231 results about "Triplestore" patented technology

The invention belongs to the technical field of equipment knowledge engineering and natural language processing, and discloses an LLM-based constraint and self-repairing uniformization equipment knowledge graph automatic construction method. The method comprises the following steps: firstly, acquiring equipment related document data through network collection, document arrangement and database query; then, utilizing an equipment domain ontology and constraints as preposed soft and hard constraints, driving LLM to generate semantic intermediate representation, and obtaining candidate triples through structured compiling; then, a self-repairing closed loop is formed through semantic unit testing, logic consistency detection and evidence binding verification, and triples which violate constraints and have conflicts or illusions are automatically recognized and repaired; and finally, entity standard identification, cross-document duplicate removal combination and conflict resolution are realized through cross-segment unification and incremental alignment. According to the method, the fragile path that the LLM directly generates the triple and blindly stores the triple is avoided, the illusion and inconsistency problems are effectively inhibited, and the correctness, interpretability and maintainability of the equipment knowledge graph are remarkably improved.

The invention discloses a knowledge graph completion method based on combined prediction of large and small models, which comprises the following steps: 1, constructing and preprocessing a knowledge graph completion reference data set, and training by adopting a RotatE model to obtain candidate entities generated by the model and confidence scores; 2, constructing a related triad, an adjacent triad and entity long text description based on the query to form a context prompt, inputting the context prompt and the query into a large language model, and performing semantic reordering and scoring by the large language model; and 3, constructing a fine tuning data set, and performing fine tuning on the large language model to obtain the KGC task optimization-oriented large language model. And based on the KGC score, the LLM score and the dynamic weight, outputting a complementation result through joint prediction of a fusion result. According to the method, the structured reasoning ability of the small model and the deep semantic understanding of the large language are effectively combined, the prediction accuracy, robustness and specialty are remarkably improved, and the defects that a single model is weak in generalization ability and insufficient in semantic utilization are overcome.

The invention discloses a document auditing method and device based on cooperation of a large model and a rule engine. The method comprises the following steps: analyzing an original document to form an intermediate representation file; extracting entities from the intermediate representation file to form an entity candidate set; inputting the thinking chain cue word into the large model to obtain a first triple, a first confidence coefficient and a first risk level, and calculating a first traceable score of the large model according to the reasoning path node; performing deterministic judgment by using the rule engine to obtain a second triple, a second confidence coefficient, a risk level and a second traceable score; calculating two weighted voting values and obtaining a conflict difference value; taking a conclusion corresponding to the high-weighted voting value as a final conclusion when the conflict difference value is smaller than a preset judgment threshold value; otherwise, starting an artificial rechecking process; and generating audit reports in various formats. According to the method, the advantages of relatively high language understanding ability of a large model and relatively high certainty of a rule engine are exerted, and the problem of missed checking or excessive marking is avoided.

The invention discloses a knowledge graph construction method and device based on a large language model and a judgment document, and the method comprises the steps: segmenting an original text of the judgment document, and obtaining a text fragment set; inputting the text fragment set into a pre-training language model and a large language model to obtain an entity set and a property clue set; performing cross-model consistency verification on the entity set and the property clue set to generate an entity-clue mapping table; performing disambiguation processing and standardization processing on entities in the entity set based on the entity-clue mapping table to obtain a standardized entity list; constructing an entity pair list based on the standardized entity list and extracting a relation triple to obtain a candidate triple set; and performing reverse verification and rule filtering on the candidate triple set, and constructing a target knowledge graph based on the high-confidence triple set. According to the method, the quality of the slave knowledge graph can be improved, and then the efficiency and accuracy of automatically discovering and associating debtor property clues from legal documents are improved.

The invention belongs to the technical field of knowledge graph construction, and particularly relates to a multi-source heterogeneous data fusion and knowledge graph automatic construction system, which comprises a semantic extraction module for extracting minimum semantic fragments from multi-source data and performing cross-source alignment to generate a symbolized semantic framework; the data purification module converts multi-source data into symbolic predicates according to the framework, filters low-evidence data and outputs a purification set; the ternary generation module inputs the initial triad candidate set into a minimum rule grammar, and extracts entities, relationships and attributes to generate an initial triad candidate set; the disambiguation calibration module generates entity two-hop topological fingerprints based on the candidate set, completes disambiguation alignment and corrects conflicts, and outputs unambiguous structured knowledge; the mapping fusion module fuses the mapping information with the minimum connected ontology, and constructs and verifies an initial mapping knowledge domain; and the incremental updating module processes newly added data, performs incremental merging and maintains consistency, and forms a complete knowledge graph. According to the method, through full-link automatic construction, efficient fusion and high-quality atlas are realized.

A system and computer-implemented method facilitate expansion of knowledge. The system allows for characterization of natural language documents and of search queries to locate those documents. A natural language processing (NLP) analyzer finds subject-verb-object (SVO) triplets in received text and assigns initial hierarchical classifications to word components of the SVO triplets. An SVO analyzer generates variation hierarchical classifications by varying the initial hierarchical classifications assigned, selects at least one hierarchical classification from the initial hierarchical classifications and variation hierarchical classifications, and produces a token stream of tokens. The tokens represent respective hierarchical classifications of the at least one hierarchical classification selected. The token stream produced may represent a natural language (NL) document to be stored to facilitate matching the NL document to a subsequently independently specified query. Alternatively, the token stream produced may represent a query and the token stream is used for generating a response to the query.

The invention provides a retrieval enhancement generation method and system in the dual-carbon field, and relates to the field of data processing. According to the method, multi-source unstructured data in the dual-carbon field is collected, after data preprocessing is carried out, a multi-granularity query problem set is formed, a dual-carbon field knowledge base is obtained, and a dual-carbon field-oriented embedding model CEMBING and a reordering model CReranker are constructed. The CEMBING model adopts a semantic partitioning method and a joint training strategy, so that semantic information of a dual-carbon field text can be effectively captured; the CReranker model adopts a negative example mining strategy and a triple loss function, candidate documents can be accurately sorted, the problems of knowledge limitation and insufficient timeliness of LLMs in the application of the dialogue system in the dual-carbon field are effectively solved, and the accuracy and efficiency of retrieval enhancement generation of the dialogue system in the dual-carbon field are improved.

The invention belongs to the field of computer vision and artificial intelligence, and provides a scene graph generation method and system based on dual-dependence joint learning, and the method achieves the feature alignment through the cross attention operation of the flattening features of an input image and the query vectors of a subject and an object. Then, subject and object features are analyzed, high-confidence pairs are screened out, and the high-confidence pairs and predicate query vectors are processed in a decoder to output triple semantic features. And constructing a global association graph based on the features, updating node features by using an attention graph convolutional network, and finally predicting the category and bounding box of each triple by using a multi-layer perceptron to complete scene graph generation. According to the method, the generation accuracy and the relation context consistency are improved, the method is suitable for the fields of image understanding, intelligent monitoring and the like, and a complete system architecture solution is provided.

The invention provides a bridge operation and maintenance knowledge management and question answering method based on a knowledge graph and a large language model. The method comprises the following steps: performing semantic dicing and dynamic cue word generation on texts such as a design report and an overhaul report through a large language model, automatically extracting an entity-relationship-attribute triple, completing entity co-reference resolution and relationship combination, and constructing an initial knowledge graph; further utilizing a curiosity algorithm to continuously merge low-similarity new knowledge in a subsequent detection report to realize iterative growth of the atlas along with an operation and maintenance life cycle; forming a multi-level community by adopting Leiden clustering, generating an abstract pyramid, and enhancing macroscopic semantic expression; and finally, through a semantic embedding model and a GraphRAG technology, precise matching and traceable answering from natural language questions to graph knowledge points are realized. According to the method, the problems of knowledge fragmentation, update lag and illusion in the bridge operation and maintenance field are solved, and the accuracy and robustness of operation and maintenance knowledge questions and answers are improved.

The invention provides a ticket business full-life-cycle anti-counterfeiting and verification system based on block chain trusted triple mapping, and relates to the field of electric digital data processing. Comprising a trusted triple construction and cryptography binding module, a block chain hash anchoring and consensus evidence storage module, a trusted triple dynamic evolution and state transition module and a multi-level anti-counterfeiting verification and anomaly detection module, the block chain Hash anchoring and consensus evidence storage module is used for storing a trusted triple in a block chain in a tamper-proof manner, and the trusted triple dynamic evolution and state transition module is used for realizing state tracking and evolution management of ticket business in a full life cycle. The multi-level anti-counterfeiting verification and anomaly detection module is used for providing static identity verification, dynamic anti-counterfeiting vouchers and abnormal behavior detection capability; according to the system, the security problem in a ticketing system is solved by enhancing the security of the entity identifier and protecting state transition privacy.

The invention discloses a high-efficiency lightweight federal recommendation method, which comprises the following steps that: a server initializes an article continuous value embedding matrix and an article offset vector, obtains a binary article matrix through binarization processing and distributes the binary article matrix to a client; the client constructs a training triple through difficult negative sample mining based on local data, carries out local training by adopting a mixed loss function combining sorting loss, reconstruction loss and regularization loss, updates user parameters and calculates an article gradient; and the server aggregates the gradient update global parameters uploaded by the client. According to the method, the model expression ability is enhanced by introducing bias terms, the sorting performance is optimized by adopting a mixed loss function, the training efficiency is improved by combining difficult negative sample mining, the recommendation precision is remarkably improved on the premise that the federated learning privacy protection advantage is completely reserved, meanwhile, the client storage, communication and calculation expenses are greatly reduced, and the user experience is improved. The method is especially suitable for mobile terminal deployment with limited resources.

The invention discloses a cross-platform business system integration method based on a knowledge graph. The method comprises the following steps: S1, reading data from a business platform database and generating a field text, an entity identifier and a relation record; s2, inputting the field text into an ALBERT model, and generating a field semantic vector through a field word vector gating layer; s3, forming a triple according to the entity identifier and the relation record, and writing the triple into a knowledge graph; s4, inputting the triple into a TransH model, and generating an entity structure embedding vector through dynamic rotation updating of a relation vector and a hyperplane normal vector; s5, generating an entity embedding vector according to the field semantic vector and the entity structure embedding vector; s6, calculating a plurality of distances based on the entity embedding vectors to obtain the similarity of the cross-platform candidate entity pairs; and S7, performing repeated entity judgment on the similarity, and updating the knowledge graph. According to the invention, accurate alignment of cross-platform service entities is realized, the data fusion efficiency and consistency are improved, and the method is suitable for a multi-source service integration scene.

The invention relates to the technical field of knowledge graph generation, in particular to a dynamic and static dual-state knowledge graph generation system, which is characterized in that an object is used for replacing an entity as a node, a traditional triple is upgraded into a tetrad containing a timestamp, and a state tetrad is newly added; quadruple elements (including timestamp mining) are extracted through a semantic parser, a parameter space is maintained, a construction engine constructs a quadruple, stores the quadruple into a graph database and executes four-item rationality detection, a vacancy filling engine calls a fine-tuned large language model, and an intelligent agent screens high-credibility answers to complement knowledge. Traditional static representation limitation is broken through, object dynamic description is realized, accurate and complete atlas is guaranteed, and an important logic basis is provided for next-generation artificial intelligence interpretable reasoning.

The invention relates to a multi-source information knowledge fusion and intelligent retrieval method and system, and the method comprises the steps: obtaining multi-source heterogeneous data, and carrying out the unified knowledge modeling of the multi-source heterogeneous data, and obtaining a unified knowledge framework; and based on the unified knowledge framework, calling a large language model to perform structured preprocessing on the multi-source heterogeneous data to generate a structured knowledge triple. And performing structured processing on the structured knowledge triple through the attribute graph, and performing vectorization storage on each entity associated data through the embedded model to obtain a fused knowledge body. And receiving a user query request, and in response to the user query request, performing deep analysis on the user input data to obtain a user query intention and query elements. According to the method, the condition graph is constructed according to the query intention and the query elements of the user, and the condition graph is mapped into the knowledge network for entity positioning and condition graph matching to generate the structured retrieval result, so that the network overhead and scheduling delay are reduced, and the retrieval response speed and accuracy are improved.

The invention discloses a remote bank fuzzy question-answer accurate matching method based on deep learning. The method comprises the following steps: firstly, constructing a business semantic system (clear business class-scene-specific intention), a term and variant mapping library and a sentence pattern template containing a replaceable entity slot position; extending the original similar question pairs to generate derivative sentences and candidate similar sentences, filtering, clustering to generate cross-sentence pattern similar pairs, and selecting negative samples to control the literal overlapping rate; then constructing a twin BERT network, mixing original and enhanced samples into a training set, and training in two stages by using improved triple loss; finally, sentence vectors are generated through the trained twin network, semantic similarity is judged according to cosine similarity, question pairs which are judged to be similar through a model are subjected to secondary verification through a service rule base, and score reduction is carried out if the question pairs do not pass verification.

The invention belongs to the technical field of large language models, and discloses an improved semantic unit-based heterogeneous government affair knowledge graph construction and multi-dimensional causal retrieval enhancement method, which comprises the following steps of: extracting an entity and relationship triple from an unstructured text through a thinking chain CoT technology guided by a large language model LLM; a semantic unit is introduced to serve as a fine-grained knowledge carrier, and a double-track heterogeneous graph structure is constructed; the method comprises the following steps: constructing three semantic dimensions of an entity, a theme and a global, respectively designing adaptive retrieval strategies, executing retrieval and matching in parallel, and realizing accurate fusion and efficient retrieval of multi-source knowledge through a multi-channel concurrent mechanism; and a causal analysis report mechanism is further introduced, semantic refining and redundancy filtering are performed on a fusion result, and the accuracy and interpretability of a question and answer result are improved.

The invention discloses an electronic archive intelligent data management method and system based on a large model. The method comprises the following steps: firstly, acquiring an electronic archive file, performing unified access, identifying a text through an OCR (Optical Character Recognition) technology, and reserving original layout coordinate information; analyzing the document page by page to generate a page-level structured object containing text and position mapping; then, on the basis of a preset domain prompt template, calling a large language model to extract file metadata from the page-level object, recognizing entities and relationships in combination with file knowledge ontology, and generating a semantic triple containing an evidence source page number; and finally, fusing the metadata and the triple to construct an electronic archive knowledge graph with a page-level traceability function. According to the invention, through a whole-process semantic governance mechanism from access, analysis to knowledge generation, the problems of difficult analysis of unstructured data, weak semantic understanding and lack of traceability in traditional archive management are effectively solved, and the intelligent level and data credibility of archive governance are significantly improved.

The invention provides a project declaration content compliance review method and system combining named entity recognition and a large model, and relates to the technical field of natural language process.The method comprises the steps that firstly, a project declaration full-cycle document set is obtained, and the project declaration full-cycle document set comprises a declaration document, a contract document, a mid-term check document and a question settlement acceptance document; extracting a structured entity triad by using the fine-tuned named entity recognition model, constructing a data set containing a logic association relationship, then constructing a compliance review prompt engineering instruction set, inputting the structured entity triad into a large language model for multi-document entity alignment and consistency verification, and finally, performing multi-document entity recognition. And identifying numerical evolution, semantic deviation and logic contradiction features and generating an identification result, and finally, constructing a traceable review evidence chain set according to the identification result, accurately positioning a problem source and defining association with compliance rules. According to the invention, the examination efficiency, accuracy and systematicness are improved.

The invention discloses an intelligent switch fault diagnosis method based on multilayer data reasoning, which relates to the field of switches, collects and fuses multi-source data of a switch, converts entities, attributes and relationships in a multi-source fusion data set into an RDF triple based on a predefined network operation and maintenance ontology model, and performs fault diagnosis on the RDF triple. The method comprises the steps of constructing a switch fault diagnosis knowledge graph, dynamically generating an SPARQL query statement based on real-time monitoring data, performing graph traversal and logical reasoning on the switch fault diagnosis knowledge graph, and outputting a switch fault diagnosis conclusion. According to the method, comprehensive upgrading of switch fault diagnosis from passive response to active prevention is achieved, the network operation and maintenance efficiency and decision quality are remarkably improved, equipment monitoring, topological relations and service data are integrated through a unified semantic framework, a structured knowledge graph is constructed, and fault diagnosis has semantic interpretability.

The invention relates to the technical field of energy data security protection, and discloses a block chain energy data security protection method, system and device based on attribute control and double-layer encryption, and a medium, and the method comprises the steps: constructing an ABAC triple policy engine based on user attributes, resource attributes and environment attributes, converting the conventional static authority management into dynamic policy verification, and carrying out the dynamic policy verification; a double-layer AES-GCM encryption algorithm is designed, the data anti-cracking capability is improved through two encryption operations, the linear time complexity is kept while the encryption security is guaranteed, and the efficiency requirement of energy data processing is considered; a dynamic key management mechanism is matched, a unique key pair is generated for each piece of data, the key leakage risk is reduced, and the problem of contradiction between safety and efficiency in a traditional encryption algorithm is solved; an on-chain and off-chain collaborative storage architecture is adopted, encrypted energy data are stored through an IPFS distributed storage system, only the hash value is subjected to on-chain verification for integrity, and capacity limitation caused by traditional block chain full-node storage is broken through.

The invention relates to the technical field of multi-agent collaboration, in particular to a task execution method and system based on multi-agent collaboration, and the method comprises the steps: carrying out the semantic analysis and multi-granularity decomposition of a user task instruction, generating a subtask dependence structure, and storing the subtask dependence structure into a dynamic task pool; performing collaborative planning and rehearsal execution on the to-be-executed subtasks, generating context snapshots, executing Push, and writing the Push into a historical state stack; retrieving an evidence chain based on the domain knowledge base and extracting a fact triple set, performing consistency comparison based on structured evidence triples on the candidate reasoning paths, and outputting conflict confidence and consistency scores; when the consistency score is lower than a threshold value, triggering a projectile stack, physically clearing wrong branch intermediate data, recovering a historical context, injecting a negative feedback prompt to generate a new inference branch, and returning to continue rehearsal execution; if the verification is passed, outputting a result and entering a next subtask; therefore, the controllability and auditing performance of multi-agent cooperative task execution are improved.

The invention discloses a service monitoring data enhancement method, system and device based on LLM and retrieval enhancement generation and a storage medium, and relates to the technical field of service monitoring and exception handling. The method comprises the steps that user exception description is received, a webpage is retrieved through semantic expansion, and triple output structured data is extracted; and comparing with a local knowledge base, processing and storing the new content classification vector, and updating the index. Performing preliminary screening and reordering by combining exception description and an update library, taking a front list as a context to enable a large language model to generate analysis, evaluation and a strategy, and performing rule check and output; a result is verified, scene variants are generated according to exception types, after duplicate removal, the scene variants, strategies and metadata are structurally stored in a knowledge base, and continuous learning of a closed loop is completed; according to the method, high-quality and high-timeliness service exception training data and processing strategies can be automatically generated, the illusion problem of a large language model in actual operation and maintenance is effectively solved, and the fault response speed and the decision accuracy are improved.

The invention relates to the technical field of natural language processing, in particular to an entity relation joint extraction method and system. Cross-span semantic clues are gathered in a channel dimension through a full-sentence semantic focusing unit so as to suppress semantic drift under long-distance dependence, and relative direction and distance information between entities is converted into learnable modulation quantity through an entity-to-geometric prior injection unit so as to reduce pairing ambiguity. And distinguishing subject and object representations through a subject-object directional interaction unit to carry out directional convergence so as to avoid role confusion, and finally realizing joint prediction of entity boundaries and relation types in a unified framework. According to the system, the stability and the accuracy of an extraction result can be remarkably improved in a multi-entity coexistence and relation overlapping scene, entity boundary intersection and subject-object inversion errors are reduced, the structured triad can be directly generated without relying on a post-processing rule, and a more reliable solution is provided for application such as knowledge graph construction and text analysis.

The invention relates to a code security auditing method and device, computer equipment, a readable storage medium and a program product. The method comprises the steps of obtaining a code graph of a target source code and a vulnerability mode of a target vulnerability library; inputting the code graph and the vulnerability mode into a graph neural network model, outputting the similarity between the code graph and the vulnerability mode, and determining an associated edge between the code graph and the vulnerability mode; constructing an initial triple among the code graph, the vulnerability mode and the associated edge, inputting the initial triple into a translation model in the relationship space, and outputting a semantic association relationship between the code graph and the vulnerability mode; inputting the semantic association relationship, the code graph and the vulnerability mode into a first large language model, and outputting a target triple formed by the code graph, the vulnerability mode and an association edge; and obtaining the confidence coefficient of the target triad, and performing security audit on the target source code based on the confidence coefficient. According to the method provided by the invention, the situation of missing detection can be avoided.

The invention discloses a software demand analysis method based on a knowledge graph, which comprises the following steps of: importing a multi-source demand text to generate a locatable demand text fragment; loading a domain demand ontology, an SHACL / OWL rule template, a term library, a synonym list and a unit and dimension specification library; generating a candidate entity set, a candidate relation set and a candidate triple set, and attaching an evidence fragment; mapping from the relation type to the clause cluster is established, and an OGG-TM model is initialized; outputting a confirmation triple set and a revised candidate entity set; synonymous normalization, unit specification and threshold specification, cross-document entity merging and identifier mapping; reasoning and consistency verification are carried out; and generating a version identifier, and executing limited incremental learning. According to the method, the knowledge graph and the OGG-TM model are fused, demand semantic analysis and self-learning closed loop are achieved, and high precision and traceability are achieved.

The application claims a time-oriented RDF quad model for MongoDB storage and a redundant attribute elimination method, which comprises the following steps: step 1, constructing a time-oriented RDF quad data model, taking time information as a new tuple of RDF triple extension, expanding the triple into a quad model containing time information, and defining the expanded time-oriented RDF quad data model; step 2, storing time-oriented RDF quad instance data in a document-oriented non-relational MongoDB database; step 3, using a weighted-based design algorithm to find out the instance attributes with higher redundancy from the time-oriented RDF quad data in the form of text stored in the MongoDB database, and eliminating these redundant instance attributes in the ontology library that has been constructed. The RDF quad-based query model designed in the application has a more significant effect on resources with time characteristics, and at the same time solves the problem of ontology ambiguity caused by repetitive instance attributes.

The invention relates to a network module verification process generation method and system and a storage medium, and relates to the technical field of embedded communication, and the method comprises the steps: S1, obtaining a to-be-analyzed AT instruction document, and carrying out the preprocessing of the AT instruction document, and obtaining a plurality of plain text segments; s2, inputting the plain text segment into a preset semantic analysis engine for semantic extraction to obtain a semantic triple; s3, constructing an AT instruction knowledge graph according to the semantic triple; and S4, generating a network module verification process corresponding to the AT instruction document according to the AT instruction knowledge graph. Compared with the prior art, the method has the advantages that zero manual reading can be realized, multi-language and multi-format documents are supported, the time sequence, dependency and conditional branches among instructions are understood, an executable graphical verification process is automatically generated, and incremental updating is supported.

The application relates to a knowledge graph updating method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring entity vectors of multiple triplets, relation vectors of the multiple triplets and a question vector of a to-be-queried question; determining multiple candidate tail entities corresponding to the question vector according to the question vector and the entity vectors in the initial vectors; determining first candidate triplets according to the multiple candidate tail entities corresponding to the question vector; determining second candidate triplets according to the first relation vectors and the question vector; and finally updating the knowledge graph according to the first candidate triplets and the second candidate triplets. The original knowledge graph triplet data is perfected by using the method, so that the knowledge graph is updated, and the probability of obtaining a question answer from the knowledge graph by a user is improved.