43 results about "Knowledge generation" patented technology

In one embodiment, the present invention is a method and apparatus for knowledge generation and deployment in a distributed network. In one embodiment, a method for processing messages in a social network includes receiving a new message from a first node in the network, the new message including a query, providing the first node with an answer to the query, if the answer is located in a repository, and initiating generation of the answer, if the answer is not located in the repository.

The invention discloses a method for automatically acquiring multi-source heterogeneous data knowledge, and aims to provide a method which has better integrity, universality and convenience and is beneficial to knowledge transmission. The method of the invention is realized through the following technical scheme: the method comprises the following steps: 1, processing; a concept-entity-attribute-relation-label is defined from top to bottom or from bottom to top, a knowledge model of an entity object is obtained, then data is obtained through direct data storage and crawler software, OCR and other recognition software, knowledge data is obtained, and conversion from a heterogeneous data source to a heterogeneous knowledge source is completed; obtaining entity-attribute-relationship triad instantiation under a known knowledge mode through a structured knowledge generation method; and updating knowledge and knowledge models by using a long-short-term memory network model (LSTM model) anda publisher-accomplisher cooperation mode to obtain a workflow for expanding and supplementing new knowledge, and obtaining a data flow accommodating concept, entity, relationship and attribute valueinstantiation triples by using the knowledge model formed by knowledge modeling.

A method for knowledge generation from raw medical records uses XML-based specifications. The method includes content extraction, data aggregation and data enrichment. The method operates on various sources of medical data including financial data, clinical documents and medical images.

The invention discloses an IaaS (Infrastructure as a Service) cloud platform network fault positioning method and system based on log analysis. The IaaS cloud platform network fault positioning system comprises a fault injection module, a log acquisition and analysis module, a knowledge generation module and a fault detection and positioning module. Firstly, by injecting various typical network faults, various corresponding fault logs are formed; then aiming at various faults, log information related to network faults of each layer of physical resources, an operation system, a virtual machine, an OpenStack and the like is respectively acquired, and fault feature mining is carried out on the acquired network fault log information by using an Apriori algorithm; on such basis, according to a maximal frequent item set and parameters, such as a supporting degree, a confidence degree and the like, association rules and knowledge, which correspond to the specific network faults, are generated by utilizing a bayes formula; and finally, when a system has a network fault again, the network fault can be compared with the association rules of a knowledge base and analyzed according to an acquired fault log, so that the layer on which the network fault occurs is positioned.

System and method for automatic entity relationship (ER) model generation for services as software is disclosed. ER model generation by automated knowledge acquisition is disclosed, and automation of knowledge generation process is disclosed. Information extraction process is automated and multilevel validation of information extraction process is provided. System comprises training module to train information extraction model, and knowledge generation module for population of ER model. Standard Operators are generated based on the ER model so generated (populated). Context aware entity extraction is implemented for the ER model generation. System and method leverages existing ER model to make the system self-learning and intelligent, and provides common platform for knowledge generation from different data sources comprising documents, database, website, web corpus, and blog.

A method for knowledge generation from raw medical records uses XML-based specifications. The method includes content extraction, data aggregation and data enrichment. The method operates on various sources of medical data including financial data, clinical documents and medical images.

An expert system based system for customizing a song for a system user. The system includes a song acquisition module having access to the internet, a knowledge acquisition control consol, the knowledge acquisition control consol operatively connected to the song acquisition module, a characteristics extraction module the characteristics extraction module operatively connected to the song acquisition module, knowledge generation module, the knowledge generation module configured to communicate with the knowledge acquisition control consol, a knowledge base module, the knowledge base module configured to work with the inference engine module and communicate with the knowledge acquisition control consol the inference engine module configured to use the knowledge base for reasoning and communicate with the song synthesizer; and an a graphics user interface to interface with system users and a song synthesizer for generating a song according to the requirements of a system user.

The invention provides a knowledge-driven business operation graph construction method. The knowledge-driven business operation graph construction method comprises two parts of knowledge generation and domain knowledge graph construction based on multi-source heterogeneous business data and whole-network domain operation graph network construction based on operation mode evolution. Knowledge generation and domain knowledge graph construction based on multi-source heterogeneous business data comprise knowledge extraction and association processing based on multi-mode full-link multi-dimensionalbusiness data, collaborative modeling and graph generation based on multi-source extraction knowledge and knowledge graph expansion based on business domain knowledge autonomous discovery. Accordingto the method, the construction problem of the business operation atlas is converted into the problem of searching related operation knowledge atlas contents from the business data knowledge atlas according to the business operation process and the required data, so that the subgraph query problem of related operation businesses is searched from the huge public business data knowledge atlas.

The invention provides a knowledge management system seamlessly combined with office software. The knowledge management system comprises a knowledge document library module, a knowledge portal module, a workflow module, a knowledge searching module and a system management module. The collaboration among the modules realizes the seamless combination of the office software and the knowledge management system, improves the customer use experience, and helps an enterprise to establish a good knowledge generation and application environment.

The invention discloses a knowledge graph construction method and device and computer storage equipment, and the method comprises the steps: firstly carrying out the knowledge extraction from a data source associated with a specific entity word, and obtaining a triple of the specific entity word; fusing the obtained triples of the specific entity words with existing triples in a concept map to obtain a fusion result; performing hyponymy reasoning on the obtained fusion result to obtain a reasoning result for expanding the triad of the specific entity word; further translating the expanded triples in the reasoning result by utilizing a knowledge generation engine to obtain a translation result; and finally, writing the obtained translation result into a storage service through a storage engine.

The invention relates to a system and a method for generating custom songs. An expert system based system for customizing a song for a system user. The system includes a song acquisition module having access to the internet, a knowledge acquisition control consol, the knowledge acquisition control consol operatively connected to the song acquisition module, a characteristics extraction module the characteristics extraction module operatively connected to the song acquisition module, knowledge generation module, the knowledge generation module configured to communicate with the knowledge acquisition control consol, a knowledge base module, the knowledge base module configured to work with the inference engine module and communicate with the knowledge acquisition control consol the inference engine module configured to use the knowledge base for reasoning and communicate with the song synthesizer; and an a graphics user interface to interface with system users and a song synthesizer for generating a song according to the requirements of a system user.

A diagnosis system and a diagnosis method of a construction machine which enable even a user who has little knowledge about procedures or techniques for diagnosing construction machines to speedily diagnose a construction machine to be diagnosed in a manner suited to the data characteristics of the machine. The diagnosis device (10) acquires diagnosis data from a diagnosis data storage device (30), extracts the data characteristics from the information contained in the diagnosis data, acquires from a diagnosis knowledge storage device (20) diagnosis techniques considered to be effective for the data characteristics, and presents the techniques to the user along with the degree of effectiveness. Then, the user selects a diagnosis technique using the degree of effectiveness and diagnoses the construction machine. Moreover, in order to make the most use of the knowledge about diagnosis stored in the diagnosis knowledge storage device (20), a diagnosis knowledge generation unit (107) classifies common data characteristics by each element of the diagnosis techniques, and stores the classified data characteristics and the elements of the diagnosis techniques as new diagnosis knowledge.

A system is disclosed which can easily search and determine the effective feature amount suitable for determining the normality / abnormality of an object to be inspected in an inspection / diagnosis apparatus and the various parameters for calculating the effective feature amount. A parameter search unit searches for the various parameters used for calculating the feature amount. A feature amount calculation unit calculates a plurality of feature amounts based on the various parameters searched by the parameter search unit from a given sample data including the normal and abnormal data. An assessment unit outputs the excellence of the various parameters as an assessment value from the result of calculation of the feature amount determined by the feature amount calculation unit. The parameter search unit searches the various parameters again based on the assessment result of the assessment unit thereby to determine an effective feature amount a high assessment value and the various parameters for the particular effective feature amount at the same time.

The invention is applicable to the technical field of satellite measurement, operation and control, and provides a visual satellite fault diagnosis knowledge generation method, device and system, and the method comprises the steps: monitoring the graphical interface input of a user for a satellite fault diagnosis system; responding to the graphical interface input, and extracting corresponding graphical features; and indexing in a pre-constructed knowledge model according to the graphic features, and generating a knowledge expression corresponding to the graphic features. The generation of the satellite fault diagnosis knowledge can be realized through the visual graphical interface input, and the visual generation of the satellite fault diagnosis knowledge can be efficiently realized without knowing a programming language by a user, so that the generation threshold of the satellite fault diagnosis knowledge is greatly reduced, and the generation efficiency of the satellite fault diagnosis knowledge is improved.

The invention provides a digital knowledge discovery method. The knowledge comprising classifying words, identifying characters and meanings of characters, words and sentences can be obtained under the condition that the cost is not added almost in digitalizing process; and all names, place names, event names and the like in documents and all initial characters, phrases, sentences, book names andthe like can be discovered. The invention has the characteristics that the discovered knowledge points are determined before a document is processed by a meaning marking method, a character marking method and a character identification marking method provided by the invention by digital processing units; and after the processing is finished, knowledge in specified format is generated by a knowledge generation module at first, and then the classification knowledge in documents are discovered by a knowledge generation acquisition module.

The invention discloses a method and device for noise detection and knowledge generation completion of a knowledge graph. The method comprises the following steps: acquiring data of the knowledge graph containing noise; projecting entities and relationships to a low-dimensional space based on a translation framework; introducing entity type hierarchical information and relationship path information; calculating the matching degree of entities and relationships in the triple; calculating the credibility of the matching degree; and calculating a triple score by integrating the matching degree and the credibility. A knowledge graph noise detection and knowledge completion basic framework integrating structure information, entity type hierarchical information and relationship path information is designed; whether a triple is true or not is judged in two steps by utilizing entity type hierarchical information and relation path information, namely auxiliary information of the knowledge graph, so that noise existing in the knowledge graph is detected, and better knowledge representation is generated.

The invention relates to the technical field of big data and artificial intelligence, in particular to a knowledge graph construction method based on a library, a fragmented knowledge generation method and electronic equipment. The construction method comprises the steps of obtaining digital literature resources; extracting metadata from the digital literature resources, and generating a metadatamap according to the metadata; obtaining object data according to the metadata, and generating an object data graph according to the object data; fusing the metadata graph and the object data graph togenerate a knowledge graph; and finally, generating fragmented knowledge of each knowledge point of the knowledge graph according to the digital literature resources and the knowledge graph, retrieving related knowledge points of the knowledge graph according to keywords input by a user, and outputting the fragmented knowledge. According to the invention, a complete knowledge system can be established, fragmented knowledge output and output knowledge traceability are realized based on the knowledge system, different requirements of users can be met, and the service efficiency of a library isimproved.

The invention provides a knowledge generation method and device based on artificial intelligence, electronic equipment, a computer readable storage medium and a computer program product. The artificial intelligence technology is involved; the method comprises the following steps: based on a first entity in a first knowledge graph, performing entity chain finger processing on a second knowledge graph to obtain a second entity associated with the first entity in the second knowledge graph; performing fusion processing on the first knowledge graph and the second knowledge graph to obtain a third knowledge graph comprising the first entity and the second entity; based on the first entity and the second entity, screening a plurality of first candidate entities included in the third knowledge graph to obtain a plurality of similar entities corresponding to the first entity and the second entity; and based on the statement relationship of the plurality of similar entities in the third knowledge graph, performing negative relationship-based prediction processing on the first entity to obtain negative statement knowledge of the first entity. According to the invention, the negative statement knowledge can be automatically and accurately generated.

The invention discloses a network knowledge point organization method and device based on a directory tree. The method comprises the steps: building a directory library in advance, and enabling the directory library to comprise a plurality of preset knowledge categories; receiving keywords input by a user during information search, matching the keywords with knowledge categories of the directory library, and a) if matching succeeds, generating a directory tree corresponding to search information according to the content of the matched knowledge categories; b) if the matching fails, displaying the search information in a conventional display mode; and when the number of the directory library knowledge categories matched according to the keywords is more than one, performing default knowledge category recommendation according to a preset recommendation rule. According to the method, the systematicness of knowledge searched by people can be improved, a user can systematically know the searched knowledge, and the learning efficiency of the user on knowledge points is improved.

The invention discloses a video question and answer method based on self-driven twin sampling and reasoning, the method comprises video segment sampling, feature extraction and reasoning strategies, the video segment sampling obtains a reference video segment through sparse sampling and obtains a twin video segment through twin sampling; the feature extraction encodes a plurality of video segment-text pairs into corresponding semantic feature representations through a video encoder, a text encoder and a multi-mode; according to the inference strategy, a twinborn knowledge generation module is used for generating refined knowledge labels for video segments, and a twinborn knowledge inference module is used for spreading the labels to all twinborn samples and fusing the labels. The method has the beneficial effects that the framework based on self-driven twin sampling and reasoning is provided and is used for extracting context semantic information in different video segments of the same video so as to enhance the learning effect of the network.

The invention discloses a posture migration algorithm framework applicable to a multi-degree-of-freedom robot, and relates to the field of robots. According to the attitude migration algorithm framework, attitude or action generation tasks of a robot in different environments are regarded as a multi-objective optimization problem; a robot posture (or action) obtained in a simple environment is used as a source domain; an attitude (or action) applicable to an unknown complex environment is used as a target domain; a high-quality initial population is generated by utilizing knowledge of the source domain during searching of an optimal solution of the target domain; thus, a robot attitude (or action) applicable to a complex environment is quickly generated by utilizing any population-based multi-target optimization algorithm. According to the invention, knowledge reuse can be carried out by using different transfer learning algorithms; and for any population-based multi-objective optimization algorithm, the algorithm framework provided by the invention can be effectively combined with the population-based multi-objective optimization algorithm without modification.

The invention relates to the technical field of emotion detection and emotion analysis, in particular to a word distributed representation learning system based on emotion knowledge enhancement, which comprises an emotion knowledge integration framework and a weak supervision knowledge generation framework, the emotional knowledge integration framework comprises a knowledge query module, a knowledge integration module and a word representation generation module; the weak supervision knowledge generation framework is used for generating a domain sentiment dictionary DSD, and the DSD integrates resources of three parts, namely, a non-label text of a target domain, a domain-independent sentiment dictionary and a label of the target domain text. According to the method, emotional knowledge integration can be well carried out.

The present invention is a method and a program as well as a system, for generating automatically an elementary design process knowledge, comprising of parent concept and children concept(s), for achieving intention or design which, and features to have a reference step and a selection step, where the reference step refers by verb part in the parent concept in order to gain unit information group, one of which consists of a skeleton for the child concept(s), where verb constitutes main part, with processing logic operating on the said skeleton, while the selection step selects one out of the unit information group gained by the reference step, where the selection is performed in logic extracting meaning of the parent concept by information such as input and output constituting the parent concept and preceding parent concept(s). Also, the present invention is a method, a program as well as a system for automatic creation of knowledge for achieving intention or design using pair of the parent concept and the children concept as elementary process knowledge, and features to have a first step forming the skeleton of data flow, a second step for completing the data flow and a third step to gain flowchart of structure chart from the data flow gained in the second step, where the skeleton is obtained, based on elementary data flow of the parent concept as input, by decomposing data in the parent concept hierarchically, and in the second step by inserting verb in function symbol in the skeleton, where the verb is inherited from the verb in the parent concept or the verb in the skeleton as decomposed from the said parent concept, and thus the knowledge is created.

The invention relates to an associated knowledge generation method, an auxiliary annotation system and application, and the method comprises the steps: for a standard question, generating N generated questions through an AMBERT model, and carrying out the screening and annotation, thereby completing the generation of associated knowledge of the current standard question; repeating until the associated knowledge of all the standard questions is generated; the AMBERT model sets a MASK token in the BERT as a mixed MASK token, and generation question prediction is carried out to obtain N generation questions; the method is applied to a rear-end generation unit of the associated knowledge auxiliary labeling system, associated knowledge generated by the rear-end generation unit is output through an output interface of a front-end operation unit, and labeling content is input from an input interface; the system is applied to the tax question-answering system. Easily understood corpora needed by the language model of the question and answer system are constructed, the difficulty of manual annotation work is solved, and the recommendation performance of the language model and the manual annotation efficiency are improved by screening out the data needing to be annotated of the model.

The invention belongs to the technical field of digital information transmission, and discloses a wide-area health knowledge acquisition method and system under a new crown epidemic situation background, and the system is composed of a medical management mechanism HCO and N data collection areas. Each data collection area is composed of a local data manager LDM integrated with an edge AI and a plurality of citizens wearing wearable devices; wherein the LDM i manages Mi citizens equipped with the wearable devices, and the LDM i represents a citizen set. According to the wide-area health knowledge acquisition method, a knowledge generation process and a knowledge transaction process are considered at the same time, and a closed expression of a knowledge transaction mechanism is deduced under the condition of incomplete information. According to the incentive mechanism, economic interaction among the entities is deeply analyzed, and the optimal strategy of each entity is explicitly given. In addition, the correctness of a theoretical result is verified through a large number of numerical simulation results.

The invention discloses a new knowledge generation system, method and storage medium based on technical requirements, wherein the method includes obtaining the technical requirements input by the user on the technical requirements platform and the technical field to which the technical requirements belong; according to the technology The field calls the preset technical achievements in the field database corresponding to the technical field; according to the innovation method and the technical achievements in the same field as the technical requirements, generate the innovative achievements to solve the technical requirements, and transfer the innovation The results are output to the required users. The invention can generate innovative achievements that solve the technical demands put forward by demand users, reduces the innovation cost of technological innovation, and improves the innovation efficiency.

The invention provides a hotspot knowledge generation method and device, and relates to the technical field of data processing, and the method comprises the steps: obtaining commodity knowledge data in a time window, wherein the commodity knowledge data comprises hot spot parameters of each commodity; grouping the commodity knowledge data according to the hotspot parameters, and writing the commodity knowledge data into a plurality of target files according to a grouping result; calculating a popularity value of the commodity according to the target file; and generating hotspot knowledge in the time window according to the popularity value of the commodity. The commodity knowledge data can be collected, grouping calculation is performed on the commodity knowledge data according to the hotspot parameters to obtain the popularity value of the commodity, and the hotspot knowledge in the time window is generated according to the popularity value of the commodity. According to the scheme, the consumed time is short, the data processing speed is high, and the obtained hotspot knowledge result is accurate.