59results about How to "Extensive knowledge" patented technology

An enhanced knowledge management system (“KMS”) is provided. The enhanced KMS provides a customizable, person-to-person, knowledge sharing portal that manages concurrent one-on-one conversations between requesters and expert resources. Through the knowledge sharing portal, the KMS provides the automatic capture, organization, and reuse of tacit knowledge, as well as integration with existing systems that manage already documented (explicit) knowledge. Example embodiments provide a Conversation Manager, which manages communication in the form of conversations (question and answer sequences) between users (requesters) and experts (expert resources), and allows system administrators to customize the system. Conversations are organized by subject matter categories and experts are ranked preferably by the system and by users, thereby increasing the likelihood of the KMS providing answers to users' questions. The Conversation Manager, in conjunction with managing these conversations, produces a dynamic knowledge base of knowledge that is searchable by other users. In this manner, the KMS enhances the ability in a multitude of environments to capture previously untapped knowledge and to integrate such knowledge with existing data.

The invention discloses a district power network equipment abnormal alarm signal association analysis and diagnosis method in the field of automation of scheduling of electric power systems. According to the method disclosed by the invention, the weather situation of a plant station region at which abnormal alarm information is located can be automatically identified so as to determine the information processing mode. The method disclosed by the invention has the beneficial effects that by realizing intelligent association analysis and auxiliary decision making of the equipment abnormal alarm information under the real-time state, and performing playback on historical alarm information and performing real-time treatment on manual set information under the research state, the abnormal treatment time is greatly reduced, the incidence of accidents is reduced, a real-time, rich and intelligent auxiliary decision-making support is provided for regulation and control staff, and the safe, high-quality, economical and stable operation of an electric fence is further ensured.

A method of collaborative learning intrusion detection applied in data grid, which draws advantages of current popular technologies like distributed detection in intrusion detection domain and ensemble learning etc., combines method of abnormal detection and feature detection, adopts BP neural network collaborative learning for complementary advantages, and makes intrusion detection system based on the method applies to data grid environment. Deploy a plurality of strong detectors integrated by BP neural network in center-nod according to security requirement of different kinds of nods in data grid by the invention, and collect new intrusion sample feature come from everywhere whenever possible to make sure about the security of important copy in center-nod. Deploy collaborative intrusion analysis engine in center-nod meanwhile to provide collaborative detection service for all normal nods. A plurality of normal nods are organized by center-nod for collaborative calculation and suspected data can be detected which cannot be judged by original signal nod so as to improve security of normal nod.

The invention provides a large aircraft aviation big data fault detection and causal reasoning system and method based on a deep random forest algorithm. The system comprises a fault diagnosis platform, a fault reason reasoning platform, a database storage computer and a client. The method comprises the following steps of comprehensively monitoring and acquiring operation parameters of each systemof an airplane in real time to form massive data sources, acquiring typical characteristics of the signals through calculation of the characteristic parameter spectrum, and extracting and describingfault characteristics in residual signals using the characteristics as parameters and storing the characteristics into a parameter database. The airplane parameter database is established through thefault diagnosis computer and the fault reason reasoning computer, so that fault information of an airplane or possible faults of the airplane is covered, faults and reasons are determined through diagnosis of the fault diagnosis computer and reasoning of the fault reason reasoning computer, a maintenance/isolation scheme is provided, and health monitoring and fault diagnosis of all systems of thewhole airplane are further realized.

The invention provides an intelligent toy which comprises a microprocessor, an environment sensing module that is electrically coupled with the microprocessor and used for sensing variation values of the environment around the toy and outputting environment sensing signals, a speech input circuit which is used for inputting a first pronunciation field and converting the first pronunciation field into a speech input signal, a speech output circuit which is used for outputting a second pronunciation field. The microprocessor sends a pronunciation control order to the speech output circuit according to the received environment sensing signal or speech input signal to trigger the speech out circuit to output the second pronunciation field. The intelligent toy is characterized by high sensitivity, strong responsivity, great interest, interactive communication, rich and renewable contents, and the like, which is a playing partner and a study medium. A use method for playing the intelligent toy is provided either.

The invention relates to an underground intelligent control system, particularly an underground environment multi-cognition solid monitoring decision support system and the method thereof, which can automatically detect the underground environment, adapt the underground environment integrally and achieve the effects of underground environment optimization, management optimization and personnel optimization. The underground environment multi-cognition solid monitoring decision support system comprises an operation management station, an exchanger, a system interface, an area controller, a fire-control monitoring station, a security monitoring station, an automatic control cabinet, a fire-control device and a security device. Compared with the conventional intelligent system, the underground environment multi-cognition solid monitoring decision support system as the multi-cognition solid system and the method thereof are characterized in that: the system and the method are capable of interacting, coordinating and cooperating with other cognition solid systems and humans in various environments; and are applicable to the intelligent control system for the underground construction engineering in the mining enterprises.

The present invention is a tool for managing spend analysis, reverse auctions, sourcing, contracts, procure-to-pay processes, requests for proposals, supplier assessment and settlement processes. It employs hardware architecture and a software framework to provide a platform as a service that allows the user to create, store, report and manage bids, requests for proposals, contracts, bid data, spend analysis, and supplier scoring information from any of a number of mobile devices of various form factors.

The invention relates to a scheduling encyclopedia system for electric system knowledge management and application. The scheduling encyclopedia system comprises a vocabulary entry management module, a user management module and a view interface management module. The vocabulary entry management module is used for managing knowledge in vocabulary entry manner, managing vocabulary entries received by the encyclopedia system, and publishing management results into an encyclopedia. The vocabulary management process includes creating, revising, submitting, verifying, publishing, abolishing, applying for revising, approving revising, rewarding, acquiring ownership, discussing, viewing by classifying, and searching content. The user management module is used for managing user information and authorities and includes personal information management, collection management, configuration authorities, operation integration configuration, tree classification configuration and vocabulary entry access rewarding time configuration. The scheduling encyclopedia system for electric system knowledge management and application realizes efficient and convenient functions of knowledge networking real-time storage, updating, management, communication, query, searching and the like, can efficiently store, update and manage various electric knowledges and can facilitate communication and learning of various practical operation experience.

The invention relates to the technical field of deep learning, and provides a semantic recognition model training method and device based on comparative learning and a medium, and the method comprises the steps: carrying out the synonym replacement of each first target vocabulary in an original sentence text, and obtaining a first processed sentence text; carrying out antonym replacement on each second target vocabulary in the original sentence text to obtain a second processed sentence text; and training an initial semantic recognition model through the original sentence text, the first processed sentence text and the second processed sentence text to obtain a target semantic recognition model. The objective of the embodiment of the invention is to provide a comparative learning method capable of identifying small semantic changes, and the problem that positive and negative samples are well distinguished in the prior art is improved, so that the model can learn richer knowledge, and the model training effect is improved.

The embodiment of the invention relates to a data security audit model device and method based on a knowledge graph and terminal equipment. A knowledge graph is constructed by performing entity relationship extraction and knowledge reasoning processing on first audit data obtained from a database; a data acquisition module is adopted to acquire second audit data needing security audit from a knowledge graph; a data analysis and mining module analyzes the audit record data in the data acquisition module to obtain an audit data rule; the polarity of the audit data rule is processed, so that a rule value can be obtained; whether the behavior in the audit record data is a violation behavior or not is judged according to a set rule threshold value; the security audit of all kinds of complex data under the background of big data can be realized; the data security audit model device based on the knowledge graph is high in security auditing efficiency, obtains the audit record data through theknowledge graph, and improves the accuracy of an audit result obtained through the analysis of the data analysis and mining module.

The invention relates to the technical field of social event detection, and discloses a multilingual social event detection method based on a federated graph neural network, comprising the following steps: S1, messages are extracted, messages in social information are extracted, and then messages related to the messages are extracted as nodes in a heterogeneous graph; S2, node edges are added, and edges between nodes are added according to the social information; s3, in a pre-training stage, a graph neural network is used for learning representation of a message, a message graph is initialized, and a model is initialized. Rich semantics and structure information in social information are fused together to obtain more knowledge, continuous social detection events can be coped with, the knowledge is expanded by using dynamic social communication, high-accuracy event detection in different language modal data environments can be realized, and the problem of minority-language event detection with few samples is effectively relieved.

The invention discloses a method for identifying a hericium erinaceus strain king by utilizing molecule marker technology, which comprises the following steps of: the culture and collection of hyphae, the extraction of genome DNA, the detection establishment of sequence characterized amplified region-polymerase chain amplification (SCAR-PCR) molecular markers and the detection of an SCAR-PCR product. A detection primer king F2/R2 is adopted, and a specific DNA band with the molecular weight of 37bp in the detection result of the SCAR-PCR product displayed in a DNA map is the marker of the hericium erinaceus strain king.

The invention discloses a calligraphy teaching system comprising: a font library; a retrieval unit used for receiving a retrieval request of a user and searching out Chinese characters satisfying theretrieval request of the user from the font library; an alternative unit for displaying the Chinese characters satisfying the user's retrieval request for selection by the user; a display unit including a first display module, a second display module, and a third display module, wherein the first display module is used for displaying basic knowledge and evolution process of the target Chinese characters, the second display module is used for displaying stroke features and spatial features of the target Chinese characters and the third display module is used for displaying the writing process of the target Chinese characters; an analysis unit used for analyzing and displaying the evolution process of the target Chinese characters from four aspects including the character shape, stroke, structure and writing method of the target Chinese characters.

The invention relates to a method for identifying the houjie strain of hericium erinaceus by making use of a molecular marker technology, which comprises the culture and collection of mycelium, the extraction of genomic DNA, the detection establishment of SCAR-PCR molecular markers and the detection of SCAR-PCR products. The method provided by the invention for identifying the houjie strain of the hericium erinaceus by making use of the molecular marker technology is high in sensitivity and less in the required quantity of DNA. Compared with the conventional morphologic detection, antagonistic test and fruiting test, the method has the advantages of short detection time, high accuracy, easy judgment, good repetition and the like, provides a rapid and effective system of bacteria identification for the utilization of the germplasm resources of the hericium erinaceus and the registration work of new species, and is very important for scientific research and production.

The invention discloses a data-driven professional knowledge graph construction method. The method comprises the following steps of: performing ontology modeling according to data sources and businesscharacteristics covered by a professional field; performing knowledge extraction from a professional knowledge data source; storing the extracted professional knowledge in a mode of combining a graphdatabase, a relational database and a document database; carrying out knowledge fusion on professional knowledge collected from each data source; professional knowledge graph is constructed. According to the data-driven professional knowledge graph construction method provided by the invention, the construction of the professional knowledge graph is effectively and accurately realized, and the knowledge covering the professional field is more comprehensive under the condition that a data source is sufficiently supported.

The invention discloses an expert recommendation method based on multi-modal information learning, and the method comprises the steps: crawling network expert information data and project information data, and arranging the expert information data in an existing expert database; constructing an expert review heterogeneous graph and an expert attribute heterogeneous graph; the text information of the expert is learned by the bert model, the attribute heterogeneous graph of the expert is learned by the graph neural network, the historical review sequence of the expert is learned by building a self-attention recommendation model, the learned embedding is input into the fusion layer to obtain expert information embedding, and a pre-training model is obtained; and extracting expert information embedding by using a pre-training model, encoding project information to obtain project information embedding, and inputting the obtained expert attribute representation and project information representation into a multi-layer perceptron to train the model to obtain recommendation scores of experts and projects. According to the method, rich semantics and attribute information are fully fused into embedding and model parameters of experts, and the accuracy of expert recommendation is improved.