, the defects that a traditional method is high in manual dependency degree, long-tail knowledge is missing, updating lags and the like are effectively relieved, and accurate support is provided for technical innovation decision making.
Owner:JILIN UNIVERSITY

Document intelligent writing and analysis system based on knowledge graph

The invention relates to the technical field of document processing, in particular to a knowledge graph-based document intelligent writing and analysis system, which comprises a graph dynamic updating module, an entity recognition and mapping module, a context connection analysis module, a semantic structure rearrangement module and a semantic coherence verification module. According to the method, the real-time data source is adopted, the knowledge graph is dynamically updated and expanded, synchronization of document content and the current information trend is ensured, noun phrases and entity distribution in a text are accurately analyzed through intelligent entity recognition, the accuracy of information extraction is improved, the coincidence degree of keywords between paragraphs is calculated, and synonymous entities are intelligently inserted, so that the information extraction efficiency is improved. According to the method, the context connection quality of the document is improved, the document structure is automatically rearranged according to the correlation of the content, the logic presentation of the information is optimized, the reading experience is enhanced, and the overall semantic consistency of the document is ensured and the interpretation ambiguity is reduced through complex semantic coherence verification.
Owner:WUDU INTERNET (XIAMEN) INFORMATION TECHNOLOGY CO LTD

Knowledge graph generation method based on multi-source data integration

The invention discloses a knowledge graph generation method based on multi-source data integration, and relates to the technical field of knowledge graph generation. The method comprises the following steps: collecting multi-format data, and performing cleaning, standardization and desensitization preprocessing to ensure that the data is integrated; using the fusion model to extract entities and relationships, and adapting to multi-source data types; similarity is calculated in combination with multi-dimensional features, and entity alignment disambiguation is achieved; carrying out weighted fusion on multi-source knowledge to construct a triple, and processing relation conflicts; evaluating the quality of the atlas through multiple indexes; triggering conditions are set, incremental updating and version management are adopted, and dynamic iteration of the atlas is guaranteed. According to the method, the multi-source data preprocessing quality is improved, the entity recognition and alignment precision is enhanced, relation conflicts are solved, and a high-quality time sequence knowledge graph is constructed; incremental updating is efficient and energy-saving, version management is traceable, and multi-field dynamic application requirements are met.
Owner:SHANGHAI HONGJI INFORMATION TECH CO LTD

Large-model-based medical knowledge graph dynamic construction method, system and equipment and medium

The invention provides a medical knowledge graph dynamic construction method, system and device based on a large model and a medium, and belongs to the technical field of medical informationization. The method comprises the steps that multi-source heterogeneous medical data is collected, and data cleaning, anonymization privacy processing and encryption security processing are carried out; performing medical entity identification and relation reasoning between medical entities on the processed medical data through a multi-modal large model, establishing a knowledge triple, and performing multi-modal feature alignment; performing IPFS fragmentation storage on the aligned knowledge triads, calculating hash values of the knowledge triads, performing chaining storage on the hash values by using a block chain, and performing dynamic verification and version management on the knowledge triads through hierarchical consensus and an intelligent contract; and establishing a semantic retrieval interface for the knowledge triad by using an SPARQL query tool to complete the construction of the medical knowledge graph. According to the method, efficient construction, dynamic updating and credible verification of the medical knowledge graph are realized, and the construction efficiency and safety of the knowledge graph are improved.
Owner:NORTH CHINA DIGITAL HEALTH TECHNOLOGY CO LTD

Likelihood-based dynamic graph prediction

Dynamic graph prediction can be achieved using a statistical model of graph dynamics that combines neural networks, including graph neural networks (GNNs), with maximum likelihood estimation. More specifically, in some embodiments, a GNN is used to compute graph embeddings representing an evolving graph at two different points in time, an additional neural network is used to create a forward image of the graph embedding associated with the first point in time, and a statistical distribution of the difference between the forward image and the graph embedding associated with the second point in time is evaluated. The GNN, additional neural network, and statistical distribution collectively constitute the statistical model, which can be trained on training data comprising pairs of graphs from one or more time series of evolving graphs. Such a statistical model may be employed, for example, to predict graph changes in a cybersecurity incident graph.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Geological archive structural integrity guarantee method and system based on graph dynamic maintenance

The invention discloses a geological archive structure integrity guarantee method and system based on map dynamic maintenance, and the method comprises the steps: obtaining an archive circulation path which is directly and indirectly connected with an archive for peripheral associated data marked as an undeletable archive, analyzing a potential breaking point in the path, and obtaining a risk region which may cause a data isolation problem; performing deep scanning on archive data in the risk area to obtain content features and historical circulation records of archives, judging whether the content features and the historical circulation records meet data accuracy standards or not, and determining a non-key archive list needing to be deleted; according to the non-key file list, analyzing the operation influence range of each file to be deleted, obtaining potential impact on the stability of the whole system after the file is deleted, and if it is judged that the information network integrity is damaged due to deletion, moving the file out of the deletion list; and for the finally determined deletion list, acquiring backup data and a flow path log of the archive, and updating the archive connection atlas through a dynamic maintenance mechanism to obtain a new information network structure.
Owner:深圳地质科技创新中心(深圳地质灾害应急抢险技术中心)

Short-term wind power cluster power prediction method based on error dynamic correction

The invention provides a short-term wind power cluster power prediction method based on error dynamic correction, and relates to the technical field of wind power generation prediction and control. The method comprises the following steps: calculating a convergence distance between wind power plants, and dynamically dividing a wind power cluster into a plurality of sub-clusters by adopting a clustering algorithm; performing power prediction on the wind power plants in the sub-clusters by using a graph dynamic attention network (GDAN) of a self-learning graph structure; in a low-power large-fluctuation period, introducing an error dynamic correction coefficient and performing multi-scale decomposition, and correcting a preliminary power prediction result by using a superposition result of correction coefficient components predicted by the GDAN; and combining prediction results of the sub-clusters, and outputting an overall power prediction value of the wind power cluster. Through dynamic clustering, graph structure self-learning and multi-feature decomposition correction strategies, the prediction precision, especially the robustness and flexibility under extreme working conditions, is significantly improved, and the method is suitable for 5-minute-level ultra-short-term prediction requirements of various scenes such as mountainous regions, plains and large-scale wind power clusters.
Owner:INNER MONGOLIA UNIV OF TECH

Dynamic generation method for network topological relation graph

The invention provides a network topology relation graph dynamic generation method, which belongs to the technical field of network topology, and comprises the following steps: starting an improved Tarjan strong connectivity component algorithm in each subnet partition to carry out loop detection, executing distributed loop verification on cross-subnet boundary nodes, collecting ARP table entries, routing table entries, OpenFlow flow tables and virtualization platform interface data, and sending the ARP table entries, the routing table entries, the OpenFlow flow tables and the virtualization platform interface data to each subnet partition; the method comprises the following steps: performing power spectrum analysis on an optical power monitoring point on optical network equipment to identify a wavelength channel occupancy state, reconstructing a wavelength routing path of a DWDM system, and performing two-stage submission on topological data acquired by distributed detection nodes by adopting a causal consistency protocol to synchronously generate a global unified network topological relation graph; the technical problems that the incremental updating efficiency is low and the cross-layer mapping relation is difficult to reconstruct in real time when the network topology dynamically changes are solved.
Owner:YUNNAN ELECTRIC POWER RUIXUNDA TECH & TRADE CO LTD

Automatic generation method of legal education based on legal knowledge and large language model

The invention belongs to the technical field of artificial intelligence and education, and discloses an automatic generation method of legal education based on legal knowledge and a large language model, which comprises the following steps: constructing a legal knowledge graph and a dynamic verification mechanism, integrating current legal provisions, judicial interpretation and typical cases to form a structured knowledge base, and generating a structured knowledge database; a law article-case-conflict point three-dimensional correlation model is designed and stored in a Neo4j graph database, and graph dynamic updating is achieved through butt joint with a national official website and a Chinese judgment document network API; a constraint module is generated through AI, legal knowledge graph nodes are embedded into a large language model Prompt, a LawBERT model is used for verifying the semantic similarity of generated content and law provisions, and illegal content is filtered in combination with a legal taboo word bank and a Drools rule engine. The AI generation constraint module ensures that the AI generation content conforms to the current legal provision as much as possible through the three-dimensional model, dynamic updating and man-machine checking, the problem of insufficient compliance is solved, and the legal preciseness is ensured.
Owner:GUILIN UNIV OF ELECTRONIC TECH

Multi-modal emotion recognition method based on graph dynamic fusion and mutual information maximization

The invention discloses a multi-modal emotion recognition method based on graph dynamic fusion and mutual information maximization. The method comprises the following steps: acquiring a multi-modal dialogue data set; constructing a multi-modal feature extraction module for encoding acoustic, visual and text features; constructing a graph structure module which is used for capturing a long-distance dependency relationship in a mode through a mode inner edge propagation feature and realizing feature interaction through an inter-mode edge; constructing a multi-modal dynamic fusion module combining an improved graph convolution layer and a dynamic gating mechanism; constructing a multi-modal mutual information maximization module for performing mutual information lower bound estimation and generating a fusion layer mutual information loss function; adding an emotion classifier to form an initial recognition model; training and optimizing the model; and performing online emotion recognition. The method is simple in implementation process, low in implementation cost and high in recognition precision, the feature complementarity is enhanced through graph structure modeling cross-modal dynamic interactive fusion and mutual information constraint, and the accuracy and robustness of dialogue emotion recognition can be remarkably improved.
Owner:CHINA UNIV OF MINING & TECH

Contextual graph dynamics for natural language to SQL conversion

A method for training a model to generate a structured query language (SQL) output using a natural language input includes receiving a training data set that includes natural language queries, corresponding SQL statements, and a corresponding database. The method also includes extracting query-specific schema from the corresponding database. Further, the method includes embedding the natural language queries and the query-specific schema to generate initialized embeddings, where each initialized embedding corresponds to a natural language query of the natural language queries, and where the corresponding SQL statement is one of the corresponding SQL statements; generating subgraphs based on the initialized embeddings and the natural language queries; training a graph neural network (GNN) using the subgraphs as inputs; generating, using the GNN, refined outputs based on the subgraphs; and training a transformer model using the refined outputs and the natural language queries to obtain a trained model.
Owner:DELL PROD LP

Intelligent writing support method and system based on semantic map

The invention discloses an intelligent writing support method and system based on a semantic map, and relates to the technical field of intelligent writing assistance. The intelligent writing support method comprises the following steps: initializing writing, determining a writing intention and a context, generating an initial context feature vector, constructing a basic semantic map model containing nodes and relation weights, and inputting the basic semantic map model into a real-time monitoring module for subsequent monitoring and adjustment. The real-time monitoring module analyzes user input, dynamically evaluates writing intention and context change, generates an intention-context state vector, transmits the intention-context state vector to the semantic map dynamic processing module, triggers semantic map dynamic expansion and updating, inputs an updated model into the writing suggestion generation module, generates personalized suggestions, and sends the personalized suggestions to the writing suggestion generation module; the model is optimized by using a graph neural network algorithm and then is output to the writing suggestion generation module, and the writing suggestion generation module looks for knowledge paths and determines writing thoughts and expansion directions by using the updated model, and presents writing suggestions in a visual mode to assist writing in combination with audience information adaptive styles and expression modes.
Owner:XIAMEN YUNQUE ZHILIAN TECHNOLOGY CO LTD

Intelligent water affair cooperative control method and system based on space-time diagram neural network

The invention discloses an intelligent water affair cooperative control method and system based on a space-time diagram neural network. The method comprises the following steps: firstly, constructing a static graph dynamic association logic diagram containing a pipe network physical topology; and then, inputting the multi-view image structure into a space-time diagram neural network, accurately predicting the liquid level and the flow of future key nodes, and particularly predicting the possible overflow risk. And finally, on the basis of the prediction result, constructing and solving a multi-objective optimization problem including multiple conflict objectives of minimizing pump station energy consumption, minimizing pipe network overflow quantity, balancing water inlet load of a sewage treatment plant and the like. Through the optimization, the system can generate a set of global cooperative control instructions for regulation and control facilities such as pumps and gates. Compared with the prior art, the method has the advantages that the prediction precision of the flood peak flow of the pipe network during rainfall can be remarkably improved, the mode conversion from passive first-aid repair to active regulation and storage is realized, urban waterlogging and sewage overflow events are effectively reduced, and stable operation of a downstream sewage treatment plant is guaranteed.
Owner:GUIZHOU WATER CONSTR ENG CO LTD

Dynamic feature-oriented micro-service application optimization resource management system and method

ActiveCN119203047AGuaranteed distribution efficiencyResource allocationResource Management SystemInternet traffic
A dynamic feature-oriented micro-service application optimization resource management system and method, comprising: a network-based load monitor, a load updater for sensing congestion and a resource efficient request emptier, when a micro-service application has load and call graph dynamics, the load monitor, according to the network monitoring data of each micro-service, updating the load updater for updating the load of the micro-service application according to the network monitoring data of each micro-service; analyzing to obtain a network flow and a network packet, and predicting to obtain a monitoring load through a linear regression technology in machine learning; the load updater calculates a real to-be-processed load of each micro-service according to a monitoring load and a blocking graph constructed through a calling relation and a calling sequence among the micro-services, and allocates a corresponding resource quantity to the real to-be-processed load; and the request emptier calculates the excessive load of each micro-service in the remaining QoS recovery time according to the real load of each micro-service output by the load updater and the current resource allocation information, and allocates excessive resources to each micro-service, thereby achieving the purpose of quickly recovering the QoS of the application. According to the method, under the condition that code modification does not need to be carried out on the micro-service application, the QoS target of the application can be quickly recovered under the dynamic nature of the micro-service application, and the resource allocation amount can be minimized to maintain the resource efficiency; and support can be provided for optimization resource management technology landing when load occurs in the micro-service application in the cloud data center and graph dynamics are called.
Owner:SHANGHAI JIAOTONG UNIV

Early fault early warning method and system based on dynamic evolution of complex industrial map

The invention relates to the technical field of fault early warning, in particular to an early fault early warning method and system based on dynamic evolution of a complex industrial map. The method comprises the following steps: constructing a multi-level industrial system knowledge graph based on acquired industrial equipment parameters; performing adaptive knowledge updating on the multilevel industrial system knowledge graph based on a graph dynamic evolution mechanism; constructing a joint reasoning framework based on the large model and the knowledge graph; optimizing a joint reasoning framework based on adaptive knowledge updating and a continuous learning mechanism; and carrying out early fault early warning on the industrial equipment by utilizing the optimized joint reasoning framework. According to the early fault early warning system based on complex industrial system graph dynamic evolution and large model joint reasoning, a dynamic knowledge graph and a large language model are fused, and early, accurate and interpretable industrial fault early warning is achieved.
Owner:YANTAI UNIV

Complex problem solving method based on discipline map dynamic updating and multi-agent collaboration

This invention belongs to the field of artificial intelligence technology and relates to a method for solving complex problems based on dynamic updating of subject graphs and multi-agent collaboration. The method includes: S1: Problem standardization processing; S2: Semantic encoding; S3: Initial subject set generation; S4: Candidate subject graph construction; S5: Initial formal subject graph construction; S6: Node and agent matching; S7: Output result acquisition; S8: State evaluation; S9: Subject graph dynamic update trigger judgment; S10: Subject graph dynamic update; S11: Termination condition satisfaction judgment; S12: Solution result generation. By introducing a dynamic updating of subject graphs and an agent collaboration mechanism, the method can adjust the subject graph in real time based on intermediate results during the reasoning process, ensuring that the subject graph always maintains a high degree of matching with the reasoning requirements, thereby significantly improving the reasoning stability, collaborative efficiency, and result accuracy in the process of solving complex problems.
Owner:BEIJING KNOWLEDGE ATLAS TECHNOLOGY CO LTD

A honeycomb array graph dynamic pre-scheduling method based on attack chain timing prediction

PendingCN122640252AAlgorithmInternet traffic
The application provides a honeycomb graph dynamic pre-scheduling method based on attack chain timing prediction, relates to the network security active defense technical field, and comprises attack chain timing sensing and feature preprocessing, dynamic attack graph construction, timing graph neural network attack chain path prediction and array graph pre-scheduling implementation. The application solves the multi-source asynchronous problem by fusing network traffic, host logs and threat intelligence and using timestamp alignment and current interpolation, constructs an attack graph which has timing state and topological correlation, and designs a joint prediction model which adopts a graph attention mechanism to capture topological dependence in space dimension and adopts a gated timing convolution to capture long-term evolution in time dimension.
Owner:INFORMATION & COMMNUNICATION BRANCH STATE GRID JIANGXI ELECTRIC POWER CO

An early fault warning method and system based on dynamic evolution of complex industrial maps

The application relates to the technical field of fault early warning, in particular to an early fault early warning method and system based on dynamic evolution of a complex industrial graph. The method comprises the following steps: constructing a multilevel industrial system knowledge graph based on obtained industrial equipment parameters; performing self-adaptive knowledge updating on the multilevel industrial system knowledge graph based on a graph dynamic evolution mechanism; constructing a joint reasoning framework based on a large model and the knowledge graph; optimizing the joint reasoning framework based on the self-adaptive knowledge updating and a continuous learning mechanism; and performing early fault early warning on industrial equipment by using the optimized joint reasoning framework. The early fault early warning system based on dynamic evolution of a complex industrial system graph and joint reasoning of a large model fuses a dynamic knowledge graph and a large language model, and realizes early, accurate and interpretable industrial fault early warning.
Owner:YANTAI UNIV

Transaction network behavior map dynamic early warning system

A transaction network behavior graph dynamic early warning system comprises a heterogeneous graph Transformer module used for extensible static graph embedding and a dynamic updater used for executing lightweight incremental graph embedding model decoupling, so that when node attributes are missing, the model can seamlessly return to a pure ID embedding mode in the training and inference process. In a static graph training stage, time complexity and memory occupation are realized, and a large-scale heterogeneous graph with billion-level nodes and edges can be expanded. In the incremental updating stage, a single-step matrix decomposition method is adopted to replace traditional gradient descent based on back propagation, the complete iterative optimization process of the model is avoided, and meanwhile the method is suitable for the production environment where GPU resources are limited or unavailable. The method does not depend on any special hardware for acceleration, can be executed on a common server CPU, and ensures real-time response and model updating of a dynamic interaction event.
Owner:SHANGHAI JIAOTONG UNIV

Product data map dynamic updating method and system based on ontology dependency relationship

The invention discloses a product data graph dynamic updating method and system based on an ontology dependency relationship, and the method comprises the steps: defining a dependency entity and a dependency relationship, and building a product data dependency relationship graph; on the basis of the product data dependency graph, the relationship between the added entity and other entities is connected according to the attribute key of the dependency relationship, the attribute key and the dependency entity thereof are added according to the dependency relationship, and the relationship between the entities and the dependency entity is connected; searching the relationship between the dependent entity and other entities, and finding out the associated dependent entity; finishing automatic adding of the product data atlas; on the basis of the product data dependency graph, entities to be deleted are put into a queue, adjacent dependent entities are sent into the queue every time, and whether the corresponding entities need to be deleted or not is determined according to edge in-degree; and completing automatic deletion of the product data atlas. According to the method, the workload of operation and maintenance personnel on map update logic maintenance is reduced, the method can adapt to map scale change, and modification on each entity update logic caused by ontology increase and decrease is reduced as much as possible.
Owner:GLOBAL ENERGY INTERCONNECTION RES INST CO LTD +2

Frequency-time fusion human motion prediction method

The invention discloses a frequency-time fusion human motion prediction method, and relates to the technical field of 3D human motion prediction. According to the method, the time domain representation and the frequency domain representation of the 3D human body motion are utilized at the same time for the first time to make up for the limitation brought by discrete cosine transform coding, on this basis, a novel model HIFT is provided, and the model can harmoniously integrate the frequency characteristics and the time domain characteristics, so that the prediction accuracy and reliability are improved; two modules, namely a frequency feature extraction module (FFM) and a time domain feature extraction module (TFM), are provided in an HIFT model, the frequency feature learning module FFM is formed by stacking multiple layers of perceptron, the time feature learning module TFM is constructed on the basis of a graph convolutional network, and in order to adaptively capture complex spatial dependence, the frequency feature extraction module FFM and the time domain feature extraction module TFM are used for adaptively capturing complex spatial dependence. The TFM provided by the invention is a double-graph dynamic convolution module, that is, the design of a double-graph convolution structure is adopted to better capture spatial features from time domain information, so that the defect of frequency domain information after DCT coding is made up.
Owner:CHONGQING UNIV OF TECH

Traffic flow prediction method based on masked autoencoder clustering and adaptive hybrid expert

PendingCN122369275AEngineeringTraffic flow
This invention provides a traffic flow prediction method based on masked autoencoder clustering and adaptive hybrid expert, belonging to the field of traffic flow prediction technology. The method first extracts deep spatiotemporal features of traffic data using a masked autoencoder and then explicitly decomposes nodes into two subsets—high-flow and low-flow—using K-Means clustering. Next, a dual-channel adaptive hybrid expert network is constructed. The high-flow expert uses a fusion pattern library and a self-similarity multi-graph dynamic graph convolutional network to capture complex spatial dependencies, while the low-flow expert uses a simplified spatial module. Both experts share a temporal feature encoder based on Transformer and temporal embedding. Finally, the prediction results of the two experts are fused and output. This invention achieves end-to-end collaborative optimization of explicit data decomposition and prediction tasks, effectively capturing the long-term and dynamic spatial correlations of traffic networks and significantly improving traffic flow prediction accuracy.
Owner:XIAMEN UNIV OF TECH

Carbon sink plotting method

The invention provides a carbon sequestration graph method. The method comprises the following steps: S1, collecting data; s2, carrying out gridding processing; s3, performing graph falling; and S4, performing graph dynamic processing. By means of the carbon sink falling graph method, dynamic monitoring can be conducted on carbon sinks, and visualization of carbon sink space distribution is achieved.
Owner:SHENZHEN SHUYAN JINHAN INTELLIGENT TECH CO LTD

System deployment diagram dynamic drawing method and device, electronic equipment and storage medium

The invention discloses a system deployment graph dynamic drawing method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining system architecture data of a target system, generating target JSON data according to the system architecture data, the target JSON data comprising node data and corresponding node attributes and edge data and corresponding edge attributes; the method comprises the following steps: creating an HTML (Hypertext Markup Language) page, introducing a JavaScript file of a preset visual library into the HTML page, and further loading target JSON data through the JavaScript file to obtain an initial network diagram; adding a click event and a corresponding interaction mode box for the initial network diagram through a visual library to obtain an interaction network diagram; and generating a corresponding animation effect according to the service flow of the interactive network diagram, and further rendering and displaying the animation effect on the interactive network diagram to obtain a system deployment diagram. The system management efficiency and accuracy are improved, and the method can be widely applied to the technical field of information.
Owner:CHINA TELECOM CORP LTD

Process knowledge graph dynamic fusion method, system, equipment and medium

The invention relates to the technical field of domain knowledge graph construction, and discloses a process knowledge graph dynamic fusion method, system, device and medium, and the method comprises the steps: building a process sub-graph according to the structure of a mode layer based on instance data in a process information file, feature vectors containing process information are generated for process nodes in the process sub-graphs; constructing a self-supervised feature aggregation model, taking each process sub-graph as training data, and enabling the self-supervised feature aggregation model to perform embedded representation and feature aggregation on the process sub-graphs through training; and based on the trained self-supervised feature aggregation model, carrying out embedded representation and feature aggregation on the new process sub-graph, and carrying out similarity matching and node merging updating through the embedded representation so as to obtain a dynamically fused process knowledge graph. According to the method, scattered process files with strong relevance can be fused into a large-scale unified and consistent professional domain knowledge graph.
Owner:SOUTHWEST CHINA RES INST OF ELECTRONICS EQUIP

Enterprise relation graph construction system

The invention relates to the technical field of enterprise graph construction, and discloses an enterprise relation graph construction system. An enterprise data acquisition module of the system acquires industry and commerce registration information, investment relation data and operation state change data of a plurality of enterprise entities in real time, and transmits the acquired enterprise basic data to an equity relation analysis module; the stock equity relation analysis module performs stock equity penetration calculation on the received enterprise basic data, generates a direct holding relation and an indirect holding proportion between enterprises, and forms a preliminary stock equity relation chain; the atlas generation control module constructs an enterprise relation network topology containing multiple layers of stock holding relations according to the preliminary stock right relation chain in combination with a preset enterprise association degree judgment rule; and the graph dynamic updating module continuously monitors newly-added data streams, and triggers node recombination and connection weight adjustment of the enterprise relation network topology when detecting that a specific enterprise equity structure is changed. According to the system, accurate construction and real-time updating of an enterprise relationship are realized, and multi-layer equity association is clearly presented.
Owner:BEIJING WEICHENG TECHNOLOGY CO LTD

Method and device for dynamically updating policy atlas

The invention discloses a policy graph dynamic updating method and device, and the method comprises the steps: obtaining a policy document, obtaining a historical related document according to the policy document, and judging whether the policy document forms an updated document of the historical related document or not based on the matching of a preset updating keyword rule base and / or based on the similarity calculation of a semantic vector; if it is determined that the updated documents are formed, extracting second knowledge of the updated documents through the first semantic model, collecting the updated documents, and accumulating vocabularies or semantic variations based on the updated documents; when the accumulated vocabulary or semantic variation meets a preset model training trigger condition, performing incremental training on the first semantic model based on the gathered update document and historical document to obtain a second semantic model, and replacing the first semantic model; and based on the second knowledge, updating the historical policy atlas to generate a target policy atlas, and replacing the historical policy atlas with the target policy atlas. According to the invention, automatic and intelligent dynamic updating of the policy knowledge graph is realized.
Owner:HUIZHI TECH (NANJING) CO LTD

A law shield AI intelligent case handling all-in-one machine system based on a large language model

The application discloses a kind of big language model-based legal shield AI intelligent case handling integrated machine system, it is related to legal artificial intelligence and judicial informatization technical field, the system includes integrated terminal equipment, case semantic modeling module, case knowledge engine, risk prediction module, big language model service interface and intelligent document generation module;The system constructs case semantic graph by multi-modal information fusion and graph neural network, carries out legal rule path matching and similarity reasoning based on case database, combines user context recognition and big language model multi-round generation capacity, outputs structured legal opinion and standard legal document, and realizes semantic graph dynamic update;The application improves the automation, structure and interpretability of case processing, and is suitable for legal aid, litigation assistance, judicial mediation and other intelligent case handling scenarios.
Owner:SHAANXI YUETU POLICE EQUIP MFG CO LTD

A medical knowledge graph dynamic construction method based on ontology guided named entity recognition and multi-hop graph reasoning and related devices

PendingCN122332579AGraph inferenceEntity type
This application provides a method and related apparatus for dynamically constructing a medical knowledge graph based on ontology-guided named entity recognition and multi-hop graph reasoning. The method includes: S1. acquiring medical text and loading a medical ontology; S2. performing ontology-guided named entity recognition based on the entity type hierarchy constraints of the medical ontology; S3. performing graph node fusion on the entity set based on a cross-sentence reference resolution algorithm; S4. generating a candidate set of relations for graph node pairs based on the relation type hierarchy of the medical ontology; S5. constructing an initial graph based on a graph neural network and performing multi-hop graph reasoning to infer implicit medical relations; S6. dynamically updating the medical knowledge graph based on a temporal window, outputting a medical knowledge graph containing multi-hop reasoning paths. This application also provides related apparatus corresponding to the method, including devices, electronic devices, computer-readable storage media, and computer program products.
Owner:ZHUHAI HENGQIN ALL-STAR MEDICAL TECHNOLOGY CO LTD

A real-time data binding and dynamic rendering method for graphic elements based on the Web

The present invention discloses a method for real-time data binding and dynamic rendering of graphic elements based on a Web terminal, including providing basic graphic elements through a set editor, users extending by inheriting basic graphics, providing converters to generate graphic elements for complex graphic elements, instantiating graphic elements to the editing area by dragging and dropping to form nodes and connect them, saving data that drives the editor in JSON format, initializing the data, and then adapting the rendered graph to the container size by calculating position information, the runner parsing the JSON, extracting the attribute mapping rules of the node configuration, establishing a mapping from the data source to the node rule information, and finding the node through rule matching after the data source is updated and updating the node variables bound in the rule, making the graph dynamic. The present invention simplifies the system configuration and monitoring process through a graphical interface, allowing non-professional programmers to participate in the design and maintenance of the automation system. It shortens the development cycle of product customization and improves the scalability of the product.
Owner:JIANGSU SHENRUIHUIYANG ENERGY TECH CO LTD