54 results about "Knowledge updating" patented technology

The invention discloses a knowledge map construction method for medical images, belonging to the field of knowledge maps. The construction process includes a step of knowledge representation with a framework theory representation method, a step of knowledge acquisition, wherein the knowledge sources of entity, attribute and attribute value extraction is unstructured data, a step of knowledge fusion with the integration of acquired new knowledge and the elimination of ambiguity, a step of knowledge processing with the knowledge reasoning and quality assessment of the data which is subjected tothe knowledge fusion and the adding of qualified data to a knowledge map, and a step of knowledge update with the update of the knowledge map according to the update and development of medical image knowledge. According to the characteristics of the medical image knowledge, and the knowledge acquisition rate is greatly improved with the unstructured data such as textbooks and academic journals asa source of knowledge.

The invention discloses a method for constructing an international maritime dangerous goods knowledge map system, wherein, the construction method of the knowledge map system of dangerous goods in international maritime transport comprises the following steps: acquiring knowledge data of dangerous goods in international maritime transport; extracting entities, entity attributes and entity relationships of the knowledge data according to the acquired knowledge data; according to the preset reasoning rules, the entity, entity attributes and entity relations being reasoned, the relationship between entity, entity attributes and entity relations being determined, and the ontology of international maritime dangerous goods being constructed according to the relationship; aiming at the ontology of international maritime dangerous goods, the quality assessment and knowledge updating being carried out, and the knowledge map of international maritime dangerous goods being constructed. The technical proposal provided by the invention expresses the complex international maritime dangerous goods transport rules and the international maritime dangerous goods with ontology knowledge, simplifies the application of the rules, reduces the manpower and time cost, and optimizes the supervision and screening of the international maritime dangerous goods.

The invention discloses an archive management model construction method and system based on a knowledge graph, and the method comprises the steps: obtaining an archive text in a computer readable format, recognizing the minimum knowledge units in the archive text, and forming the semantic relation among all knowledge units based on the correlation of all minimum knowledge units; establishing a dynamic file multi-dimensional association model through a knowledge graph based on semantic relations among the knowledge units; according to the dynamic archive multi-dimensional association model, establishing an archive knowledge graph semantic model which can be recognized by a computer through an editing tool and a modeling language, using archive knowledge alignment and knowledge disambiguation to carry out knowledge fusion on archive knowledge, enabling the archive knowledge to mutually mapped with an archive knowledge organization model, and enabling semantic association to be subjectedto knowledge updating and replacement through a knowledge reasoning process. According to the method and system, the multi-dimensional association model and the knowledge fusion technology are established by identifying the knowledge unit with the minimum identification, so that the semantic association degree and the utilization rate of the archives are improved.

The invention discloses a Web intelligent test method based on a knowledge graph. The Web intelligent test method comprises the following steps: step 1, performing generalized ontology modeling in combination with characteristics of a Web application and an HTML page; step 2, carrying out knowledge extraction from a page of the tested Web application; step 3, storing the ontology tree, the extracted file relationship and the knowledge graph through a graph database; step 4, carrying out knowledge detection on the knowledge graph; step 5, carrying out knowledge reasoning on the knowledge graphto generate a test case; 6, compiling an automatic test script according to the test case, executing the test and generating a test report; step 7, when version iteration or operation is carried out,carrying out knowledge updating on the knowledge graph; and step 8, carrying out quality evaluation on the knowledge graph. According to the Web intelligent test method, the blank that the knowledge graph has no application in the test field is filled up, and the design, maintenance, automatic execution, self-optimization and continuous updating of the test process are completed without manual participation.

The invention discloses a dynamic feature selection method which is used for mode classification. The method is carried out according to the following steps: a requirement is sent out to a knowledge base after a sample is preprocessed by a preprocessing module, if the requirement is a classifying requirement, the sample is regularized by an optimal feature combination that can be obtained by the preprocessing module from the knowledge base and then is handed into a classifier for classification; if the requirement is a feature selection requirement, a part of samples are output to the knowledge base by the preprocessing module and is combined with a part of samples of the knowledge base to carry out the combination, a part of samples are output from the combined samples to enter into a feature selection module, the parameter and the ratio coefficient that need to be dynamically adjusted by the feature selection module and the classifier are output from the knowledge base, the feature selection module and the classifier are instructed to carry out the feature selection and the relevant parameter is fed back to the knowledge base for carrying out the knowledge updating after the selection is finished. The method can dynamically select the optimal feature combination from the mode samples that are continuously changed, thereby being more accordant with the actual situation and satisfying the requirements of high-precision classification.

Systems and processes are disclosed for real-time updating of virtual assistant media knowledge. Virtual assistant knowledge can be updated with timely information associated with playing media (e.g., a sporting event, a television show, or the like). A data feed can be received that includes data relating events to particular times in a media stream. A user request can be received based on speech input, and the user request can be associated with an event in a media stream or show. In response to receiving the request, the media stream can be cued to commence playback at a time in the media stream associated with the event referred to in the request. In another example, a response to the user request can be generated based on the data relating to the events. The response can then be delivered to the user (e.g., spoken aloud, displayed, etc.).

The invention provides a knowledge graph updating method and device, and relates to the field of artificial intelligence. The method comprises the following steps of: in response to a knowledge graphupdating request, calling a first service to obtain first identification information in a message queue, obtaining network resources corresponding to the first identification information in an HBASE database according to the first identification information, and performing knowledge extraction on the network resources to obtain triple information; calling a second service to fuse the triple information and original triple information so as to obtain fused triple information; calling a third service to process attributes and attribute values in the fused triple information to obtain intermediate triple information, and performing information fusion according to entity information in the intermediate triple information to obtain target triple information; and calling a fourth service to process the target triple information to obtain an updated knowledge graph, and writing the updated knowledge graph into the HBASE database. According to the invention, the updating efficiency of the knowledge graph can be improved, and the real-time performance of knowledge updating is ensured.

The invention discloses an ontology-based education resource model construction method, which comprises the following steps: (1) extracting education resource terms and concepts, analyzing and extracting concept words from each file in a corpus by using a statistical method; (2) determining the hierarchical relationship between concepts, and using the hierarchical clustering algorithm to calculatethe similarity between concepts to form a hierarchical clustering; (3) defining the attribute and attribute relation of the concept, and establishing the semantic annotation and semantic relation ofthe scattered educational resources on the network; (4) creating an instance of educational resources, filling the ontology with the instance, and establishing the logical knowledge base. The invention adopts the uncertainty of the information entropy filter concept and utilizes the hierarchical clustering algorithm to determine the hierarchical relationship between concepts, clearly represents the main concepts, terms, attributes and interrelationships in the field of education, and formally describes the attributes of the activities in the field of education, which improves the learning level of users, knowledge updating, technology development and so on.

Systems and methods that supply a global knowledge on what nodes are available in the system, via employing routing tokens that are analyzed by a centralized management component to infer status for the nodes. When nodes fail, the routing tokens associated therewith are acquired by neighboring nodes, and the global knowledge updated. Moreover, upon inferring a failed or down status for a node, a challenge can be sent to a node reporting such failure to verify actual failure(s).

The invention relates to a hypertensive patient self-comprehensive management intelligent question-answering system based on a knowledge graph and an establishment method thereof. The system comprisesa user system interaction layer, a voice text conversion layer, a matching reasoning layer, an information search layer and a resource layer, wherein the resource layer is used for realizing data acquisition, knowledge extraction, knowledge fusion and processing and knowledge updating to form a framework of the knowledge graph; the user system interaction layer is used for carrying out language interaction with a user and answering questions raised by the user; the voice text conversion layer is used for completing conversion between voice and text; the knowledge graph can analyze the questions presented by the natural language of the user, understand the questions of the user and complete knowledge reasoning; the information search layer is used for searching or completing reasoning in the resource layer based on the text converted by the voice text conversion layer; and the matching reasoning layer is used for matching the information searched by the information search layer with the questions raised by the user, outputting matched answers after matching succeeds, and outputting specific answers if matching fails.

The invention discloses a knowledge graph generation method based on multiple indexes, and belongs to the technical field of computer text processing, and the generation method comprises the following specific steps: (1) information extraction; (2) knowledge fusion; (3) knowledge processing; (4) knowledge updating; according to the invention, tourism websites and Baidu encyclopedia are taken as data sources, entities are extracted by taking word segmentation, word removal and part-of-speech tagging as extraction modes, and meanwhile, entity relationships and entity attributes are extracted based on expert definition rules, so that the data extraction is relatively accurate, and the follow-up tourism field atlas application search accuracy can be improved; besides, the confidence degree is used as a judgment basis, the confidence degree is composed of a word vector, a sentence vector and an editing distance, and the tourism field knowledge graph is subjected to long-term incremental updating through the confidence degree, so that the quality of the tourism field knowledge graph is guaranteed for a long time, and the accurate searching capability of the tourism domain knowledge graph is continuously improved.

The invention provides a networking audit training device, which is to be used by state audit, internal audit and social audit workers for networking audit service skills practice. The device comprises four parts, namely a production environment simulation subsystem of the audited object, a data collector, a data transmission module and a data storage processing subsystem. The four parts of the device are connected with a 10M / 100M switch by five types of unshielded twisted-pairs to form a networking audit simulation training local area network. The networking audit skill train, such as data collection, audit data query, data analysis, and audit early warning, can be carried out. The train demands for carrying out different types of networking audits of users can be met. The networking audit training device has a modularized structure, has the advantages of simplicity, practicality, strong pertinence, high expansibility and high popularity, enables audit units to save a large amount of human resource training cost, enables auditors to fast improve the ability of applying the networking audit and capturing the audit doubts in a short period, and efficiently promotes the auditors to update the professional knowledge and change the working manner.

The invention relates to a scheduling knowledge management system for intelligent manufacturing. The system comprises a scheduling knowledge learning module driven by data, which is used for knowledgemining of scheduling data samples to obtain scheduling knowledge. A scheduling knowledge application module, responsive to receiving a scheduling request, for calling the scheduling knowledge to generate a scheduling policy matching with an intelligent workshop production state and obtaining a scheduling result; An on-line scheduling knowledge evaluation module, responding after obtaining a scheduling result, for judging the validity of the scheduling knowledge according to the scheduling result; The scheduling knowledge updating module responds when the scheduling knowledge is judged to be invalid, and is used for applying an online learning method to adjust the scheduling knowledge on the basis of adding updated samples. Compared with the prior art, the invention can better improve theadaptability of the scheduling knowledge, ensure the scheduling effectiveness, and has the advantages of continuously optimizing the overall performance of the intelligent workshop.

The invention relates to a knowledge graph mining method and system, and the method comprises the steps: obtaining a text, and carrying out the error correction of the text; according to a preset word list, performing word segmentation and part-of-speech tagging processing on the text after error correction processing to obtain words in the text and part-of-speech of the words; according to the words and the part-of-speech, identifying entities in the text, and according to the words, the part-of-speech and the entities, extracting attributes and relationships of the entities in the text. According to the method, entity linking is carried out according to the entities, knowledge fusion is carried out according to the entity linking result and the attributes and relations of the entities, and the knowledge graph is obtained, through the method, the problem that large hysteresis exists in knowledge updating of the knowledge graph in the related technology is solved, and the effect of updating the knowledge of the knowledge graph in time is achieved.

The invention provides a production field exception handling knowledge recommendation and knowledge updating method. The method is characterized in that: a set of software system for production abnormality knowledge management is established, and the software system comprises a production abnormality solution recommendation algorithm, an abnormality disposal tree improvement and troubleshooting guiding module and a self-improvement and recommendation upgrading knowledge base. According to the method, by using the system, when an abnormal problem occurs in a production field of a manufacturing enterprise, the system automatically recommends a disposal scheme according to an abnormal matching algorithm to quickly solve the problem. The method has the beneficial effects that manufacturing enterprises are mainly helped to precipitate valuable treatment experience as knowledge, and the exception treatment tree is continuously perfected according to accumulation of the treatment experience. When an abnormal problem occurs in a production field, the system automatically recommends a disposal scheme according to an abnormal matching algorithm. Sharing of high-value schemes in enterprises and industries is promoted.

The invention discloses an IT equipment operation and maintenance management system and method. The IT equipment operation and maintenance management system comprises a task management module, a problem management module, a knowledge management module, an asset management module, a statistics and analysis module and a system management module. The task management module is used for equipment technical state management, planned task, temporary task and equipment maintenance account management; the knowledge management module is used for knowledge collection, knowledge query and knowledge updating; the asset management module is used for asset account management, printing bar code functions, inventory functions, configuration management, change management, asset allocation, asset rejection and assets disposal; and the statistics and analysis module is used for query statistics and performance assessment. The IT equipment maintenance system has the advantages that the IT equipment can beprotected by the system according to preset settings, the IT equipment maintenance speed is high, the working efficiency is high, solutions in the knowledge base can be searched when the IT equipmentis maintained, and the blindness of IT equipment maintenance is reduced.

The problem to be solved by the invention is to collect the students' answers to fill in the gaps and find the frequent answers that are inconsistent with standard answers. Through a teacher's upgrading system in the system, interacting is performed without causing teachers' subjective attention; the answers that are inconsistent with standard answers and frequently occur are subjected to the secondary judging; if it is found that the answers can be regarded as correct answers, the answers can be added to a database to make up deficiencies in the existing database. To solve the above problem, the invention provides the on-line learning system with the automatic-correction function. As for a gap filling question, when a number of students have made the same answer and the answer is not among the standard answers, the answer is filled back to the original question and submitted as a true or false question to the corresponding teacher to be judged, and the answer approved by the teacher is automatically added to a question bank. Accordingly, active knowledge updating of the platform is realized, thereby raising the efficiency of database maintenance and reducing data updating cost.

The invention discloses a knowledge graph method for identifying water environment pollution. The method comprises the following steps: determining a water environment area; collecting pollution data of the water environment area, wherein the pollution data comprises pollution source data collected from pollution source general survey and load calculation data of various pollution sources; a database suitable for expressing pollution-causing information is selected, the database is Neo4j graph data and has natural extension characteristics and an unstructured data format, and new nodes, relations or attributes can be added according to requirements; based on the pollution source data, the load calculation data of various pollution sources and the entity information of the water environment area, constructing a pollution-causing knowledge graph by using the Neo4j graph data; based on the pollution-causing knowledge graph, performing knowledge retrieval and knowledge updating to obtain pollution-causing knowledge; and according to the pollution-causing knowledge, identifying a pollution type and a pollution source of the water environment, and positioning a pollution source analysis result.

The invention discloses a comprehensive benefit-oriented resource intelligent collaborative scheduling method in a space-ground-air integrated network, and the method comprises the steps: carrying out the analysis of the topological state of the space-ground-air integrated network, taking reinforcement learning as a research tool, carrying out the joint scheduling of the utilization rate of various resources, and taking the actual business service quality as an overall optimization target, and carrying out the comprehensive benefit-oriented resource intelligent collaborative scheduling of the space-ground-air integrated network. By means of the service analysis module, resource requirements of daily service requests are judged, reasonable allocation and scheduling of resources are carried out, and the method is oriented to comprehensive benefits instead of the utilization rate of a certain kind of resources. According to the method, a reinforcement learning strategy is adopted to carry out autonomous learning from historical scheduling experience, knowledge updating is carried out, weight distribution is carried out on evaluation criteria, the most reasonable planning decision based on the globality is selected from resource scheduling problems, and learning improvement is carried out according to feedback information completed at this time; the resource scheduling service quality is improved, the resource scheduling rationality is improved, the resource waste is reduced, and the resource scheduling method meeting the comprehensive benefit is realized.

Provided are a knowledge extraction device for extracting, from an electronic document that is delivered at any time while not being associated with a knowledge information extraction object, knowledge information relating to the knowledge information extraction object, and a program. A knowledge extraction device of an embodiment is provided with: an information reception unit for receiving an electronic document; a knowledge extraction unit for extracting a concept from the electronic document on the basis of an object word for extracting knowledge information, and a clue word for extracting the knowledge information, and creating the knowledge information in which the extracted concept and the object word are associated with each other; a storage unit for storing the extracted knowledge information; and an information analysis unit for, after the knowledge information is stored, analyzing the electronic document on the basis of the knowledge information in the storage unit.

The invention discloses a meta-knowledge federation method for behavior analysis, which relates to the technical field of computers and comprises the following steps: acquiring user behavior data andreceiving first meta-knowledge; performing meta-knowledge learning based on the first meta-knowledge and the user behavior data to obtain meta-knowledge update; sending the meta-knowledge update to aserver, so that the meta-knowledge update is subjected to federated collection to obtain updated first meta-knowledge; receiving the updated first meta-knowledge and judging whether the first meta-knowledge is converged or not, if so, taking the first meta-knowledge as reference meta-knowledge, and performing behavior analysis; and if not, continuing meta-knowledge learning. According to the method, user data privacy is effectively protected, the client can quickly obtain customized meta-knowledge only through a small amount of user data, behavior analysis on any client is achieved, and the method is high in applicability, convenient to apply and good in user experience. The invention furthermore discloses a meta-knowledge federation method for behavior analysis, an electronic device, a computer storage medium and a system.

The invention discloses a teaching system used for improving verbal ability and artistic appreciation of students of tourism major. The system comprises a government traffic network base station, a road condition information acquisition unit, a communication unit, an information receiving module, a starting node coordinate detector, a central processing unit, a tourism information and cultural knowledge updating module, a map data storage unit, a liquid crystal display screen, a man-machine conversation unit, a language unit, a virtual-real tour guide system, a virtual-real demonstration system, a monitoring module, a resource sharing module and a user management module. According to the teaching system, tourism information and cultural knowledge can be obtained from a real environment and are updated in real time; the virtual-real system is used for teaching public basic courses including tourism tour guide practice, English for tourism, hotel management, business English majors, practical writing and the like; meanwhile, the learning condition of students can be monitored and recorded in real time and the learning efficiency is further improved.

The invention discloses an IT equipment allocation management and control system and an allocation method thereof. The IT equipment allocation management and control system comprises a task managementmodule, a problem management module, a knowledge management module, an asset management module, a statistics and analysis module and a system management module; the task management module is used fortechnical state management, planned task, temporary task and equipment maintenance ledger management of the equipment; the knowledge management module is used for knowledge collection, knowledge query and knowledge updating; the asset management module is used for asset standing book management, a bar code printing function, a checking function, configuration management, change management, assetallocation, asset scrapping and asset disposal; and the statistics and analysis module is used for query statistics and performance assessment. The IT equipment allocation management and control system has the advantages that the IT equipment can be protected by the system according to preset settings, the IT equipment maintenance speed is high, the working efficiency is high, solutions in the knowledge base can be searched when the IT equipment is maintained, and the blindness of IT equipment maintenance is reduced.

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.

The invention provides a clinical auxiliary decision knowledge base platform, a configuration method and device thereof, and a medium. The method comprises the steps of configuring knowledge types anddisplay forms of labels for different knowledge, so as to form a knowledge configuration document which is convenient to store, edit and manage, inputting rules, respectively encoding the rules and knowledge in the knowledge base, and docking the rules and the knowledge through encoding matching, and according to knowledge matched with the rule, displaying in a display form of the corresponding label, and recommending to the target role. According to the method, business rules and scenes can be directly used, non-computer background business personnel are supported to carry out personalized configuration according to the requirements for the display content and form of the knowledge base, the learning cost is low, and business expression is clear, simple, convenient, verified and modified; the communication cost is reduced, the research and development speed is increased, and the friendliness optimization, agile iteration and knowledge updating of the clinical auxiliary decision system are greatly improved.

The invention discloses an end-to-end-based large knowledge graph construction and storage method and system. The system comprises a knowledge graph construction system, a knowledge construction module, a knowledge management module, a knowledge application module, a knowledge extraction module, and a processing and storage module. The knowledge graph construction system is in communication connection with the knowledge construction module, the knowledge management module, the knowledge application module, the knowledge extraction module and the processing storage module. The knowledge construction module comprises a knowledge collection module, a knowledge fusion module, a knowledge evaluation module and a knowledge updating module; the knowledge application module comprises a cognition service module, a language understanding module and an inference engine module; the reasoning engine module is in communication connection with the understanding service module and the language understanding module, and the language understanding module is in communication connection with the understanding service module. According to the invention, required data can be obtained more quickly and efficiently; through cooperation of data integration, data cleaning and data updating in the data cleaning and perfecting module and the processing and storing module, quick search is facilitated.

The invention discloses an assembly skill direct generation method based on a virtual assembly environment, and the method comprises the steps: an assembly demonstrator controls a mechanical arm to work in a first-person operation mode, carries out the assembly operation of an industrial product in a virtual environment through a tool and process equipment which accord with a real assembly environment; for entities such as end effectors, parts, tools, process equipment, parts and assemblies involved in the assembling process and operations such as alignment, approaching, grabbing, inserting holes and screwing between the entities, a dynamic operation knowledge graph is directly generated according to defined entities and operations, and a primary framework of the operation knowledge graph is established; knowledge updating can be continuously carried out by operating the knowledge graph, and new entities and actions are added into the ontology library. The knowledge graph can be used as a standard format of operation skills and is used for operation skill transmission among different agents, and the method can also be expanded to other operation skill learning fields.

The invention belongs to the technical field of dynamic knowledge updating, and particularly relates to a dynamic knowledge updating method based on three decisions in a variable-precision rough set model, which comprises the following steps: 1, setting a threshold value, and selecting data precision in a rough set; 2, selecting a data relationship in the rough set according to a set precision threshold value, and carrying out data region judgment; 3, generating fuzzy set data in the rough set after judging that the data is finished, and setting an incommitment rule for the fuzzy set data; 4,selecting an approximate space, substituting the generated fuzzy set data into the approximate space, and judging the regional value of the data again; and 5, performing intra-region data comparison on the data generated after judgment, selectively discarding the generated repeated information to obtain updated data, and through three decisions, effectively reducing data updating vulnerabilities caused by two decisions, reducing repeated data of dynamic knowledge updating, and facilitating subsequent updating.

The invention discloses a hot event mining method based on a large-scale knowledge base. The method is characterized by including the steps of based on data acquired through the internet, automatically establishing a text-understanding-oriented large-scale knowledge base, and allowing for automatic optimization and knowledge updating of the base; based on the large-scale knowledge base, performing structural information extraction on short texts to be detected, sorting the short texts to be detected, according to extracted structural information, and screening out corresponding event texts; based on the large-scale knowledge base, clustering the screened event texts to screen out hot events. The method has the advantages that structural knowledge representation is automatically extracted from the internet, structural tuple representation is established for semantic relation between instances and concepts, a knowledge back-tracking mode is provided, and accuracy in extraction of structural information from short texts is improved.

The invention discloses a mobile application knowledge graph composite completion method and a device based on encyclopedia knowledge, and the method comprises the steps: reading a configuration filecorresponding to a given encyclopedia site, and screening an encyclopedia page, correlated with a mobile application, in the encyclopedia site through the information in the configuration file; capturing and storing the screened encyclopedia pages by utilizing a web crawler; adopting different attribute recognition algorithms for different mobile application attribute values, extracting structuredknowledge from the encyclopedia page, and storing the structured knowledge in a predetermined format; and according to the extracted structured knowledge, updating the attribute information of the mobile application in the AlleroGraph, and returning an update file to prompt an original database to perform synchronous update completion of the mobile application atlas data.