221 results about "Graph generation" patented technology

The invention relates to a system (100) for generating real-time causal reasoning insights in real time. The system (100) comprises a global causal graph creation module (101), a natural language query processing module (102), an information extraction module (103), a query-centric subgraph generation module (104), and an adaptive causal reasoning engine (105). The queries from users are processed to identify relevant causal relationships in the global causal graph. The adaptive causal reasoning engine (105) refines the insights iteratively based on user feedback, improving accuracy. The system (100) converts technical insights into structured narratives. A visualization module presents causal relationships through graphs and charts. The feedback mechanism allows users to correct errors and adjust outputs, facilitating user-driven data analysis and causal reasoning, delivering actionable insights for a variety of applications.

This application discloses a creative composition generation method, apparatus, device, storage medium, and product, relating to the field of artificial intelligence technology. The creative composition generation method includes: acquiring and extracting input sketch information to generate a structured sketch fingerprint; acquiring and extracting input semantic prompt information to generate a structured semantic fingerprint; constructing an intent alignment matrix based on the structured sketch fingerprint and the structured semantic fingerprint to characterize the association between sketch elements and semantic entities; and driving a preset image generation model to perform a composition generation process according to the intent alignment matrix and preset innovation coefficients. This application solves the technical problem in the prior art where it is difficult to simultaneously consider both precise spatial information of the sketch and rich semantic creative prompts, resulting in output creative images that are either too rigidly bound to the sketch and lack creativity, or deviate from the sketch's constraints and have poor practicality.

The application discloses a circuit pre-training method and device based on a graph neural network and electronic equipment, comprising the following steps: for a large-scale circuit, a circuit network graph is constructed, a random walk road is generated, and the road is used as a sample for model training; a node2vec model is trained using the road sample; a model with the minimum loss function value is selected as an optimal model; and the optimal model is loaded, and representation vectors of all nodes are output and saved. In the application, the node2vec pre-training model of the graph neural network is used, the information of a long-distance standard unit is fully absorbed to absorb local circuit structure features, deep representation of nodes is automatically learned from the circuit structure, and tedious manual feature engineering is avoided, thereby providing high-quality representation vectors for a downstream model. The node representation learned by the node2vec model is a task-independent general feature, can be flexibly applied to various downstream tasks, and provides support for subsequent circuit analysis and optimization design work.

This application discloses a master data integration method, apparatus, electronic device, and storage medium. The method includes: acquiring multi-source heterogeneous master data; standardizing and cleaning the multi-source heterogeneous master data to generate multiple block keys and inverted index lists, and constructing a candidate comparison set; extracting and normalizing the multi-level similarity of each pair of candidate records in the candidate comparison set, and constructing a standardized feature vector; inputting the standardized feature vector into a learning model to obtain the matching probability of each pair of candidate records, and making hierarchical decisions based on the matching probability and at least one matching threshold; constructing an undirected matching graph and generating entity clusters from the undirected matching graph; determining the data quality score of each field of each candidate record within the entity cluster, determining the optimal value of each field based on the data quality score, and generating the integrated master data. This application significantly reduces the number of comparisons, improves comparison efficiency, eliminates the need for manually writing matching rules, and can adapt to various data types and new data sources.

The application discloses a semantic segmentation method and device based on depth information position coding guidance, and the method comprises the following steps: acquiring an image to be processed; inputting the image to be processed into a pre-trained spatial depth perception auxiliary network to extract multi-scale features, and obtaining corresponding depth feature maps according to the multi-scale features; generating multi-scale feature vectors according to the multi-scale features and the corresponding depth feature maps; processing the multi-scale feature vectors by using a multi-scale attention mechanism and a feedforward neural network to obtain final features; performing fusion processing on the final features, and performing semantic segmentation on the processed fusion features to obtain a semantic segmentation map; in this way, the depth information is embedded in the features, the calculation cost is reduced, and the image segmentation performance is improved.

The application discloses a kind of deep fake detection and tracing systems for network phishing attack, including the following steps: multi-source data acquisition module is used to form pre-processing multi-source data;Feature extraction module is used to form associated feature data;Association graph generation module is used to build fake content association layer and phishing propagation association layer, form unified attack association graph;Path screening construction module is used to identify effective relationship section, and build calculation path set;Similarity calculation backwrite module is used to perform PathSim similarity calculation, form the unified attack association graph after state update;Iterative calculation update module is used to re-execute PathSim similarity calculation, form candidate association result;Back-checking analysis output module is used to verify based on fake evidence and propagation evidence, and convert the candidate association result after verification into attack analysis result.The application improves the accuracy of deep fake content identification in network phishing attack scenario.

This invention discloses a traffic flow prediction method and system based on Transformer, belonging to the fields of intelligent transportation and deep learning technology. Addressing the technical problems of existing traffic flow prediction models, such as difficulty in simultaneously considering long-term and short-term dependencies, inability of static road network topology to characterize dynamic spatial heterogeneity, and poor modeling performance of spatiotemporal feature coupling, this invention proposes a multi-timescale adaptive graph attention Transformer model. This method first reconstructs the original traffic data at low, medium, and high time scales, and then aggregates spatiotemporal features through a temporal convolutional network and a compressed excitation network. Next, an adaptive data graph generation module learns node embedding vectors to generate an adaptive adjacency matrix that integrates static topology and dynamic associations. Finally, an encoder incorporating temporal one-dimensional convolutional multi-head attention and spatial graph attention, and a decoder integrating causal convolution and temporally gated convolution, are constructed to achieve high-precision multi-step prediction of traffic flow. This invention effectively captures the spatiotemporal dependencies of traffic flow, with prediction accuracy and generalization superior to mainstream models, and can be widely applied to urban intelligent traffic management, dynamic path planning, and traffic congestion mitigation scenarios.

A processor-implemented method for indoor navigation map generation with accessibility information is provided. The method includes collecting a plurality of colored point cloud maps by utilizing both mobile and stationary mapping systems. The map can be aligned with an outdoor map if the GNSS or the global coordinate is available. The method also includes performing semantic segmentation based on at least implicit representation and synthetic data- aided training network for generating a plurality of structural elements and a plurality of functional elements. The method also includes performing topology-aided structural modeling by generating a structural building information modeling (BIM) using topology information at a plurality of levels of topology and by automatically applying a plurality of levels of topological constraints associated with the structural elements. The method also includes performing parametric modeling by detecting a plurality of functional objects in the functional elements using one or more simulated datasets including simulations of lighting, and environmental conditions.

The application discloses a patent theme graph generation method and system based on deep semantic hierarchical clustering, comprising: obtaining a patent literature set PT to be generated into a patent theme graph; using a patent deep semantic representation model to perform semantic coding on each patent literature in the patent literature set PT, and obtaining a semantic representation vector matrix V={v1,...,v N}; inputting the semantic representation vector matrix V into a hierarchical clustering algorithm to obtain a hierarchical clustering tree structure corresponding to the patent literature set PT; generating a corresponding theme description for each non-leaf node on the hierarchical clustering tree structure; and combining the generated theme description and the hierarchical clustering tree structure into a patent theme graph with an upper and lower hierarchical structure. The patent theme graph generation method and system can help users quickly mine upper and lower hierarchical relationships of patent literatures at a theme level, meet the analysis needs of users for large-scale patent information, and improve the efficiency of patent analysis of users.

The application discloses a kind of cross-version vulnerability identification systems based on depth map neural network, comprising: multi-version code metadata acquisition module, for collecting multiple versions of software source code and parsing generation multi-version code metadata set;Multi-version code graph generation module, for constructing multi-version code graph set;Characteristic representation matrix generation module, for generating the characteristic representation matrix of multi-version code graph;Depth map neural network modeling module, for using GLEM model, obtains the embedding matrix of each node;Potential vulnerability node identification module, for identifying the potential vulnerability node set across version;Result output module, for outputting cross-version vulnerability identification result and generating detection report.The application adopts depth map neural network and cross-version modeling method, realizes multi-version vulnerability automatic identification, with the advantages of strong intelligence, high adaptability, detection precision.

This application discloses a document analysis method, apparatus, device, and medium based on a retrieval-enhanced generation framework, applied in the field of document analysis technology. The method includes: extracting target information from parsed information obtained from parsing several unstructured documents to construct an initial knowledge graph; the target information includes table information, text information, relationships between table information and text information, and relationships between table information; the nodes in the initial knowledge graph include table-related nodes determined based on the table information; performing entity linking and node relationship reasoning on the initial knowledge graph to obtain a target knowledge graph; the entity linking operation includes identifying target entities pointing to the same real-world object in different documents to establish cross-document links; retrieving the target subgraph of the query request from the target knowledge graph, using a large language model and generating query results based on the target subgraph to achieve the analysis of unstructured documents. This method can improve the document analysis results and enhance accuracy.

The application relates to a method and system for mining and analyzing the correlation of clinical comorbidity of discharged patients. The method comprises the following steps: constructing an individual diagnosis and treatment narrative graph for each patient according to the discharge medical record text, generating a time sequence transaction sequence corresponding to each patient, and constructing a sequence database; based on the database, the original time sequence frequent pattern set is constructed by analyzing through an improved generalized sequence pattern algorithm; each pattern in the set is classified to obtain multiple classification clusters, and the original time sequence frequent pattern in each classification cluster is processed through multi-sequence alignment to construct a generalized clinical path graph, and the information in the generalized clinical path graph is extracted to generate a natural language abstract. The method improves the time sequence logic, knowledge abstraction degree and clinical interpretability of the clinical comorbidity correlation mining by constructing a diagnosis and treatment narrative graph, mining a time sequence frequent pattern, and constructing a generalized clinical path graph through clustering and multi-sequence alignment.

The embodiment of the specification discloses a fire hydrant system schematic diagram generation method and device of a three-dimensional model, relating to the fire protection technical field, the method comprising: obtaining the target schematic diagram generation parameters triggered by the user through the preset graphical user interface, the target schematic diagram generation parameters including the target fire hydrant system, the connection mode and the labeling setting parameters; according to the target fire hydrant system, performing instance extraction in the pre-acquired building three-dimensional model, determining multiple target fire hydrant instances and the fire hydrant attribute information corresponding to each target fire hydrant instance; based on the connection pipe set, traversing each connection pipe in the building three-dimensional model, performing the pipe merging and connecting operation based on the target fire hydrant entity, and determining multiple functional pipe sets; generating the pipeline topology graph through the multiple functional pipe sets, the connection mode and the preset drawing rule, setting the pipeline topology graph based on the labeling setting parameters, and generating the corresponding fire hydrant system schematic diagram.

The application provides a knowledge graph question and answer reasoning method based on potential energy increment triggering, which comprises the following steps: S1, obtaining a user question, constructing a neighborhood subgraph according to the user question, generating an initial candidate operation set based on the neighborhood subgraph, and screening a candidate operation set in the initial candidate operation set according to the executability judgment and the semantic similarity ranking; S2, inputting the user question and the candidate operation set into a large language model, and outputting the selected operation by the large language model; S3, calling a retrieval execution unit, executing the selected operation output by the large language model, and outputting the corresponding entity; S4, obtaining the subject entity quality and the virtual entity quality according to the entity, extracting the user question, and calculating the semantic distance; S5, calculating the potential energy of the current step, and calculating the potential energy increment, and performing a rollback operation when the potential energy increment exceeds a preset threshold value, until the final answer is output.

The application discloses a knowledge base and multi-agent collaborative academic review automatic generation method, system, device and storage medium, relates to the field of artificial intelligence and natural language processing technology, and comprises the following steps: adopting a mixed extraction mechanism to extract an agent to original unstructured literature, and constructing a bottom-layer JSON knowledge base containing technical indexes and quantitative data; mapping the knowledge base information to a preset target hierarchical structure through a planning agent, and generating a global review outline; adopting a block retrieval enhancement strategy, a writing agent carries out chapter text synthesis and graph generation under the constraint of forced binding quantitative evidence; comparing the source text and the generated text through entity lexical analysis, and performing quality evaluation.The application adopts the above-mentioned knowledge base and multi-agent collaborative academic review automatic generation method, system, device and storage medium, effectively improves the local fact accuracy and global logical coherence of the generated literature, and realizes automatic and high-fidelity compilation of the academic review.

Method for dynamic conversation graph generation, including receiving as input multimodal sensor data, and building a real-time representation of dynamic social interactions having varying numbers of participants and sub-group formations over time, in the form of a graph with dynamic edge weights.

The application provides a general transferable physical world optical adversarial attack method, including the following steps: step 1, constructing an agent model and selecting a small sample data set as a training basis; step 2, defining optical adversarial patch parameters and a generation space based on an adaptive graph generation algorithm; step 3, introducing a local and global disturbance repetition mechanism to enhance irrelevant high-frequency features and improve disturbance transferability; step 4, constructing a general patch search framework based on a differential evolution algorithm; step 5, using a density-aware fitness function to comprehensively attack effectiveness and disturbance secrecy, and evaluating candidate patches; and step 6, projecting the adversarial graph to the target object using a laser projection device to realize physical attack. The application is suitable for adversarial testing and security evaluation of image classification, target detection and segmentation and other visual-based deep learning systems in a physical scene, and has high engineering use value due to non-invasive deployment, fast projection and removal.

This invention discloses a knowledge graph-based method for identifying enterprise digital transformation needs. It constructs a multi-dimensional business operation knowledge graph; extracts a semantic subgraph representing pain point obstacles in enterprise business flow; constructs a high-order semantic representation matrix of pain points; extracts a set of corresponding matching candidate digital transformation need nodes; obtains a comprehensive need feature graph; and generates a set of target digital transformation need paths with a quantified execution priority sequence. This invention ensures the establishment of a globally optimal mapping relationship with extremely high confidence between different modal features, significantly improving the fusion depth and lossless alignment capability of underlying business data.

The application discloses a general-purpose computer hologram generation method and system based on structured propagation, equipment, medium and product, and relates to the field of computer holography. The method comprises the following steps: decoupling a zero-frequency reference diagonal spectrum method transfer function to construct a structured propagation model; obtaining a target scene graph and a laser wavelength; based on the target scene graph and the laser wavelength, a structured propagation model is used to obtain a structure normalized input field; the structure normalized input field is input into a hologram generation model to obtain a pure phase hologram; and the hologram generation model is obtained by training a U-net network through a sample input field and a sample pure phase hologram. The application can improve the accuracy of hologram generation.

This invention discloses a method, device, fusion map, and storage medium for generating a safety risk emergency evacuation fusion map. The method includes acquiring multiple safety risk factors contained in a target floor, a functional zoning plan of the target floor, and multiple emergency evacuation factors contained in the target floor; assessing the risk level of each safety risk factor to obtain its actual risk level; determining the target color for each safety risk factor based on its actual risk level and the correspondence between risk level and color coding; and drawing the target colors and emergency evacuation factors on the functional zoning plan based on a first correspondence, a second correspondence, and preset drawing rules to obtain the safety risk emergency evacuation fusion map. This application significantly improves emergency response efficiency, achieving an upgrade from scattered data to integrated, visualized, and intelligent management.

The approaches presented here can be used to generate three-dimensional scenes (3D scenes) using one or more 3D assets derived from a layout image. The layout image can be produced from an input prompt, such as a text prompt, and objects at least partially represented by the layout image can be identified and then used to generate the one or more 3D assets. One or more trained models can be used as part of a pipeline to receive input, generate the one or more layout images, identify objects at least partially represented by the one or more layout images, produce one or more 3D assets based on a description of the objects and / or a cut-out image of the objects, and then produce a 3D scene representing the layout image.

This invention relates to the field of intelligent control technology for drainage pipe networks, and particularly to a low-carbon collaborative optimization method and system for drainage pipe networks based on reinforcement learning. The method includes: S1, data acquisition; S2, constructing a drainage pipe network topology map and dividing it into multiple collaborative control sub-graphs; S3, generating a partitioned carbon quota sequence corresponding to the current control cycle and subsequent control cycles before the predicted peak water inflow time; S4, constructing a hierarchical reinforcement learning decision model to output candidate control actions; S5, constructing an executable action masking matrix and performing masking and filtering to obtain executable collaborative control actions; S6, calculating actual carbon emissions based on feedback data and calculating baseline carbon emissions; S7, constructing reward data and continuously updating the hierarchical reinforcement learning decision model. This invention achieves low-carbon collaborative control while ensuring the hydraulic safety of the drainage pipe network and the executableness of equipment actions.

This invention discloses a hyperspectral image classification method based on graph convolutional neural networks and a state-space model, primarily addressing the challenge of balancing detection efficiency and classification accuracy in existing hyperspectral image classification models. The method includes: 1) inputting the original hyperspectral image and preprocessing it; 2) constructing a multi-hop image generation mechanism and extracting spatial features from the multi-hop images obtained through superpixel segmentation; 3) building a graph convolution-state-space module (GM) for extracting hyperspectral image features by combining graph convolution and a state-space model; 4) constructing a multi-hop graph convolution-state-space model (MGMN) based on the GM module and training it using a cross-entropy loss function; 5) using the trained MGMN model to complete hyperspectral image classification. This invention effectively improves the computational efficiency of hyperspectral image classification models and enhances detection performance while maintaining classification accuracy. It is applicable to fields such as environmental monitoring and healthcare.

The application discloses a protective shoe AI generation method based on physical process constraints and safety standard verification, relates to the technical field of product design automation, and comprises the following steps: assembling the topological relationship of the protective component and the material process constraint based on the scale conversion benchmark and the determinable rule table, binding the rules according to the functional partition, forming a parameterized constraint set, generating a shoe scheme according to the parameterized constraint set and the appearance intention, performing semantic segmentation, key point positioning and edge extraction measurement and verifying the rules, when the verification result indicates that the shoe scheme does not conform to the determinable rule table and the parameterized constraint set, sequentially performing local shape correction, local redrawing generation and discarding regeneration, and obtaining a final scheme, rechecking the final scheme, outputting a multi-view design drawing, a partition annotation drawing, a vectorized contour line, a key dimension table, a material list and a process specification, and performing encryption and decryption, clearing the plaintext and recording the access log.

According to an embodiment, an information processing device (10) has an editing unit (152) and a generation unit (154). The editing unit (152) adds information that indicates deletion to designated subgraphs that are subgraphs of a knowledge graph. The generation unit (154) reports that an answer to an inputted question is not to be generated when an inputted subgraph that is a subgraph of the knowledge graph includes the information that indicates deletion and uses a language model to generate an answer to the question that is an answer that is based on the subgraph when the subgraph does not include the information that indicates deletion.

This invention discloses a crowdsourced logistics overlapping community detection method based on graph convolutional networks and probabilistic decoding, applied to the field of overlapping community partitioning in complex networks. The method includes: obtaining a graph adjacency matrix and a worker node attribute matrix based on the relationships between worker nodes; performing feature encoding on worker nodes using an improved graph convolutional network to obtain a worker node-community membership matrix; introducing learnable community weight parameters to define the structural association strength between node pairs; and decoding the structural association strength as the probability of edges existing between node pairs using a Bernoulli-Poisson random graph generation mechanism; constructing a structural reconstruction loss function using a set of positive sample edges and a set of negative sample non-edges sampled from the graph adjacency matrix; and introducing community membership constraints and attribute consistency constraints, which are then weighted and combined to form the overall optimization objective function of the model. This invention achieves accurate overlapping community partitioning of worker nodes, effectively improving the accuracy and practicality of the partitioning.