95 results about "Relational reasoning" patented technology

An intelligent analysis method based on medical document structure perception and multi-modal fusion comprises the following steps: carrying out structure topology modeling on a medical document, extracting visual layout, text meta-information, space coordinates and semantic keyword features, constructing a semantic topological graph and dynamically shielding irrelevant contents; selecting an extraction path according to a document type, performing deep semantic analysis and entity recognition on a text-type document, and performing visual enhancement OCR recognition on a scanning-type document; the features are injected into a medical knowledge graph, and feature fusion, semantic verification, relation reasoning and information completion are achieved through a graph neural network; a three-stage strategy optimization model of basic pre-training, domain adaptation and online reinforcement learning is adopted; and large-scale processing is realized through a dynamically aggregated distributed architecture. The method is used for intelligent analysis and structured conversion of documents of hospitals, medical insurance and medical scientific research. The problems that heterogeneous medical document analysis adaptability is poor, multi-modal fusion is difficult, medical knowledge utilization is insufficient, and large-scale processing efficiency is low are solved.

The invention belongs to the technical field of engineering information intelligent processing, and relates to a highway bridge drawing multi-modal information extraction and semantic understanding method and system.The method comprises the steps that firstly, self-adaptive judgment is conducted on a vector drawing and a scanning drawing, geometric distortion correction, drawing frame and title bar positioning and layout segmentation are completed, and then the vector drawing and the scanning drawing are obtained; constructing a hierarchical document structure comprising texts, tables, images and two-dimensional drawing objects; then, a front-end target detection network and a rear-end cross-modal document understanding model are fused, and detection and relation reasoning of elements such as view blocks, labels, symbols and tables are achieved; and image-text feature alignment is further performed by using a visual coding network and a text coding network, structural description conforming to engineering semantics is generated by means of a multi-modal language model, an engineering parameter database is established, and parameter query and multi-modal question and answer output are supported. According to the method, the accuracy and efficiency of automatic acquisition and semantic understanding of the key information of the highway bridge drawing are improved.

The invention provides a document element rapid extraction system based on a pre-trained large model, and relates to the technical field of computer software application, the system comprises a parameter field adaptation module used for textualizing a document and constructing an industry standard corpus based on a textualized processing result, adjusting a preset language model by utilizing an industrial standard corpus; the dynamic document partitioning module is used for performing semantic segmentation processing on the industrial standard document to obtain a plurality of text blocks; the entity alignment module is used for carrying out entity and relation extraction on the text blocks and carrying out entity alignment in combination with a uniform manifold approximation and projection method; and the relation reasoning and knowledge graph completion module is used for performing completion processing on the preliminary knowledge graph and storing a completion result. According to the method, the element extraction efficiency can be directly improved without pre-defining a rule template or performing data annotation.

The invention relates to the field of compliance management, and particularly discloses a real-time compliance management system dynamic evaluation system and method based on data driving. External law and regulation documents and enterprise internal compliance rule documents are respectively mapped into knowledge maps; semantic association analysis is carried out on cross-graph regulation provisions and compliance rule provisions to identify the relationship type between the two provisions, and when conflicts are found, a correction mechanism is triggered to realize cross-graph node relationship bridging. When the regulation is changed, further positioning the embedding position of the change provision in the map, capturing the diffusion path of the affected compliance rule provision, and performing semantic analysis and relation reasoning on the regulation change provision and the affected compliance rule set to reveal the chain influence mode of the regulation change on the enterprise compliance rule; and generating compliance rule updating suggestions. According to the method, dynamic evaluation and optimization of the compliance management system can be realized, and the efficiency and accuracy of enterprise compliance management are improved.

The invention discloses a target retrieval method and system. The method comprises the following steps: S1, data access and preprocessing: acquiring multi-source data, performing cleaning, formatting and time-space standardization, and performing target detection and cutting on an image / video to generate a structured target object; s2, feature extraction: extracting deep semantic feature vectors and auxiliary understanding information, which have discriminability and adapt to complex scenes, from the target image; s3, constructing a data index, including constructing a spatio-temporal semantic hypergraph index of multiple types of nodes and hyperedges based on deep features and spatio-temporal information of the targets to express a complex relationship between the targets; and S4, data query: receiving multi-modal query information of a user, performing candidate region screening, feature matching and relation reasoning by utilizing a hypergraph index, and finally outputting a high-confidence target retrieval result. According to the method, the robustness of complex scenes and target changes and multi-dimensional query of depth are improved.

The invention relates to the technical field of financial data analysis and artificial intelligence, in particular to a multi-source heterogeneous financial data fusion and intelligent analysis system which comprises a data standardization processing module, a time sequence event fusion module, a knowledge graph construction module, a relation reasoning module and a self-adaptive anomaly detection module. The data standardization processing module is used for converting heterogeneous financial data from different sources into unified tensor representation; the time sequence event fusion module adopts a double-clue cooperation mechanism to establish a mapping relation between continuous time sequence data and discrete events; the knowledge graph construction module extracts financial entities and relationships thereof, and constructs a multi-level knowledge graph; the relation reasoning module performs deep reasoning based on a graph attention mechanism; and the adaptive anomaly detection module dynamically adjusts the detection threshold according to the market environment. According to the system, implicit association in heterogeneous financial data can be deeply mined, market anomalies are recognized in advance, and comprehensive support is provided for financial decision making.

The invention relates to the technical field of artificial intelligence and data processing, and discloses a multi-mode identity relation inference system based on a graph neural network. The system comprises a multi-modal feature extraction module, a cross-modal alignment module, a graph structure construction module, a dynamic relation reasoning module and a decision output module. According to the method, the cross-modal alignment module is introduced to project the image features and the text features to a unified public semantic space, so that the nonlinear distribution difference of heterogeneous modals in an embedding space is effectively eliminated, and cross-modal alignment errors are avoided from the source; by integrating the attention mechanism of modal perception in the graph neural network, the system can dynamically learn the semantic association strength between the nodes in different modals, adaptively adjust the weight distribution in the neighborhood information aggregation process, and significantly improve the accuracy of node characterization.

The invention discloses a group behavior identification method based on multi-view individual relationship interaction, which comprises the following steps of: firstly, acquiring joint point information of different individuals in a scene by utilizing a skeleton point estimation network and a position information coding technology; then extracting multi-granularity feature representation of the body part through a depth model; then, utilizing an attention mechanism in Transform to respectively construct a structured relation reasoning module in the individual under multiple view angles and a spatio-temporal information interaction module among individuals under multiple view angles, and realizing deep interaction of individual body part information from different view angles; self-adaptive fusion factors are designed, cross-view cross-granularity individual interaction features are integrated, and high-discrimination individual content representation is obtained. And finally, a multi-head loss training strategy is added, the types of the individual and group behaviors are judged from the enhanced individual and group behavior characteristics, and a group behavior recognition task in a complex scene is realized.

The invention discloses a knowledge graph construction method, device and equipment and a readable storage medium, and is applied to the technical field of natural language processing and knowledge engineering.The method comprises the steps that document content is divided to obtain initial document fragments, and all the initial document fragments are merged and divided based on semantic similarity to obtain target division blocks; based on the target division block, subject-predicate-object formatting processing is carried out to obtain a subject-predicate-object formatting result; entity and relation extraction is carried out according to the subject-predicate-object formatting result to obtain a display triple, implicit relation reasoning is carried out to obtain an implicit relation triple, entity and relation type normalization is carried out to obtain a normalized triple, and the knowledge graph is constructed based on the normalized triple. The block segmentation driven by semantic similarity is adopted to avoid sentence breakage, cascade errors are reduced based on subject-object formatting processing, and the problems of fragmentation, link missing and the like are solved based on implicit relations, so that the integrity and accuracy of knowledge graph construction are improved.

The invention provides a robot task planning method and device, computer equipment and a storage medium, and the method comprises the steps: receiving a natural language instruction of a user; determining a task target based on the natural language instruction and scene context information; constructing a semantic map based on the environment data and the visual identification and relation reasoning result; based on the task target and the semantic map, generating an action sequence through a formalized planning engine; and controlling the robot to execute the action sequence. By adopting the method, the usability, accuracy and reliability of robot task planning can be improved.

The invention discloses a subject entity labeling method and system fusing image recognition and a knowledge graph, and relates to the technical field of image recognition and natural language processing. The method comprises the following steps: carrying out preprocessing and image-text association on multi-source heterogeneous subject data; detecting a visual entity in the image through an improved YOLO model, and extracting and linking a text entity in combination with a subject dictionary and a knowledge graph; cross-modal collaborative disambiguation is realized by calculating the semantic similarity of visual candidate entities and text context vectors; multi-modal entities are combined, relation reasoning and enrichment labeling are carried out in a knowledge graph, and a deep labeling result containing the entities and a semantic relation network of the entities is generated; the problems of difficulty in multi-source data fusion, inaccurate professional entity recognition and difficulty in semantic ambiguity elimination are effectively solved, the depth and accuracy of subject knowledge semantic understanding are remarkably improved, and key technical support is provided for intelligent education application.

The invention discloses a sub-graph reasoning method fusing logic rule learning and attack semantic enhancement. The method comprises the steps that an input layer dynamically integrates knowledge graph topology and an AMIE rule base, an initial k-hop sub-graph is generated, and structured input is provided for attack chain mining; the sub-graph extraction module is used for executing double confidence filtering, screening high-value attack chains and applying dictionary filtering to enhance semantic reliability; the sub-graph coding module adopts an entity perception update layer and a relationship aggregation evolution layer of a dual-channel mechanism to collaboratively model the spatial-temporal characteristics of an attack chain; the relation reasoning optimization module is used for dynamically injecting high confidence rules and optimizing triple scores; and the training optimization module is used for implementing task perception negative sampling. According to the subgraph reasoning method fusing logic rule learning and attack semantic enhancement, based on inductive reasoning and semantic perception modeling, by taking subgraph modeling guided by a logic path as a core, attack chain rules with high confidence in a training graph are mined, and the understanding ability of a model structure is improved.

The invention relates to an intelligent question and answer and scheme recommendation system based on a fire-fighting toughness knowledge graph, in particular to the field of knowledge graphs, according to the scheme, full-process optimization of fire-fighting knowledge from collection to application is achieved through cooperation of multiple modules, a data processing module converts heterogeneous data into standardized knowledge units, and the knowledge units are stored in a database; the problem of multi-source data fusion is effectively solved; the relation reasoning module remarkably improves the knowledge quality through dynamic relation reasoning and conflict detection; the graph updating module realizes real-time evolution of the knowledge graph based on an event-driven mechanism, so that the timeliness of information is ensured; a closed-loop optimization mechanism formed by the optimization verification module continuously improves the processing precision of each module, the overall scheme effectively enhances the consistency, accuracy and real-time performance of knowledge, reliable knowledge support is provided for intelligent question answering and scheme recommendation, and the decision-making efficiency of fire-fighting emergency command is remarkably improved.

Methods and processors are disclosed. The method includes acquiring an input indicative of a Relational Question-Answering (RQA) problem, generating an instance graph based on the input, generating an intermediate output indicative of one or more reasoning paths in the instance graph and generating, based on the input and the intermediate output, an output indicative of one or more potential answers to the RQA problem.

The invention discloses a character relationship reasoning system and a character relationship reasoning method based on a knowledge graph, and the method comprises the steps: aligning entities in different data sources to entities in the knowledge graph, extracting character relationships from the data sources, and adding the character relationships into the knowledge graph; extracting features of a plurality of modes from the figures in the knowledge graph, projecting the extracted features of the plurality of modes to the same semantic space, and generating a unified semantic representation after fusion; on the basis of a graph neural network model, performing representation learning on entity and character relationships in the knowledge graph after the unified semantic representation is generated, so as to obtain graph topological structure information and semantic information of knowledge; an incremental learning technology is used, and the graph neural network model is trained only through newly added data; utilizing a domain adversarial network to extract domain features of each data source, and dynamically adjusting parameters and a structure of the graph neural network model according to the domain features; and capturing associated entities and relationships in the reasoning process by using an attention mechanism, and generating a reasoning path.

The invention belongs to the technical field of data retrieval, and particularly discloses an inquiry method and system based on a vector database and graph query, a terminal and a medium, and the method comprises the following steps: importing structured data into a graph database, and constructing a knowledge graph with entity nodes and edge relationships; generating a first semantic vector through the semantic coding model, storing the first semantic vector into a vector database, and establishing an index; a user inquiry text is received, and after sensitive information detection and context analysis are executed, a second semantic vector is generated through the semantic coding model; performing similarity retrieval in a vector database based on the second semantic vector to obtain a plurality of candidate node identifiers; executing query in a limited range by taking the candidate node as a starting point in the graph database, and extracting associated nodes and relationships to form a sub-graph; performing joint scoring on the sub-graph structures, and sorting the paths based on a scoring result; and generating and outputting an answer text according to the sorting result. The problem that in the prior art, semantic understanding and relation reasoning are disjointed and difficult to co-process is solved.

The invention discloses a manufacturing enterprise supply chain digital transformation maturity evaluation method driven by multi-dimensional indexes. The method comprises the following steps: widely collecting internal and external multi-source data of an enterprise through a data acquisition module, storing preprocessed data in a graph structure through a knowledge graph construction module, and optimizing query efficiency; potential association and abnormal modes among multi-modal data mining indexes are fused through a semantic understanding and relation reasoning module, field adaptability parameter adjustment and optimization are performed on each key model through a model training optimization module, and a hierarchical evaluation system is established and a quantitative improvement scheme is generated through an intelligent evaluation and improvement suggestion module. And finally, a complete closed loop from data acquisition to decision optimization is formed, and accurate evaluation and continuous improvement of the digital transformation maturity of the supply chain of the manufacturing enterprise are realized. The method is characterized in that a manufacturing enterprise supply chain digital transformation maturity evaluation system driven by a multi-dimensional index is used for evaluation.

The invention provides a process flow diagram intelligent analysis method based on YOLO computer visual identification, which combines a YOLO algorithm with specific domain knowledge of a process diagram, carries out technical combination of symbol detection, connection relation reasoning and semantic information extraction aiming at a data set construction and data enhancement method, and establishes a process flow diagram through embedding a CBAM attention module in YOLO Backbone. According to the method, the symbol key area can be dynamically concerned, the interference of complex backgrounds (characters and grid lines) is inhibited, the detection precision of small targets, easy-to-confuse targets and non-standard drawings is improved, the strict requirements on the quality of the drawings are reduced, the scene adaptability of the method is enhanced, and the process diagram analysis efficiency is remarkably improved; finally, the structured JSON data can be directly connected with visual software, efficient data support is provided for digital twinning and other industrial digital scenes, and the problems that a traditional method is low in efficiency and difficult to connect with downstream digital application are solved.

The application relates to the technical field of intelligent reasoning and safety judgment, and discloses a high-speed rail platform safety judgment method and system based on mixed-precision reasoning, which comprises the following steps: acquiring multi-source semantic observation records and generating a safety observation element set; constructing a platform safety relation graph; determining relation conflict density, closed residual error, cross-source divergence degree and reasoning difficulty level; generating a mixed-precision bit width scheduling table; performing graph relation reasoning to obtain an initial safety judgment vector and an initial judgment boundary quantity; in step 6, a final judgment vector is determined; and in step 7, a locked safety level is determined and a safety judgment package is output. The application realizes mixed-precision safety judgment and locked output driven by multi-source semantic relation of a high-speed rail platform.

This invention discloses a method for constructing a relationship-driven cybersecurity knowledge graph. This method, driven by relational semantics, sequentially executes the following steps: multi-source threat intelligence collection and preprocessing, relational semantic modeling, relationship-priority-driven knowledge extraction, entity alignment based on relational context, and knowledge graph construction. By constructing a relational system with entity type constraints and relational reasoning rules, it achieves complete attack chain modeling and implicit relational derivation; it employs a reverse extraction mechanism of relational identification → entity location to reduce error propagation; it introduces relational context to achieve accurate cross-source entity alignment; and finally, it establishes an indexed knowledge graph based on a graph database, supporting efficient querying and attack attribution.

The application provides a dynamic contour attention driven cross-modal fusion method and system, the method comprising: generating a set of part nodes carrying pure three-dimensional geometric attributes from three-dimensional point cloud data; forming a dynamic irregular region of interest closely fitted with the contour thereof by accurately projecting the part nodes to a two-dimensional image; adaptively determining a plurality of sampling points with the richest information in the region of interest by using a deformable attention mechanism, and performing weighted pooling on the visual features of the sampling points to obtain a representative semantic feature vector, thereby completing the cross-modal attribution of the part nodes; constructing a dynamic undirected attribute graph based on the set of part nodes that have completed attribution, and performing relationship reasoning and instance aggregation by a graph neural network to output a final perception result. The application effectively reduces information loss and sensor calibration sensitivity, and significantly improves the robustness, explainability and computational efficiency of the system in complex scenes such as occlusion.

The application discloses a mineral prediction method based on spatial intelligence, relates to the technical field of spatial intelligence, and comprises the following steps: identifying the spatial relationship of a spatial entity element list, constructing a topological connected graph, extracting connected structure attributes, executing semantic relationship reasoning, and generating an object-level spatial intelligent scene graph; based on the object-level spatial intelligent scene graph, constructing an anisotropic cost field, calculating a minimum cost channel distance, mapping into a channel weight expression, and generating a channel weight layer; performing spatial alignment and multi-modal spatial correlation feature fusion on a multi-source mineralization evidence data set, the object-level spatial intelligent scene graph and the channel weight layer, executing mineral inference through a mineral prediction machine learning model, and generating a mineral prediction layer. The application realizes dynamic modeling of a mineralization path, and improves prediction accuracy and engineering practicability.

A vision transformer (ViT) is a deep learning model that performs one or more vision processing tasks. ViTs may be modified to include a global task that clusters images with the same concept together to produce semantically consistent relational representations, as well as a local task that guides the ViT to discover object-centric semantic correspondence across images. A database of concepts and associated features may be created and used to train the global and local tasks, which may then enable the ViT to perform visual relational reasoning faster, without supervision, and outside of a synthetic domain.

This application provides a method for multi-source intelligence semantic analysis and compliance risk early warning, applied to intelligent processing devices. The method includes: transforming multi-source heterogeneous intelligence data into a unified semantic representation vector through a cross-modal semantic mapping model; performing entity linking and relationship reasoning on the unified semantic representation vector based on an enterprise multi-source intelligence knowledge graph library to generate an intelligence semantic analysis graph; matching the intelligence semantic analysis graph with a multi-level compliance rule library through an enterprise compliance rule reasoning engine to mine and assess the severity and associated transmission paths of potential compliance risk points to generate a risk transmission path diagram; and generating tiered compliance risk early warning information based on the risk transmission path diagram. This application improves the effectiveness of multi-source intelligence semantic analysis and the rationality of compliance risk early warning compared to existing solutions, and better meets the actual needs of enterprises for refined management of compliance risks.

This invention provides a rapid document element extraction system based on a pre-trained large model, belonging to the field of computer software application technology. The system includes: a parameter domain adaptation module for textualizing documents and constructing an industry-standard corpus based on the textualization results, then adjusting a pre-defined language model using the industry-standard corpus; a dynamic document segmentation module for semantically segmenting industry-standard documents to obtain several text blocks; an entity alignment module for extracting entities and relations from the text blocks and performing entity alignment using uniform manifold approximation and projection methods; and a relational reasoning and knowledge graph completion module for completing a preliminary knowledge graph and storing the completion results. This invention eliminates the need for pre-defined rule templates or data annotation, directly improving element extraction efficiency.

The application designs a document-level financial relationship extraction method fusing entity and window attention, and comprises the following steps: data is preprocessed in a sliding window mode and is input to a pre-training model; the expression of each entity is obtained through the output of the pre-training model, the expression of the head entity-tail entity and the distance of the head entity-tail entity are further combined, and then one convolutional neural network is used to realize the interaction of global entity information; the document-level attention output by the pre-training model is extracted for local information by using a fixed window; the two kinds of features are fused and input to a U-shaped neural network for relationship reasoning; and finally, relationship prediction is performed through a bilinear function. The method can extract document-level financial relationships and achieves good extraction effect.

The application discloses an enterprise credit score intelligent evaluation method based on traffic travel consumption data, relates to the technical field of enterprise credit intelligent evaluation, and comprises the following steps: extracting multi-dimensional credit features from original traffic consumption records and constructing an enhanced behavior portrait, constructing a dynamic enterprise credit evaluation graph network, performing relationship reasoning and credit state diffusion calculation by injecting a feature vector, quantifying and conducting the risk of associated enterprises, performing time sequence evolution evaluation of the credit level based on the portrait, introducing an external risk label for constraint correction after generating a preliminary trajectory, starting backtracking verification by using historical score data flow, and finally outputting the credit score after consistency test. The method overcomes the limitations of isolated evaluation, can systematically identify associated risks, and generates a stable and logically self-consistent credit evolution result in the time dimension.

The application discloses a kind of knowledge graph completion methods of combining relationship perception anchor point enhancement and graph convolution network, including in input data and construct relationship perception neighbor set, construct relationship perception anchor point layer, construct feature extraction layer, construct feature fusion layer, construct relationship reasoning layer, construct training layer and loss function layer.Affinity effect lies in: by introducing anchor point semantic information before knowledge reasoning, designing semantic-structure-anchor point three modal fusion mechanism and introducing anchor point consistency constraint term in loss function, so that generalization ability is superior and scalable, stable in zero-sample relationship and low-resource entity scene, modular design can be integrated into existing KGC or semantic reasoning system, can be widely applied in intelligent question answering, knowledge retrieval, recommendation system and medical knowledge reasoning etc.Scenario, with high precision, scalable, interpretable technical advantages.

The invention provides an aircraft system fault diagnosis method based on knowledge expression. The method comprises the following steps of 1, collecting fault description files; step 2, constructing a fault relation element category library; step 3, constructing a fault knowledge element library; step 4, constructing a fault relationship of the fault description file; and 5, constructing a fault relation reasoning model, and diagnosing the aircraft system fault through the fault relation reasoning model. According to the method, various fault description files such as various maintenance manuals and fault trees are collected, a text processing mechanism and a knowledge graph mode are adopted, the incidence relation between faults is extracted from a fault description text, a fault reasoning relation graph is constructed, and a fault diagnosis reasoning model for fault relation reasoning oriented to knowledge expression is constructed; the method has the capability of reasoning unknown faults and relations based on the existing faults and relations, so that complementation of a fault reasoning model and prediction of unknown fault relations can be realized.

This invention discloses a method and system for extracting sentiment-cause pairs from documents, belonging to the field of natural language processing technology. The method involves acquiring semantic role labels for each clause in a target document, extracting three core semantic role relationships within each clause based on these labels: agent, sentiment, and cause. A word-sentence heterogeneous graph is constructed based on these semantic role relationships. Information is aggregated from word-word relationship edges to update the word node information in the word-sentence heterogeneous graph. The updated word node information is then aggregated through word-sentence association edges to obtain sentence node information that integrates semantic role relationships. Based on the sentence node information, sentiment clauses and cause clauses are identified, yielding sentiment clause features and cause clause features, and generating candidate sentiment-cause pairs. Relational reasoning is performed on the candidate sentiment-cause pairs to obtain the extracted sentiment-cause pairs. This method, by capturing structured semantic information within clauses, can output complete and accurately paired sentiment-cause pairs.