89 results about "Knowledge extraction" patented technology

The application discloses a kind of based on multi-source data fusion's catering intelligent decision-making method and system, it belongs to site selection decision-making technical field, by using big language model to carry out knowledge extraction to multi-source data, and to this construction catering site selection knowledge graph, based on knowledge graph automatically calculates geographic position index, traffic accessibility index, consumption potential index and the objective weight of competitive environment index, simultaneously using big language model to the qualitative description of the region to be selected is retrieved to obtain membership vector, according to objective weight and membership vector calculation comprehensive suitability degree score, the recommended site selection region is obtained by ordering comprehensive suitability degree score, it quantifies index weight by catering site selection knowledge graph, avoids subjective dependence on expert experience, quantifies index using big language model, significantly improves the accuracy and efficiency of catering site selection, adapts to large-scale multi-source heterogeneous data scene, and in the face of dynamic factors can respond to update in time, convenient for application and promotion.

The application discloses a knowledge graph construction method and device of a promotion path, wherein the method comprises the following steps: step S1, combing core concepts related to the promotion path and semantic relations thereof, constructing a basic knowledge framework, and creating an ontology model based on the basic knowledge framework; step S2, setting mapping rules between ontology data and a graph database, and mapping the ontology model to the graph database; step S3, collecting multi-source information, performing knowledge extraction on the multi-source information to obtain knowledge triples and constructing entities, and constructing a knowledge graph by comprehensively combining the ontology model and the entities; and step S4, performing retrieval and correlation analysis based on the knowledge graph, forming promotion path instances, dynamically updating the promotion path instances to the knowledge graph, and obtaining a promotion path knowledge graph. The promotion path knowledge graph is obtained based on dynamic updating of the knowledge graph.

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 present disclosure provides a model training method and device, a knowledge extraction method and device, equipment and a medium, relating to the field of artificial intelligence, specifically to the field of knowledge graph technology. The scheme is: analyzing a sample document, determining the level to which each element in the sample document belongs in the sample document, and generating a document tree according to the level to which each element belongs, wherein the nodes of each level in the document tree are used to indicate the elements of the corresponding level in the sample document; for each node in the document tree, querying a target knowledge extraction model matching the type of the element indicated by the node, and using the target knowledge extraction model to extract knowledge from the element indicated by the node to obtain predicted knowledge; and training the target knowledge extraction model according to the difference between the predicted knowledge and the annotated knowledge corresponding to the element indicated by the node on the sample document. Thus, based on deep learning technology, each knowledge extraction model is trained, which can improve the prediction effect of each knowledge extraction model.

The application relates to a marine activity knowledge extraction method and device based on a large language model for marine knowledge extraction. The method comprises the following steps: initially setting a prompt word and optimizing the initial prompt word by setting a prompt word optimization strategy, guiding the large language model to perform sentence transcription on reconstructed data by using the optimized prompt word, and obtaining a preliminary extraction result; labeling the preliminary extraction result according to a pre-set extraction error label system, taking the labeled text as a similar error text, performing sentence structure analysis on the similar error file, generating a simulation text question and answer pair, feeding back and modifying the optimized prompt word, guiding the large language model to perform knowledge extraction on marine activity data by using the modified prompt word, and obtaining marine knowledge. The method can realize marine knowledge extraction.

This invention discloses an intelligent knowledge extraction system based on natural language processing, comprising: a text data acquisition module that acquires unstructured text and forms raw data; a text data preprocessing module that removes noise and standardizes the format of the raw data, outputting standardized text data; a text feature encoding module that converts the standardized text data into feature vectors that satisfy the input of an improved W2NER model; a knowledge extraction module that processes the feature vectors based on the improved W2NER model to obtain entity extraction results; an entity normalization module that performs ontology mapping and normalization on the entity extraction results; a knowledge fusion module that performs deduplication and fusion on the entity knowledge set; a knowledge storage module that stores the fused knowledge data in a structured manner; and a knowledge application service module that provides user knowledge query and reasoning services. This invention improves the accuracy of knowledge extraction and the efficiency of data application.

This application provides a method, system, medium, and terminal for constructing a knowledge graph of faults in key ship equipment. The technical solution of this application is aimed at building a professional ontology model for ship equipment fault diagnosis, defining seven types of entities and five types of relationships, and is compatible with component nesting and bilingual expression. It can completely depict the equipment architecture, fault propagation, and maintenance knowledge. Relying on the large model prompt word engineering, it achieves efficient knowledge extraction with few samples, saving large-scale data annotation and reducing the cost of database construction. It integrates a hybrid alignment algorithm of semantic vectors and edit distance, coupled with a three-level decision mechanism, to efficiently solve the problem of differences in domain entity representation and complete the fusion of multi-source knowledge. The overall solution has outstanding versatility and scalability, and can be quickly adapted to the construction of fault knowledge graphs for various industrial equipment by fine-tuning parameters.

The application provides a scientific research business management and control system based on large model technology, comprising a data acquisition module for acquiring multi-source heterogeneous data in the whole process of power scientific research business; a knowledge extraction module for extracting knowledge from the multi-source heterogeneous data according to a power knowledge graph and a data extraction model to obtain a semantic matrix; a model reasoning module for reasoning knowledge from the semantic matrix according to an intelligent reasoning large model to obtain decision information; a bidirectional association interface for determining a reasoning direction according to a structured field constraint of the data extraction model and determining prior knowledge of the intelligent reasoning large model according to the power knowledge graph; and a business management and control module for managing and controlling the scientific research business according to the decision information. Through multi-module cooperation and deep integration of large models and domain knowledge, the application realizes full mining and accurate analysis of multi-source heterogeneous data in the whole process of power scientific research, makes the management and control basis more comprehensive, and guarantees the accuracy and scene adaptability of the reasoning direction.

The present application relates to the technical field of artificial intelligence large model, specifically to a report generation agent autonomous construction method based on knowledge enhanced large model, which comprises: knowledge extraction on business domain structured documents and unstructured texts and construction of domain knowledge graph, adoption of an improved progressive knowledge injection algorithm to integrate knowledge into general large language model parameters to form a knowledge enhanced base model. Extraction of task planning sequences and operation trajectories generated by historical reports to construct a demonstration sample library, and fine tuning of a primary report generation agent through a behavior cloning strategy. A reinforcement learning training field containing multiple rounds of complex tasks and diversified environmental disturbances is built, interactive data is collected to form a behavior experience pool, decision parameters are iteratively updated based on proximal policy optimization, and autonomous construction of the agent is completed. This method can improve the effect of domain knowledge fusion and enhance the task planning and autonomous decision-making ability of the agent in complex scenarios.

This invention provides a method and system for biodiversity analysis combining neural networks and knowledge graphs in the field of biodiversity analysis technology. The method includes: Step S1, creating a biological knowledge extraction model; Step S2, acquiring a large amount of historical biological data to construct a dataset and training the biological knowledge extraction model; Step S3, extracting named entities, entity relationships, and multimodal information from the latest biological data using the biological knowledge extraction model to construct structured triples; Step S4, defining an ecological ontology and converting the ecological ontology and structured triples into knowledge representations; Step S5, constructing a knowledge graph based on the knowledge representations and defining logical rules for biodiversity analysis; Step S6, obtaining biodiversity analysis results through analysis and reasoning using the knowledge graph and logical rules. The advantage of this invention is that it greatly improves the accuracy of biodiversity analysis.

The application discloses a power transaction knowledge extraction method based on semantic coding and feature enhancement, comprising the following steps: cleaning and term standardization on unstructured text in the power transaction field to obtain preprocessed text; using a pre-training language model based on an error correction mask mechanism to code semantic features of the preprocessed text to obtain a semantic coding sequence; according to the semantic coding sequence, sequentially performing bidirectional long-distance semantic dependence capture, dynamic attention weight distribution and local semantic detail fusion to obtain an enhanced feature sequence; based on a layered pointer network, performing entity and relation joint extraction on the enhanced feature sequence to obtain a triple composed of a head entity, a relation and a tail entity; and performing deduplication and completion processing on the triple to complete the knowledge extraction of the power transaction. The application realizes the goal of automatically and high-quality extracting structured knowledge of the power transaction from unstructured text.

A method, system, and computer device for extracting quality knowledge in engine production, relating to the field of natural language processing technology, include: acquiring engine production process data; extracting quality knowledge from the engine production process data using a knowledge extraction model; and storing the quality knowledge in a quality knowledge base for users to query quality knowledge related to the engine production process. This invention can effectively extract quality knowledge from engine production, enabling rapid identification of quality problems and improving the quality control level of the entire engine production process.

This application discloses a knowledge extraction method, apparatus, and electronic device, relating to the fields of big data and artificial intelligence technology. The disclosed method includes: obtaining page images and text information of a target page; constructing target prompt information; the target prompt information includes the page image, the text information, and guidance information, the guidance information including target constraint information, the target constraint information representing the hierarchical and granular constraints on knowledge extraction; and using a target model to extract knowledge from the page image and text information in the target prompt information based on the target constraint information in the guidance information, thereby obtaining the page knowledge of the target page.

One example method includes performing a first data ingestion process that includes (1) receiving a complete SUD (semi-unstructured data) dataset from a data lake and (2) returning a list of prompts for each SUD type with the complete SUD dataset, performing, by an LLM (large language model) a knowledge extraction process on the complete SUD dataset, and the knowledge extraction process uses optimized attribute names and the list of prompts for each SUD to obtain a complete structured dataset, and returning the complete structured dataset to the data lake.

The application provides an agricultural knowledge large model training data construction method, system and device, the method comprises the following steps: S1, constructing a Mamba classifier based on an agricultural text data classification standard and performing text classification; S2, constructing a text structured rule generation model based on the text classification result and performing knowledge extraction; S3, constructing agricultural large model training data based on the knowledge extraction result; S4, evaluating the agricultural large model training data and adjusting the Mamba classifier and the text structured rule generation model based on the evaluation result. The application can accurately match the diversified training needs of the agricultural large model, ensure that the data is highly adapted to the training needs of the agricultural field through multi-dimensional data screening, and thus provide reliable data for large model multi-scene training tasks.

The application discloses a task intention driven data link network dynamic construction method, first extracts the key information of the task intention through knowledge extraction, constructs a task intention knowledge graph, perceives the state information of each node and reports to the management center to obtain the network state information, constructs a network state knowledge graph and a field professional knowledge graph, reasons the network topology configuration and the business message type corresponding to the task intention, determines the communication node type and the node communication demand according to the business message type, then determines the source node and the destination node of the business message transmission, and the data link network node connection relationship suitable for the current task intention, performs collaborative reasoning through the construction and fusion of the three graphs of the task intention, the network state and the field professional knowledge, converts the abstract task intention into specific network construction parameters, performs real-time solving by using an optimization algorithm, and improves the adaptive ability and task response speed of the on-demand construction of the data link network.

This invention presents a knowledge evolution poisoning attack method for graph-enhanced retrieval and generation systems, belonging to the field of retrieval enhancement and generation. Through knowledge evolution forgery attacks and multi-target cross-subgraph collaborative attacks, it can generate evolutionary corpora that satisfy temporal constraints and have stronger structural connectivity without compromising the overall consistency of the knowledge graph. This allows for a more thorough exposure of GraphRAG's vulnerabilities in knowledge extraction, community partitioning, subgraph retrieval, and evidence aggregation stages in authorized evaluation environments. Compared to direct splicing injection, the samples generated by this method more closely resemble the "real knowledge update" distribution and can be used for pre-deployment red team evaluation, post-deployment regression testing, and effectiveness verification and parameter selection for defense modules such as consistency detection, retrieval filtering, and fact verification.

The application discloses a ship structure strength calculation formula fine-grained knowledge extraction method, which faces a ship structure strength calculation scene and comprises the following steps: generating a specified format text file by analyzing a ship structure strength calculation guide PDF; constructing a ship structure strength calculation formula fine-grained extraction large model; obtaining text-level full-quantity triple by adopting a general ontology model guided text-level full-quantity triple extraction method and a semantic-based triple edge relationship supplementing and correcting method; perfecting the ontology model by adopting an ontology model generation and attribute expansion method based on rule filtering and hierarchical clustering; formulating attribute value text description by adopting a triple snowflake type expansion method based on attribute semantic depth mining; and specifying attribute value reference description by adopting a triple supplementing method based on reference association expansion, so as to obtain formula-level full-quantity triple, thereby constructing a calculation formula graph and realizing the structured management of the calculation formula.

This invention relates to the field of data processing technology, specifically to a method for constructing a knowledge base based on multimodal fusion. The method includes: evaluating the information entropy of image and text features at the input layer to determine mutual information between different modalities, and performing dynamic feature pruning. Subsequently, a bidirectional cross-attention mechanism is used in the intermediate layer for deep feature fusion to form collaborative features. These collaborative features are then input to a knowledge extraction unit to extract knowledge triples, and a semantic consistency score is calculated using a cross-modal similarity verification mechanism. Finally, the knowledge triples are filtered based on the score, and knowledge with high reliability is written into a multimodal knowledge graph. This invention, through optimized data preprocessing and structured knowledge filtering logic, ensures the accuracy of the knowledge base content and the stability of the system operation.

This invention provides an industry knowledge graph-driven multi-source data AI insight and trend prediction system and method. The system includes a multi-source data source, a data acquisition module, an input preprocessing and semantic standardization module, an industry knowledge extraction module, an industry knowledge graph construction module, an intelligent insight and trend analysis module, and a trend prediction result output module. The method includes the following steps: S1, multi-source data acquisition; S2, input preprocessing and semantic standardization; S3, industry knowledge extraction and feature mapping; S4, industry knowledge graph construction; S5, knowledge aggregation and intelligent insight analysis; S6, trend modeling and evolution path analysis; S7, trend prediction result output. This invention can achieve deep fusion, semantic understanding, and trend evolution analysis of multi-source heterogeneous data, providing more comprehensive, accurate, and forward-looking intelligent insight support for industry decision-making, thereby improving the accuracy, forward-looking nature, and interpretability of industry data insights.

This invention relates to a knowledge graph-based method for recommending manufacturing resources, comprising the following steps: establishing a supply and demand information model for the manufacturing domain; constructing a manufacturing domain ontology model to represent the concepts and relationships of demand information and manufacturing resources, serving as the schema layer of the manufacturing domain knowledge graph; performing knowledge extraction; utilizing the knowledge graph for visualization; implementing knowledge graph embedding, during training, obtaining erroneous triples (i.e., negative samples) by randomly replacing head entities; continuously optimizing the loss function using stochastic gradient descent to obtain qualified embedding vectors; after training the vector representations of entities using the TransE model, using vector value calculation to measure the degree of conformity of each resource, and employing cosine similarity calculation to calculate the similarity between vectors; and adding resource QoS service matching based on feature matching.

The application provides a kind of dynamic ontology automatic discovery and generation method based on business semantic alignment, through preset AI technology and change detection function, the feature extraction and business mode recognition of multi-source data are carried out, and the recognition result is obtained;In the case where the business mode is recognized to change, similarity calculation and semantic conflict detection are carried out according to the existing entity and candidate entity, and the semantic alignment result is obtained;Through pattern recognition and knowledge extraction algorithm, ontology recognition is carried out according to candidate entity and semantic alignment result, and new ontology element is obtained;According to the existing entity and new ontology element, ontology model construction and consistency check are carried out, and ontology model is obtained;Realize the automatic ontology discovery and generation process, reduce manual intervention through AI technology, improve ontology construction efficiency;Through semantic alignment mechanism, ensure the consistency of new ontology and existing business semantics, enhance the accuracy and adaptability of knowledge system.

This invention relates to the field of natural language processing technology, and in particular to a question-and-answer knowledge extraction method and system. The method constructs a knowledge graph storage structure, forming a grid structure from the stored data. It then uses the knowledge graph to identify entities and relational elements in user questions, generating an overall question vector. Based on this question vector, it retrieves historical data from the database that matches the user's question. It then retrieves the corresponding question-and-answer pairs from these historical data and directly outputs the answer data from each pair as the search result. If no matching data is found in the historical data, the method performs vector and graph searches on the user question. The search results are then sorted by confidence level, and a limited number of results are weighted and fused to obtain an accurate final result. This invention achieves more accurate search results and improves search efficiency through global semantic similarity and structured correlation analysis.

The application relates to a big data quality control method, a system, a supercomputer and a computer readable storage medium, wherein the method comprises the following steps: a source data acquisition step of acquiring source data from a plurality of preset data sources; a knowledge graph construction step of constructing a knowledge graph based on the source data through knowledge extraction and data alignment, wherein the knowledge graph comprises entity data, relationship data, triple data and subgraph data; a quality control model construction step of configuring quality control parameters, constructing a quality evaluation dataset based on the quality control parameters and the knowledge graph, constructing a multi-modal end-to-end big data quality control model, training the quality control model by using the quality evaluation dataset, and using the trained quality control model to calculate and output a data confidence value based on input entity data, subgraph data and / or triple data. Through the application, big data quality control based on graph data is realized, and the domain expansion of the quality control method is improved.

This invention discloses a 3D human pose estimation method, device, and storage medium, belonging to the field of computer vision technology. To address the problems of existing technologies ignoring inconsistencies in human body part motion, susceptibility to noise interference from auxiliary views, and disruption of spatiotemporal entanglement structures, this invention proposes a cross-view feature adaptive enhancement and spatiotemporal collaborative modeling network. First, multi-view 2D keypoints are acquired; then, enhanced pose features are generated by jointly modeling the overall human body and part-specific features through a hierarchical knowledge extraction module; auxiliary view features are extracted and filtered using the spatial correlation of the current view as weights, achieving cross-view adaptive enhancement and fusion; subsequently, dual normalization along the channel and time dimensions is performed, and global spatiotemporal correlation is calculated by combining spatiotemporal identifier encoding to extract spatiotemporal collaborative features that retain the original motion entanglement structure; finally, the 3D coordinates are regressed and output. This invention effectively improves the estimation accuracy and robustness of 3D human pose.

The application provides a knowledge correlation analysis method and device for a power distribution secondary system, and the method comprises the following steps: obtaining target information in the power distribution secondary system, wherein the target information comprises asset maintenance information, threat dimension information and vulnerability dimension information; removing the target information according to an improved J-Hash method to obtain short text information after removing the target information; generating knowledge triples for the power distribution secondary system by using an optimized knowledge extraction model according to the short text information; and generating a knowledge graph for the power distribution secondary system according to the knowledge triples and an external expert knowledge base. Through the application, the problem of low efficiency of knowledge correlation analysis for the power distribution secondary system in the related art is solved.

The application discloses a field extensible knowledge graph construction method and device, equipment and medium. The method comprises the following steps: constructing an ontology structure of a field knowledge graph, and collecting field data; deploying a plurality of preset algorithms required in knowledge extraction to an algorithm warehouse, and generating a calling API of each algorithm in a micro-service mode; performing entity and relationship extraction on the collected field data by calling the API of a target algorithm, forming a triple, importing the formed triple into the field knowledge graph, and obtaining a constructed field knowledge graph. The field knowledge graph construction method provided by the application has good field extensibility, can realize rapid integration of different field algorithms and models, reduces the human and time costs of accessing algorithm models in different field applications, and improves the graph construction efficiency. Moreover, the field knowledge is fused by using self-training knowledge enhancement, external knowledge bases are not introduced, and the dependence on field data is reduced.

The application discloses a self-adaptive heat management control system based on a knowledge graph, relates to the technical field of intelligent cooking control, and comprises a graph construction module, which creates a structured knowledge graph containing global main cooking system material thermal property nodes, typical cuisine process parameter nodes and various heating stove performance specification nodes, and the nodes are connected through attribute relationship edges; a knowledge extraction module extracts associated nodes and edges in response to a user recipe selection instruction; a temperature analysis module analyzes recommended core processing temperature, maximum safety threshold and texture change temperature range; a data acquisition module acquires real-time temperature and power sequence; and a reasoning control module constructs a Bayesian probability reasoning network based on data and analysis parameters, calculates posterior probability and outputs double-loop control decisions. Through multi-dimensional knowledge association and probabilistic reasoning, the system realizes self-adaptive precise heat management in the cooking process, improves safety and achieves consistency of material texture.

The application belongs to the technical field of data processing, and specifically discloses an intelligent report generation and deep analysis method for government administration personnel analysis, which comprises the following steps: first, forming information data packets from the relevant data of target personnel; then, inputting the unstructured data in the data packets into a large language model for knowledge extraction and forming a personnel knowledge graph; then, generating corresponding language paragraphs according to the data in the personnel knowledge graph and filling them into a report template; based on the generated report content, question answering, correlation search and thinking chain analysis can also be performed. In view of the problem of low work efficiency of personnel analysis and research for government administration key personnel, the application realizes template-based automatic generation of reports by querying aggregated data and automatically extracting and integrating information by a large model, thereby solving the problem of low work efficiency of government personnel caused by the difficulty in processing unstructured data and the heavy burden of report writing in the personnel analysis and research of government administration key personnel under the prior art.