Product
Feature
Quick Research
Generate reliable direction feasibility study reports for your R&D in just a few steps.
Technical Q&A
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
Find Solutions
As an expert in R&D theories, this can generate solutions to your technical problems instantly.
Evaluate Feasibility
Analyze your overall solution with one click, know your potential R&D risks in advance.
Monitor Landscape
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
41 results about "Knowledge modelling" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Manufacturing design knowledge individualized pushing method based on knowledge graph (Man-tree)
InactiveCN106156090AGood answerProof of feasibilitySpecial data processing applicationsPersonalizationKnowledge modelling
The invention belongs to the technical field of knowledge management and knowledge pushing oriented to manufacturing enterprises, particularly relates to a novel and efficient knowledge management and knowledge pushing method based on a knowledge graph and discloses a knowledge pushing method based on a manufacturing design knowledge graph structure (Man-tree). By means of the method, the comprehensiveness and accuracy of enterprise knowledge pushing can be effectively improved. The knowledge pushing method comprises the step that a knowledge modeling module, a knowledge extracting and subject discovering module, a knowledge graph Man-tree establishing module, a user knowledge possess degree calculation module and a knowledge pushing module are established by introducing an LDA method. By quantitatively evaluating the degree of the knowledge processed by a user, the knowledge graph is expanded, and semantic association between knowledge and the user is established. According to the specific technology, formation of a database, extraction of knowledge, discovery of knowledge association, knowledge storage design, and a quantitative calculating method for the degree of the knowledge processed by a user are included. The novel method for knowledge pushing in the manufacturing design field is given on the basis that the manufacturing design graph is proposed.
Owner:上海宽文是风软件有限公司
Structured knowledge modeling and extraction from images
Embodiments of the invention relate to structured knowledge modeling and extraction from images. Techniques and systems are described to model and extract knowledge from images. A digital medium environment is configured to learn and use a model to compute a descriptive summarization of an input image automatically and without user intervention. Training data is used to train a model using machine learning in order to generate a structured image representation that serves as the descriptive summarization of an input image. The images and associated text are processed to extract structured semantic knowledge from the text using natural language, which is then associated with the images. The structured semantic knowledge is processed along with corresponding images to train a model using machine learning such that the model describes a relationship between text features within the structured semantic knowledge. Once the model is learned, the model is usable to process input images to generate a structured image representation of the image.
Owner:ADOBE SYST INC
Electric power communication network knowledge graph construction method based on BERT model
PendingCN112613314AImprove accuracyReduce term ambiguityData processing applicationsSemantic analysisKnowledge modellingFeature extraction
The invention relates to an electric power communication network knowledge graph construction method based on a BERT model, and the method comprises the following steps: S1, original document library construction: selecting data of different sources and structures as a basis, and constructing the original document library; S2, label migration: labeling the original knowledge data of the power communication network, and carrying out label migration on the basis of labeling information; S3, semantic feature extraction: performing training based on a BERT model to realize semantic feature extraction of the structured document data of the power communication network; and S4, knowledge graph construction: performing named entity identification on the extracted semantic features based on a BiLSTM-CRF model, extracting knowledge concepts and interrelations, and forming the knowledge graph in cooperation with knowledge modeling. The method effectively solves the typical problems of many professional terms, few training corpora and the like, improves the accuracy of key steps such as named entity recognition and the like, and finally improves the performance of the knowledge graph.
Owner:INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER
Collaborative recommendation model construction method based on knowledge graph preference propagation
PendingCN113158033AAutomatic mining of latent preferencesImprove interpretabilityData processing applicationsRelational databasesKnowledge modellingRecommendation model
A collaborative recommendation model construction method based on knowledge graph preference propagation comprises the following steps: (1) performing knowledge modeling by using an ontology modeling tool, extracting entities and relationships to obtain a triple, and constructing a domain knowledge graph; (2) obtaining multi-layer preferences of the user through the preference propagation model, and calculating vector representation of the user preferences according to the multi-layer preferences of the user; (3) learning the vector representation of the article based on the user-article interaction matrix, and performing dot product operation on the preference vector representation of the user and the implicit vector representation of the article to calculate the click probability of the user on the article; and (4) recalling articles interested by the user according to the click probability, comparing a recall result with a user interaction list, and performing descending sorting after excluding the articles operated by the user to obtain a recommendation list. According to the recommendation model provided by the invention, the path structure information of the knowledge graph can be fully utilized, and the interpretability and diversity of recommendation results are improved.
Owner:ZHEJIANG UNIV OF TECH
Equipment resource configuration optimization method based on knowledge graph driving
ActiveCN111191821AEasy to handleReduce the cost of optimal configurationRelational databasesForecastingKnowledge modellingConfiguration optimization
The invention discloses an equipment resource configuration optimization method based on knowledge graph driving. The method comprises the steps that a knowledge graph of manufacturing resources is organized and generated, and machining process knowledge modeling and workshop machining equipment modeling are involved; the formed knowledge graph is subjected to a distributed representation learningand resource prediction matching method, and the relation between the knowledge graph and mining manufacturing resource implicit knowledge is further represented; when a processing order is issued, acandidate equipment set is constructed in combination with a fuzzy hierarchy method based on knowledge graph driving, and further the candidate equipment set is evaluated and screened through a community load model to complete reconstruction of the manufacturing unit; and finally, configuration optimization of an order task is completed by utilizing an optimization algorithm of the resource configuration mathematical model, an available processing equipment set link is formed, and a production process is guided. According to the method provided by the invention, the data processing capabilityis enhanced to a great extent, the equipment utilization rate and the equipment processing flexibility are improved, and meanwhile, the optimal configuration cost of manufacturing resources requiredby a processing task is also reduced through integrated knowledge reuse.
Owner:DONGHUA UNIV
Automated legal evaluation using a decision tree over a communications network
InactiveUS8423482B2Digital computer detailsNatural language data processingKnowledge modellingOperations research
A method for legal knowledge modeling and automated legal evaluation, such as for online, questionnaire-based legal analysis, is provided. Information, such as facts and characteristics of a legal situation or legal scenario, as it relates to a legal conclusion or a legal result, are modeled in a decision tree. The decision tree may comprise a plurality of nodes and a plurality of edges connecting the nodes, wherein each node is associated with a variable that represents either an answer to a legal inquiry or a legal conclusion, and an edge represents a conditional dependency between variables of nodes. The decision tree is automatically updated on a periodic basis to reflect new legislation or court decisions. Using the decision tree, a legal conclusion based on the user's answers to a questionnaire may be determined. The legal conclusion is modified upon the input of evidence, which is typically in the form of answers to a dynamic set of questions designed to identify a legal conclusion or a legal result.
Owner:GANSNER HARVEY L
Knowledge graph construction method and system
PendingCN114064910ARealize dynamic updateImplement extensionsSpecial data processing applicationsSemantic tool creationKnowledge modellingOriginal data
The invention provides a knowledge graph construction method and system. According to the knowledge graph construction method and system provided by the invention, the method comprises the steps: obtaining original data and a background knowledge graph, performing knowledge modeling of the original data based on the background knowledge graph, generating concept layer data, and thus obtaining more complete concept layer data; meanwhile, on the basis of the background knowledge graph, performing encyclopedia triple extraction and / or relation triple extraction on the original data, to obtain instance layer data, and thus obtaining more complete instance layer data in the mode that encyclopedia triple extraction and open relation extraction are combined; and finally, on the basis of the concept layer data and the instance layer data, constructing a new knowledge graph, and updating the background knowledge graph by using the new knowledge graph, so as to achieve the dynamic updating of the knowledge graph and the expansion in the use process.
Owner:TSINGHUA UNIV
Knowledge graph construction method and device, server and computer readable storage medium
InactiveCN111291135AImprove retrieval efficiencyEasy to classifySemantic analysisRelational databasesKnowledge modellingTheoretical computer science
The invention relates to a knowledge graph construction method and device, a server and a computer readable storage medium, and the method comprises the steps: obtaining the resource data of a presetfield, carrying out the preprocessing of the resource data of the preset field to obtain the preprocessed resource data; carrying out knowledge modeling on the preprocessed resource data to obtain a knowledge graph body, wherein the knowledge graph body comprises entity nodes, literal quantity nodes, relationships between the entity nodes and relationships between the entity nodes and the literalquantity nodes; extracting triple data conforming to the knowledge graph body from the preprocessed resource data, constructing the knowledge graph according to the triple data, wherein the triple data is composed of entity nodes, literal volume nodes, relationships among the entity nodes and relationships among the entity nodes and the literal volume nodes. The entity nodes and the literal quantity nodes are extracted from the resource data respectively, and the resource data can be better classified, so that the retrieval efficiency of the constructed knowledge graph is improved.
Owner:SHENZHEN ZHUIYI TECH CO LTD
Ancient poem proposition method and system
ActiveCN111400506AQuality improvementRich poetry informationSemantic analysisNeural architecturesKnowledge modellingSemantics
Owner:AISPEECH CO LTD
Multi-disaster coupling and secondary derivative evolution prediction system based on disaster chain
PendingCN112365078APlay a predictive roleMathematical modelsForecastingEmergency treatmentKnowledge modelling
The invention discloses a disaster chain-based multi-disaster coupling and secondary derivative evolution prediction system. The system comprises a disaster chain correlation knowledge modeling module, a multi-disaster emergency dynamic comprehensive management module and a multi-disaster coupling prediction module, the disaster chain correlation knowledge modeling module is used for constructinga disaster chain for natural disasters by using a disaster source to form a semantic network graph, and representing disaster chain knowledge by using a Bayesian network method in combination with actual background demand analysis of a cause and effect type disaster chain; the multi-disaster emergency dynamic comprehensive management module is used for realizing dynamic management of real-time processing, analysis and decision of natural disaster information; and the multi-disaster coupling prediction module divides a disaster chain-based prediction process into single-disaster prediction andmulti-disaster coupling prediction according to two factors of catastrophe and a disaster-affected body. According to the invention, through the multi-disaster coupling evolution model, occurred disasters can be analyzed in an omnibearing and multi-angle manner, and various emergency treatments after the disasters occur can be carried out.
Owner:NANJING LES INFORMATION TECH
Knowledge graph construction method and device
PendingCN113268606ARealize dynamic updateImplement extensionsDatabase updatingRelational databasesKnowledge modellingOriginal data
The invention provides a knowledge graph construction method and device. The method comprises the following steps: acquiring original data and a large-scale knowledge graph; performing knowledge modeling on the original data to obtain a knowledge modeling result; generating concept layer data based on the knowledge modeling result and the large-scale knowledge graph; performing knowledge acquisition on the original data, including entity extraction, entity classification and first entity attribute extraction, to obtain entities, entity categories and entity attributes; inputting the entity as a keyword into the large-scale knowledge graph, and obtaining entity related information of the entity; fusing the entity, the entity category, the entity attribute and the entity related information to obtain complete entity layer data; and constructing a new knowledge graph based on the concept layer data and the entity layer data. According to the method, construction of the knowledge graph is achieved, and meanwhile updating of the knowledge graph in the using process can be achieved through the steps.
Owner:TSINGHUA UNIV
Banking industry-oriented full-stack financial knowledge graph platform
PendingCN114238662AShorten the production cycleShort build cycleFinanceSpecial data processing applicationsBanking industryKnowledge modelling
The invention relates to a banking industry-oriented full-stack financial knowledge graph platform, which comprises a graph construction layer configured to perform source data management, logic graph ontology creation, graph production, graph treatment and task scheduling; the map warehouse management layer is configured to store maps of different fields for specific business scenes; the service application layer is configured to perform map visual search, map data mining, map query and map model application; and the application interface layer is configured to provide financial knowledge graph service access capability for the platform. Compared with the prior art, the method has the advantages that key graph management links of knowledge acquisition, knowledge representation, knowledge storage, knowledge fusion, knowledge modeling, knowledge calculation and knowledge application are realized, the whole process from knowledge raw materials to intelligent data conversion is supported, full-stack graph production and application service capability is provided, and graph construction and production efficiency is improved.
Owner:BANK OF COMMUNICATIONS
Semantic and knowledge graph analysis method, platform and device based on dynamic ontology
PendingCN113326381AFast Association MiningImprove use valueSemantic analysisText database queryingKnowledge modellingTheoretical computer science
The invention discloses a semantic and knowledge graph analysis method, platform and device based on a dynamic ontology. The method comprises the following steps of acquiring the to-be-processed data; performing text semantic analysis and ontology mapping processing on the to-be-processed data, and extracting an ontology structure which comprises an object, an attribute and a relationship; and on the basis of the relation among the object, the attribute and the relationship, constructing a knowledge graph library so as to analyze and process the to-be-processed data. According to the technical scheme, multiple technologies such as dynamic ontology knowledge modeling, a knowledge graph technology and a big data technology are fused, the integrated processing of multi-source heterogeneous data is achieved, the ontology structure can be automatically extracted through a text semantic analysis and ontology mapping processing method, then the knowledge graph library is constructed, the rapid association mining of massive multi-source heterogeneous data is realized, comprehensive analysis of the multi-source heterogeneous data can be realized, and the use value of the data is improved.
Owner:BEIJING TOPWALK INFORMATION TECH
System and method for knowledge modeling
ActiveUS9558184B1Shorten the timeReduce communication costsDatabase updatingRelational databasesInformation retrievalAdaptive computing
A computer-integratable global knowledge modeling system comprising electronic means for expressing a plurality of entity representations interconnected by relations is described, wherein the entity representations, comprising modeling base elements and rules, are organized according to a fine-grained hierarchical or fractal structure, the relations between entity representations being highly detailed; a plurality of variants, representing each a particular point of view, are associated to at least a part of an entity representation in order to customize the corresponding entity representation; and the knowledge modeling system is usable in an adaptive computer-executable artifact.
Owner:VANHALLE JEAN MICHEL
Clinical guideline knowledge modeling method and system
ActiveCN113488180AMeet application needsImprove practicalityMedical simulationVisual data miningKnowledge modellingData set
The invention discloses a clinical guideline knowledge modeling method and system. The method comprises the following steps: acquiring a clinical guideline data set; performing text analysis on the clinical guideline data set, and generating document layer information; based on the document layer information, determining a hierarchical structure corresponding to each version of clinical guidelines and module content corresponding to each hierarchy, and generating module layer information; subjecting module content in the module layer information to knowledge-based processing, and obtaining knowledge layer information which represents knowledge graph information of the clinical guidelines; and constructing an association relationship among the document layer information, the module layer information and the knowledge layer information, generating an association relationship library, and visually displaying the association relationship library to obtain a cross-layer multi-dimensional association model. According to the technical scheme, the clinical guidelines of different versions are standardized and integrated, layer-by-layer display of the association relationship and content of the guideline information is facilitated, application requirements for clinical guideline knowledge is met, and the practicability of clinical guideline knowledge modeling is improved.
Owner:中国医学科学院医学信息研究所
Intelligent auxiliary operation and maintenance method and system for power communication network based on knowledge graph
PendingCN112580831AEfficient hit strategyImprove intelligent interaction capabilitiesData processing applicationsNeural architecturesKnowledge servicesKnowledge modelling
The invention discloses a power communication network intelligent auxiliary operation and maintenance method and system based on a knowledge graph, and the method comprises the following steps: constructing a power communication network intelligent auxiliary operation and maintenance architecture based on the knowledge graph, wherein the architecture comprises a data collection layer, a knowledgeobtaining layer, a knowledge fusion layer, a knowledge storage layer, and a knowledge service layer, and the core module comprises a knowledge modeling module, an intelligent interaction module and aknowledge operation and maintenance module. Based on various data and operation management modes, multivariate data is fused, communication network intelligent auxiliary operation and maintenance of the knowledge graph are achieved, barriers among multi-system, multi-dimensional and multi-structure data are broken through, the intelligent interaction capacity is improved, and knowledge support foron-site operation and maintenance is achieved.
Owner:INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER
Construction method of intelligent fishery question-answering robot based on knowledge graph
PendingCN111966787ADifficult to solveImprove construction integrityData processing applicationsArtificial lifeThird partyKnowledge modelling
Owner:SHANGHAI OCEAN UNIV
Regulation and control knowledge modeling method based on Bi-LSTM technology
PendingCN112307767AUniqueUnambiguousNatural language data processingNeural architecturesKnowledge modellingKnowledge framework
The invention relates to a regulation and control knowledge modeling method based on a BiLSTM technology, and the method comprises the steps: constructing a power domain ontology based on the BiLSTM technology, extracting conceptual entities in the ontology, combining the conceptual entities to obtain basic terms, and manually determining important terms in the basic terms; dividing the importantterms into three categories: department units, behavior categories and information data, and defining inheritance structures among the categories by adopting a top-down method; defining attributes andconstraints of the class, thereby creating an instance of the class; and outputting the instantiated ontology according to the input text and the created instance of the class. A professional knowledge framework can be provided for regulation and control personnel, and sharing of regulation and control professional knowledge in the electric power field is achieved.
Owner:STATE GRID FUJIAN ELECTRIC POWER CO LTD +1
Block chain data supervision method and system based on knowledge graph and computer equipment
PendingCN114064801AAchieving Data Governance PurposesImprove securityRelational databasesDatabase distribution/replicationKnowledge modellingTheoretical computer science
The invention discloses a block chain data supervision method and system based on a knowledge graph and computer equipment, and the method comprises the steps: carrying out knowledge modeling, and defining business entities, relationships and attributes according to different block chain business meanings and data types; knowledge extraction: extracting business entities, relationships and attribute data in each chain; knowledge fusion: carrying out entity combination and entity attribute and relationship combination on data in different block chains; knowledge storage: storing the block chain data into a graph database to form a block chain data knowledge graph; and knowledge calculation: defining a data supervision rule and a corresponding reasoning logic based on the block chain data knowledge graph, and finally obtaining a reasoning conclusion based on the supervision rule by adopting knowledge reasoning and graph mining methods so as to achieve the purpose of data supervision. The universal block chain data supervision method and system are provided by adopting the knowledge graph technology, the supervision rule can be flexibly configured, the purpose of block chain data supervision is achieved, and the security of block chain business is improved.
Owner:CHINA ZHESHANG BANK +1
Innovation knowledge base construction tool, electronic device and computer readable medium
InactiveCN112199558ASatisfy Semantic Concept MappingOther databases indexingOther databases clustering/classificationKnowledge modellingEngineering
The invention provides an innovation knowledge base construction tool, an electronic device and a computer readable medium. The tool comprises a knowledge modeling module, a knowledge processing module and a knowledge base management module. The knowledge modeling module is used for modeling functions, attributes, parameters and multivariate relationships related to TRIZ inventive measures. The knowledge processing module extracts innovative knowledge concepts and instances. And the knowledge base management module comprises knowledge editing and knowledge updating. The tool provides a feasible scheme for precision invention innovation, technical transformation and auxiliary industry upgrading.
Owner:北京如易堂科技有限公司
Hierarchical knowledge modeling structure taking relation as core and knowledge graph construction method
PendingCN114282009AEffective classificationImprove organizationKnowledge representationSemantic tool creationKnowledge modellingTheoretical computer science
The invention discloses a hierarchical knowledge modeling structure taking a relation as a core and a knowledge graph construction method, and relates to the technical field of knowledge modeling. The basic idea of the method is that the relationship is used as a first class of entities, the knowledge is expressed by taking the relationship as a core, and different entity elements are associated through the relationship. Through relation modeling knowledge, a knowledge graph is organized and managed so as to support unified identification and effective modeling of complex relations such as binary relations, multivariate relations and high-order relations. According to the method, knowledge can be effectively concluded and classified by adopting the hierarchical knowledge graph, so that knowledge organization is facilitated; the high-level knowledge graph can be reused, so that the construction cost of the knowledge graph is reduced, and the low-level knowledge can correspond to the uniqueness of different fields, so that the modeling of field knowledge rich in characteristics is facilitated.
Owner:PEKING UNIV
Electric vehicle communication electromagnetic interference suppression method based on knowledge modeling
ActiveCN112069681AElectromagnetic Interference Suppression ImplementationElectromagnetic Interference Suppression OvercomingDesign optimisation/simulationSpecial data processing applicationsKnowledge modellingInterference (communication)
The invention discloses an electric vehicle communication electromagnetic interference suppression method based on knowledge modeling. The method comprises the specific steps: 1) carrying out knowledge modeling on an external interference source; 2) performing simulation verification on an external interference source knowledge model; 3) modeling electric vehicle communication knowledge in combination with an external interference source simulation result; 4) performing simulation verification on the electric vehicle communication knowledge model; 5) circularly judging the interference suppression effect, and ending if the requirement is met; and 6) if the requirement is not met, optimizing an interference source module, and turning to the step 3 for loop iteration until the interference suppression requirement is met. According to the invention, knowledge modeling can be rapidly and accurately carried out on a target, and electromagnetic interference suppression is realized, so that electromagnetic interference of communication equipment in operation of the electric vehicle is overcome.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA
Intelligent fault processing system and method, and storage medium
InactiveCN110990251AEasy to settleUse intelligenceSoftware testing/debuggingKnowledge modellingMonitoring system
The invention relates to an intelligent fault processing system and a method, and a storage medium, and the system comprises a fault knowledge modeling module, and a minimum-function assembly appearing in a server system, and the fault knowledge modeling module and the minimum-function assembly serve as vertexes and are inputted into a graph database; wherein possible faults of each component serve as 'attributes' to be affiliated to the component, and the'attributes' and the component are recorded into a graph database together; for any two associated components, respectively designing a corresponding relationship, and inputting the corresponding relationship into a graph database as an edge; and a fault grading and processing mode confirmation module which is used for defining the stateof each component, establishing a relationship between the states and the corresponding processing modes, and recording the relationship as an edge into a graph database. A central control unit is connected with the monitoring system and the graph database in a butt joint mode, and the monitoring system feeds back monitored assembly changes to the central control unit in real time; and the centralcontrol unit searches a corresponding processing strategy from the graph database according to the component fault and adopts a corresponding fault processing action.
Owner:SUZHOU LANGCHAO INTELLIGENT TECH CO LTD
Encyclopedia-based cross-language knowledge graph construction method and device
PendingCN112541087AImprove build efficiencyHave diversitySpecial data processing applicationsSemantic tool creationData packKnowledge modelling
The invention provides an encyclopedia-based cross-language knowledge graph construction method and device, and the method comprises the steps: obtaining original encyclopedia data of a target field,and enabling the original encyclopedia data to comprise at least two languages and at least two sources of original data of the target field; preprocessing the original encyclopedia data to obtain preprocessed target data; based on the preprocessed target data, executing knowledge modeling operation, and obtaining concept data, hyponymy relations between different concepts and concept attribute data; based on the preprocessed target data, executing knowledge acquisition operation to obtain instance data, a relationship between an instance and a concept and instance attribute data; and executing knowledge fusion operation to generate a knowledge graph of the target domain. According to the method, the construction of the encyclopedia-based cross-language domain knowledge graph is realized,data sources are diversified, and the construction efficiency of the knowledge graph can be effectively improved.
Owner:TSINGHUA UNIV
Web-based domain knowledge map construction system and method
ActiveCN108345647BReduce difficultyHigh precisionSpecial data processing applicationsSemantic tool creationEntity linkingKnowledge modelling
The invention discloses a system and method for building a domain knowledge map based on Web, wherein the system includes: a knowledge modeling subsystem, which is used to obtain an initial knowledge model according to a preset data resource, and receive an operation instruction from an operation interface to Construct the data model of the knowledge map to obtain the knowledge model; the data and entity link subsystem is used to extract knowledge based on various types of data, and store the extracted knowledge into the knowledge map; the manual auxiliary labeling subsystem is used to receive user labeling instructions, To change the knowledge map according to the user's annotation instruction; the knowledge visualization subsystem is used to visually present the knowledge model, the dynamic link between the knowledge model and the entity, and the changed knowledge map. The system can easily and conveniently complete knowledge modeling, knowledge acquisition and knowledge visualization, which greatly reduces the difficulty of domain knowledge graph construction and helps to improve the accuracy of domain knowledge graph.
Owner:BEIJING UNIV OF POSTS & TELECOMM
Method and device for constructing knowledge graph in field of Pu'er tea
PendingCN114238660AReduce dependenceImprove accuracyRelational databasesSpecial data processing applicationsKnowledge modellingMedicine
The invention discloses a Pu'er tea field knowledge graph construction method and device, and relates to the technical field of Pu'er tea, and the method comprises the steps: building a Pu'er tea field first-layer knowledge ontology classification model; establishing a Pu'er tea field second-layer knowledge ontology classification model; and establishing a Pu'er tea field knowledge entity model associated with the first-layer knowledge ontology classification model and the second-layer knowledge ontology classification model for constructing the Pu'er tea field knowledge graph. According to the method, a construction mode of expanding from the center to the periphery is adopted, two-level knowledge ontology classification is performed on the Pu'er tea field knowledge, an entity model is extracted in combination with a knowledge ontology classification model feature word library, and the entity model is associated with a knowledge ontology classification model to form the Pu'er tea field knowledge graph. By adopting the method, the complex relationship between the entity models can be managed in a classified manner through the knowledge ontology, the dependence on professionals in the incremental knowledge extraction process is reduced, and the knowledge modeling accuracy is improved.
Owner:YUNNAN KUNMING SHIPBUILDING DESIGN & RESEARCH INSTITUTE
Question generation method and device, electronic equipment and storage medium
PendingCN114281904ARealize generationReduce the impact of noiseDatabase management systemsDatabase modelsQuestion generationKnowledge modelling
The invention provides a question generation method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a to-be-processed knowledge sub-graph from a knowledge graph, the knowledge graph being obtained by carrying out graph structuring on a knowledge text, and part of nodes in the knowledge sub-graph carrying answer node marks; the knowledge sub-graphs are input into a question generation model, a question text output by the question generation model is obtained, the question generation model is obtained through training based on a sample question text and a corresponding sample knowledge sub-graph, part of nodes in the sample knowledge sub-graph carry sample answer node labels, and a knowledge graph of non-strict ontology constraint is constructed; the domain correlation between the knowledge text and the knowledge graph is ensured, the knowledge modeling fineness is improved, the influence of noise in the knowledge text is reduced, the defect that in a traditional scheme, a question and answer pair generation method is not suitable for a long knowledge text is overcome, the utilization rate of structural information of the long knowledge text is improved, and the user experience is improved. The problem text is generated.
Owner:IFLYTEK SOUTH CHINA ARTIFICIAL INTELLIGENCE RES INST GUANGZHOU CO LTD
Knowledge modeling method and system for intelligent calculation and adjustment of power flow of power grid
PendingCN113378457ADesign optimisation/simulationSpecial data processing applicationsKnowledge modellingPower flow
The invention discloses a knowledge modeling method and system for intelligent calculation and adjustment of power flow of a power grid. The method comprises the following steps: dividing knowledge involved in intelligent calculation and adjustment of the power flow of the power grid into power grid data knowledge, power grid state knowledge and adjustment rule knowledge; representing the power grid data knowledge, the power grid state knowledge and the adjustment rule knowledge in a triple form, and constructing a knowledge base; and according to the currently known facts, the power grid data knowledge, the power grid state knowledge and the adjustment rule knowledge in the knowledge base are utilized, performing reasoning according to a reasoning method and a control strategy, updating and prefecting the knowledge base, and ensuring the correctness and integrity of the knowledge.
Owner:CHINA ELECTRIC POWER RES INST +3
Representation method and system of knowledge graph and text information based on referring sentence
ActiveCN110275960BQuality improvementPositive technical effectSemantic analysisKnowledge representationKnowledge modellingKnowledge graph
The invention discloses a representation method and system of a knowledge graph and text information based on a referential sentence, and relates to the technical field of machine learning. The method includes: modeling the knowledge graph to obtain an entity vector and a relationship vector; The deep semantic information related to the relationship is obtained, and the knowledge modeling is carried out to obtain the textualized relationship vector; the deep semantic information related to the entity contained in the plain text is obtained, and the knowledge modeling is carried out to obtain the textualized entity vector; based on the Entity vectors, the relationship vectors, the textualized relationship vectors, the textualized entity vectors, and the word vectors construct optimization parameters to realize the joint representation of knowledge graphs and text information. The present invention uses "referring sentences" to perform textual modeling on entities in the knowledge map, and realizes noise reduction for the joint representation of the knowledge map and text information, thereby improving the quality of knowledge representation and deduction.
Owner:CHINA ACADEMY OF ELECTRONICS & INFORMATION TECH OF CETC
Method and System of Proposition of Ancient Poems
ActiveCN111400506BQuality improvementRich poetry informationSemantic analysisNeural architecturesKnowledge modellingSemantics
The embodiment of the present invention provides a method for propositioning ancient poems. The method includes: extracting at least one keyword of each poem in a poem training set based on a knowledge graph, determining it as a semantic feature of each poem, using a neural network to model the semantic feature of each poem, and obtaining the input as the semantic feature of the poem, and the output is Poetry model of other semantic features with similar semantics; use knowledge graph to model the poetry training set to obtain a structured model of the poetry information in the poem training set; based on the semantic features of each poem, associate the poetry model and the structured model, and predict the The question type is input into the associated poetry model and the structured model, and the question corresponding to the preset question type is output. The embodiment of the present invention also provides an ancient poetry proposition system. The embodiment of the present invention uses the semantic features of poems for modeling, and can distinguish related words of poems. By structuring the information of poems, rich information of poems can be obtained, and topics with higher quality can be generated.
Owner:AISPEECH CO LTD
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com