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

42 results about "Knowledge object" patented technology

Data processing method based on simple element dynamic structures

A method is provided for processing information which includes storing in a memory of an information processing system (i) a plurality of individually identified information-bearing entities ("IBEs"), and (ii) a dictionary including a plurality of simple elements, each simple element having a meaning. A plurality of dynamic structures are stored in the memory, each dynamic structure being stored in association with at least one stored IBE, wherein each dynamic structure includes (i) at least one knowledge object including a plurality of simple elements selected from the stored dictionary, (ii) first information identifying the selected simple elements in the at least one knowledge object and (ii) second information identifying links between the selected simple elements. At least ones of the stored IBEs are processed with a processor of an information processing system, using the first and second information contained in the stored dynamic structures associated with the ones of the IBEs.
Owner:KANKOON

Method and system for machine comprehension

The AKOS (Artificial Knowledge Object System) of the invention is a software processing engine that relates incoming information to pre-existing stored knowledge in the form of a world model and, through a process analogous to human learning and comprehension, updates or extends the knowledge contained in the model, based on the content of the new information. Incoming information can come from sensors, computer to computer communication, or natural human language in the form of text messages. The software creates as an output. Intelligent action is defined as an output to the real-world accompanied by an alteration to the internal world model which accurately reflects an expected, specified outcome from the action. These actions may be control signals across any standard electronic computer interface or may be direct communications to a human in natural language.
Owner:NEW SAPIENCE

Academic knowledge acquisition method and academic knowledge acquisition system based on knowledge network nodes

The invention discloses an academic knowledge acquisition method and an academic knowledge acquisition system based on knowledge network nodes. The method includes the following steps: academic knowledge carriers are acquired and indexed, and knowledge object data in academic knowledge are extracted; the knowledge object data are stored and indexed; according to the types of the indexed knowledge object data, a knowledge network node relation model is created; according to the data in a physical storage, knowledge network nodes are created; the correlated knowledge network nodes are connected. The system comprises an acquisitor, an indexing device, a data storage and indexing device and a connection establishment module. The method and system provided by the invention can traverse the entire knowledge network from any node through the correlation characteristic between the nodes, consequently, the problem that a retrieval system can produce information islands in terms of knowledge acquisition is solved, and an academic knowledge acquisition method and an academic knowledge acquisition system which can provide comprehensive information, are interconnected and are traversable are provided for readers.
Owner:TONGFANG KNOWLEDGE NETWORK TECH CO LTD (BEIJING)

Custom electronic learning system and method

A system and method for generating a custom learning object. The system and method generate the custom learning object based on a knowledge object and a set of user characteristics for a user. In one embodiment, the knowledge object is converted to a set of knowledge atoms. Each knowledge atom is then mapped to a container defining an output format. One or more containers are combined to define the custom learning object.
Owner:KNOWLEDGEXTENSIONS

Multivariate intelligence-fused adaptive learning knowledge graph construction method and multivariate intelligence-fused adaptive learning knowledge graph construction system

The invention relates to the technical field of knowledge graph construction, and discloses a multivariate intelligence fused adaptive learning knowledge graph construction method and system. The method comprises the steps: S1, extracting domain knowledge element entities; s2, setting attributes of elements of the domain knowledge model, and integrating attributes for describing the learning ability of a learner in a multivariate intelligent theory into attributes of knowledge points in the domain knowledge model; s3, constructing a relationship between elements of the domain knowledge model;and S4, dynamically updating the netty knowledge graph. In the prior art, knowledge node attribute extraction in domain knowledge only pays attention to knowledge point subject attributes; according to the method, the technical problem that when knowledge point achievement degree calculation is carried out based on knowledge point features and learner features, an accurate basis is lacked due to the fact that the internal relation between the learner features and attributes of knowledge objects learned by the learner features is ignored, and therefore the accuracy of self-adaptive learning path recommendation is reduced is solved.
Owner:ZHENGZHOU UNIV

Knowledge graph visualization method based on semantic attention model

The invention discloses a knowledge graph visualization method based on a semantic attention model, and provides a knowledge visualization solution by combining multi-level multi-angle knowledge semantic similarity distance measurement with a user semantic attention model so as to support a visualization method of a global+local structure. According to the method, a semantic attention model between knowledge objects in a knowledge space is established, and the semantic attention between a focus object and the knowledge objects in the knowledge space is calculated; and visually displaying the knowledge graph according to the semantic attention. According to the invention, complex battlefield situation big data is analyzed and processed; the information objects with relatively short semanticdistances are highlighted and actively presented to the user; the big data knowledge graph retrieval method and system are beneficial to intelligently assisting a user in retrieving complex big dataknowledge, so that the user can see local details of an interested object and keep the overall impression of surrounding information, and good visual support is provided for big data knowledge graph retrieval application.
Owner:NO 709 RES INST OF CHINA SHIPBUILDING IND CORP

Method and system for machine comprehension

The AKOS (Artificial Knowledge Object System) of the invention is a software processing engine that relates incoming information to pre-existing stored knowledge in the form of a world model and, through a process analogous to human learning and comprehension, updates or extends the knowledge contained in the model, based on the content of the new information. Incoming information can come from sensors, computer to computer communication, or natural human language in the form of text messages. The software creates as an output. Intelligent action is defined as an output to the real-world accompanied by an alteration to the internal world model which accurately reflects an expected, specified outcome from the action. These actions may be control signals across any standard electronic computer interface or may be direct communications to a human in natural language.
Owner:NEW SAPIENCE

Associated search method and system of chemical knowledge

The invention provides an associated search method and system of chemical knowledge. The method takes a chemical resource bundle file (8) as the base and comprises the following steps: receiving the keywords to be searched which are input by a user; searching the keywords and obtaining an index address of a chemical substance matched with the keywords; obtaining the chemical substance content according to the index address of the chemical substance and displaying the chemical substance content such as the name of the chemical substance on a result list; taking the chemical substance on the result list as a center knowledge object; obtaining reactants associated with the chemical substance, resultants associated with the chemical substance or other reactants capable of reacting with the chemical substance, and then taking the reactants, the resultants or the other reactants as divergent knowledge objects; constructing a dynamic relation network chart composed of the center knowledge object and the divergent knowledge objects and displaying the knowledge content relative to the objects in the dynamic relation network chart. According to the associated search method and system of the chemical knowledge, the semantic associated search is supported, and the chemical substances and associated knowledge points which the user wants to learn can also be searched so that the study efficiency can be obviously improved.
Owner:SHENZHEN YOUXUETIANXIA EDUCATION DEV CO LTD

Information retrieval method and apparatus

The invention discloses an information retrieval method and apparatus, belongs to the field of the internet, and aims to improve the accuracy of a retrieved result of a problem to be solved by a user. The method comprises the steps of receiving an input to-be-solved problem; determining the technical field which the to-be-solved problem belongs to; according to a pre-established knowledge base in the technical field, determining a target document matched with the to-be-solved problem in the technical field, wherein the knowledge base comprises problem objects, knowledge objects, document objects, corresponding relationships between the problem objects and the knowledge objects, and corresponding relationships between the knowledge objects and the document objects, and the knowledge objects are selected from one part of the problem objects; and returning the target document. The method and the apparatus are used for answering the to-be-solved problem.
Owner:PEKING UNIV

Knowledge graph guided multi-scene image generation method

The invention provides a knowledge graph guided multi-scene image generation method, and belongs to the field of image generation. According to the method, the knowledge graph is used for assisting in completing an image generation task for the first time, firstly, the knowledge graph containing object layout relations is constructed, then, a set of object labels are input into the graph, and a plurality of layout relation graphs conforming to facts is obtained through a layout search module; Knowledge information in the graph is extracted from the layout relation graph through a pre-trained knowledge module, and finally a generator and a discriminator are trained in combination with a knowledge object matrix and a global knowledge vector obtained in the knowledge module when the layout relation graph passes through an image generation module, so as to generate a scene image corresponding to each relation graph. According to the invention, the knowledge graph is utilized to realize a one-to-many task of generating a plurality of images by using a group of labels, and the image generation quality is improved by embedding knowledge representation information. The present invention is evaluated using a real image data set, and the improvement on the most advanced baseline is observed.
Owner:DALIAN UNIV OF TECH
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