74 results about "Relationship extraction" patented technology

The application provides an enterprise resource planning system data flow conversion monitoring method, relates to the technical field of abnormal cause analysis in an enterprise resource planning system, and aims to solve problems such as difficult extraction of abnormal propagation causality, unexplainable traceability path, and low efficiency of quasi-real-time cause analysis in a multi-node complex business process. The core technical scheme includes the following steps: collecting and standardizing time series data of business key state indicators, establishing a local causal correlation cache by using a sliding window and a causal reasoning algorithm, recursively tracing back to an abnormal node as a terminal to form a preliminary causal path, screening high-confidence causal links through multi-dimensional time consistency evaluation, generating a simplified dynamic path by using a node semantic aggregation mechanism, and finally embedding the path in an operation and maintenance interface in the form of a visual trajectory to realize interactive cause analysis verification. The scheme improves the accuracy and explainability of abnormal cause analysis, realizes full-process automation and man-machine fusion optimization from data to root cause links, and significantly enhances the intelligent level of system abnormality handling.

The application provides a knowledge graph-based user portrait generation method and device and a storage medium. The method comprises the following steps: performing event causal correlation identification on a continuously collected user behavior record sequence to generate a user behavior causal event pair set; performing entity relationship extraction on the set to generate a triple set; further generating a user behavior knowledge graph; performing multi-hop relationship propagation calculation on the user behavior knowledge graph; fusing multi-order neighbor feature information of each entity to generate an entity embedding vector set; performing path mining on the entity embedding vector set through a preset causal reasoning model to identify potential causal conduction paths between different behavior entities; calculating influence weight coefficients between behavior patterns and result states based on the potential causal conduction paths; generating user behavior causal correlation features; fusing the user behavior causal correlation features with the entity embedding vector set to generate user behavior pattern classification results; and generating a user portrait label system. The application improves the depth and application value of the user portrait.

The application provides an artificial intelligence-based engineering cost intelligent agent method and system, relates to the technical field of engineering budget, and comprises the following steps: collecting multi-modal data and performing a pretreatment operation to obtain pretreated multi-modal data; an engineering knowledge graph model performs entity extraction on the pretreated multi-modal data, analyzes entity relationships through a relationship extraction submodel, matches attribute values, and constructs an engineering cost knowledge graph; a cost intelligent reasoning model analyzes input engineering project files, extracts project key information, matches budget items based on the engineering cost knowledge graph, and generates an engineering budget scheme; and an anomaly detection model detects whether the engineering budget scheme is abnormal, intelligently analyzes different budget items, and obtains an engineering budget scheme that meets a normal difference range. The above technical scheme builds an engineering cost intelligent agent, realizes the processing of engineering project files, obtains an engineering budget scheme, and effectively improves the engineering cost budget efficiency.

The application discloses a kind of big language model enhanced emission trading knowledge graph construction method and system, it is related to machine learning field.The present application obtains the unstructured text data in the field of emission trading, carries out document analysis and text segmentation to text data, obtains standardized text fragment;Based on the field of emission trading adaptability prompt engineering guides big language model, carries out entity recognition and relationship extraction to the text fragment, obtains initial knowledge triple and processing, obtains high-quality knowledge triple;Text fragment is converted and constructs structured triple with high-quality knowledge triple and semantic vector fusion's bimodal knowledge representation;The bimodal knowledge representation is stored to graph database, and constructs the field of emission trading knowledge graph;Based on double-path retrieval, carry out retrieval and knowledge traceability to knowledge graph, realize the field of emission trading intelligent question and answer and knowledge application.The present application realizes the efficient conversion from unstructured data to structured knowledge.

The application belongs to the field of knowledge graph, and particularly relates to a knowledge graph construction and completion method based on joint extraction and link prediction, comprising: a joint entity relationship extraction method based on latent relationship detection and conditional entity mapping, which is used to construct a knowledge graph; and a knowledge graph link prediction method fusing graph structure information and multiple features, which is used to automatically complete the knowledge graph generated in the extraction stage. The method solves the problems of relationship redundancy and noise in the existing knowledge graph construction method in the triple extraction process, which cannot accurately identify overlapping triples, and the problems of insufficient global feature capture and failure to utilize graph structure information in the knowledge graph completion stage.

The application discloses a network security vulnerability knowledge graph construction method based on HPO-BiLSTM-CRF, which comprises the following steps: collecting public vulnerability data from related databases in the network space security field, preprocessing, and constructing a data set; analyzing and extracting existing data source feature information, and constructing a network security vulnerability domain ontology model CSVDO; based on the optimized bidirectional long short-term memory network and the conditional random field fusion model HPO-BiLSTM-CRF, realizing named entity recognition and relationship extraction; adopting an integrated entity alignment method for knowledge fusion, matching different instances of the same object in different ontologies based on an improved similarity measurement algorithm, and constructing a knowledge graph; carrying out knowledge graph embedding, storing the result into a graph database, and completing knowledge graph construction and graphic visualization. The application can improve the efficiency of entity recognition and relationship extraction in network security vulnerability knowledge, and has the advantages of high efficiency and high accuracy compared with other graph construction methods.

This invention discloses a government affairs intelligent question-answering method and system based on pre-trained model enhancement. The method includes: standardizing the original government affairs text data; extracting government affairs entity relationship triples using a PW2NER+CASREL entity relationship joint extraction model; constructing a government affairs knowledge graph stored in a graph database; for user-inputted government affairs natural language questions, parsing the core entities and user intent in the questions through entity extraction, question classification, and question-answering enhancement processing, converting unstructured questions into structured query triples recognizable by the graph database; converting the structured query triples into graph database query statements; performing accurate retrieval in the government affairs knowledge graph; formatting and optimizing the retrieval results; and providing the user with the final answer and related visualization information, thus realizing government affairs question-answering. This invention can effectively improve the accuracy of government affairs entity relationship extraction and question intent recognition, and can be widely applied to intelligent government service scenarios.

This invention relates to the field of computer vision technology and discloses a method, apparatus, device, and readable storage medium for table recognition. The method includes: acquiring an image to be recognized; inputting the image to be recognized into a preset table detection model to identify a table image from the image; inputting the table image into the preset table recognition model to determine the endpoint coordinates of each cell in the table image and the connection relationships between the endpoints; and generating a target table based on the endpoint coordinates and connection relationships. By implementing this invention, table recognition is achieved through endpoint extraction and endpoint connection relationship extraction, eliminating reliance on table line extraction, ensuring the accuracy of table structure recognition, and improving the accuracy of table information recognition.

The application discloses an improved knowledge graph construction method and system for textile weaving, relates to the technical field of textile manufacturing, and solves the problems of insufficient feature description ability of the knowledge graph of the prior art for the textile weaving industry, difficulty in expressing the time sequence logic evolution characteristics and the causal relationship under the multi-source disturbance, lack of entity boundary definition and semantic recognition mechanism for weaving professional terms, and serious semantic mismatch of relationship extraction, the method comprising: constructing a knowledge base data set of the improved knowledge graph, modeling five concept domain ontologies, defining a semantic link paradigm, enhancing co-occurrence of graph entity boundaries, and enhancing attention graph extraction with relationship type perception, carrying out weaving knowledge entity recognition and relationship extraction result reasoning output, introducing a structured energy consumption semantic network to realize the transition of the model from data driving to knowledge driving, and realizing the transition from "numerical correlation" to "causal interpretability" through an embedded semantic layer fusion mechanism.

The application provides a training method of a classification model, a content recommendation method and related equipment, and is used for solving the problem of low classification accuracy of the classification model. The method at least comprises: based on the arrangement relationship between each word segmentation contained in a sample review text, extracting a review semantic feature of the sample review text, and based on the context relationship between each sentence contained in a sample introduction text, extracting an introduction semantic feature of the sample introduction text; fusing the review semantic feature and the introduction semantic feature to obtain a semantic fusion feature; based on the difference between the sentiment category and the sentiment label predicted by the semantic fusion feature, adjusting the model parameter of the classification model. By fusing the multi-modal texts such as the sample review text and the sample introduction text to train the classification model, the classification accuracy of the trained classification model can be improved.

The application relates to the field of intelligent agricultural information processing and discloses a flower disease and pest knowledge graph construction system and method based on artificial intelligence, which comprises the following steps: a collection module is used to carry out domain sampling on multi-source corpus, a parsing module is used to extract four-channel time sequence elements containing a calendar, a phenological stage, an operation event and an environmental threshold; an entity recognition module extracts graph entities based on channel gating values, a relationship extraction module generates a period vector and constructs a graph quadruple by using the four-channel time sequence elements; a time sequence conversion module extracts a double-axis time sequence operator to output a disease window coordinate by fitting the mapping relationship between the operation event and the period vector; a knowledge fusion module spatially aligns the disease window coordinate with the graph entities; and finally, a graph application module establishes a graph network and outputs the same. The application can realize deep fusion of cross-source information, significantly improve the intelligent level of flower disease and pest early warning and diagnosis, and accelerate the feedback efficiency of agricultural instructions.

This invention proposes a method for extracting entity relations from power technology standards based on multi-turn automatic question answering, comprising: Step 1. Constructing a corpus of power technology standards; Step 2. Constructing information extraction element templates for different types of power technology standards corpus; Step 3. Constructing a question-and-answer corpus of power technology standards based on the information extraction element templates; Step 4. Constructing a text classification module for the power technology standards corpus described in Step 1; Step 5. Automatically constructing a multi-turn question-and-answer and question module by matching the text classification results with the information extraction element templates in Step 4. This module breaks down complex questions into simpler ones and provides step-by-step reasoning answers; Step 6. Constructing a machine reading comprehension module for the power technology standards question-and-answer corpus, which provides step-by-step reasoning answers to the questions automatically constructed in Step 5, thus completing the extraction method of this invention. This invention can effectively alleviate the phenomena of overlapping relations and cross-sentence dependencies in complex texts.

This invention discloses an intelligent retrieval method and system for business requirements based on big data, specifically relating to the fields of big data and natural language processing. The invention acquires multi-source heterogeneous data to construct a unified big data resource pool; extracts user behavior features to construct a multi-dimensional user profile including explicit and implicit tags; performs entity recognition and relationship extraction based on business description text and historical requirement data to construct a requirement knowledge graph; receives user retrieval requests and uses a deep semantic matching model combined with the user profile to parse them into structured query instructions; executes graph traversal retrieval based on the knowledge graph and vector similarity retrieval based on the resource pool in parallel to obtain first and second retrieval result sets, respectively; finally, based on a multi-objective optimization algorithm, and combined with user profile preference weights, dynamically fuses and sorts the two results to generate the final retrieval result.

The application discloses a large language model instruction data screening method and device, equipment and a storage medium, which can be applied to the technical field of large language models, and the instruction data set to be screened is acquired, the implicit interaction relationship of the instruction data set is extracted, an instruction graph structure is obtained, the uncertainty perception influence score of each node in the instruction graph structure is calculated in combination with the influence and uncertainty of the node on the instruction graph structure, a target function is constructed with the maximum uncertainty perception influence score as the target, the target function is solved again based on the target function, and the optimal instruction set is obtained, so that the screened instruction data is obtained. The screening effect of the instruction data is significantly improved through the above method, and high-quality instruction data is obtained.

The application belongs to the technical field of artificial intelligence and food safety information, and discloses a question and answer system of a meat product whole-chain safety knowledge graph based on deep learning, which is composed of a knowledge graph construction module and a system question and answer module; wherein the knowledge graph construction module comprises a data acquisition unit, a data processing unit, an entity recognition unit, a relationship extraction unit, a critical control point selection unit and a knowledge graph construction unit; the system question and answer module comprises a user question analysis unit, a query statement generation unit, a standard answer generation unit and an intelligent question and answer Web system construction unit. The question and answer system of the meat product whole-chain safety knowledge graph based on deep learning is adopted, a more easy-to-use and more intelligent natural language question and answer system is developed by constructing the meat product whole-chain safety knowledge graph, and finally the professional, scattered and complex meat product safety knowledge is efficiently, accurately and friendly provided to the end users.

The application relates to the technical field of knowledge graph, in particular to a policy question and answer system and method based on multi-model cooperation and graph enhancement and a medium, the method comprising automatically generating a policy knowledge ontology structure, configuring a multi-model cooperative extraction engine, performing entity recognition and relationship extraction tasks on a standard policy corpus, and cross-verifying and aligning the extraction results of multiple large language models through a preset conflict resolution strategy to obtain a structured policy knowledge triple set; based on the policy knowledge ontology structure, mapping the structured policy knowledge triple set to a graph database to construct a dynamic policy knowledge graph. The application configures a multi-model cooperative extraction engine and cross-verifies and aligns the extraction results of multiple large language models through a conflict resolution strategy, thereby improving the accuracy of the structured policy knowledge triple and effectively correcting the semantic illusion or extraction deviation that may exist in a single model.

The application discloses an enterprise knowledge graph construction and intelligent decision system based on artificial intelligence, comprising the following modules: an evidence construction module, which is used for collecting enterprise multi-source business data and constructing time-aware evidence anchor points, and generating an enterprise evidence unit set; a relationship extraction module, which is used for performing entity-event-relationship linkage extraction, and generating enterprise candidate relationship edges; a conflict identification module, which is used for constructing a conflict decision matrix and generating a cross-source evidence conflict graph; a credibility generation module, which is used for generating an enterprise evidence credibility vector; a graph pruning module, which is used for generating a credible enterprise knowledge graph; a decision retrieval module, which is used for generating an enterprise decision evidence set based on an improved LightRAG retrieval architecture; and a decision output module, which is used for generating an enterprise intelligent decision result and a traceable evidence chain. The application can improve the credibility of the enterprise knowledge graph, the accuracy of the decision evidence and the traceability of the decision process.

The application provides a speech recognition method and device, human-computer interaction equipment and a storage medium, wherein the method comprises: determining an environment video of an environment in which a to-be-recognized speech is located; performing entity extraction on a video description text of the environment video, and updating a keyword library based on an entity extraction result, and / or performing entity relationship extraction on the video description text, and updating a knowledge graph based on an entity relationship extraction result; and performing speech recognition on the to-be-recognized speech based on the updated keyword library and / or the updated knowledge graph. The speech recognition method and device, human-computer interaction equipment and storage medium provided by the application can form personalized knowledge for a user, can expand text corpus that conforms to the habit of the user or matches current environment information, thereby improving the accuracy of speech recognition, improving the success rate of speech command interaction, and improving the user experience.

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 disclosure provides an artificial intelligence-based variant site prediction screening system and method, in the disclosure, the literature retrieval module is used to grab the data of multiple sources of evidence, and a medical knowledge graph for variant site prediction is constructed based on the grabbed data; wherein, the trained graph construction model is used for entity recognition, relationship extraction of the grabbed data, and the medical knowledge graph is constructed based on the identified entity and the extracted relationship; the evaluation index extraction module is used to extract the evaluation index by using the medical knowledge graph, and determine the dynamic weight corresponding to each evaluation index based on the scene label and the time attenuation factor; the scoring module is used to determine the risk score value of each point in the to-be-detected gene sequence based on each evaluation index and the dynamic weight corresponding to each evaluation index; the variant site screening module is used to screen abnormal point from each point according to the risk score value; the user interaction module is used to display the abnormal point and show the modification text box of the dynamic weight corresponding to each evaluation index, so that the user inputs the correction value of the dynamic weight corresponding to each evaluation index.

The application relates to the field of sports question and answer model construction, and discloses a sports question and answer model feature extraction method, device, equipment and medium, which comprises the following steps: obtaining sports text; performing entity extraction on the sports text to obtain sports entity data; performing relationship extraction on the sports entity data to obtain entity relationship data; constructing a sports text knowledge graph according to the sports entity data and the entity relationship data, and extracting graph feature data from the sports text knowledge graph; and processing the sports entity data, the entity relationship data and the graph feature data through a multi-source fusion function to obtain sports comprehensive features. The application can support the construction of a sports question and answer model and improve the quality of sports response text.

The present application relates to the technical field of land resource management, and is especially a kind of plot full life cycle compliance dynamic evaluation and multidimensional operation monitoring method, obtains plot full life cycle multi-source heterogeneous data, constructs initial plot state graph by time-space benchmark alignment and entity relationship extraction;By the embedding of the differentiable rule and the time-space graph attention network, the dynamic compliance state vector and the compliance risk gradient are output;Based on cross-modal feature alignment, calculate the operation dimension deviation time sequence, identify the operation abnormal mode;Build a compliance operation two-way coupling optimization module, establish a joint optimization model and iteratively solve to generate adaptive control instruction set;The execution feedback and compliance risk gradient residual are fused, the plot state graph node feature and edge weight are dynamically updated, and the state closed loop iteration is completed.The present application realizes the integrated management of plot full life cycle, early warning compliance risk, balances the compliance bottom line and operation benefit, and improves the intelligent level and comprehensive utilization efficiency of land resource management.

The application provides a city information model knowledge graph construction method and device and a readable storage medium. The method comprises: a CIM concept classification system: constructing conceptual knowledge as a standard for inducting or classifying specific CIM entities; CIM entity construction: converting discrete CIM data into specific objects according to the conceptual knowledge; CIM relationship extraction: extracting relationship information from various objects through the processes of knowledge extraction, relationship linking and relationship reasoning; CIM knowledge fusion: quantifying CIM knowledge into a CIM concept layer, a CIM entity layer and a CIM relationship layer by using a top-down construction method to obtain a CIM knowledge graph. The application combines actual CIM business needs, adds CIM business relationships on the basis of main semantic relationships, and is used for fusing semantic relationships and spatial relationships to realize large-scale multi-source heterogeneous data storage management and information retrieval.

The application discloses a kind of structured knowledge extraction method, system, equipment and storage medium of automobile software design document, the method includes: to automobile software design document is carried out format conversion and area division, obtains structured data block set;Through sequence mark model, named entity recognition and type mark are carried out to text type data block, and obtain entity type label list;According to preset automobile software relationship rule, generate multiple groups of entity candidate relationship pairs according to entity type label list;According to text type data block, relationship extraction is carried out to each group of entity candidate relationship pairs by graph neural network, to generate relationship triple set;Entity type label list, relationship triple set, the structured information in text type data block is stored.The present application is sequentially linked by the steps of file analysis, entity recognition, relationship extraction and data storage, effectively solves the problem of intelligent extraction structured knowledge from automobile software multi-modal design document.

A method and system for automatic classification of unstructured data based on business semantic understanding is disclosed, relating to the domain of computer systems based on a specific computational model. This method constructs a classified domain ontology library containing business concept nodes and logical relationship edges, and builds sensitive semantic template graphs with different security levels based on the ontology library. For the unstructured data to be classified, entity instances and their dependencies are extracted using an entity relationship extraction model and mapped to the ontology library to form a subgraph of facts to be tested. By calculating the matching score between the subgraph of facts to be tested and each sensitive semantic template graph, the security level corresponding to the template graph with the highest matching score exceeding a threshold is selected as the classification result. This application aims to improve the efficiency of unstructured data sharing and analysis across departments.

This application provides a method and system for managing activities related to ancient architecture research and study, relating to the field of digital culture. The method includes: acquiring multi-source data on ancient architecture and basic data of research and study users; performing entity recognition and relationship extraction on the multi-source data to construct a knowledge graph of ancient architecture and form structured knowledge of ancient architecture; constructing a set of rules for the knowledge graph of ancient architecture based on the multi-source data and the knowledge graph of ancient architecture; constructing user profiles based on the basic data of research and study users and the knowledge graph of ancient architecture; the user profiles are used to characterize the user's cognitive level, interests, preferences, and learning abilities; retrieving knowledge subgraphs from the knowledge graph that match the user profiles, and generating research and study activity paths. This application, used in the management of activities related to ancient architecture research and study, solves the technical problem that existing technologies cannot meet the needs of multi-dimensional knowledge integration and application in ancient architecture research and study activities.

This invention relates to the field of machine learning technology, specifically to a method and system for intelligent spatial data analysis and decision support based on a large language model. The method includes the following steps: acquiring spatial entities, location phrases, and task descriptions; analyzing word order and modification relationships; extracting task elements and action sequences; constructing continuous semantic paths; identifying geographic terms and range changes; extracting statements whose angle between action instruction direction vectors is less than a preset threshold; and obtaining a set of spatial action structures. In this invention, a semantic task list is constructed by extracting spatial entities, location phrases, and task content. Actions are ordered by combining action words and word order relationships. The connection methods between segments are analyzed, and a coherent task path is organized. The sequential matching and semantic connection between spatial objects and actions are completed. By filtering the information structure of action direction and location changes, task statements are arranged in an orderly manner according to the process, avoiding ambiguity and interruptions in instruction transmission, and maintaining the orderly integration and flow of spatial information.

The application relates to the technical field of large model industry application, in particular to a large model empowerment private knowledge base construction and integration method for industry scenarios, which comprises the following steps: multi-source heterogeneous data structured preprocessing, industry large model entity relationship extraction and knowledge graph construction, unified semantic space vector mapping, bidirectional knowledge alignment, privacy isolation knowledge integration interface layer construction, and collaborative reasoning scheduling whole process design; a large model fine-tuning, full life cycle incremental updating and hierarchical permission control mechanism are matched, high-precision construction of an industry private knowledge base and deep safety integration of a large model are realized, large model reasoning illusion is greatly reduced, response efficiency and business matching degree of a scenario reasoning are improved, and the method has good industry expansibility and engineering landing practicability.

Embodiments of the present application disclose a sequence diagram-based test scenario generation method, device, equipment, medium and product. The method comprises: acquiring a design sequence diagram and a preset sequence diagram standard. The design sequence diagram comprises interactive elements for describing message passing and control flow between objects. The sequence diagram standard is used for describing rules and requirements for drawing a sequence diagram. Element relationship extraction is performed on the design sequence diagram according to the sequence diagram standard, to obtain mutual relationships between interactive elements in the design sequence diagram. An interactive directed graph for describing interactive element flow is constructed according to the mutual relationships. Each operation path described by the design sequence diagram is extracted from the interactive directed graph, and a target test scenario corresponding to the design sequence diagram is generated according to each operation path. The technical solution of the embodiments of the present application realizes standardization and automation of test scenario generation, guarantees coverage and accuracy of the test scenario, and reduces dependence on experience of test personnel.

The application discloses a kind of open source software supply chain malicious package detection platform based on social network graph centrality, it is related to safety detection technical field, including the file acquisition module to be measured, for obtaining open source software package to be measured, parsing source code file, installation script file and dependent declaration file, and based on uniform intermediate representation mechanism extraction API call relationship data and basic supply chain attribute data;Static relationship extraction module is used to construct static API call directed graph according to API call relationship data, and constructs cross-layer supply chain association graph according to basic supply chain attribute data;Characteristic vector generation module is used for multidimensional centrality joint calculation to static API call directed graph and cross-layer supply chain association graph.The application realizes the depth fusion of static preliminary screening and dynamic verification, accurately identifies hidden malicious package, significantly improves the accuracy and reliability of open source software supply chain malicious package detection.