485 results about "Relationship extraction" patented technology

The invention discloses a 3D intelligent simulation generation method for clothing styles based on a model library, and relates to the technical field of digital twinning, and the method comprises the steps: carrying out the entity relation extraction and semantic mapping of multi-source clothing data, constructing a cross-modal knowledge graph, and extracting a physical constraint rule of the cross-modal knowledge graph; performing association reasoning and cross validation on the physical constraint rule and the version library to obtain a basic version template set; inputting the basic model template set into an intelligent clothing model, performing structured feature decoupling by the parameter analysis layer, dynamically adjusting a topological structure by the geometric generation layer, and generating 3D simulated clothing; and carrying out digital modeling on the basic model template set through a digital twinning algorithm, constructing a digital twinning body, carrying out physical simulation and optimization verification on the 3D simulation clothing by using the digital twinning body, and outputting a clothing style 3D simulation scheme. According to the invention, by constructing the pattern library and the intelligent garment model, the efficiency, accuracy and individuation level of garment 3D simulation generation are improved.

The invention discloses an electronic medical record LLM generation method based on animal injury, which realizes dialogue structuring and timestamp synchronization through multistage speech recognition and role affiliation. Using standardized medical term mapping and coding to align the free text to a standardized medical entity, and constructing a high-confidence medical entity network based on a semantic anchor point pool; according to the method, context-sensitive entity relationship extraction is realized by combining a large language model and a semantic enhancement template, a high-accuracy structured relationship chain is generated through clinical logic rule set verification, and finally, an electronic medical record template under diagnosis and treatment specifications is automatically filled and privacy desensitization processing is completed. The semantic consistency, the structural accuracy and the data security of automatic generation of the electronic medical record are improved, and standardization and intelligent circulation of medical information are effectively promoted.

The invention relates to a grid-connected scheduling management method and device constructed in combination with a knowledge graph, equipment and a medium. According to the method, a comprehensive data set is constructed by integrating multi-source data such as new energy output, power grid topology, load, weather and historical fault records, and then a dynamic knowledge graph is formed by using entity recognition and relation extraction technologies; a probability causal graph model is constructed by extracting a causal path and adding probability parameters, and uncertainty propagation intensity is quantified in combination with a sequence diagram neural network; on the basis of a propagation model, risk index conditional probability is calculated by adopting probability causal reasoning, and a fault propagation sequence is simulated through a cascade failure theory to realize multi-level risk assessment; based on a multi-objective optimization model and deep reinforcement learning, an adaptive scheduling strategy is generated, a complete technical closed loop from data fusion and causal reasoning to intelligent decision is realized, and the technical effects of describing a new energy uncertainty propagation path, prospectively evaluating a power grid risk situation and dynamically generating an optimal grid-connected scheduling scheme are achieved.

The invention discloses a knowledge question-answering method and system based on topic knowledge graph retrieval enhancement, and the method comprises the steps: firstly extracting a local topic represented in a triple form based on an original document through employing a large language model, carrying out the clustering, and generating a global topic triple set representing the global perspective of the whole document; secondly, on the basis of the global topic triple set, topic-guided entity and relation extraction is adopted, and a mixed knowledge graph is constructed; secondly, providing a semantic perception personalized PageRank algorithm, matching query semantics with semantics of edges in the mixed knowledge graph, and dynamically adjusting the weight of score propagation between nodes; and finally, designing a three-level progressive retrieval mechanism, retrieving multi-level information related to user query from the mixed knowledge graph, and inputting the multi-level information into the large language model to generate a final answer. According to the method, the semantic integrity and retrieval precision of the knowledge graph are remarkably improved, and the accuracy, comprehensiveness and enabling performance of generated answers are ensured.

The invention discloses a management decision-making method and system based on a knowledge base construction technology. The method comprises the following steps: performing sequential relationship extraction on multi-source financial data to obtain a sequential relationship set related to query content; constructing an event-entity incidence matrix corresponding to the time sequence relation set; according to the time sequence relation set and the event-entity incidence matrix, constructing a dynamic knowledge graph; determining causal effect parameters in the causal graph structure by adopting a dual machine learning model; constructing a structural causal model according to the causal graph structure and the causal effect parameters; and generating an anti-fact prediction result by using the structural causal model, and generating a decision scheme corresponding to the query content based on the anti-fact prediction result. The technical problem that decision information including accurate causal basis and prospective simulation information cannot be generated due to the fact that the causal relationship between financial data is difficult to determine and the intervention effect cannot be dynamically deduced in a related management decision method is solved.

The invention discloses an intelligent construction and tracing method and device for an attack graph, and relates to the technical field of network security. The method comprises the steps of performing semantic analysis and entity relationship extraction on a multi-source heterogeneous security log according to a predefined structured security data model, and generating a standardized security entity relationship triple set; based on the set, taking an entity in an initial alarm as a starting point, and adopting an iterative closed loop driven by a large language model to dynamically construct an attack graph; and carrying out attack technique and tactics mapping and threat attribution based on the final map, and generating a response strategy of priority ranking. According to the method, automatic and high-precision source tracing and response of the attack chain are realized, and the problems that the prior art depends on static rules and semantic segmentation and lacks dynamic reasoning capability are effectively solved.

The invention relates to the technical field of intelligent recommendation, and discloses an AI intelligent matching method based on a knowledge graph, and the method comprises the steps: constructing a quaternary knowledge graph containing a time dimension; identifying legal entities and semantic relationships by adopting an entity identification and relationship extraction technology; multi-level semantic features are extracted through a two-layer progressive semantic matching algorithm of a grammar layer, a semantic layer and a reasoning layer; constructing lawyer ability portraits based on a heterogeneous graph neural network and a time sequence perception graph convolution technology; progressive matching calculation is adopted, the optimal matching weight is learned through a multi-layer attention mechanism, and dynamically optimized intelligent matching is achieved. The technical problems of cold start, insufficient semantic understanding ability and poor timeliness processing ability in the existing legal consultation matching system can be solved, and the matching precision and the user satisfaction are improved.

The invention relates to the technical field of intelligent decision rule base construction, and discloses an intelligent decision framework construction method and device based on a dynamic ontology. The method comprises the following steps: acquiring original data streams from a plurality of heterogeneous data sources in real time, and constructing an initial dynamic ontology structure through a dynamic ontology modeling unit; performing semantic annotation and relation extraction on the original data flow by using the structure to generate semantic enhanced data; generating a candidate decision rule set based on the semantic enhancement data, and obtaining a verified rule set through consistency verification and conflict detection; calculating the adaptability score of the verified rule set in combination with the real-time environment data, and screening out an optimal decision rule subset according to the score and a preset threshold value; the method is integrated into an intelligent decision rule base, and an optimization loop is triggered based on an update state of the base. According to the method, the data utilization efficiency and the rule quality are improved, the rule base can dynamically adapt to the environment, and decision effectiveness and reliability are enhanced.

The invention relates to a digital archive intelligent processing method, a storage medium and a system, which are suitable for multi-source heterogeneous archive management scenes such as colleges and universities. The method comprises the following steps of: classifying structured and unstructured data such as paper archive scanning pieces and database views, and extracting metadata and entity information by adopting a scanning and OCR (Optical Character Recognition) technology; a complex table and document content are analyzed through a model, semantic analysis (entity recognition, relation extraction and event abstract) is achieved in combination with a language model of a Transform architecture, and a structured report containing a data abstract, an entity relation graph and abnormal annotations is generated. The system is internally provided with a parameter template automatic generation module, supports cross-page content continuous restoration and sensitive data encryption desensitization, and realizes safe sharing through an API interface. The method solves the problems of low efficiency, difficulty in multi-source data fusion and the like of traditional archive processing, improves the automation level and data value mining capability of archive management, and is suitable for intelligent upgrading of complex archive scenes.

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

The invention discloses a retrieval method based on a semantic enhanced knowledge graph, which relates to the technical field of information, and comprises the following steps: receiving a natural language query of a user, and carrying out deep analysis on the query, including named entity recognition and linking, relationship extraction and query intention classification; and based on an analysis result, extracting a related local sub-graph from the knowledge graph, generating a query context vector, and generating dynamic semantic embedding for the sub-graph through a query-perceived graph attention network to obtain a dynamic enhanced semantic graph. According to the retrieval method based on the semantic enhancement knowledge graph, the retrieval precision and the recall rate are remarkably improved, the limitation of static knowledge representation is solved through a dynamic semantic enhancement mechanism of query intention perception, so that the local semantic representation of the knowledge graph is highly aligned with the query intention of a specific user; and the ability of understanding and answering complex, fuzzy, ambiguous and multi-hop queries is improved.

The invention relates to a data AI analysis management method and system based on a production element association map. The method comprises the steps that a multi-source heterogeneous production data flow covering the whole industrial production cycle is obtained; constructing a whole-process production element association map through an entity recognition and relationship extraction technology; actual operation indexes of the production nodes are calculated in real time and compared with a reference threshold value, and potential production bottleneck nodes are accurately recognized; upstream associated node data are backtracked, historical data in the same period are combined to be input into the bottleneck root cause diagnosis model, and core influence factors are accurately obtained; generating an optimal scheduling strategy according to the core influence factors and issuing the optimal scheduling strategy to a production execution system; according to the scheme, the multi-source heterogeneous data of the whole period of industrial production can be effectively analyzed and managed, accurate regulation and control of the production process are achieved, and the production efficiency and the product quality are improved.

The invention discloses a recommendation system-oriented high-concealment poisoning attack detection method and application, and the method comprises the following steps: S1, user behavior and relationship modeling: constructing a user feature vector and symbiotic relationship graph, and describing user scoring behavior preference and a co-occurrence relationship; s2, importance pre-screening: based on similarity measurement and importance modeling of score distribution, filtering out normal users weakly related to potential attack users; s3, cross-graph relation decoupling: carrying out key relation extraction and dynamic and static relation separation on the user relation graph, and obtaining high-quality relation representation through a cross-graph fusion mechanism; and S4, double-hyper-sphere cooperative detection: normal user representation is restrained by using a concentric hyper-sphere shell, and abnormal user detection is realized through the degree of deviation from the boundary. According to the method, high-concealment poisoning attacks can be effectively detected in a real recommendation system environment, the detection accuracy is remarkably improved, the false alarm rate is reduced, and the method has good practicability and robustness.

The invention discloses a ship knowledge graph construction method based on a large model and a graph neural network, and the method comprises the steps: carrying out the format conversion and protection type partitioning processing of a professional document, and completing the recursive segmentation through a placeholder protection formula, a table and other structures according to the semantic hierarchy, and obtaining a text block suitable for the extraction of an entity and a relation; extracting domain entities by utilizing a large language model containing thinking chain cues, and positioning candidate entities in combination with an AC automaton so as to improve the coverage rate and accuracy of relation triple extraction; performing new entity backfilling and relation standardization on an extraction result, and constructing an initial knowledge graph with a consistent structure; and inputting the initial knowledge graph into a graph neural network model with directional expansion and a multi-scale decoder, and complementing a missing relationship through link prediction, so that node distribution and a relationship structure of the graph are more complete. According to the method, a continuous processing chain from text preprocessing, knowledge extraction to graph completion is formed.

The invention provides a biomedical relationship extraction method and system based on a large language model, and relates to the technical field of natural language processing, and the method comprises the steps: constructing a cue word strategy of a biomedical relationship extraction scene; calling a large language model to generate external knowledge such as entity description information and entity relationship description information of the target entity or the entity pair; fusing the original semantic features and the external knowledge features of the biomedical text by adopting a feature fusion strategy to obtain a target fusion feature vector; and inputting the data into a relation extraction model for training, and outputting a structured triple of the biomedical relation after convergence. According to the method, field external knowledge is introduced through the large language model and deep fusion is carried out, the precision and generalization ability of biomedical relationship extraction are effectively improved, and the method is suitable for a relationship extraction scene of biomedical texts.

The invention discloses a multi-modal large model reasoning method and system based on self-driven feedback and symbol collaboration, and the method comprises the steps: carrying out the structural representation of multi-modal information through a knowledge graph, carrying out the entity recognition and relation extraction in combination with a large model, constructing a unified knowledge graph, and generating a knowledge ternary set; defining a symbol logic expression, constructing a diversified symbol logic rule by using the knowledge ternary set, and calculating a symbol consistency award of a reasoning path; constructing a symbol-human feedback collaborative reward mechanism to obtain a mixed reward function; in the process of interacting with the multi-modal environment, sampling a group of outputs for specific tasks, and constructing an intra-group relative reward optimization strategy network objective function in a multi-task scene in combination with a mixed reward function; the system interacts with the environment to realize autonomous evolution cycle to generate a training sample, and iterative cycle realizes self-driven feedback without a large amount of manual annotation data; and the logicality, the interpretability and the autonomous evolution ability of the multi-modal large model in a complex reasoning task are promoted.

The invention discloses a multi-dimensional natural language reasoning method based on a safety emergency knowledge graph. The method comprises the following steps: S1, collecting multi-source heterogeneous data, and carrying out standardized cleaning, entity recognition and relationship extraction; s2, constructing an emergency knowledge graph, performing storage and indexing by adopting a graph database, and designing an incremental updating mechanism; s3, intention classification and keyword recognition are conducted on natural language questions input by a user through the deep learning model, and the questions are mapped into initial entity nodes in the graph; s4, performing multi-hop reasoning around an initial entity in the knowledge graph, screening out a most relevant and logically coherent Top-K path in combination with reinforcement learning and a graph sorting algorithm, and realizing deep correlation analysis and answer candidate generation of the question; s5, generating an answer in a structured and natural language mixed form based on a reasoning result, and providing a visual reasoning path for display; a user feedback mechanism is introduced, and continuous optimization of the system and iterative updating of the model are supported.

The invention provides an intelligent recommendation method and system for scientific and technological achievement transfer, and the system comprises a data processing module which is used for collecting and preprocessing achievements, enterprise demands, and third-party data; the knowledge graph module is used for constructing a knowledge graph through entity recognition and relation extraction and supporting incremental updating; the intelligent recommendation module is used for calculating the semantic association degree, the semantic matching degree and the collaborative filtering degree, generating a comprehensive recommendation score through weighted fusion and carrying out sorting recommendation on the scientific and technological achievements; and the feedback and optimization module is used for collecting user feedback scores to dynamically optimize weight distribution. According to the method, the knowledge graph and multi-index fusion are utilized, recommendation accuracy and adaptability are improved, and scientific and technological achievement transfer is promoted.

The invention belongs to the technical field of natural language processing and power system intelligent information processing. Comprising the following steps: S1, preparing data; s2, performing named entity recognition and relation extraction on the text block by utilizing a pre-trained large language model; s3, constructing a knowledge graph in the urban power distribution field by using the triple summary; s4, generating a semantic abstract with a hierarchical structure for each theme community; s5, querying and retrieving: retrieving related information from the vector index and the knowledge graph in parallel by receiving a natural language query of a user, and fusing results into a context knowledge set; and S6, an answer generation step: inputting the query and the context knowledge set thereof into a large language model, and generating an answer which is coherent in semantics, accurate in facts and covers query requirements through a preset prompt strategy guide model. According to the method, the accuracy and practicability of the question-answering system are remarkably improved, and core technical support is provided for intelligent operation and maintenance of the power distribution network.

The invention relates to a medical relationship extraction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an original medical text, calling a plurality of different large models to carry out voting integration processing on the original medical text, and generating weak supervision data. And pre-training the BERT model through the medical corpus of the large model to construct the MedBERT model, and training the MedBERT model in combination with the preprocessed local medical data. And generating a medical relation tuple based on the weak supervision data, and performing weak supervision fine tuning on the trained MedBERT model to obtain a weak supervision MedBERT model. And taking the manually labeled medical relationship tuple library as the input of a weak supervision MedBERT model, performing strong supervision fine tuning on the weak supervision MedBERT model, and constructing a medical relationship extraction model. And calling the medical relationship extraction model to process the current medical text, and outputting a medical relationship tuple list corresponding to the current medical text.

The invention discloses a first-aid medical knowledge graph construction method and device, equipment, a medium and a product, and relates to the technical field of computers. The first-aid medical knowledge graph construction method comprises the following steps: acquiring a first-aid medical knowledge data set; knowledge extraction is conducted on the first-aid medical knowledge data set through a pre-trained final condition time sequence attention mechanism model, structured relation data is obtained, and the final condition time sequence attention mechanism model is obtained through training of an improved meta-learning framework; and performing knowledge graph construction on the structured relation data to obtain a first-aid medical knowledge graph. According to the method, training is carried out by improving the meta-learning framework, the small sample problem is solved, the final condition time sequence attention mechanism model more adaptive to the first-aid medicine direction is obtained, the accuracy of extracting the relation in the first-aid medicine knowledge data set is improved, and the reliability of the knowledge graph is improved.

The invention discloses a port field knowledge graph automatic construction method based on cooperation of multiple intelligent Agents, and the method comprises the steps: processing structured data, semi-structured data and non-structured data of a port field through intelligent Agents with an autonomous decision-making capability, and achieving the entity recognition, relation extraction and knowledge fusion; a plurality of intelligent Agents with the cooperation function are used for executing knowledge discovery, new knowledge verification, conflict detection, knowledge fusion and graph updating tasks respectively, cooperative communication among the intelligent Agents is achieved through a message queue, and dynamic evolution of a knowledge graph is completed; processing the knowledge graph by adopting a customized knowledge graph embedding method and a semantic fusion algorithm designed for professional terms and knowledge structures in the port field; and storing the processed knowledge graph data based on a distributed architecture, wherein the distributed architecture supports high concurrent processing and real-time response. According to the method, the port domain knowledge graph can be efficiently and automatically constructed.

The invention relates to the technical field of computers, and discloses a knowledge management method and system, electronic equipment and a storage medium, and the method comprises the steps: receiving a knowledge task initiated by a user, analyzing the task intention of the knowledge task, dynamically selecting and combining one or more special intelligent agents from a plurality of predefined special intelligent agents based on the analyzed task intention, and storing the selected special intelligent agents. Generating a workflow for the corresponding knowledge task; the workflow is scheduled and executed, so that the selected special intelligent agents cooperatively work in sequence or in parallel, a task result is generated, and generated derivative knowledge achievements are captured; and processing the derivative knowledge achievement, calling an information extraction class agent to perform entity and relationship extraction on the derivative knowledge achievement, and after entity disambiguation, updating a structured result into the mapping knowledge of the unified knowledge base to form a knowledge closed loop. According to the method, knowledge can be driven to be actively, accurately and efficiently converted into actual productivity in various scenes, and knowledge application ecology capable of being evolved continuously is formed.

The invention discloses a content abstract generation method based on chapter structure analysis, and belongs to the technical field of natural language processing. The method comprises the steps that firstly, an original text is preprocessed, then text structure deep analysis is carried out, the text type of the text is recognized, an explicit / implicit text relation is extracted, and special symbols are introduced through a Prompt normal form for implicit text relation extraction to strengthen logic semantics; secondly, scoring sentences by adopting a double-path scoring mechanism in combination with a deep neural network model of chapter structure features and an optimized text sorting algorithm, and fusing scores through a logistic regression model; then, screening target sentences based on a chapter relation weighted secondary modulus function and a greedy algorithm, and finally, carrying out post-processing to generate an abstract. According to the abstract generation method, the chapter structure logic is deeply utilized, so that the problems of logic unsmoothness, information redundancy or key relation missing in the existing abstract generation are solved, and the semantic coherence and information integrity of the abstract are improved.

The invention belongs to the field of computer vision and industrial design assistance, particularly relates to an industrial drawing similarity detection method based on deep learning, and aims to realize efficient and accurate similarity analysis of industrial drawings. Comprising the following steps: collecting an industrial drawing data set, and carrying out target detection labeling and feature extraction on each drawing; a YOLO model is adopted to detect a target, and a non-maximum suppression method is adopted to remove duplication so as to obtain each visual angle of the part in the drawing and an overall marking frame; recognizing characters in the drawing, and obtaining part names and material information through keyword extraction and domain dictionary filtering; local and global feature vectors are extracted, multi-modal feature alignment is realized through comparative learning, and part semantic representation based on image-text association is constructed. And storing the extracted image and OCR text feature vectors into a Faiss index database, establishing a multi-modal mapping relation of local and global feature vectors and text semantics, extracting the image and text features of a to-be-detected drawing, and outputting a similarity result through similarity retrieval of a vector database.

This invention provides a transformer fault diagnosis method and system based on the integration of knowledge graphs and large language models. [Solution] The knowledge graph question-and-answer system includes acquiring unstructured and semi-structured text; constructing a question-and-answer module including an encoding layer, a head entity recognition layer, a relationship extraction model including a tail entity and relationship recognition layer, a LangChain model, and a large language model that takes the output of the LangChain as input; acquiring fault problem text; inputting the fault problem text into the LangChain model; outputting expert knowledge; inputting the expert knowledge and fault problem text into the large language model; outputting an expert fault diagnosis answer; alternately combining the expert fault diagnosis answer with high-quality knowledge triple text; and outputting a final fault diagnosis answer. The present invention can significantly improve the health management level of power transformers.

A collaborative management authority rule optimization system based on community discovery comprises a feature extraction module, an organization role screening module and a data attribute screening and authority distribution control module. Generating a standardized user feature vector and a data vector through structured coding and semantic modeling; the organization role screening module constructs a user collaboration graph based on a community division algorithm, and reasones user optimal role mapping by using a community portrait model; the data attribute screening module is combined with a data classification tree and a structure dependency relationship extraction algorithm to recognize a semantic category and upstream and downstream dependency chains of target data; and the permission allocation control module performs reasoning in combination with a permission knowledge base according to roles, data classification and a dependency relationship, and finally generates a permission allocation table, so that dynamic permission configuration and strategy matching oriented to a collaborative scene are realized. Through automatic role mapping, data semantic association analysis and authority inheritance reasoning, accurate authority distribution and real-time strategy adjustment in a ship collaboration scene are realized, so that data security and collaboration efficiency are improved, and core support is provided for digital transformation of the ship industry.

The invention relates to the technical field of power information network threat intelligence analysis, and provides a power information network multi-source threat intelligence analysis method, system and device and a medium, and the method comprises the steps: obtaining to-be-analyzed multi-source threat intelligence data of a power information network; performing attack entity relationship extraction analysis on the text intelligence data according to a preset attack entity data model and a preset entity association mode table to generate an attack reconstruction main graph; carrying out attack entity relationship extraction analysis on the attack vulnerability codes based on a preset code large model and an attack entity retrieval database to generate a plurality of attack reconstruction sub-graphs; and combining the attack reconstruction main graph and the attack reconstruction sub-graphs to generate a target attack reconstruction graph. According to the method, an attack entity relationship extraction mechanism based on a unified attack entity data model is combined with a multi-source attack graph reconstruction mechanism, so that the accuracy and comprehensiveness of attack entity recognition are improved, the reliability of threat detection and attack tracing is ensured, and the security defense capability of the electric power information network is improved.

The invention discloses a knowledge graph construction method for alternative planting of poppy, which comprises the following steps: acquiring soil humidity, illumination intensity, air temperature and rainfall data from Internet of Things sensing nodes deployed in an alternative planting area, analyzing a crop growth state in combination with a remote sensing image, and generating a structured environment observation tuple; entity recognition and relation extraction are carried out on policy and regulation texts, agricultural technology manual and historical planting records, and an initial triple set is constructed; inputting the structured environment observation tuple and the initial triple set into a graph neural network encoder to generate a node embedding vector; on the basis of the node embedding vectors, calculating semantic association weights among entities by adopting a graph attention mechanism, and constructing a dynamic adjacency matrix; the objective of the invention is to solve the problems of lack of semantic association, fragmentation of knowledge expression, weak reasoning ability and insufficient cross-domain collaboration of multi-source heterogeneous data in existing alternative planting management.

The invention discloses an internal and external rule matching method and system facing a system compliance scene. The method comprises the following steps: performing entity relationship extraction on an internal system document to construct an entity relationship graph; identifying a semantic community from the entity relationship graph, wherein the semantic community is composed of entities and entity relationships which are closely linked semantically; binding the semantic community, the entity node and the original paragraph of the internal system document; and executing entity matching, community recall and original text tracing according to the external specification terms so as to obtain a community report, an original text paragraph and an entity node matched with the external specification terms. According to the embodiment of the invention, based on a multiple recall mechanism of the knowledge graph, the hierarchical community structure and the full-chain traceability are combined, matching, comparison and review between the internal system and the external regulation are realized, and the automation degree of system compliance alignment and the credibility of an output result are remarkably improved.