448 results about "Knowledge extraction" patented technology

A system and method for searching documents in a data source and more particularly, to a system and method for analyzing and clustering of documents for a search engine. The system and method includes analyzing and processing documents to secure the infrastructure and standards for optimal document processing. By incorporating Computational Intelligence (CI) and statistical methods, the document information is analyzed and clustered using novel techniques for knowledge extraction. A comprehensive dictionary is built based on the keywords identified by the these techniques from the entire text of the document. The text is parsed for keywords or the number of its occurrences and the context in which the word appears in the documents. The whole document is identified by the knowledge that is represented in its contents. Based on such knowledge extracted from all the documents, the documents are clustered into meaningful groups in a catalog tree. The results of document analysis and clustering information are stored in a database.

A method for securing an IT (information technology) system using a set of methods for knowledge extraction, event detection, risk estimation and explanation for ranking cyber-alerts which includes a method to explain the relationship (or an attack pathway) from an entity (user or host) and an event context to another entity (a high-value resource) and an event context (attack or service failure).

A method and system for automated knowledge extraction and organization, which uses information retrieval services to identify text documents related to a specific topic, to identify and extract trends and patterns from the identified documents, and to transform those trends and patterns into an understandable, useful and organized information resource. An information extraction engine extracts concepts and associated text passages from the identified text documents. A clustering engine organizes the most significant concepts in a hierarchical taxonomy. A hypertext knowledge base generator generates a knowledge base by organizing the extracted concepts and associated text passages according to the hierarchical taxonomy.

Techniques for providing privacy protection are provided. A query is received. Privacy policy information, extracted knowledge and optional information about available public information are determined. Information about the knowledge extraction transformations applied to create the extracted knowledge and the source data is determined. Privacy protecting transformations are determined and applied to transform the extracted knowledge based on the selected privacy policy, optional information about available public information, the characteristics of the applied knowledge extractions transformations, the source data and optional previous user queries.

The invention discloses a knowledge graph-based enterprise risk prediction method and system. The method comprises the steps of 1) constructing entities of an enterprise knowledge graph, establishingrelationships between the entities, and extracting knowledge from set data sources to form the enterprise knowledge graph; 2) capturing news information of enterprises and related entities, processingthe captured news information based on the enterprise knowledge graph, marking relationships between the related entities and events, and storing marked information in a structured knowledge base toform an enterprise news information knowledge graph; and 3) performing enterprise risk prediction based on the enterprise knowledge graph and the enterprise news information knowledge graph. The blankof an existing knowledge graph in the field of enterprise risk analysis is filled; and the constructed enterprise knowledge graph and enterprise news information knowledge graph have relatively highpracticality.

A system and method for cross-language knowledge searching. The system has a Semantic Analyzer, a natural language user request / document search pattern / semantic index Generator, a user request search pattern Translator and a Knowledge Base Searcher. The system also provides automatic semantic analysis and semantic indexing of natural language user requests / documents on knowledge recognition and cross-language relevant to user request knowledge extraction / searching. System functionality is ensured by Linguistic Knowledge Base as well as by a number of unique bilingual dictionaries of concepts / objects and actions.

The invention relates to the field of knowledge extraction and particularly relates to a knowledge extraction method and system based on a memory neural network and a device. The invention aims to solve the problem of information redundancy existing in the prior art. The method comprises a step of obtaining a possible relationship type in an input text and a semantic coding vector by using a convolutional neural network under the premise of giving a predefined relationship type, a step of carrying out semantic encoding by using a two-way long and short time memory neural network and obtaininga semantic vector, a step of taking the relationship type as an initial value of the two-way long and short time memory network and a first label in a decoding module and thus fusing the relationshiptype information into encoding information and label information of the decoding module, and a step of obtaining a label sequence by using a decoding module of a single-way long and short time memorynetwork and then obtaining structured information by parsing the label sequence. According to the knowledge extraction method and system and the device, the efficiency of structured information extraction is greatly improved, and the problem of information redundancy existing in the prior art is solved.

A system and method that does trustworthy multi-objective structural synthesis of analog circuits, and extracts expert analog circuit knowledge from the resulting tradeoffs. The system defines a space of thousands of possible topologies via a hierarchically organized combination of designer-trusted analog building blocks, the resulting topologies are guaranteed trustworthy. The system can perform a search based on a multi-objective evolutionary algorithm that uses an age-layered population structure to balance exploration vs. exploitation, with operators that make the search space a hybrid between vector-based and tree-based representations. A scheme employing average ranking on Pareto fronts is used to handle a high number of objectives. Good initial topology sizings are quickly generated via multi-gate constraint satisfaction. To explicitly capture expert analog design knowledge, data mining is employed on the sized circuits to: automatically generate a decision tree for navigating from performance specifications to topology choice, to do global nonlinear sensitivity analysis, and to generate analytical models of performance tradeoffs.

A system and method for cross-language knowledge searching. The system has a Semantic Analyzer, a natural language user request / document search pattern / semantic index Generator, a user request search pattern Translator and a Knowledge Base Searcher. The system also provides automatic semantic analysis and semantic indexing of natural language user requests / documents on knowledge recognition and cross-language relevant to user request knowledge extraction / searching. System functionality is ensured by Linguistic Knowledge Base as well as by a number of unique bilingual dictionaries of concepts / objects and actions.

The invention adopts the between-class square error and the gray scale information to realize the rapid positioning of the inside and outside boundaries of the iris. Firstly, the interested pupil region is extracted through blocking; the between-class square error is adopted to obtain the pupil binary threshold for the extracted pupil region; then the inside boundary of the iris is positioned accurately through the searching of the boundary points and the curve fitting; the interested region of the iris outside boundary is extracted according to the prior knowledge and the pupil position parameter; the selected region is processed with median filtering and first-order gradient conversion; the iris outside boundary is determined through the local gradient integration method; finally, the iris outside boundary parameter is determined through the circle fitting. The method avoids the image binary from depending on the histogram; the image positioning time is greatly improved because only the interested region is processed; the whole image is not processed; the experiment indicates that the robustness and the positioning efficiency of the algorithm can satisfy the real-time processing requirement of the image.

The invention discloses a dynamic legal event map construction method oriented to the legal field, and a dynamic legal event map oriented to the legal field is constructed by utilizing a natural language processing technology. In the prior art, the dynamic legal event map construction method does not appear in the legal field, compared with the prior art, the minimum unit of the dynamic legal event map of the present invention is a legal event rather than an entity, and the constructed map is composed of a relationship between the legal event and the legal event. Compared with the traditionalevent extraction, the knowledge in the constructed dynamic legal event map is dynamic, computable and reasonable instead of a simple extraction event. According to the method, the dynamic legal eventmap oriented to the legal field is constructed, the map is constructed by combining a traditional knowledge map knowledge extraction technology and an event mining technology, and then the legal eventmap metering is carried out by modeling the legal event elements in the legal event map and the relations among the legal events respectively.

A system for use in managing activity of interest within an enterprise is provided. The system comprises a computer configured to (i) receive sensor data that is related to key activity to the enterprise, such key activity comprising a type of object and the object's activity at a predetermined location associated with the enterprise, the sensor providing information from which an object's type and activity at the predetermined location can be derived, (ii) process the sensor data to produce output that is related to key activity to the enterprise, and (ii) store the information extracted from the processed data in a suitable manner for knowledge extraction and future analysis. According to a preferred embodiment, the object is human, machine or vehicular, and the computer is further configured to correlate sensor data to key activity to the enterprise and the output includes feedback data based on the correlation.

Methods and systems for knowledge extraction and prediction are described. In an example, a computerized method, and system for performing the method, can include receiving historical data pertaining to a domain of interest, receiving predetermined heuristics design data associated with the domain of interest, and using the predetermined heuristics design and historical data, automatically creating causal maps including a hierarchy of nodes, each node of the hierarchy of nodes being associated with a plurality of quantization points and reference temporal patterns, the plurality quantization points being known reference spatial patterns. In an example the computerized method, and system for performing the method, can further include receiving, at each node, a plurality of unknown patterns pertaining to a cause associated with the domain of interest, automatically mapping the plurality of unknown patterns to the quantization points using spatial similarities of the unknown patterns and the quantization points, automatically pooling the quantization points into a temporal pattern, the temporal pattern being a sequence of spatial patterns that represent the cause, automatically mapping the temporal pattern to a reference temporal pattern, automatically creating a sequence of the temporal patterns, and automatically recognizing the cause using the sequence of temporal patterns.

The invention discloses a knowledge-engineering-based automatic scheme generation and evaluation system. The automatic scheme generation and evaluation system comprises a project management subsystem, a demand management subsystem, a product database subsystem, a collaborative design subsystem and an electronic product design technology platform, wherein the project management subsystem is in charge of providing solving ideas and tools; the demand management subsystem is used for decomposing the product design demand, converting into task indicators and multi-level task sequences, realizing dependence mapping and providing real-time monitoring of the indicators; the product database subsystem is used for managing design data and setting data standards and regulations; the collaborative design subsystem plays the role of a bridge; the electronic product design technology platform is in charge of generalizing and managing typical data, design methods and digital prototype models of all products and pushing information to the collaborative design subsystem. A method comprises the steps of knowledge extraction and classification, professional knowledge base setting, knowledge-engineering-based platform construction and automatic design scheme generation and evaluation. According to the invention, knowledge engineering is introduced into the electronic product design, so that the reuse rate of knowledge and other resources is effectively improved, automatic generation and evaluation of product schemes are realized, the product research and development time is shortened and the intelligence degree is high.

The invention discloses an automatic construction method for a big data knowledge graph in the public security field, relates to the technical field of data mining and artificial intelligence, and comprises the following steps: firstly, establishing a standard system for the public security field, and then establishing an Entity-mapping library in the public security field; storing the main attributes of the entities into a file storage database; pushing the data to a memory storage database, carrying out automatic series connection on fragmented entities, abstracting the data into three categories of entities, relations and events after the previous preparation work is finished, and sequentially finishing automatic construction of the public security field knowledge map by virtue of machine learning and deep learning services through knowledge modeling, knowledge extraction and entity fusion; Besides, the automatic construction capability is realized, the quality control and optimization of the knowledge graph are carried out, the public security field search intention analyzer is constructed, the intelligent recommendation of the user search is promoted, and the efficiency of obtaining effective information by the user search is improved.

One method using for picture detecting technology field, is especial a kind of color picture person face detecting method in complicated background. Detect the candidate area of person face using whole complexion and figure character, then detecting person face by eye and mouth local character. Take illumination compensate for pictures and partly eliminate the influence for detecting from illumination, then divide up and unite the two value picture traversed by complexion model to get the candidate area of person face. Detecting person face figure, eye and mouth to judge if the candidate area having the face and finish the face detecting. It can accurately locate face position and the face with large gauche angle. The examine rate is 89.7% for 1015 color face pictures taken in changing illumination and complex background containing gauche ones.

The invention discloses a secondary clustering segmentation method for a satellite cloud picture. According to the secondary clustering segmentation method for the satellite cloud picture, firstly, block processing is carried out to the whole wide-range satellite could picture; secondly, corresponding multi-channel spectral features and three-patch length between perpendiculars (TPLBP) textural features are sequentially extracted from each of sample points of each sub regional could picture for fine initial kernel clustering segmentation so as to obtain multiple sub regional could picture segmentation results; and at last, secondary kernel clustering segmentation is carried out to the global cloud picture on the basis of the initial kernel clustering segmentation results by utilization of the initial kernel clustering segmentation results as prior knowledge to extract a variety of grayscale average features and density indicator features of the initial kernel clustering segmentation results in a corresponding original sub regional cloud picture range so as to ensure integrity of cloud classification. The secondary clustering segmentation method for the satellite cloud picture has the advantages of being high in precision and robustness, and capable of identifying cloud classification in a fine mode according to huge and complicated geographical information, ocean information, atmospheric information and other information which are contained in the wide-range meteorological satellite cloud picture.

The invention provides a thermal power plant main operating parameter target value determining method based on association rule mining. The rule knowledge of a unit under certain operating conditions is acquired by using steady operating data stored in a historical operating database through an association rule mining technology, and finally the knowledge is used to guide the unit optimization operating. The method comprises the steps that the steady operating data are extracted from a unit historical operating data set through a data preprocessing technology; discretization of continuous attributes is carried out on a specific condition data set through a condition dividing result to complete data set preparation of association rule mining; and rule knowledge extraction is carried out on a discretized data set through an association rule mining technology to acquire a unit historical operating knowledge database. The knowledge database can assist an operator or a control system to make relevant decisions. According to different target attributes, the economy, stability and environment protection of unit operating can be improved, and a unit is under an excellent operating condition for a long time.

Systems, methods and recordable media for facilitating user-guidance of computational analysis and knowledge extraction tools for use with biological data for disambiguation and determination of causation in representations of the data. Systems, methods, tools and computer readable media for user-guided expansion of biological networks and manipulations of the same. Tools for qualitative simulation of network models, for identifying interactions between multiple networks and form maintaining knowledge about multiple alternative biological networks. Combinations of portions of networks may be constructed to provide optimal networks. Networks may be evaluated against experimental data and networks of interest may be identified based on experimental data.

The invention discloses a method for constructing a public safety knowledge map. The method comprises the following steps of 1 carrying out the ontology modeling according to data sources and businesscharacteristics covered by the public safety field; 2 carrying out knowledge extraction from that current public safety data source; 3 storing that extracted knowledge in a combine manner of a graphdatabase, a relational database and a document database; 4 fusing knowledge collected from each data source; 5 performing the knowledge processing on the knowledge map which is used to complete the knowledge fusion. The invention makes the knowledge covering the public safety field more comprehensive under the condition that the data source is sufficiently supported.

The invention discloses a construction method of a general medical special disease data system. According to the method, clinical text analysis and knowledge extraction are carried out to integrate two kinds of heterogeneous clinical data sources including unstructured medical records and structured clinical data; and then a general medical special disease data system for disease characteristic analysis is constructed. The method is characterized in that on the basis of a special disease segmentation dictionary, the analysis is carried out by combing contexts of medical records, the structuralization of the electronic medical records is completed; with the pattern matching and feature mining technologies, characteristic value of diseases in the medical records are obtained to complete analysis and digging of the semantics of medical records, so that disease condition features and disease condition prognosis conditions of diseases in the unstructured electronic medical records are provided and dug. The analysis and mining of the disease characteristics, disease outcomes, and the treatment process of the medical special diseases are completed by integrating the structured clinical data and thus a comprehensive complete medical data system is built.

The present invention provides a method for extracting relationships between words in textual data. Initially, a classifier is trained to identify text data having a specific format, such as situation-response or cause-effect, using a training corpus. The classifier receives input identifying components of the text data having the specified format and then extracts features from the text data having the specified format, such as the part of speech for words in the text data, the semantic role of words within the text data and sentence structure. These extracted features are then applied to text data to identify components of the text data which have the specified format. Rules are then extracted from the text data having the specified format.

The present disclosure includes a system and method for learning (or discovering and extracting) business knowledge from a collection of source code. The collection of source code is abstracted to generate an abstracted data stream, which is then transformed to an Extensible Markup Language (XML) format. The transformed data in XML format can be further converted to target formats or processed to satisfy different needs such as software system documentation, migration, impact analysis and security analysis. The disclosure also includes an implementation and operation for a pattern abstraction engine configured to receive an input data stream and format it for abstraction into a standard format using a pattern matching mechanism. The disclosure also includes an implementation and operation for a contextual pattern decoder engine configured to extract knowledge attributes and contextual taxonomy from classified blocks of an input data stream.

The invention discloses a method for constructing industrial knowledge map based on industrial chain, which relates to the technical field of knowledge map in artificial intelligence. Firstly, the industrial chain is modeled, and then the industrial knowledge map is constructed according to the constructed industrial chain model. The industry knowledge map based on the industry chain established by the technical proposal of the embodiment of the invention can clearly reflect the entity-relation-entity and ' entity-eroperties-attribute value ' between the industry chains and within the industrychains, can facilitate financial researchers to further use knowledge mapping to study industrial chain conduction and event driving to find important events, to analyze information emotion and so on; The construction of industry knowledge map based on industry chain can effectively reduce the problem of excessive noise in the process of industry knowledge extraction, and the cold start problem of knowledge extraction can be avoided by using feature thesaurus to construct entity relationship.The embodiment scheme can realize incremental knowledge learning and effectively reduce the dependenceon professional researchers.

A long-term memory network method and system for text comprehension. A recurrent neural network can be provided, which includes an external memory module and a long-short term memory unit, wherein said recurrent neural network encodes raw text information into vector representations, forms memories, finds relevant sentences to answer questions, and generates multi-word answers to said questions utilizing the long short term memory unit.

The invention relates to a disease prediction method based on automatic medical specialist knowledge extraction, and belongs to the technical field of intelligent medical treatment. The method comprises the following steps: firstly, constructing a disease relation network according to historical diagnosis record data, calculating the disease feature vectors on the network through the explicit andimplicit correlations between the disease entities by using the neural network model, and calculating the correlation matrix between the diseases through disease feature vectors to serve as medical specialist knowledge; secondly, designing a disease prediction model based on deep learning, and subjecting the original medical index data of the patient to dimensionality reduction through a noise reduction self-encoder stack model, and predicting the potential disease of the patient by taking the data as the input data of the multi-label disease prediction model; and finally, in the parameter learning part of the model, taking a disease similarity matrix which is automatically extracted in the first step as a medical background constraint condition, making an optimal parameter of the algorithm learning model, and taking a disease with relatively high incidence probability as a prediction result. Compared with the prior art, the disease prediction accuracy is improved.

The invention relates to a rail transit diagnosis method and system based on a rough set. The method comprises the following steps: (1) collecting monitoring data of rail transit signal equipment and extracting the characteristics of the collected monitoring data so as to establish a fault diagnosis decision table, (2) based on the rough set, conducting knowledge extraction and attribute reduction on the fault diagnosis decision table so as to obtain a best attribute reduction combination, (3) establishing a neural network model, using the condition attribute in the best attribute reduction combination as input, using the decision attribute of the best attribute reduction combination as the output target of a neural network, and adopting the neural network for training, (4) using the trained neural network for calculating the possibility of a possible fault area of the real-time fault information, using the fault area largest in possibility as a fault diagnosis result and outputting the result. The rail transit diagnosis method can solve the problems that work load is large, efficiency is low, and risk performance is high when rail signal system failures are judged manually, and improves the efficiency and the accuracy of rail transit data analysis and failure diagnosis.

The invention provides an electrocardiogram signal detection method based on a belief rule base and a deep neural network. The method comprises the following steps: constructing a deep neural networkmodel in accordance with input signals, selecting a network loss function and driving the deep neural network to conduct training in accordance with input data via the network loss function; extracting artificial characteristics via expert knowledge in accordance with the input signals; inputting the artificial characteristics as well as characteristics learned by the deep neural network, so as toconstruct the belief rule base, optimizing parameters of the belief rule base via an improved covariance matrix adaptive evolution strategy, and reducing rules in the belief rule base; and implementing decision fusion on judgment outputs of the deep neural network model and the belief rule base via a fusion method. The electrocardiogram signal detection method provided by the invention, through the full development of advantages of modeling based on expert experience knowledge and discovering complex patterns from mass data based on deep network learning, can automatically judge potential diseases, which may exist, in accordance with electrocardiogram signals of a tested object, so that obtained judgement is more robust and accurate.