47 results about "Relational knowledge" patented technology

The invention relates to the technical field of financial data analysis and artificial intelligence, in particular to a multi-source heterogeneous financial data fusion and intelligent analysis system which comprises a data standardization processing module, a time sequence event fusion module, a knowledge graph construction module, a relation reasoning module and a self-adaptive anomaly detection module. The data standardization processing module is used for converting heterogeneous financial data from different sources into unified tensor representation; the time sequence event fusion module adopts a double-clue cooperation mechanism to establish a mapping relation between continuous time sequence data and discrete events; the knowledge graph construction module extracts financial entities and relationships thereof, and constructs a multi-level knowledge graph; the relation reasoning module performs deep reasoning based on a graph attention mechanism; and the adaptive anomaly detection module dynamically adjusts the detection threshold according to the market environment. According to the system, implicit association in heterogeneous financial data can be deeply mined, market anomalies are recognized in advance, and comprehensive support is provided for financial decision making.

The invention discloses an intelligent dialogue memory management method and system based on the logistics field, and relates to the technical field of logistics intelligent dialogues, and the method comprises the steps: obtaining the historical logistics dialogue data of a target user, generating a user feature-interactive entity-semantic relationship initial knowledge graph based on a QWen2.5-32B large language model, and constructing a Milvus semantic vector library; monitoring a logistics dialogue flow in real time, and starting an adaptive memory management mechanism by taking three rounds of dialogue as a judgment threshold value; extracting user dialogue content attribute features and behavior preferences, and dynamically updating a user feature-interactive entity-semantic relationship initial knowledge graph and a Milvus semantic vector library; and triggering a logistics dialogue according to a target user, starting a multi-modal memory recall mechanism, cooperatively retrieving a user feature-interactive entity-semantic relationship knowledge graph and a Milvus semantic vector library, generating a personalized intelligent dialogue response, and realizing a logistics intelligent dialogue memory management closed loop. The beneficial effect of the invention is that the intelligent and personalized capabilities of the system are enhanced.

The invention discloses an AI artificial intelligence-driven tax, accounting and auditing method and system, and relates to the technical field of tax and financial management, and the method comprises the following steps: S1, data collection and preprocessing; s2, performing iterative optimization on the xLSTM model through an improved Adame optimizer; s3, extracting a financial data articulation knowledge graph; s4, tracking an abnormal source by using the articulation knowledge graph; s5, generating a comprehensive regulation suggestion; and S6, generating a standardized audit report. According to the method, the problems of long manual calculation time, low tax risk prediction precision, auditing response lag and the like in a traditional financial management method are solved, and an efficient, accurate and real-time financial management technical solution is provided through intelligent automatic analysis.

The invention discloses a data insight report generation method and system based on knowledge enhancement and fact verification. Building a domain index relation knowledge graph by training a large language model; mapping the insights to a map, constructing a weighted insights map, carrying out spectral clustering, and dividing insights theme areas; a viewpoint unit is generated through the writing agent, and consistency verification and correction are carried out through the fact verification agent; the user intention is analyzed, candidate topics are screened, and a report outline is generated through heuristic search arrangement based on SRCI scoring, semantic progression and logic entropy calculation; finally, the verified viewpoint units are integrated according to the outline, and a final report is output. According to the method, the full-automatic and high-credibility report generation is realized, and the accuracy, logicality and interpretability are improved.

The invention provides an enterprise supply chain financial risk prediction method fusing a dynamic knowledge graph and a graph neural network. The method comprises the steps of multi-source data loading and preprocessing, supply chain knowledge graph construction, financial feature extraction, risk label generation and the like. Aiming at the problems that multi-subject information of core enterprises, suppliers, customers and the like in supply chain data is dispersed and is inconsistent with independent financial data structures, the method solves the problems that manual integration is low in efficiency and prone to errors through automatic data cleaning, entity matching and relation mapping, and a unified and structured enterprise supply chain relation knowledge graph is constructed; the limitation of manually designing network features is overcome by utilizing a graph attention network; an effective feature fusion strategy is designed, and joint feature representation with higher discriminative force is formed; and constructing an end-to-end evaluation framework, training classifiers such as a support vector machine to learn the fusion features, realizing accurate and stable classification of high-risk and low-risk enterprises, and providing probability output to enhance result interpretability and decision support capability.

The invention discloses a medical image super-resolution reconstruction method based on incremental learning, and aims to solve the problem that a super-resolution reconstruction network is easy to have disastrous forgetting during incremental learning of a multi-modal medical image through a cooperative strategy of adaptive memory buffer management, relational knowledge distillation and dynamic gradient equilibrium. And efficient learning of the new mode and stable retention of the reconstruction capability of the old mode are realized. According to the method, adaptive gradient weighted difficulty scoring is combined with farthest point sampling to efficiently screen playback samples, a characteristic space geometrical relationship is maintained by utilizing relational knowledge distillation, and conflicts are monitored in real time and weights are automatically adjusted through a dynamic gradient balance mechanism. According to the method, the disastrous forgetting degree is remarkably reduced, a single model can learn multiple modes in sequence and continuously keep the super-resolution reconstruction capacity for all the learned modes, and the method can be widely applied to multi-mode medical image super-resolution reconstruction tasks such as MRI and chest X-rays and has high clinical application value.

The invention discloses an epilepsy medical knowledge graph construction method and system based on rhodic acid C, and relates to the technical field of knowledge graph construction. The method comprises the following steps: acquiring initial medical text information; preprocessing the initial medical text information to obtain non-standard medical text information; performing term conversion on the non-standard medical text information according to a medical term relationship knowledge base to obtain standardized medical text information; extracting medical information related to a mode of action of a rhodic acid C molecule and epilepsy diagnosis and treatment from the standardized medical text information; and adding the medical information into a knowledge graph database. According to the method, the non-standard medical text information can be converted into the standardized medical text information in combination with the medical term relationship knowledge base, so that the knowledge graph is constructed, and the data recognition accuracy and the knowledge graph quality are improved.

Causal discovery is performed using knowledge graph link prediction. Information from a causal network is transformed into a causal knowledge graph according to a mapping, the causal knowledge graph including a plurality of causal links, wherein each causal link includes a cause entity, a causal relation, and an effect entity, with the potential for a mediator. The causal knowledge graph is converted into embeddings, where the embeddings include a latent vector space representation of the causal knowledge graph. The embeddings are trained using a subset of the causal links of the causal knowledge graph. The embeddings are used for causal discovery to predict additional causal links of the causal knowledge graph.

The invention discloses a medicine research and development industry knowledge base system and method based on artificial intelligence, and belongs to the technical field of medicine information processing and artificial intelligence. The system comprises a data acquisition module, a data preprocessing module, a knowledge extraction module, a knowledge integration module, a knowledge reasoning module, a knowledge updating module and an intelligent center layer. The data acquisition module acquires multi-modal medicine research and development data, the preprocessing module performs cleaning, standardization and feature alignment, the knowledge extraction module adopts a deep learning model based on Transformer to extract entity relationships, the knowledge integration module checks conflicts through a chemical rule knowledge base and constructs a knowledge graph, and the knowledge graph is used for establishing a knowledge database. The knowledge reasoning module performs association prediction by using a graph neural network and a time sequence model, the knowledge updating module realizes parameter optimization and incremental updating based on human feedback reinforcement learning, and the intelligent central layer overall plans all the modules to work cooperatively based on a large language model arrangement framework. According to the method, multi-source heterogeneous data can be integrated, domain semantics can be deeply understood, a knowledge structure is dynamically evolved, intelligent decision support is provided, and the efficiency and accuracy of medicine research and development knowledge management and application are remarkably improved.

The invention relates to the technical field of health care knowledge question answering, in particular to a historical health care knowledge question answering method and device based on knowledge graph and large-scale language model fusion, and the device comprises a knowledge graph module, a question processing and retrieval module and a large-scale language model module; the knowledge graph module is used for storing entities and relation knowledge in a historical health-care field and binding time attributes and literature sources; the question processing and retrieval module is used for analyzing user questions and retrieving knowledge entries related to the questions in the knowledge graph module to form an evidence chain; and the large language model module is used for generating an answer result based on the user question and the evidence chain. The method has the advantages that the problems that'illusion 'easily occurs in a general model, answers are difficult to verify, knowledge is difficult to dynamically update and the like in a historical health and care context are effectively solved, and the method can be widely applied to scenes such as health and care policy research, long passport photo-care service knowledge base construction, educational training and academic retrieval and the like.

The invention discloses an index data management method and device, equipment, a medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining a target structured query statement calculation rule, a target index data job log, a target index database table relationship, a target index metadata vector and a reference index metadata vector; adopting a data direct blood relationship detection model to identify the target structured query statement calculation rule, the target index data job log and the target index database table relationship to obtain a direct association index having a direct data blood relationship with the target index; according to the reference similarity between the target index metadata vector and the reference index metadata vector, determining an indirect association index having indirect semantic association with the target index; and according to the target index, the direct association index and the indirect association index, constructing a target index comprehensive relationship knowledge graph. According to the technical scheme, the analysis efficiency of the index data is improved.

The invention discloses a database construction method and system for building construction carbon emission calculation, and relates to the technical field of building construction carbon emission calculation, and the method comprises the steps: obtaining a three-level standard data set, and constructing a three-level initial knowledge graph; identifying and extracting a construction large class and a corresponding large class construction process, obtaining a large class process standard carbon emission value, and updating the three-level initial knowledge graph; dividing the large-class construction procedures into a plurality of middle-class construction procedures, acquiring standard carbon emission values of the middle-class procedures, and further updating and perfecting the three-level initial knowledge graph; establishing an eight-dimensional associated knowledge graph; obtaining a refined construction project and a corresponding fine particle standard carbon emission estimated value; obtaining a fine particle standard carbon emission value after the reverse checking calculation is qualified, and solidifying the initial eight-dimensional association knowledge graph; according to the method, the technical problems that in the prior art, three-level data are mutually independent, a plurality of standard data sets cannot achieve a synergistic effect, and the adaptability of a database for building construction carbon emission calculation is poor are solved.

The invention provides a pipeline cathode protection operation and maintenance question-answering robot system and method, a fault relation knowledge graph based on cathode protection monitoring data is constructed, and causal modeling of potential abnormity, current change, anode failure, reference electrode failure, test piece abnormity, wiring error or abnormity and other problems can be achieved; an atlas inference engine is introduced to realize data-driven fault diagnosis and maintenance suggestion generation; by combining natural language processing (NLP) and question and answer system technologies, operation and maintenance personnel are supported to put forward operation and maintenance related questions in a natural language mode, and the system can automatically analyze semantics, recognize intentions, infer answers and provide accurate and executable response suggestions. According to the method, the pipeline cathode protection system can be assisted to realize intelligent fault diagnosis, and an intelligent question and answer service of'understanding questions and clearing answers' can be provided for operation and maintenance personnel.

This invention discloses a method for automatically generating evidentiary documents for a document management system manual. First, the chapter requirements of the evidentiary document to be generated are obtained, and relevant knowledge is retrieved from a corpus containing ISO standard texts, organizational background documents, and historical evidentiary documents. A chapter-entity-relationship knowledge graph is constructed by parsing ISO standard clauses. A three-level progressive retrieval strategy is used to match specific instance information from the corpus, and the standard requirements and instance information are integrated to generate dynamic prompt words. After generating preliminary content using a large language model, a multi-level rule-based verification system is used to verify grammatical format, standard compliance, and organizational adaptability layer by layer. If a verification fails, a feedback loop is triggered for correction. Key corpora are stored on a blockchain to ensure the traceability of the generated content. Finally, revision opinions from reviewers are obtained and feedback is used to optimize the generation strategy. This invention achieves automated and compliant generation of evidentiary documents, significantly improving generation efficiency and content quality.

The invention relates to the technical field of data storage, and particularly discloses a scholar relationship network storage construction method and system based on an artificial intelligence graph database, and the method comprises the steps: constructing a heterogeneous scholar relationship knowledge graph of each heterogeneous academic data source; extracting a joint feature vector of each scholar node in each heterogeneous scholar relationship knowledge graph; performing alignment target coarse screening on every two scholar nodes in the heterogeneous scholar relationship knowledge graph of the different heterogeneous academic data sources based on the self attribute vector of each scholar node to obtain a plurality of to-be-aligned scholar node combinations; calculating the similarity of the joint feature vectors of all scholar nodes in each to-be-aligned scholar node combination; based on the similarity scores of all the to-be-aligned scholar node combinations, fusing all the heterogeneous scholar relationship knowledge maps to obtain a unified scholar relationship network, and storing the unified scholar relationship network to a distributed native graph database; the method and device are used for meeting efficient access requirements of scholar relational network data.

The invention relates to the technical field of information retrieval, in particular to an information retrieval method, a medium and equipment, which support the retrieval of three types of keywords, integrate multiple types of nodes in a graph, pre-construct a material relationship knowledge graph containing multi-dimensional nodes and association relationships, and combine visual output of a material information table and an association sub-graph, so that the information retrieval efficiency is improved. A logic chain between the medicine and each associated element is visually displayed, and associated query requirements of a user in multiple scenes can be met without cross-platform multiple retrieval; according to the method, authoritative data are integrated in the atlas construction process, so that association of drugs, treatment schemes and diseases has clinical reasonability and authority, meanwhile, association sub-atlases are extracted through association extension, false association and irrelevant information are effectively filtered, and the accuracy and reliability of retrieval results are improved; by outputting the first retrieval result page and the second retrieval result page in stages, the requirement of a user for rapidly screening target substances is met, deep detailed information can be provided, and the retrieval efficiency and the information depth are balanced.

The application provides a drug recommendation method and device based on a three-layer super-relation knowledge graph model, and the method comprises the following steps: obtaining user attribute information of a target user, wherein the user attribute information comprises disease conditions, clinical symptoms, physical examination and physiological state information; constructing a three-layer super-relation knowledge model based on a super-relation knowledge graph, inputting the user attribute information into the three-layer super-relation knowledge model to convert the user attribute information into search conditions of a graph query statement; translating the search conditions into a correct graph database query statement, obtaining a reasoning result by calling a graph database search engine according to preset reasoning conditions; adding the reasoning result to a drug use scheme, obtaining a target drug according to the drug use scheme, and pushing the target drug to the target user. The application realizes a medical rule-based drug recommendation auxiliary decision application.

The application discloses a data insight report generation method and system based on knowledge enhancement and fact verification. A domain index relationship knowledge graph is constructed by training a large language model; the insight is mapped to the graph, a weighted insight graph is constructed, and spectral clustering is performed to divide the insight theme area; a viewpoint unit is generated by an intelligent agent, and consistency verification and correction are performed by a fact verification intelligent agent; user intent is analyzed, candidate themes are screened, a report outline is generated by heuristic search arrangement based on SRCI score, semantic progression and logic entropy calculation; finally, verified viewpoint units are integrated according to the outline, and the final report is output. The application realizes the generation of a fully automatic and high-credibility report, and improves accuracy, logic and explainability.

The application discloses a kind of epilepsy medical knowledge graph construction method and system based on rose acid C, it is related to knowledge graph construction technical field, method includes: obtaining initial medical text information;The initial medical text information is preprocessed, and non-standard medical text information is obtained;According to medical terminology relationship knowledge base, the non-standard medical text information is converted into terminology, and standardized medical text information is obtained;From the standardized medical text information, the medical information related to rose acid C molecule mode of action and epilepsy diagnosis and treatment is extracted;The medical information is added to knowledge graph database.The application can convert non-standard medical text information into standardized medical text information by combining medical terminology relationship knowledge base, to construct knowledge graph, improve data recognition accuracy and knowledge graph quality.

The embodiment of the invention provides a multi-relation knowledge graph construction method and device, equipment and a medium, and the method comprises the steps: obtaining a global role embedding matrix of an initial multi-relation knowledge graph, and determining a role embedding vector of a role played by each entity in a target relation according to the global role embedding matrix; determining a global feature vector of the target relationship according to the feature vectors of the plurality of sub-relationships included in the target relationship; constructing a projection relation matrix of the role embedding vector and the entity feature vector; and according to the role embedding vector played by each entity in the target relationship, the projection relationship matrix and the global feature vector of the target relationship, determining an association score of each entity and the target relationship. Therefore, the model can understand multi-relation data more deeply, role semantic perception of the entity in multiple relations is fully utilized, and the accuracy and effectiveness of subsequent link prediction are improved.

The invention relates to the technical field of computer simulation, and discloses a military simulation scenario description method based on a knowledge graph, which comprises the following steps: acquiring command and control message data and electromagnetic environment link state data, and dividing command session sets according to message header identifiers; constructing a multi-layer associated knowledge graph comprising a session layer, a statement layer and a traceability layer; counting accumulated link connection duration according to the electromagnetic environment link state data, triggering a scenario grounding operation when a preset threshold is met, and generating an execution element layer in the atlas; statistics is carried out on the pixel scale change amplitude before and after each grounding operation, and a session traceability expansion index is generated through weighting processing; and finally, establishing a complexity identification node bearing the index, writing the complexity identification node into a graph, and outputting a final knowledge graph file, a command and control message sequence capable of being played back and a simulation executable scene package. The structure expansion risk caused by the environment and the protocol mechanism can be quantified in the description stage, and the method is suitable for large-scale simulation interoperation.

The application relates to the technical field of data storage, and particularly discloses a scholar relationship network storage construction method and system based on an artificial intelligence graph database, which comprises the following steps: constructing a heterogeneous scholar relationship knowledge graph of each heterogeneous academic data source; extracting a joint feature vector of each scholar node in the heterogeneous scholar relationship knowledge graph; performing coarse screening on two scholar nodes in the heterogeneous scholar relationship knowledge graph of different heterogeneous academic data sources based on the self attribute vector of each scholar node, so as to obtain a plurality of to-be-aligned scholar node combinations; calculating the similarity of the joint feature vectors of all the scholar nodes in each to-be-aligned scholar node combination; fusing all the heterogeneous scholar relationship knowledge graphs based on the similarity scores of all the to-be-aligned scholar node combinations, so as to obtain a unified scholar relationship network and store the unified scholar relationship network into a distributed native graph database; and the unified scholar relationship network can meet the efficient access demand of scholar relationship network data.

The invention discloses a cardinal number estimation method, system, equipment and medium based on a hyper-relation knowledge graph, which are applied to the field of data query, and comprise the following steps of: obtaining a query vector and a relation vector according to a query graph, fusing a supplementary definer vector and an explicit definer vector which are obtained after supplementation to obtain a comprehensive definer vector, and calculating the cardinal number of the comprehensive definer vector according to the comprehensive definer vector. Combining and synthesizing the determiner vector and the relation vector, performing multi-round iterative information transmission and vector updating on nodes in the query graph through a graph neural network to generate final representation of each node, aggregating the final representation of each node to form global representation of the query graph, performing nonlinear regression mapping on the global representation, and obtaining the query graph. And outputting the cardinality estimation value of the query graph. According to the method, the conditional variation auto-encoder is adopted to intelligently supplement the definitive words, and the rotation operation is combined to deeply aggregate the definitive words, so that sufficient capture and utilization of meanings of the complex definitive words in the super-relation knowledge graph are ensured, and the defect of insufficient utilization of definitive word information in a traditional method is overcome.

The application discloses a kind of indoor multi-scene semantic map construction method based on semantic relation graph, comprising: based on laser radar using grid map algorithm constructs 2D grid map;Using binocular camera obtains scene image, obtains depth map by stereo matching and identifies object in environment using trained target detection model, obtains the class and coordinate of landmark, image data adopts bayesian filtering technology to combine prior information and carries out scene classification, obtains the semantic label of current scene, using the semantic label obtained using the semantic map of occupancy grid method;Based on target identification dataset constructs prior relation graph, fuses space relation knowledge graph and prior relation knowledge graph to construct graph layer, obtains multi-scene semantic map.The semantic relation map of the present application based on deep learning and knowledge graph construction stores a large amount of prior knowledge, gives map comprehensive and accurate environmental information, can realize quick search in multi-scene rescue and daily service.

The application discloses a method and related device for discovering unregistered place names and reasoning spatial positions, and relates to the technical field of geographic information. The method comprises the following steps: constructing a place name space-time derivation relationship knowledge graph based on an open source geographic database; inputting target place name text data into a sequence labeling model to obtain a labeling result, and extracting candidate derived place names based on the labeling result; performing common name segmentation on the candidate derived place names to obtain potential basic place names, and judging whether the potential basic place names meet preset association conditions based on the place name space-time derivation relationship knowledge graph; if yes, the potential basic place names are excluded; if no, the potential basic place names are determined as unregistered place names; and determining the spatial positions of the unregistered place names according to the common names of the unregistered place names and the place name space-time derivation relationship knowledge graph. The application can improve the automation degree of discovering unregistered place names and reasoning spatial positions.

The invention discloses an intelligent network connection vehicle traffic accident knowledge base construction system, and the system comprises a large model adaptation module which is provided with a lightweight large language model facing the field of intelligent network connection vehicle accidents; the knowledge graph construction module is configured with a structured knowledge graph which is constructed by extracting entities, attributes and relationships from a multi-source corpus based on a lightweight large language model and a preset knowledge modeling rule; the knowledge base generation module is configured with a knowledge base which is generated by carrying out collaborative scheduling on the lightweight large language model and the knowledge graph based on a graph-model complementary fusion inference mechanism; the graph-model complementary fusion inference mechanism performs fusion and confidence evaluation on semantic related knowledge from the large language model and structured associated knowledge from the knowledge graph in response to the query request, and generates an inference result based on the evaluated confidence; and the user interaction module is used for receiving the query request and visually outputting a reasoning result. Meanwhile, the invention further discloses a method and equipment.

This invention belongs to the field of computer vision technology, specifically relating to an image description method that integrates knowledge graphs and sentiment recognition. The method includes: acquiring an image to be processed and performing feature extraction and object detection to obtain object information, image features, and sentiment features; completing an external general knowledge graph using a graph attention network to obtain a dense knowledge graph; inputting the object information into the dense knowledge graph to query entity relationships, obtaining relational knowledge vectors; and using a Transformer decoder to process the relational knowledge vectors, image features, and sentiment features to obtain descriptive text for the image. This invention solves the problems of insufficient semantic understanding, lack of sentiment expression, and weak external knowledge support in existing technologies, generating highly accurate, complete, and emotionally rich image descriptions with promising application prospects.

The invention discloses an AI-based interface model automatic conversion system, which comprises an AI analysis module for identifying interface model information in a document and converting the interface model information into a fixed format text containing a field name, a field meaning and a data type; the AI mapping module is used for mapping partner interface fields into local internal standard data model fields and assembling a mapping relation in a JSON format; the knowledge base management module is used for storing historically completed model mapping configuration and content results of subsequent AI configuration; the content with incorrect configuration is fed back to the AI mapping module through API (Application Program Interface) calling; the AI integration and calling module is used for integrating a large model by using Spring AI and calling the large model through ChatClient to realize interaction; and converting an AI processing result into a format meeting system requirements by customizing an output model format. According to the invention, rapid and accurate conversion of the interface model can be realized.