193 results about "Entity type" patented technology

A system and method for persistent cognitive computation with temporally synchronized multimodal processing implements a geometric approach to artificial intelligence through typed latent entities within a dynamic manifold substrate. The system maintains a latent manifold incorporating heterogeneous data modalities where local curvature reflects semantic density and typed entities are stratified according to structural properties. Temporal synchronization coordinates asynchronous multimodal data streams through generation of temporal alignment fields within the manifold that preserve semantic coherence across modal boundaries. Type-aware geometric operations enforce operation legality based on entity type and local manifold geometry, enabling structured recombination, compression, and traversal while preventing semantic distortion. The system executes synchronized manifold reorganization during idle periods through coordinated optimization operations including perturbation analysis and topological surgery. This architecture enables persistent memory through geometric encoding where frequently accessed concepts develop high-curvature regions and cognitive patterns emerge from usage-based manifold evolution.

The invention belongs to the technical field of natural language processing and multi-modal information extraction, and particularly relates to a multi-modal named entity recognition method based on semantic alignment and cross-modal graph fusion, which comprises the following steps: S1, acquiring a data sample containing a text sequence and image content; s2, encoding the text and the image into vectors respectively; s3, similarity is calculated through a trainable bilinear function, and optimization is carried out through loss comparison; s4, cross-modal attention is used to enhance association information between modals; s5, determining the proportion of reserved image information through a modal matching module; s6, introducing a gating mechanism to dynamically fuse visual and text features; s7, realizing local and global information complementation by a cross-modal graph fusion model; and S8, inputting the fused representation into the CRF layer to predict the entity type. According to the method, fine semantic alignment can be realized in a weak image-text correlation context, and balance between local entity recognition and global semantic understanding can be achieved.

The invention relates to an unmanned aerial vehicle fault traceability analysis method and device, equipment and a storage medium. The method comprises the steps of defining entity types and relationship types among entities based on a predefined fault ontology model to construct a mode layer of an unmanned aerial vehicle fault knowledge graph; based on the mode layer, extracting a fault triple from the multi-source operation data of the unmanned aerial vehicle by using a mixed extraction model, and constructing a fault knowledge graph containing instance data; endowing a dynamic weight probability representing confidence to a relation edge in the fault knowledge graph, and generating a probabilistic fault knowledge graph; and mapping to-be-analyzed fault information to the probabilistic fault knowledge graph, performing traceability analysis by using a hybrid inference engine, and outputting a fault reason and a transmission path. According to the method, structured deep fusion of domain knowledge and data value is realized, and the traceability conclusion is improved from qualitative judgment to quantitative decision support with confidence measurement.

The invention discloses a knowledge graph-based search engine relation chain recommendation method, which comprises the following steps of: receiving a relation chain recommendation request submitted by a user through a search engine to obtain initial query information; performing semantic analysis and intention recognition on the initial query information, and determining a corresponding entity type and a relationship type; calling a dynamic knowledge selection and evaluation mechanism according to the entity type and the relationship type, and dynamically screening the original knowledge graph to obtain effective knowledge sub-graphs; performing diffusion type reasoning based on a knowledge graph diffusion model to generate a candidate relation chain path set; evaluating the quality score of each candidate path in real time; and performing dynamic screening according to the path quality score, and outputting a relation chain path recommendation result. According to the method, accurate mining and dynamic optimization of the knowledge graph relation chain path are realized, and the accuracy of a recommendation result and the flexibility of user interaction are improved.

The invention provides an electric power document keyword extraction method based on Prompt and a knowledge graph, relates to the technical field of electric power document processing, and constructs a lightweight multi-level index knowledge graph in the electric power field by combining entity type and relation type division based on an electric power industry standard document and an electric power field corpus. The method comprises the following steps: performing vector modeling on a power document, constructing a multi-level index from an entity to a vector, realizing standardized semantic modeling and efficient hybrid retrieval of a power document field background, and obtaining a topic vector and a core paragraph of the power document in combination with power key information; according to the method, entity types are indexed in a knowledge graph by using subject vectors, similar entities are obtained to form knowledge sub-graphs, so that multilayer Prompt is obtained to guide a large language model to extract keywords, then knowledge graph similarity constraints are introduced to decode the output of the large language model, the keyword recognition capability in the power field is improved, and the keyword recognition efficiency is improved. And the accuracy of keyword type identification and the normalization of term naming are both considered.

The invention discloses a structured data storage method based on natural language transformation, which comprises the following steps of: a system initialization configuration stage: deploying a protocol adapter in a local memory of a PC (Personal Computer) client, and loading natural language processing pipeline configuration parameters; a heterogeneous data acquisition stage: capturing a multi-source text data stream through the protocol adapter, uniformly converting the multi-source text data stream into a standardized data packet, and sending the standardized data packet to a message queue theme; a text cleaning stage: a named entity recognition stage: inputting the pure text data into an NER module deployed with a language model loader; in the conditional feature extraction stage, feature vectors are generated for texts meeting preset conditions on the basis of entity type tags in the entity recognition result; and a consistent storage stage: inserting the entity identification results into a relational database in batches, and updating the entity mapping relationship in the cache. According to the method, the intelligent level of cache management is remarkably improved, and the access fluency of the key data of the user is guaranteed.

Systems, devices, and techniques are disclosed for efficient knowledge graph indexing and retrieval. Document chunks may be generated from documents. Summarizations may be generated from document chunks. Entity types, entity properties, relations, and relation properties may be generated from a subset of the summarizations. A schema including entity types, entity properties, relations, and relation properties may be generated. Entity property triplets and entity relation triplets may be generated from the summarizations based on the schema and linked to the document chunks. A knowledge graph including nodes representing entities from the entity property triplets and entity relation triplets and edges representing the entity property triplets and the entity relation triplets may be generated. A search query may be received. Nodes and edges of the knowledge graph that include the entities, the entity property triplets and the entity relation triplets most similar to keywords of the search query may be determined.

The invention discloses a coal mine hidden danger event intelligent reasoning method based on a knowledge graph, and belongs to the technical field of coal mine safety, and the method specifically comprises the steps: obtaining a to-be-deduced entity with a real-time data flow recognition state parameter exceeding a threshold value range; calling a state transition rule set according to the entity type and constructing an independent deduction process; executing state transition calculation in each deduction process to generate a state evolution sequence; state combination matching is carried out based on the relation mode of the static knowledge graph, and entity state pairs meeting relation triggering conditions are recognized; establishing a cross-process data channel between the related deduction processes and performing parameter conversion; state deduction is executed again based on the input parameters, and deduction network topology is constructed; and finally, a complete hidden danger evolution path is obtained through reverse tracking parameter transfer relation integration. According to the method, dynamic deduction of the coal mine hidden danger forming process and accurate identification of the linkage risk conduction path are realized, and the accuracy of potential safety hazard early warning is effectively improved.

The invention discloses a business database natural language question and answer processing method fused with a large model technology. The method comprises the following steps: S1, receiving an emergency query request input by a user in a natural language form; and S2, carrying out analysis and intention recognition on the emergency query request based on a large language model, and generating a group of candidate query intentions arranged in a descending order according to matching degree scores and corresponding key entity information. According to the method, a core link can be optimized by introducing a large language model technology: in an intention recognition stage, intention recognition accuracy is improved through a formula of fusing semantic similarity and entity type matching degree; a priority-based asynchronous execution strategy is adopted to improve the response efficiency; the response reliability is guaranteed through real-time and conflict verification; meanwhile, the system performance is continuously improved in combination with an offline model optimization link, the defects of an existing processing method are finally overcome, and an accurate, efficient and reliable solution is provided for business database natural language question answering in an enterprise emergency scene.

The invention discloses an insurance intelligent question and answer method based on a large model RAG technology. The method comprises the following steps: constructing a vectorization knowledge base; receiving a question of a user, extracting an insurance proprietary entity from the question by combining the big language model with the cue word project, and labeling an entity type; the entity is linked with the standard product full name in the knowledge base, and question sentences are automatically clarified or rewritten based on a confirmation result; performing intention recognition by using a prompt word project in combination with a preset intention type, executing semantic routing according to a recognition result, and guiding a question sentence to a vectorized knowledge retrieval, structured data query or FAQ processing flow; in vectorization knowledge base retrieval, a multi-path recall and reordering method is adopted, and top-K reference knowledge blocks are output; and calling a large language model to generate a natural language answer. According to the method, high-precision, low-cost and extensible intelligent question answering can be realized in an insurance service scene, and the agent query efficiency and question answering experience are remarkably improved.

The invention provides a diversified text sensitive data synthesis method for desensitization effect evaluation, which comprises the following steps: constructing a sensitive entity system meeting desensitization evaluation requirements, the sensitive entity system comprises a general field, a medical field and a financial field, and each field comprises a plurality of entity types; obtaining an original data set, counting entity distribution on the original data set, constructing a target distribution model, and designing a diversified strategy based on entity types and sentence patterns; guiding the large language model to generate candidate corpora according to the target distribution model and the diversification strategy, performing character-level alignment labeling and consistency verification on the candidate corpora, and generating a synthetic data set based on the candidate corpora; and performing multi-dimensional quality verification on the synthetic data set from the data layer, the entity layer and the semantic layer to obtain an evaluation result, and feeding back the evaluation result to a closed-loop controller to adjust a quota and a generation parameter so as to generate a final synthetic data set. The method can be applied to validity evaluation of a data desensitization tool, and the problems of single evaluation dimension, data sparsity and the like in text desensitization evaluation are solved.

Provided in the embodiments of the present disclosure are a knowledge graph construction method, a storage medium, an electronic device and a computer program product. The method comprises: acquiring text to be processed and a plurality of schema extraction tasks of different entity types; on the basis of the plurality of schema extraction tasks, extracting a plurality of pieces of entity schema information from said text; converting the plurality of pieces of entity schema information into a plurality of triples; and constructing a knowledge graph on the basis of the plurality of triples.

The present disclosure proposes a method, an apparatus and a computer program product for entity extraction based on edge computing. A web document may be obtained. A text feature of the web document may be identified. A visual feature corresponding to the text feature may be identified. An entity type sequence corresponding to the web document may be extracted based on the text feature and the visual feature.

The invention relates to the technical field of knowledge maps, and provides a screening type dynamic classification self-adaptive relation extraction method, device and equipment, and the method comprises the following steps: defining an entity type list, inputting a text by a user according to a cue word template in a labeling format, judging the length of the text, and extracting the entity type list according to the length of the text; selecting a corresponding strategy according to the text length to generate a candidate entity pair; the association strength of each candidate entity pair is calculated by combining static corpus statistics and a dynamic semantic hybrid scoring model, and the candidate entity pairs with low association are filtered; constructing a dynamic prompt request LLM to generate a natural language abstract describing the subject entity and the object entity, and classifying the abstract into a predefined relationship type to obtain a structured triple; and importing the triple into a graph database to construct the knowledge graph. According to the method, the knowledge extraction efficiency is improved, and the problems of calculation redundancy and high cost are solved.

The invention provides an industrial product parameter extraction method based on domain knowledge learning, and the method comprises the steps: 1, collecting a plurality of technical documents of a preset industrial product field as knowledge sources, and constructing a structured domain knowledge model through a man-machine cooperation mode; 2, based on the domain knowledge model, generating a training data set with entity type labels, and training one or more deep learning extraction models by using the data set to enable the extraction models to learn parameter knowledge of the industrial product field; 3, receiving a new to-be-processed digital technology document, and processing the document by adopting the trained deep learning extraction model so as to identify and extract structured data corresponding to parameter entities in the domain knowledge model; and 4, storing the extracted structured data into a database, and selectively utilizing the data to carry out iterative updating and enhancement on the domain knowledge model.

The invention provides an entity pair guided scientific and technical literature document level relation extraction method and system, and the method comprises the steps: carrying out the entity recognition of an input scientific and technical literature document, and obtaining an entity set in the scientific and technical literature document; based on an entity pair pre-screening mechanism of multiple sampling and similarity verification, screening out a candidate entity pair set from all possible entity pairs of the entity set; then generating enhanced relation description fusing corresponding entity type information and relation semantics between the entity pairs; based on a pre-constructed relation semantic knowledge base, a double-layer filtering mechanism is adopted, and a corresponding fine screening candidate relation set is retrieved for each enhanced relation description; and guiding the large language model to perform triple fact judgment by using detailed semantic description of the candidate relationship to obtain an output result. According to the method, high-precision relation extraction is ensured, and meanwhile, the calculation overhead of long text processing is remarkably reduced, so that scientific and technical literature document-level relation extraction is more accurate and efficient.

The embodiment of the invention provides an entity relationship extraction method and device, equipment, a storage medium and a program product, pseudo entities are constructed based on continuous vocabulary segments of which the length is within a preset range in a target text, feature vectors of the pseudo entities are extracted, the feature vectors corresponding to any two pseudo entities are spliced, and an entity relationship extraction result is obtained. Constructing feature vectors corresponding to the pseudo-relationships, screening out the pseudo-relationships with confidence greater than or equal to a preset threshold value as effective relationships, taking pseudo-entities corresponding to the effective relationships as effective entities, constructing an effective entity relationship graph, extracting feature vectors corresponding to the effective entities from the effective entity relationship graph by using a graph convolutional neural network, and obtaining feature vectors corresponding to the effective entities; according to the method and the device, the effective entities are extracted, the feature vectors corresponding to the effective relations are constructed, the feature vectors corresponding to the effective entities and the feature vectors corresponding to the effective relations are identified, the entity types and the relation types corresponding to the target texts are obtained, and waste of operation resources can be reduced in the entity relation joint extraction process.

The invention belongs to the technical field of spacecraft product quality and reliability analysis modeling, and particularly relates to a fault tree generation method and device based on a knowledge graph and a large model fusion technology. The method comprises the following steps: constructing a spacecraft product fault domain ontology model, establishing a tag system comprising entity tags and relation tags, and extracting related knowledge from a technical document, a SysML model and an FMEA table by using a large language model to form a triple; according to entity types and relation types of different source knowledge, fusion is carried out, and a fault knowledge graph is constructed; obtaining a function dependence sub-graph, a fault behavior sub-graph and a redundant sub-graph of a function or a composition structure from the fault knowledge graph, and retrieving a specific sub-graph from the fault knowledge graph according to a user question; analyzing fault propagation relation and redundant structure information based on function dependence in the specific sub-graph to construct an OR gate and an AND gate, and mapping nodes in the specific sub-graph to a basic event, an intermediate event, a top event and a gate to generate a fault tree.

The application provides a knowledge graph-based information query method and device, equipment and a storage medium. The method comprises: constructing a target entity vector of a to-be-queried text according to an entity word in the to-be-queried text and an entity type corresponding to the entity word; determining a target query mode corresponding to the target entity vector, and obtaining a graph feature item corresponding to the target query mode; wherein the target query mode is used to indicate a query process of the to-be-queried text in a knowledge graph; associating the entity word to the corresponding graph feature item by using the target query mode; generating a corresponding graph query statement according to the target query mode and the graph feature item associated with the entity word; and querying the knowledge graph according to the graph query statement to obtain a corresponding first query result. The method provides the accuracy of the query result.

Follow ups to user queries are generated in text-to-database query conversion services based on context provided by generated database queries and / or database query execution results. A query generation service extracts an entity type(s) from a database query generated from a user query and, if applicable, from the execution results. The query generation service retrieves a user query template(s) and corresponding database query template(s) for a same table of a target database as the database query and have parameters of the same types as the extracted entity type(s). The query generation service populates the parameter(s) of each user query template and database query template with an entity name(s) that correspond to the entity type(s) and were extracted from the database query and / or database query execution result. The populated user query templates are provided in response to the user query as follow up queries.

The application discloses a network security entity identification method and system based on a multi-layer channel attention, and belongs to the technical field of network security entity identification. The specific method comprises the following steps: performing data preprocessing on a real network security entity text data set; constructing a named entity identification model based on a multi-layer channel attention; inputting the preprocessed network security entity text data set into the named entity identification model for model training, so as to obtain a trained named entity identification model; inputting an actual network security entity text data set into the trained named entity identification model, and outputting a label sequence; identifying the entity category of each word in the actual network security entity text data set according to the output label sequence, and realizing network security entity identification based on a multi-layer channel attention. The application can accurately identify various entity types in network security text, and improve the monitoring and analysis capability of network security events.

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.

A system includes a processor configured to receive, from a registrant device, an upload of at least one document such as incapacity or end-of-life documents. The system stores the at least one document and receives access selections designating each of (i) contact and demographic information of one or more designated individuals and (ii) one or more types of entities permitted to request access to the at least one document as permitted entity types. The system receives an access request identifying a registrant for whom the at least one document is sought and verifies that the requester is a designated individual or associated with one of the permitted entity types. The system provides, to the requester device, access to the at least one document.

This invention discloses a method, device, and storage medium for identifying potential hazards in power transmission channels based on collaborative reasoning using object detection and knowledge graphs. The method generates a knowledge graph of potential hazards in power transmission channels, a rule base for reasoning about potential hazards in power transmission channels, and an object detection model. The object detection model detects and identifies multiple current entity target categories from the current power transmission channel image. These multiple current entity target categories are associated with entity types in the knowledge graph of potential hazards in power transmission channels, resulting in a knowledge graph of potential hazards in power transmission channels that incorporates a transient semantic subgraph. Then, the knowledge graph of potential hazards in power transmission channels that incorporates a transient semantic subgraph is traversed and matched based on the rule base for reasoning about potential hazards in power transmission channels. Reasoning is performed using the obtained hazard reasoning rules to obtain the hazard identification result for the current power transmission channel. The device and storage medium are used to implement the method. This invention can obtain accurate hazard reasoning results, and the hazard logical reasoning process is interpretable.

The invention discloses a cross-type biomedical named entity recognition method and device based on knowledge distillation in the technical field of natural language processing and biomedical information processing. The method comprises the following steps: firstly, acquiring a plurality of single-type data sets for different biomedical entity types, and independently training a teacher model for each data set; meanwhile, gathering all single-type data into a unified training set, and constructing a unified multi-entity type label space; then, for the data in the unified training set, obtaining prediction results of all teacher models, and fusing prediction distributions of a plurality of teacher models into a unified aggregation probability distribution (namely a soft label) by adopting a probability aggregation strategy based on an independence hypothesis; and finally, constructing a student model, and training the student model by using a mixed loss function jointly formed by the aggregation probability distribution and the original label. According to the invention, through knowledge fusion and compression, the problem of label conflict in multi-entity type learning is effectively solved, high identification precision is ensured, a lightweight student model is supported, and the balance between identification performance and calculation requirements is realized.

The application discloses a commercial bank knowledge graph construction and intelligent question and answer method and device based on a large language model, equipment, medium and product. Including: obtaining a data set, and performing entity extraction operation on the data set based on the large language model to obtain an extraction result; the extraction result includes each entity and the relationship between entities; the entity types include customers, products, transactions, organizations and events; the relationship types include owning accounts, purchasing or holding products, product types, subordinate relationships and existing transactions; a commercial bank knowledge graph is generated according to each entity and the relationship between entities; an input question is obtained, and semantic understanding is performed on the input question to identify a query intention; based on the query intention, the commercial bank knowledge graph is matched and queried to obtain a query result. Through the technical scheme of the application, the large language model technology in the field of artificial intelligence can be used to develop and design a knowledge graph for commercial banks, and intelligent question and answer and knowledge management are realized.

The application provides an entity linking method and system, an electronic device and a readable storage medium, wherein the method comprises the following steps: determining a representation of a denotation and a context entity; determining an entity vector of a candidate entity, wherein the entity vector of the candidate entity is obtained by using an average method of word vectors to initially represent entity words of the candidate entity; inputting the entity type feature vector, the entity distance feature vector, the entity relationship feature vector and the entity vector of the candidate entity into an entity disambiguation model to obtain a similarity between the denotation and the candidate entity. The application models entities with complex interaction relationships, maps the entities into low-dimensional vectors, carries more semantic information, improves the accuracy of the model, can fully utilize the context of the text where the entity is located and the background information of the text, disambiguates the entities in the unstructured text, and serves subsequent graph expansion and graph merging and the like.

The invention provides a multi-round dialogue intention classification method and device, and the method comprises the steps: defining and extracting a single-valued slot which is a core keyword contained in an FAQ intention; constructing intention clusters based on the single-valued slots, wherein the intention clusters of the same entity type and the intention clusters of the same single-valued slots are constructed; a single-valued slot inheriting slot mechanism is introduced into multiple rounds of dialogues, and different dynamic score adding strategies are performed on the intention clusters of the same entity type and the intention clusters with the same single-valued slot based on the recognition result that the hit intention has the single-valued slot; and performing intention classification again according to the intention score after score addition. The intention recognition accuracy and effectiveness can be improved.

The subject technology relates to context-based response formulation for retrieval-augmented generation systems. An example method facilitating context-based response formulation for retrieval-augmented generation systems includes supplementing a query provided to a machine learning model with supplemental entity data, resulting in an augmented query, where the supplemental entity data is determined based on context information associated with the query and expected entity types associated with a determined intent of the query. The method can further include determining an estimated degree of error associated with a document retrieved by the machine learning model in response to the augmented query, and facilitating, in response to the estimated degree of error being lower than a threshold degree of error, generating a response to the query based on the document.

The invention discloses an electric power operation plan generation method and device based on semantic analysis, electronic equipment and a storage medium, and belongs to the field of electric power, and the method comprises the steps: obtaining a to-be-analyzed electric power operation log text, and inputting the to-be-analyzed electric power operation log text to a preset operation element extraction model to generate an operation element sequence; wherein the operation element extraction model is obtained through supervised training based on an electric power field corpus with an entity type label; the operation element sequence is input into an operation plan generation model to generate an electric power operation plan, and the operation plan generation model is obtained by performing supervision training on historical data with the operation element sequence as input and the corresponding electric power operation plan as an output label; therefore, by implementing the method, the problems of weak relevance between operation steps and risk management and control measures and insufficient pertinence of safety measures in the prior art can be solved.