47 results about "Entity relation diagram" patented technology

The invention discloses a SysML model automatic generation system based on mixed AI and domain knowledge, and the system comprises a preprocessing module which is used for carrying out the text preprocessing and structural enhancement of an engineering document of a PDF or Word version; the NLP extraction module is used for identifying six types of core entities by adopting aviation corpus fine tuning BERT, constructing a document-level relational graph by utilizing GNN, modeling a cross-paragraph dependency relationship, calling LLM for semantic fuzzy sentences to generate a thinking chain, extracting a reasoning path and solving ambiguity; the rule conversion engine module is used for mapping the entity relation graph into a SysML memory object tree; and the controllable generation module is used for carrying out limited decoding on the LLM by utilizing a Guidance framework. The invention further discloses an automatic SysML model generation method based on the mixed AI and domain knowledge. According to the method, the problems of low manual modeling efficiency and poor semantic consistency in traditional MBSE implementation are solved.

The invention relates to the technical field of natural language processing, in particular to an NLP-based multi-source data fusion system and method.The NLP-based multi-source data fusion system comprises a data collecting and processing unit, an NLP processing unit, a data fusion unit and an output unit.The data collecting and processing unit collects multi-source heterogeneous data and executes standardization processing to obtain preprocessed data; the NLP processing unit extracts entity, relation and emotion features through deep semantic analysis, a context-aware entity relation graph is constructed by adopting a bidirectional attention mechanism model and a graph attention network, and the data fusion unit realizes cross-source entity ambiguity resolution through an iterative graph neural network based on a graph topological structure. The emotion confidence weight is dynamically distributed to generate a fusion vector, a rule feedback reconstruction map is extracted, and the output unit converts the fusion vector into a target format for output, so that the problem of semantic conflict of multi-source data is solved, and semantic coherence and availability of fusion data are improved.

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 discloses a software development project progress prediction management method based on artificial intelligence, and relates to the technical field of project management, and the method comprises the steps: extracting a causal relation from entity relation graph data, and constructing a causal knowledge graph; a graph structure analysis method and a time sequence prediction method are combined, predicted completion time and delay probability are calculated for the causal knowledge graph and the associated time sequence data, and a progress risk assessment result is generated; performing causal chain identification on the progress risk assessment result and the causal knowledge graph by adopting a causal reasoning method to generate delay interpretation information; according to the delay interpretation information, a preset resource priority and a task weight, a rule driving and priority scheduling strategy is adopted to construct a compensation scheduling scheme; and implementing a compensation scheduling scheme, collecting implementation effect data and analyzing a scheduling effect through a closed-loop feedback and dynamic adjustment mechanism, and generating an optimized scheduling management scheme. The intelligent level and the practical value of project progress management are greatly improved.

The invention relates to the technical field of data compliance. According to the AI-driven data compliance rule intelligent method, device and equipment and the medium, the method comprises the steps that natural language input of a user is obtained, and user demand description is obtained; performing multi-dimensional semantic analysis on the user demand description through a pre-trained large language model, and generating a structured semantic framework comprising an intention vector, an entity relation graph and a constraint condition set; performing compliance correction on the structured semantic framework to generate an optimized semantic framework; performing logic conflict detection and performance simulation test on the domain-specific language rule to generate an executable compliance rule; and deploying the executable compliance rule to the target data governance platform so as to achieve the technical effects of reducing the learning threshold and the manual error rate generated by the domain specific language rule, improving the semantic adaptation capability in a complex business scene and optimizing the operation stability of the rule on the data governance platform.

The invention belongs to the technical field of databases, and particularly relates to an LLM-Text2SQL-oriented database table relation exploration method. According to the method, a multi-stage cooperative processing strategy is adopted, database metadata and data content features are integrated, and semantic enhancement and structured completion are performed on original information through a large language model. And on the basis, a potential association candidate set is screened in combination with an algorithm based on feature similarity, multi-dimensional verification and judgment of an association relationship are performed by fusing a predefined rule and a large language model reasoning mechanism, and finally an entity relationship graph supporting interactive editing and iterative optimization is generated. According to the method, end-to-end automatic processing from a heterogeneous database with constraint missing and data integrity impaired to a standardized ER graph is realized, and a solid foundation is laid for remarkably improving the success rate of natural language SQL generation based on a large language model.

The invention relates to the technical field of building safety, and discloses a safety transformation monitoring system for building construction and a method thereof. The system comprises a data acquisition and standardization module, a dynamic security entity relationship map construction module, an organization capability and cognitive load modeling module, a hybrid risk identification and conduction calculation engine, a self-adaptive security transformation strategy generation engine and a closed-loop self-calibration module. According to the method, a dynamic security entity relation graph is constructed and updated in real time, the cognitive load of management personnel is quantified, and the cognitive load is used as a dynamic adjustment factor of the conduction probability of risks on the graph; when a safety transformation strategy is generated, comprehensively evaluating a risk reduction effect, resource cost and additional cognitive load cost to output an optimal adaptive strategy; and finally, performing closed-loop self-calibration on the system model by utilizing execution feedback. According to the method, dynamic prospective risk prediction, self-adaptive strategy generation and continuous self-optimization are realized.

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.

The invention provides an attack detection and processing method and device, electronic equipment, a medium and a program product, and can be applied to the technical field of big data, the technical field of artificial intelligence and the field of financial science and technology. The method comprises the following steps: acquiring multi-source network security data, and constructing an entity relation graph based on the multi-source network security data; carrying out attack chain analysis on the entity relation graph to obtain an attack chain analysis result; constructing an attack graph based on the attack chain analysis result; and generating a processing strategy based on the attack graph, and executing the processing strategy in response to the fact that the processing strategy is verified to have no service influence.

This invention discloses an automatic SysML model generation system based on hybrid AI and domain knowledge, comprising: a preprocessing module for text preprocessing and structure enhancement of PDF or Word versions of engineering documents; an NLP extraction module for identifying six core entities by fine-tuning BERT using aviation corpus, constructing a document-level relationship graph using GNN, modeling cross-paragraph dependencies, and generating "thought chains" by calling LLM for semantically ambiguous sentences to extract inference paths and resolve ambiguities; a rule transformation engine module for mapping entity relationship graphs to SysML in-memory object trees; and a controllable generation module for performing restricted decoding of LLM using the Guidance framework. An automatic SysML model generation method based on hybrid AI and domain knowledge is also disclosed. This invention solves the problems of low efficiency and poor semantic consistency in traditional MBSE implementations involving manual modeling.

The invention belongs to the technical field of large model application, and relates to an enterprise technology demand prediction method and system based on large model driving, and the method comprises four parts: enterprise problem deep analysis, problem technology essence identification, technology knowledge base intelligent retrieval and multi-granularity technology demand prediction. In the deep analysis of enterprise problems, the problem description is subjected to structured processing, an entity relationship graph is constructed, and domain knowledge is aligned. The problem technology essence identification utilizes large model semantic understanding to analyze core challenges, and classifies technical problems through a multi-label classification model. And the technical knowledge base intelligently retrieves and calculates the similarity between the problem semantic vector and the knowledge graph, fuses multi-source data expansion, and screens candidate technologies according to the technology maturity. And performing multi-granularity technology demand prediction analysis on the core technology field and the subdivision direction to form a multi-level demand result. According to the invention, through systematic analysis and intelligent prediction, enterprise technology demands are accurately identified, and the method is suitable for scenes such as industry-university-research cooperation, technology transfer and innovative resource configuration.

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

A database system includes at least one data storage device storing at least one database and one or more processors configured to identify, from Structured Query Language (SQL) commands received for the at least one database, entities of the SQL commands, attributes of the entities, and relationships between the entities. The identified entities, attributes, and relationships are translated into a visual markup language code using a Large Language Model (LLM). In some aspects, the LLM or another LLM may be provided with the SQL commands to identify the entities, attributes, and relationships. An Entity Relationship Diagram (ERD) is generated or updated for the at least one database based on the translated visual markup language code. In other aspects, at least two of the identified entities, attributes, or relationships are merged for representation in the ERD.

Techniques for generating SQL queries from natural language requests are described. In some examples, a method for generating a SQL query from a natural language request includes performing entity extraction on the natural language query to extract entities and predict domains; determining required tables of the relational database to answer the natural language query; generating a SQL generation ready entity relationship graph based on the determined required tables; and generating a SQL query from at least the SQL generation ready entity relationship graph.

This invention discloses an intelligent analysis and management system for certificates of conformity based on evidence collaboration, comprising a document analysis module, an evidence collaboration module, a trusted evidence storage module, a business linkage module, and a visualization governance module. The document analysis module performs structured analysis of certificate images and generates field content and confidence levels. The evidence collaboration module establishes and verifies the correspondence between certificates of conformity and physical products based on RFID / NFC tags, production chain data, and environmental chain data. The trusted evidence storage module uses blockchain technology to write operation records into a trusted ledger, achieving end-to-end evidence storage. The business linkage module automatically triggers business processes such as warehousing, release, and review based on consistency scores and on-chain compliance status, and records business behaviors. The visualization governance module constructs an event timeline and entity relationship diagram, providing comprehensive data presentation and traceability. This invention achieves integrated management of certificate of conformity information, improving the accuracy, reliability, and traceability of certificate of conformity management.

The invention discloses an Internet infrastructure abnormal service representation recognition and extraction method and product. In the scheme, based on to-be-identified data, an internet infrastructure entity relation graph is constructed; processing the Internet infrastructure entity relation graph of the plurality of time steps to obtain feature vectors of nodes in the Internet infrastructure entity relation graph of each time step, constructing time sequence data based on the feature vectors of the nodes in the Internet infrastructure entity relation graph of the plurality of time steps, and obtaining the time sequence data based on the time sequence data. Determining fusion feature vectors of nodes in the Internet infrastructure entity relation graph of the plurality of time steps; and performing abnormal behavior identification based on the fusion feature vectors of the nodes in the Internet infrastructure entity relation graph of the multiple time steps to obtain an identification result. Compared with the prior art that the accuracy of an abnormal behavior recognition result is low due to the fact that information loss is prone to occurring in a complex internet infrastructure scene, the method and the device have obvious advantages.

The present application relates to enterprise management and data processing technical field, specifically to a kind of cross-platform operation task collaborative allocation method and system based on feature fusion, comprising: the uniform operation situation view is formed by integrating cross-platform desensitization element feature, and business entity relationship diagram is constructed based on this;The association of node and attribute in the graph is analyzed using entity association analysis model to discover collaborative workflow requirements;And according to the desensitization element feature combination of demand candidate, adapt workflow template to determine task process, while evaluating and recommending the corresponding candidate;Finally, task scheduling instructions are assigned to related platforms and performance meta-feature feedback is monitored to achieve closed-loop management.The present application realizes intelligent discovery, automation planning and closed-loop optimization of cross-platform collaborative tasks through feature fusion technology, improving the accuracy of enterprise operation efficiency and resource allocation.

The invention discloses a cross-literature type retrieval system and method fusing a graph structure, hierarchical aggregation and a generative language model. The cross-literature type retrieval system and method are used for solving the problems of semantic gaps, structural differences and noise interference during unified retrieval of scientific papers and patents. The system uniformly represents two types of heterogeneous texts through an entity-relation graph, constructs a multi-layer abstract knowledge graph by using recursive semantic clustering, extracts evidence sub-graphs by using a query anchoring and structure guiding mechanism, and finally performs joint reasoning by using a large language model and generates a retrieval result with high correlation, high interpretability and reference. Experiments show that the method is obviously superior to the prior art in correlation, coverage and readability indexes.

The invention discloses an electric power safety regulation cross-text retrieval method and system based on graph retrieval. According to the method, firstly, an electric power regulation document is preprocessed, a knowledge data set is constructed, an entity relation graph and an intra-sentence co-occurrence hypergraph are synchronously constructed according to user problems, and a unified fusion graph matrix is formed through fusion; then, under the constraint of a preset token budget, an information-path collaborative sub-graph retrieval algorithm is adopted, and logically coherent evidence sub-graphs are accurately screened out from the fusion graph; the sub-graph is coded through a graph neural network, multi-dimensional features such as nodes, texts, topologies and types are fused, and a graph-level semantic vector is generated to serve as a structured soft prompt. And finally, splicing the soft prompt and text information, inputting the spliced soft prompt and text information into a parameter-frozen large language model, and driving the model to generate an accurate answer and a clear reasoning path. According to the method, the problems of evidence fragmentation and inference chain incompleteness in multi-hop questions and answers in the field of electric power security are effectively solved, and the accuracy, reliability and interpretability of answers are remarkably improved.

The application provides an abnormal behavior recognition method and system based on multi-dimensional data analysis, including cleaning and standardizing structured data and unstructured data to obtain a uniform format data set, using natural language processing technology to process document texts therein, extracting entity, relationship and behavior information, and generating a structured feature vector; using the feature vector and the structured data to construct behavior statistics, time sequence and association features, using a sampling algorithm to select feature combinations, establishing an entity relationship graph according to the association data in the constructed multi-dimensional feature set, calculating the association strength between entities, and optimizing the entity relationship graph to establish a network structure model; setting a feature weight system according to the model and the multi-dimensional feature set, calculating a multi-dimensional abnormal score by using a pruning tensor structure measurement method, comprehensively calculating an abnormal score by using a low-rank tensor recovery technology, outputting a warning list, and improving recognition accuracy and efficiency.

The invention discloses a dynamic retrieval method and a dynamic retrieval system. The dynamic retrieval method comprises the following steps: receiving a query language of a user, and enabling a preset language model to generate a retrieval request for multiple times in single-round query interaction according to the query language; calling a graph database based on the retrieval request, so that the graph database outputs an entity relationship graph based on the retrieval request; and forming a query reply based on the entity relationship graph, and feeding back the query reply to the user. According to the technical scheme provided by the invention, the requirement of a user on accurate and deep knowledge acquisition can be effectively met, and the application in a complex business scene is met.

The invention discloses a data generation method based on small sample seeds and multi-round reinforcement and electronic equipment. The method comprises the following steps: acquiring and preprocessing labeled seed data related to a data task of the intelligent question-answering system to obtain a standardized seed data set; constructing an initial entity set and a relationship set, and performing normalization and weighting processing to generate an entity relationship graph; generating first basic question and answer data based on the entity relation graph, applying consistency constraint, and filtering to obtain second basic question and answer data; performing retrieval enhancement on the second basic question and answer data to generate enhanced training data containing external knowledge support; utilizing reinforcement learning to take the data generation strategy as a decision action, and taking the reinforcement training data as input to generate a reinforcement learning decision process; preliminary training sample data are generated through multiple rounds of reinforcement learning, and training sample data meeting task requirements are automatically generated. According to the method, the generalization ability and robustness of the large language model in intelligent question and answer generation are effectively improved.

The present application belongs to the field of software fault diagnosis, and provides a fault diagnosis intelligent agent data preprocessing method and system based on multi-modal alignment to solve the problems of information mismatch and low reasoning accuracy. The fault diagnosis intelligent agent data preprocessing method based on multi-modal alignment includes dynamic resampling of log event sequence; time-aligned index sequence and log event sequence; matching and calling tracking data of a set time period from cache data; constructing an entity relationship graph; real-time updating the entity relationship graph; processing the real-time updated entity relationship graph to obtain a spatio-temporal aligned index sequence, log event sequence and tracking data sequence; corresponding extracting index features, log features and tracking features and fusing them to obtain fused features; and converting the fused features into natural language descriptions as inputs of the fault diagnosis intelligent agent. The method can perform spatio-temporal alignment preprocessing on multi-modal data, and improve the accuracy and efficiency of fault diagnosis.

The invention provides a construction and deployment method and device of an observable data management model and electronic equipment, and belongs to the technical field of cloud native. The method comprises the following steps: for any entity field related to a target entity, constructing a data graph of the entity field based on the entity field, at least one observable data set related to the entity field and a field description information set of the entity field; based on the entity relationship between the at least one entity field, constructing an entity relationship graph of the at least one entity field; based on the data graph and the entity relation graph of the at least one entity field, an observable data management model of the target entity is constructed, and the observable data management model is used for indicating a definition mode and an association relation of data related to the target entity so as to perform unified management on observable data related to the target entity. According to the method, the observable data related to the target entity in the system is defined and managed in a unified manner, so that the management complexity is reduced, and a data island phenomenon is avoided.

The invention discloses a data modeling method and device for demand modeling in software development, equipment and a medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring enterprise-level business data; dividing and establishing an enterprise subject domain model based on the business domain; for each subject domain model, forming an enterprise concept data model; mapping the business concepts into business entities, defining entity relationships among the business entities, and determining attributes and attribute domains for the business entities; dividing the plurality of attribute domains into an attribute domain group, and determining an attribute domain instance for the attribute domain belonging to the code class; forming an enterprise logic data model based on the business entity, the entity relationship, the attribute and the attribute domain; generating an application physical data model based on the enterprise logic data model; wherein the enterprise concept data model is visually presented to business personnel in the form of a classification hierarchy graph; and presenting the enterprise logic data model to technicians in the form of an entity relation graph. The data quality of an enterprise is improved.

The application belongs to the technical field of databases, and particularly relates to a database table relationship exploration method for LLM-Text2SQL. The method adopts a multi-stage collaborative processing strategy, integrates database metadata and data content features, and performs semantic enhancement and structured completion on original information through a large language model. On this basis, a potential association candidate set is screened by combining an algorithm based on feature similarity, and multi-dimensional verification and judgment of the association relationship are performed by fusing a predefined rule and a large language model inference mechanism, so as to finally generate an entity relationship graph supporting interactive editing and iterative optimization. The method realizes end-to-end automatic processing from a heterogeneous database with missing constraints and damaged data integrity to a normalized ER graph, and lays a solid foundation for significantly improving the success rate of natural language SQL generation based on a large language model.

The invention relates to a span-based construction method of a knowledge graph about dangerous chemicals. The method comprises the following steps: acquiring original data; preprocessing the original data to extract text information; marking the preprocessed data, and dividing a marked data set into a training set, a verification set and a test set; according to the original text, utilizing a pre-training language model to extract entities in sentences, and predicting entity types; screening entity pairs according to the correlation of the entities; predicting the relationship between the entity pairs, and constructing an entity relationship graph; and performing knowledge representation on the extracted entities and entity relationships by using an RDF (Resource Description Framework), and constructing a knowledge graph. The named entity identification method based on the span has the beneficial effects that by adopting the named entity identification method based on the span and introducing the start-stop marks and the position IDs, the problem of boundary fuzziness easily occurring in chemical name and attribute item identification of traditional BIO sequence labeling is effectively solved, and the accuracy of entity identification is improved.

Embodiments of the present application provide a data generation method for text-to-SQL task, an electronic device and a storage medium. The method comprises: constructing a first entity relationship graph containing entities and relationships based on the relationship class table and the entity class table in the first database schema diagram of the original text-to-SQL data; obtaining a second entity relationship graph by at least graph transformation of the nodes or edges in the first entity relationship graph; generating a second entity relationship graph of relationship class change according to the second entity relationship graph, and generating structured data enhanced text-to-SQL data based on the abstract syntax tree determined by the second entity relationship graph. Embodiments of the present application can automatically generate a large amount of data suitable for structure generalization research with a small amount of annotation, and at the same time, the structured text-to-SQL data generated by the method can be used for data enhancement to improve the robustness of the text-to-SQL system, and thus improve the experience of user voice interaction.