Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

14 results about "Knowledge graph" patented technology

A Knowledge Graph is a model of a knowledge domain created by subject-matter experts with the help of intelligent machine learning algorithms.

Power operation and maintenance information knowledge graph construction method

InactiveCN108460136AImprove effective useImprove the level of intelligent applicationNatural language data processingSpecial data processing applicationsNamed-entity recognitionKnowledge extraction
The invention provides a power operation and maintenance information knowledge graph construction method. A deep learning algorithm is introduced in construction of a power field knowledge graph; andtwo major machine learning tasks of named entity identification and entity relationship extraction are adopted for solving two difficult problems of knowledge unit extraction and knowledge unit relationship extraction. The effective utilization of power data is improved; the hidden value of the data is exerted; the intelligent application level of a power network is improved; and based on knowledge representation of the knowledge graph, a low-dimensional and mutually isolated information display mode in the past is changed, and association among power knowledge is presented more intuitively. Apower information operation and maintenance system knowledge library is constructed; historical operation and maintenance data is converted into knowledge; online autonomous consultation and problemsolving of a user are supported; intelligent question and answer are realized; the operation and maintenance efficiency is improved; important values are exerted in power network operation and maintenance work; and based on this, a power information operation and maintenance field knowledge graph optimization storage technology is finished.
Owner:STATE GRID FUJIAN ELECTRIC POWER CO LTD +1

Industrial fault analysis expert system based on knowledge graph

InactiveCN110705710AEnhance expressive abilityProcessing speedKnowledge representationInference methodsFuzzy inferenceEngineering
The invention provides an industrial fault analysis expert system based on a Knowledge Graph. The industrial fault analysis expert system based on the Knowledge Graph comprises the following steps that expert experience knowledge is obtained and preprocessed to eliminate anomalies and complement missing values; knowledge data fuzzification is carried out, and a knowledge graph is constructed in the field of industrial fault analysis by applying a semantic net technology and a graph calculation engine according to the knowledge data fuzzification. The simplification and high efficiency of a knowledge graph structure are ensured through a graph dynamic self-optimization process, and the calculation efficiency is improved; industrial faults are diagnosed and analyzed based on a fuzzy reasoning method, and data or equipment abnormity is efficiently and accurately judged.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA)

Knowledge graph hyponymy relation identification method based on mode expansion and BERT classification and storage device

ActiveCN112417161AReduce complexityReduce labor inputNatural language data processingNeural architecturesConcept recognitionText recognition
The invention relates to the technical field of text recognition, in particular to a knowledge graph hyponymy relation recognition method based on pattern expansion and BERT classification and a storage device. The knowledge graph hyponymy relation recognition method based on pattern expansion and BERT classification comprises the steps: extracting potential hyponymy relation pairs from external data based on pattern expansion, and forming a hyponymy relation model training seed corpus in combination with a preset resource library; obtaining a to-be-predicted hyponymy data set, and predictingthe to-be-predicted data set based on the BERT-Attention-Bi-LSTM model to obtain a hyponymy prediction result; and further processing the hyponymy relationship prediction result through a preset ruleto obtain a final hyponymy relationship prediction result. The method greatly reduces the complexity and labor investment of rule compilation, has stronger realizability compared with another mainstream statistics-based hyponymy concept identification method, and can provide technical support for the construction of various professional knowledge maps.
Owner:FUJIAN YIRONG INFORMATION TECH

Knowledge graph construction and use method and device and medium

PendingCN112749287AImprove processing efficiencyImprove the role of consultationMedical communicationRelational databasesKnowledge graphData mining
The embodiment of the invention provides a knowledge graph construction and use method and device and a medium. The method specifically comprises the following steps: determining a problem entity according to a disease feature entity, wherein the question entity is used for representing a question related to the disease feature entity; and in the knowledge graph, establishing association between the disease feature entity and the question entity. According to the embodiment of the invention, the effect of the knowledge graph on inquiry can be improved, and the processing accuracy of the medical information can be improved.
Owner:BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD

Cultural element construction method based on knowledge graph technology

PendingCN112667764ATimely integrationRenewed on timeData processing applicationsMultimedia data browsing/visualisationSensing dataInformation space
The invention discloses a cultural element construction method based on knowledge graph technology. The method comprises the following steps of collecting basic information of spatial data, cultural data and tourism data; wherein the spatial data basic information at least comprise aerospace remote sensing data, oblique photogrammetry data, topographic data and basic geographic data; wherein the cultural data basic information at least comprises literature data, multi-source three-dimensional data, multimedia data and cultural heritage distribution data. The invention provides a linear cultural heritage tourism map which can well link cultural information, tourism information and geographic information of various heritage places aiming at the actual situation that the cultural information, the tourism information and the geographic information are isolated and even deficient due to the fact that the cultural heritage places along the linear cultural heritage are large in quantity, scattered in distribution and large in area span. According to the method, heritage resources scattered along the line of linear cultural heritage are comprehensively arranged to form an organic integral two-dimensional and three-dimensional integrated display and application cultural heritage tourist map.
Owner:江苏思远集成电路与智能技术研究院有限公司 +1

Combined loan business platform based on block chain and loan management method

PendingCN112508681AImprove liquidityAvoid Duplicate Loan SituationsFinanceSpecial data processing applicationsRisk ControlBusiness enterprise
The invention discloses a combined loan service platform based on a block chain and a loan management method, and the combined loan service platform mainly provides combined credit for borrowers for amain loan financial institution and a small loan participation company, loans the borrowers according to an agreed capital proportion condition, and undertakes risks according to an agreed risk undertaking mode. And the platform registers and uplinks asset information and basic information of participants by using a block chain technology, so that tamper resistance of data is realized, and data reliability is ensured. And the platform combines big data risk control and a knowledge graph, carries out portrait and association network construction on customer data, and provides risk management and early warning after lending of a borrower. And the joint loan business platform is also connected with other transaction platforms to realize participant asset transfer requirements and self-financial requirements, so that the liquidity of funds of small loan companies is improved. The combined loan business platform is also connected with an industry supervision system, thereby simplifying theflow of small loan enterprise data reporting, and facilitating the real-time supervision of a supervision department for the small loan industry.
Owner:CHINA ZHESHANG BANK

Tax knowledge middle platform based on natural language understanding and construction method of platform

InactiveCN112148840AAchieve finishingImplement updateSemantic analysisKnowledge representationNatural language understandingBusiness enterprise
The invention discloses a tax knowledge middle platform based on natural language understanding and a construction method of the platform. The tax knowledge middle platform comprises a knowledge alignment module, a knowledge understanding module and a knowledge interaction module. When the middle platform is constructed, the three modules are respectively constructed by comprehensively utilizing natural language processing technologies such as a knowledge graph, search and recommendation. The platform can be used as an entrance for knowledge query in the tax policy field, efficient association, updating, retrieval and learning of multi-source tax knowledge are achieved, the platform is suitable for tax-related workers and can also be used as a platform for tax payment individuals or enterprise related personnel to learn tax policy knowledge, and a question-answering system in the tax policy field can also be constructed based on the platform.
Owner:SHANDONG SYNTHESIS ELECTRONICS TECH

Industrial capability docking technical method based on knowledge graph

PendingCN113641865APrecise dockingOther databases indexingBuying/selling/leasing transactionsData miningKnowledge graph
The invention relates to an industrial capability docking technical method based on a knowledge graph, and the method comprises the steps: obtaining a demand which comprises a category, a yield, a deadline, a performance index, and a demand flow direction, wherein the demand flow direction is inflow or outflow, inflow is input from the target enterprise, and outflow is output to the target enterprise; determining sub-graphs meeting categories, yields, deadlines and performance indexes in the requirements from the knowledge graph; determining a target enterprise from the sub-graph according to the demand flow direction in the demand; wherein the knowledge graph comprises first-level points and second-level points, the first-level points are in one-to-one correspondence with the positions of the industrial chains, the second-level points are in one-to-one correspondence with the enterprises, and the edge between the two first-level points represents the flow relation of the two first-level points in the industrial chains; wherein the edge between the two second-level points represents the business relationship of the enterprises corresponding to the two first-level points, the attribute of each second-level point is the attribute of the corresponding enterprise, and the weight of the edge between the second-level points is determined according to the attribute of the corresponding enterprise of the second-level points.
Owner:扬州制汇互联信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products