66 results about "Knowledge unit" patented technology

The invention relates to the technology of a knowledge atlas, and aims to provide a Chinese medical knowledge atlas construction method based on deep learning. The Chinese medical knowledge atlas construction method comprises the following steps: obtaining relevant data of a medical field from a data source; using a word segmentation tool to carry out word segmentation on unstructured data, and using an RNN (Recurrent Neural Network) to finish a sequence labeling task to identify entities related to medical care, so as to realize the extraction of knowledge units; carrying out feature vector construction on the entity, and utilizing the RNN to carry out sequence labeling and finish the identification of a relationship among the knowledge units; carrying out entity alignment, and then utilizing the extracted entities and the relationship between the entities to construct the knowledge atlas. According to the Chinese medical knowledge atlas construction method, a recurrent neural network is artfully used for extracting the knowledge units and identifying the relationship among the knowledge units so as to favorably finish the processing of the unstructured data. According to the Chinese medical knowledge atlas construction method, features suitable for the medical care field are put forward to carry out a training task of a network. Compared with general features, the features put forward by the method can better represent a medical entity, and therefore, the relationship among the extracted knowledge units can be more accurate and comprehensive.

A method, system, and computer program product for storing and managing a knowledge profile are described. The knowledge is stored in knowledge units representative of unconstrained natural language (NL). Any given knowledge unit is associatable with at least one other knowledge unit with the given knowledge unit being a context knowledge unit, and the at least one other knowledge unit being a detail knowledge unit of the associated context knowledge unit, and such that every given context knowledge unit that has at least one associated detail knowledge unit satisfies a NL relationship there-between that corresponds to one of the NL-expressible forms of the NL word "have". The profile includes a core set of knowledge units for a core vocabulary of words, at least some of which are associated with knowledge units to provide a basic meaning of the associated words. The profile further includes a core set of knowledge units for core processing and core parsing NL-expressible knowledge. The knowledge units are arranged in accordance with a predefined structure that reflects context-detail relationships and that is dynamically extensible to include other knowledge units during run-time; and the placement and relationships of knowledge units within the predefined structure further reflect semantic interpretations of the knowledge units and support algorithmic reasoning about the knowledge in the profile. In certain embodiments, the profile includes NL class structures to form knowledge units to represent NL words and phrases, and the profile includes NL word class structures to form knowledge units to represent NL words.

The invention discloses a method for dynamic construction of a professional field mapping knowledge domain based on term paraphrase knowledge units and relates to the field of computer information management and information processing. The method is characterized in that a natural knowledge processing technology is used to extract and update knowledge units automatically from a real text; real contents of professional knowledge can be reflected by finer granularity contents; dynamic updating and management can be achieved; traditional problems such as insufficient timeliness, excessive subjectivity and difficult updating and maintenance caused by pure dependence on manual judgment could be solved; and a better technological manner can be provided for construction of a large knowledge library in professional fields. In addition, a mesh-shaped topological structure is adopted, so correlation between the knowledge units is closer, and semantic dimensions become diversified; a visualized knowledge map manner is used for visualized display, so a good knowledge foundation can be laid for automatic finding, inference and computation of knowledge; and the method can support engineering application effectively.

The invention discloses a generation method and system for an operation and maintenance knowledge graph. The method comprises the following steps that: adopting an extraction method based on semantic analysis and machine learning to extract an original operation and maintenance knowledge data source to obtain a candidate knowledge unit; adopting a fusion method based on correlation and a confidence coefficient to carry out knowledge fusion on the candidate knowledge unit to obtain a knowledge fusion result; carrying out processing on the knowledge fusion result to obtain the operation and maintenance knowledge graph, wherein the operation and maintenance knowledge graph consists of a mutual relationship between operation and maintenance knowledge entities; and obtaining the new operation and maintenance knowledge data source to carry out adaptive update on the operation and maintenance knowledge graph. Since the method comprises the step that the new operation and maintenance knowledge data source is obtained to carry out adaptive update on the operation and maintenance knowledge graph, instantaneity is high; and the extraction method based on the semantic analysis and the machine learning and the fusion method based on the correlation and the confidence coefficient are comprehensively adopted, efficiency is higher, cost is lower, and the method is more convenient. The method can be widely applied to the field of computer application.

A multidimensional dynamic local knowledge map is composed of a resource layer, a meta-knowledge layer, a logic analysis layer and a presentation layer, the resource layer provides resource and data support for the meta-knowledge layer, the meta-knowledge layer uniformly describes the resources and data and provides required knowledge for the logic analysis layer, the logic analysis layer obtains the knowledge required by the user from the meta-knowledge layer and sets up an incidence relation of knowledge points, and the presentation layer converts the knowledge points and the incidence relation into graphic elements and presents the graphic elements for the user. A constructing method of the multidimensional dynamic local knowledge map comprises the six steps of 1, collecting and clearing up various kinds of information, 2, constructing a body for the collected knowledge, 3, packaging the knowledge, 4, utilizing meta data for describing a knowledge object, 5, setting up the incidence relation of the knowledge units to form a knowledge relevance link, and 6, utilizing a visualization technology for conducting multidimensional presentation on the knowledge nodes and the relevance of the knowledge map.

The invention discloses a method for establishing a medical image atlas based on image segmentation and the CNN. A CNN method is used to segment medical images finely, image segmentation identification is carried out on the collected medical images, medical knowledge unit segmentation is carried out on medical diagnosis knowledge, and knowledge units of different medical images are formed; an image relation of image segmentation is analyzed to connect the different image knowledge units and communicate with an additional medical illness knowledge unit, a knowledge base association relation isestablished on the basis of connection between medical image identification and medical diagnosis knowledge; characteristic matching is carried out on the knowledge units after image segmentation, entities with the same type of attribute serves as entity nodes in the knowledge atlas, a knowledge base entity is established by fusion, and entities are aligned; and a knowledge atlas is established byusing the entities and the associations therebetween. Suspected diagnosis prompt and treatment suggestion are provided, and AI diagnosis is made possible.

A system to automatically enhance, tag, classify, categorize, cluster and index products described in unstructured text-based electronic documents. The system and method incorporate the use of text normalization, regular expressions, product number matching rules, text segmentation, entity detection, language models, predictive modeling, hierarchal subspace clustering, formal concept analysis, and a weighted combination of all techniques to detect and infer knowledge extracted from a digital version of raw, unstructured product text. Knowledge extracted and inferred comprises knowledge units including: main conceptual entity, entity text patterns, product language models, and conceptual hierarchies. The extracted knowledge units are utilized to store and index products in a product knowledge database and the products and knowledge units are made available to users via a user interface.

The invention discloses a method of generating a navigation learning path on a knowledge map. The method is characterized by comprising the following steps: (1) judging whether a general list Gen-T for storing the knowledge map is empty or not: if the general list Gen-T for storing the knowledge map is not empty, turning to the step (4) to excavate the learned knowledge of a user; (2) generating a total path t-nlr: computing the hierarchy level and learning centrality of a knowledge unit and secondarily ordering the knowledge unit according to the ascending order of the hierarchy level and the descending order of the learning centrality so as to obtain the total path t-nrl; (3) generating the general list Gen-T; (4) excavating the learned knowledge of the user: identifying the user type according to a user login account, generating the existing learned knowledge vector pre-kU of a learner U according to an excavating strategy for the learned knowledge of different types of users; (5) generating a user navigation learning path nlrU by reference to the total path t-nlr and the general list Gen-T according to the pre-kU of the learner U and an input learning goal OU. The user navigation learning path generated by the method provided by the invention has sufficiency, necessity and high efficiency for a leaner to understand the learning target.

The embodiment of the invention provides a Neo4j-based power grid equipment information management method, which comprises the following steps of: obtaining input contents of a knowledge graph, and extracting knowledge units from the input contents; Performing semantic description on the extracted knowledge units according to a resource description framework, and determining complex semantic association between efficient computing entities in a low-dimensional space; And performing database modeling based on the Neo4j data model on the obtained complex semantic association content, and determining a topological relation between the power grid equipment according to the established model. Equipment information management is carried out through Neo4j, so that the integrity of data can be ensured; Topological characteristics of a power grid are considered, the problems of low concurrent read-write performance, inflexible increase and decrease of model attributes, low topological analysisperformance and the like when a relational database is used for power grid equipment information management are solved, and the power grid equipment information retrieval and extraction efficiency isimproved.

The invention discloses an incidence relation excavation method for a text-oriented knowledge unit. The method comprises the following steps of: (1) carrying out aggregation for a text set, finding a text subset with a similar theme, on the base, utilizing nonsymmetry of term distribution in the text and excavating a linear incidence relation between texts; (2) utilizing locality of the incidence relation of a knowledge unit pair, and generating a candidate knowledge unit pair; (3) based on characteristics of term word frequency, distance and semantic types of the knowledge unit pair, carrying out a bi-level classification for the candidate knowledge unit pair, and distinguishing the incidence relation of the knowledge unit pair. In the incidence relation excavation method, numbers of candidate knowledge units can be greatly reduced, and time complexity of relation excavation can be effectively reduced on the premise that accuracy is ensured.

The invention provides a product design knowledge management method and a product design knowledge management system, and relates to the field of computers. The method comprises the following steps of: collecting and organizing design cases related to each design activity according to the knowledge requirements of each design activity in a product design process, and combining the design cases into knowledge units corresponding to the design activities. Or, after the formation of the knowledge units, the method also comprises the following steps of: analyzing design steps of each design activity and a required solver, and packaging the knowledge unit, the design steps and the solver, which correspond to each design activity, into a knowledge component corresponding to the design activity. After being formed, the knowledge components also can be registered and published to form shared knowledge service. The product design knowledge management scheme has the advantages of integration, knowledgeability, parameterization, automation, configurability, navigability and the like, complexity in problem solving is lowered, and requirements for the design experiences of a designer are lowered.

The invention discloses an automatic test paper composition method in a B / S (Brower / Server) mode based on a knowledge hierarchy in the field of computers. The method comprises the following steps of 1, judging whether the current question bank meets a test paper composition requirement according to a test paper composition condition and resetting a test paper composition parameter if the current question bank fails to meet the test paper composition requirement; 2, sequentially and circularly drawing questions which are not drawn previously in a specified question type for test papers until all required questions are drawn by a random drawing algorithm based on the knowledge hierarchy in the constructed field, in accordance with a sequence of a knowledge module and a knowledge unit in the module and by following a priority principle of knowledge points of the questions which are not drawn; and 3, computing an average difficulty value of each question type in the test papers after drawing completion and performing difficulty value adjustment with a circular replacement algorithm until the requirement is met. With the adoption of the method, demands that the test papers have no repeated test questions, the knowledge points of the test papers are evenly distribution and maximized, the difficulty of the same question types of the test papers is consistent and a test paper composition range can be flexibly set can be ensured when the test papers are required to be simultaneously composed.

The invention discloses a synergetic design method for mechanical and electrical products. The method comprises the following steps: (1) determining a design task, and determining a design activity; (2) carrying out modeling on the design process; (3) deciding the design activity; creating a decision template, transferring a knowledge unit and making a decision; (4) controlling the design process,and solving an execution sequence via an algorithm; and (5) outputting results: outputting the execution sequence to complete the design of the mechanical and electrical products. The invention carries out modeling on the synergetic design process and describes the synergetic design activity and a synergetic relationship between the activities in a formalization mode so that the synergetic relationship associated with the design task carried by the design body can be clearly discovered by the design body; in addition, the invention creates a decision process model based on knowledge so that the synergetic decision of synergetic designers is established based on the reliable knowledge and normative flows, thereby improving reliability and the efficiency of decision, optimizing the a synergetic design process model, and improving synergetic efficiency of the design.

The invention discloses a learning cognitive path generation method based on a cognitive map. A cognitive learning path is recommended to a learner in combination with the cognitive dimension ontologyand the course knowledge graph; firstly, a cognitive map modeling and constructing method is provided; on the basis, for a learner and a target learning unit are given, firstly, the current cognitivestate of a learner is recognized according to a learning log; a cognitive learning path of the target knowledge unit is generated by combining the cognitive ability of the target knowledge unit; andrecommendation and generation of cognitive paths in personalized learning can be realized, wherein a cognitive dimension ontology diagram is designed, it is guaranteed that learners can analyze and diagnose the learning situation of each knowledge unit in a finer-grained mode, a learning target cognition path is generated based on the course knowledge graph, and the algorithm integrating the cognition dimension, the learning record and the learner cognition attribute can better provide more accurate personalized learning services for the learners.

The invention discloses a major formula analysis and discovery method, relates to the technical field of traditional Chinese medicine special departments and diseases, doctors and literature major formula big data correlation research, and solves the problems that a correlation rule-based analysis method is relatively fuzzy for definition of correlation among medicines and a clustering-based major formula correlation research method has relatively large difference in eigenvalue extraction and similarity measurement methods in the prior art. According to the major formula analysis and discovery method, each knowledge unit is endowed with coordinate mapping by utilizing a deep learning technology based on a knowledge graph; distance information is fully utilized to reflect correlation among major formulae; the advantages of correlation rules, sample clustering and complex network community discovery can be integrated; and the advantages, namely, multi-dimensional knowledge graph presentation and knowledge reasoning, inexistent in the conventional method are achieved. A user can freely set a community quantity; and the method has remarkable superiority in common medicine pair semantic retrieval, visual traditional Chinese medicine community discovery, single medicine and basic formula correlation research.

The invention discloses a document theme partitioning method based on a domain knowledge map community structure, and the partitioning problem of document resources related to subject knowledge or document knowledge is mainly solved, so that documents related to a theme can be stored in a close logical place, and learning efficiency is improved. The document theme partitioning method is characterized in that a level community discovery algorithm based on the Fast Geedy algorithm and the GN algorithm is proposed, and a theme structure tree is built; in the process of feature extraction, knowledge units directly serve as feature vectors, and due to the fact that the knowledge units have semantic integrality, compared with a traditional method based on participles, the document theme partitioning method can reflect theme characteristics of the feature vectors better; in the process of calculating feature vector values, the method of combination of degree centrality and knowledge unit file frequency is proposed, wherein the concept of the degree centrality reflects the status of the knowledge units in a knowledge map whole situation. Through the method, accuracy of document theme partitioning is effectively improved, and the method is suitable for the document theme partitioning based on the domain knowledge map community structure in general scenes.

The invention discloses a grid-based computational chemistry application integrated system, which comprises distributed chemical resource modules, a grid middleware module and an operation interface module. The chemical resource modules are distributed at different grid nodes and include computing resources provided with computational chemistry application software and chemistry knowledge units with conceptions and methods relative to the chemistry field. The grid middleware module realizes share and collaboration of resources, forms a computing platform having performance higher than that of the single machine, and comprises a service interface unit, an operation dispatching unit and a knowledge base unit. The operation interface module comprises a molecular modeling unit for transforming molecular models into data structures inside computers, a molecular visualization unit for displaying three-dimensional structure of molecules, an operation managing unit for assisting users to submit operations to the grid and monitoring, operating and downloading the operations, and a management community unit. Molecular modeling, visualization, computing and result acquisition can be realized for users by the system, so that the users enjoy the convenient one-stop service.

According to one aspect of the present invention, a method for providing education service based on knowledge units is provided, comprising the steps of: (a) generating a curriculum based on a user's achievement for at least one knowledge unit, said curriculum including at least one problem composed based on said at least one knowledge unit; and (b) providing said at least one problem to said user.

The invention relates to a health state monitoring system for spatial environment simulation test equipment, and the system comprises a data collection unit (100), a data receiving and transmitting unit (200), a systematic knowledge unit (300), a fault diagnosis unit (400), a health management unit (500), and a real-time display unit (600). The fault diagnosis unit (400) comprises a diagnosis unit (410), a mode analysis unit (420), and a guide unit (430). The system can carry out the reasonable utilization of the measurement and control data resources of the spatial environment simulation test equipment, improves the accuracy, completeness and automation degrees of fault emergency processing, guarantees the safe and normal operation of the system, and provides support for the maintenance decision making.

Knowledge automation techniques may include displaying, by a data processing system, a graphical user interface including a first area, a second area, and a third area. The first area may display a plurality of knowledge unit icons, each knowledge unit icon in the first plurality of knowledge unit icons corresponding to a knowledge unit. The techniques may include detecting selection of a first knowledge unit icon displayed in the first area and placement of the selected first knowledge icon in the second area to add a first knowledge unit corresponding to the first knowledge icon to a target knowledge pack for one or more target knowledge consumers, and in response to detecting the placement of the first knowledge unit icon in the second area, displaying, in the third area, a list of one or more suggested knowledge consumers for the target knowledge pack.

The present invention involves a system for processing and acting on information comprising a processor and associated storage with a plurality of knowledge units. Each knowledge unit includes at least one item of data or a sequence of further knowledge units. An observation software module obtains experiential data from external events and stores experiential data in a Universe of Information Units. An operator software module acts on information units in a plurality of operations including at least one of: conditional association, causal relationship, assignment of a value, editing operation, self-observation, shock initiation, shock resistance, threshold determination, and generalization. A dynamic engine software module coordinates interaction of the observation and operator software modules and modifies contents of the knowledge units. An energy software module directs activation of at least one knowledge unit. A goal software module applies rules for determining actions of the dynamic engine module. An object software module encapsulates information units. A domain software module provides a predetermined set of information units relating to a particular domain, and has a rules software module that determines dynamic rules for the predetermined set of information units.

The invention discloses an online help and learn system and a construction method thereof, belonging to the technical field of information processing. The system comprises, a setting unit, a service map constructing unit, a service event analog unit and a data input unit, wherein the setting unit is used for setting the knowledge unit in different levels; the service map constructing unit is used for constructing a service map according to the structure relationship among the knowledge units in different levels; the service event analog unit is used for establishing the analog service event corresponding to different enterprise roles according to the service map; and the data input unit is used for inputting the knowledge data corresponding to the knowledge units in different levels. The invention can enable imitation of the business activity during the operation of enterprises via a graphical interface so as to meet the individualized learn requirements of users in different levels.

Knowledge automation techniques may include discovering data files from one or more content repositories, and identifying key terms in the data files. For each of the identified key terms, a frequency of occurrence of the key term in the corresponding data file, and locations of the key term in the corresponding data file can be determined. A plurality of knowledge units can be generated from the data files based on the determined frequencies of occurrence and the determined locations of the key terms.

The invention discloses an automatic knowledge venation construction method based on massive digital books. The method comprises the steps that metadata information of the digital books is stored in aLucene index file, and if a user retrieves a theme q, a set of the books related to the q can be obtained; the similarity of directory titles is calculated through a weighted word2vec method, first-level directories of the q-related textbooks are clustered through a bottom-to-up condensation-type hierarchical clustering algorithm to obtain a knowledge unit set; the connection relation among knowledge units is established according to the partial ordering relation among chapters in the books, and finally a complete knowledge map is constructed; and TOP K important, ordered and little-redundancy learning paths are mined out from the knowledge map, and the knowledge venation formed by the learning paths is visually displayed by imitating the form of a subway map. According to the method, a digest extraction framework based on the massive digital books is proposed for the first time, the knowledge venation extracted by the framework can comprehensively consider the informativity, the smoothness and the coverage, and therefore a user can quickly and efficiently learn knowledge.

The invention discloses a method through a segmentation and extraction of independent knowledge unit existing in the books, relying on the books to build digital library (treasurer). The method breaks the restriction in traditional digital book management methods which take the page as the basic management unit, and do data processing and establish the connection with the original book image through the concept of knowledge unit. The invention is not limited to dealing with the various characters printed publication of books, journals, papers and maps, drawings in history, but also covers all types of literature unearthed, such as the poems, songs, and so on. This approach can overcome the information redundant and information defective problems in traditional page-based book management so as to enhance digital library (library) effectiveness, allowing users to get more precise, effective search results.

A multidimensional dynamic local knowledge map is composed of a resource layer, a meta-knowledge layer, a logic analysis layer and a presentation layer, the resource layer provides resource and data support for the meta-knowledge layer, the meta-knowledge layer uniformly describes the resources and data and provides required knowledge for the logic analysis layer, the logic analysis layer obtains the knowledge required by the user from the meta-knowledge layer and sets up an incidence relation of knowledge points, and the presentation layer converts the knowledge points and the incidence relation into graphic elements and presents the graphic elements for the user. A constructing method of the multidimensional dynamic local knowledge map comprises the six steps of 1, collecting and clearing up various kinds of information, 2, constructing a body for the collected knowledge, 3, packaging the knowledge, 4, utilizing meta data for describing a knowledge object, 5, setting up the incidence relation of the knowledge units to form a knowledge relevance link, and 6, utilizing a visualization technology for conducting multidimensional presentation on the knowledge nodes and the relevance of the knowledge map.

Knowledge automation techniques may include receiving a request for determining a representative image for a knowledge unit and determining a set of one or more images associated with the knowledge unit. The techniques may include providing the set of one or more images to a user on a client device and receiving user input indicative of a selection of a first image from the set of one or more images. Based on the first image, a thumbnail image for the knowledge unit can be generated. The techniques may further include associating the thumbnail image with the knowledge unit and displaying the thumbnail image to the user via the client device. In some embodiments, the techniques include generating a thumbnail image for a knowledge pack, wherein the knowledge pack comprises one or more knowledge units.

The invention provides a situational interactive cognitive teaching system and a teaching method thereof. The method comprises the following steps: S1: transmitting a game data request command to a network server by virtue of a mobile terminal in accordance with an operation order which is received by a situational interactive input unit and inputted by a user; S2: dynamically extracting knowledge units from a situational game content library by virtue of a situational content aggregation unit of the network server and generating a combined situational game data packet, and transmitting the situational interactive game data packet to the mobile terminal; S3: conducting situational game interaction with the network server by virtue of the mobile terminal in accordance with a situational game flow; and S4: recording interactive data of the user in a situational interactive game process by virtue of a user learning library. According to the teaching system and the teaching method disclosed by the invention, the interactivity and the interesting of children in a cognitive learning process are improved, and meanwhile the learning contents and learning process of the children are also automatically recorded, so that the cognitive competence of the children can be gradually improved.

A method for processing data structures with the aid of networked semantic units includes: acquiring a data structure, and generating, modifying, deleting and storing semantic structure units and networking them on the basis of the acquired data structure while using a knowledge base comprised of a network of semantic knowledge units. Semantic structure units and their network are classified in iterative steps. Based on this classification, a specific processing is activated which modifies a respective semantic structure unit and a particular partial network.

The invention relates to a method for constructing a medical-oriented causality knowledge base. The method includes the steps: a document unit is capable of acquiring a plurality of related documentscontaining a plurality of diseases and classifying the same to form a plurality of document unit bodies to construct a library of original documents, so that a data unit can acquire the main feature parameters based on the document unit bodies, and constructing a data set based on the main feature parameters; a causal unit constructs a Bayesian network based on the main feature parameters and thedata set to analyze the average causal effect between symptoms through the data pattern, so that a knowledge unit can construct a knowledge base in a way of forming a corresponding relationship between symptoms and the average casual effect between the symptoms based on the documents.