83 results about "Knowledge building" patented technology

A method and a language processing and knowledge building system (LPKBS) for processing textual data, receives textual data and a language object; segments the textual data into sentences and each sentence into words; generates a list of one or more natural language phrase objects (NLPOs) for each word by identifying vocabulary classes and vocabulary class features for each word based on vocabulary class feature differentiators; creates sentence phrase lists, each including a combination of one NLPO selected per word from each list of NLPOs; groups two or more NLPOs in each sentence phrase list based on word to word association rules, the vocabulary classes, the vocabulary class features, and a position of each NLPO; replaces each such group of NLPOs with a consolidated NLPO; maps each segmented sentence to a sentence type; identifies a semantic item for each mapped NLPO; and identifies and stores associated attributes and relations.

The invention discloses an Internet financial risk monitoring system based on knowledge map, which comprises a data source module, a multi-label graph module and an analysis module. The data source module extracts entities according to different data sources, fuses entity knowledge, constructs relationships, integrates all the basic data sources from different business systems, and organizes theminto unambiguous and well-defined entity knowledge and definite relationships among entities according to business logic. The multi-tag graph module constructs a multi-tag knowledge map according to the knowledge acquired from the data source, and maps the social behavior and attributes of the members into the network map to form the behavior attributes association map of the members; The analysismodule analyzes the potential risk factors and characteristics of members in the process of Internet finance by constructing a good knowledge map. The invention changes the existing analysis dimension of the wind control model, thereby optimizing the traditional method that only the analysis dimension is added to improve the model precision.

The present invention provides a system and method for building and analyzing a quantitative model from qualitative tacit knowledge. In one aspect of the present invention, there is provided a system for creating and analyzing a model of a user's semantic knowledge. The semantic knowledge model is based on cause and effect relationships as defined by the user. In another aspect of the present invention, there is provided a system for creating and analyzing a model of a user's episodic knowledge. The episodic knowledge model is based on the user's past experiences, including recalled stimuli and responses. The semantic and episodic models are used to describe the users internal mental model.

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 provides a knowledge graph driving type legal intelligent consultation system. The knowledge graph driving type legal intelligent consultation system comprises a knowledge construction module used for constructing a question and answer corpus and a legal knowledge base; a legal language understanding module used for training to obtain a corresponding entity recognition model, an intention attribute recognition model and a question answer pair matching recognition model; a feature recognition module used for recognizing legal features; a knowledge association module used for searching attributes associated with the questions; a query matching module used for querying and matching answers in a knowledge base and forming a system question and answer log; and a knowledge operation module used for screening out effective questions in the system question and answer logs and updating answers matched with the effective questions into a knowledge base. According to the system andthe method, the user can be intelligently answered and guided to solve legal knowledge problems, the cost of legal consultation of common people is saved, manpower and material resources are saved, and the working efficiency of the user and legal professionals is improved.

An novel recipe that embodies a higher level description than currently used in the industry is described. The novel recipe is referred to herein as an “advanced recipe.” A traditional recipe consists of a general set of instructions called a ‘recipe’ which is used to make a product. An advanced recipe integrates the intent behind these set of instructions. A novel knowledge management system for capturing, integrating, and using broad knowledge is also described below. Some embodiments of the knowledge management system enable modification of recipes for maximizing the overall processing objectives. An example embodiment of the knowledge management system comprises a Knowledge Builder, a Structured Knowledge Repository, and a Decision Maker.

The invention discloses a domain knowledge graph based on a semantic triangle and a query method. The graph comprises a concept layer and an entity layer; the concept layer is composed of a set of concepts, and each concept has a unique identification and is represented by a represent word item and a candidate word item set; according to field related knowledge and the concept set of the concept layer, multiple entities corresponding to each concept are instantiated, the entity layer is formed, the entities are extensions of concepts, and each entity has a unique identification and is represented by a represent word item and a candidate word item set; an association relationship established according to the field related knowledge is set between the related concepts; an association relationship established according to the field related knowledge is set between the concept layer and the entity layer; an association relationship established according to the field related knowledge is set between the entities. By means of the method, separation of the concepts and the entities is achieved, knowledge summarization is convenient, different effects of the concepts and the entities in knowledge understanding and application are distinguished, and the query efficiency is improved.

The invention discloses a tax domain-oriented knowledge graph construction method. According to the construction method, a top-down and bottom-up combined mode is adopted. The method comprises the following steps: firstly, constructing a tax knowledge graph mode based on tax knowledge in a tax expert system; then, data processing including tax data source selection and acquisition, data cleaning and the like is carried out; then information extraction is carried out, and information extraction is carried out on the processed data according to different types and a mode diagram; tax knowledge fusion is carried out, knowledge sources in a tax knowledge graph are different, problems of knowledge repetition, relationship redundancy and the like need to be subjected to mode matching, entity alignment and the like, and knowledge is stored in a knowledge base after knowledge fusion is completed. And finally, knowledge feedback is carried out, and knowledge conflicts in intelligent tax model construction are solved by using a tax expert system. And finally, the problem of untight combination of the knowledge graph and the tax scene is solved.

The invention provides a knowledge graph driven personalized accurate recommendation method. The method comprises the steps of obtaining related knowledge of an article from a knowledge base accordingto historical behaviors of users, constructing a knowledge graph, initializing vector representation of each node and connection, and determining a feeling domain of each node; generating a trainingsample according to the historical behaviors of the users, and initializing vector representations of all the users and articles; obtaining the feeling domain of the corresponding entity of the articles in the training sample in the knowledge graph, and taking the feeling domains and the sample as graph neural network model input to obtain a possibility prediction value of interaction between theusers and the articles; optimizing model parameters by minimizing a loss function; and after the model optimization process is finished, sorting the prediction values of the possibility of interactionbetween a certain user and all the articles to obtain the recommendation list of the user. According to the method, the knowledge graph information is utilized, the sparsity of historical behavior information of an original user is made up, the users and the articles are described from the multi-dimensional perspective, and the personalized recommendation result is more accurate.

The invention discloses a multi-source heterogeneous remote sensing data association construction and multi-user data matching method. The multi-source heterogeneous remote sensing data association construction and multi-user data matching method comprises the following steps of 1, inputting a remote sensing service data set and a remote sensing product data set; 2, performing data cleaning and preprocessing; 3, performing data classification modeling; 4, performing knowledge extraction, including attribute extraction of remote sensing business data and feature extraction of remote sensing product data; 5, performing multi-source heterogeneous knowledge fusion, constructing a link relationship for the plurality of knowledge, and fusing attribute similarity of different ontology data according to metadata information extracted from the remote sensing data to construct the link relationship of a plurality of knowledge systems; 6, constructing an association relationship model; 7, miningand analyzing a large amount of collected user identities and behavior data, and constructing a user portrait label; 8, carrying out similarity calculation on the identity and behavior of the user; and 9, constructing a personalized user portrait model, and matching the personalized user portrait model with a result in the association relationship construction model.

The invention discloses a class identification method for a zero sample picture. The method includes constructing a knowledge graph according to the knowledge of the human to represent explicit relationships among the categories; according to the method and the device, the problems of implicit relation learning and fuzzy and uncertain relation between categories in a semantic space are avoided, meanwhile, a residual image convolutional network is constructed and trained for migrating knowledge between the categories, and category recognition is carried out by adopting maximum inner product values, so that the category recognition accuracy of the zero sample picture is improved.

An integrated system organizes a company's experiences, operating procedures, best practices, information sources, competitive information and analytical tools. The goal is increasing profitability within a due diligence process while facilitating ongoing operations. The system incorporates a method for collaborating on due diligence issues to affect knowledge building within due diligence teams. The method includes accessing stored, accumulated knowledge in a repository from prior due diligence exercises, applying to due diligence decisions criteria based on consolidated analytical building blocks of past due diligence exercises and storing newly accumulated knowledge from the current due diligence exercise into the repository of accumulated knowledge.

The invention discloses a power grid knowledge graph construction method and a power grid knowledge graph construction system, and aims to solve the technical problem that a practical and efficient knowledge graph construction tool is lacked in the technical field of power grids in the prior art. The method comprises the steps of collecting power grid related contents and arranging power grid corpora; constructing and training a natural language processing model according to the power grid corpus; and performing power grid knowledge extraction based on the natural language processing model, and storing an extraction result into a graph structure database. According to the method, the power grid knowledge can be effectively extracted, the knowledge graph of the power grid field is constructed, and a support guarantee is provided for subsequent knowledge graph application.

The invention discloses a generation type dialogue abstract method integrated with common knowledge, and belongs to the field of natural language processing. According to the invention, the problems of inaccurate generated dialogue abstract and low abstraction caused by the fact that the conventional generative dialogue abstract method does not utilize common knowledge are solved. The method comprises the following steps: acquiring a common knowledge base ConceptNet and a dialogue abstract data set SAMSum; introducing tuple knowledge into a dialogue abstract data set SAMSum by utilizing the obtained common knowledge base ConceptNet, and constructing a heterogeneous dialogue diagram; training the dialogue heterogeneous neural network model constructed in the step 3, and generating a final dialogue abstract from a section of dialogue through the trained dialogue heterogeneous neural network model. The method is applied to generation of the dialogue abstract.

The invention discloses a method and a device for constructing a power grid fault processing knowledge graph. Domain high-quality professional phrase mining and named entity identification are carriedout; relationship extraction of equipment, events, operations and the like is carried out; knowledge is automatically extracted from massive structured and unstructured data such as power grid operation data and fault processing plans; a power grid dispatching fault processing knowledge graph is constructed, the limitation that a traditional power grid dispatching expert system customizes knowledge regularly and is long in period and slow in updating is well broken through, and computer intelligent autonomous collection, cross-domain analysis and all-time learning of the power grid dispatching fault processing knowledge are achieved.

The invention discloses a code abstract generation method based on a code knowledge graph and knowledge migration. The method comprises the following steps: 1, extracting and fusing multi-source datato construct the code knowledge graph; 2, generating an abstract syntax tree by using a code parsing tool, and traversing method calling nodes in the abstract syntax tree to obtain an API calling sequence; 3, searching API description information in the API calling sequence from the code knowledge graph; 4, mining large-scale open source projects, constructing an API sequence abstract generation data set, training a text abstract generation model, and learning background knowledge related to API functions; 5, constructing a code abstract generation model; and 6, training a code abstract generation model on the code abstract data set, and generating a code abstract by utilizing the model. According to the method, the code knowledge graph and knowledge migration are used for the code abstract generation task, the ability of the model to extract code functional semantic information can be enhanced, the model is assisted in understanding codes, and the code abstract generation quality is improved.

The invention discloses a task guidance type smart agricultural planting expert system. A knowledge obtaining module builds a knowledge base by obtaining agricultural planting knowledge, a knowledge base management module sets confidence for each rule type knowledge, and the inference accuracy of uncertain events is improved; The reasoning task is generated; An improved Rte network mode matching algorithm is adopted; knowledge stored in the knowledge base is inquired and a rule required by the reasoning task is subjected to matching and activating operation in the knowledge base and variablesin a variable library and the external user data are combined, reasoning of the reasoning task is completed according to the confidence coefficient of the activated rule, and finally a structured production task is generated for guiding a user to carry out agricultural production activities to realize scientific planting. By adopting the embodiment of the invention, the method can be extended to model establishment and reasoning of other crops, and after a rule base and a knowledge base are continuously huge, the method has higher matching speed, reasoning efficiency and model generalization.

The invention discloses a graph model intelligent commodity recommendation method fusing a knowledge graph and user interaction, and the method comprises the steps: 1, collecting the historical interaction record data of a user for a commodity, constructing a user commodity interaction matrix Y for training a recommendation model, and constructing a user commodity interaction bipartite graph; 2, collecting commodity attribute features and association features between attributes, and constructing a knowledge graph by using priori knowledge; 3, constructing a recommendation model fusing the knowledge graph and user interaction, and selecting a proper loss function to optimize model parameters and feature vectors; and 4, predicting the probability that the user interacts with the non-interacted commodities in the future by using the recommendation model, and selecting the commodity with the maximum interaction probability to recommend to the user, thereby completing a commodity recommendation task. According to the method, graph convolution operation on the knowledge graph and the interactive bipartite graph is combined, and semantic and structural information carried by the knowledge graph can be more sufficiently captured, so that a more accurate recommendation effect is realized.

The invention provides a method for modeling a dynamic radar environment knowledge base. The method comprises two stages; in the first stage, the history knowledge is used for building a static radar environment knowledge base, and each auxiliary knowledge is initialized under a Cartesian coordinate system; in the second stage, the radar environment knowledge base is dynamically updated by instant information and real-time data. The method has the advantages that the radar environment knowledge base is built under the background of a radar knowledge auxiliary system, and the purpose of strong systematicness and practicality is realized.

The invention discloses a network security data association analysis method and device, equipment and a storage medium, and the method comprises the steps: collecting data capable of representing thecurrent security condition of a network as a sample, extracting corresponding information from the sample as knowledge according to a preset business logic, and constructing a knowledge graph throughthe knowledge; respectively extracting features from each preset rule to obtain corresponding rule features, wherein the rule is data representing that the network has a security threat; and carryingout deep search on the knowledge graph, and if knowledge matched with any rule feature exists in the knowledge graph, determining that the knowledge is a knowledge identification risk matched with anyrule feature. According to the invention, the accuracy and effectiveness of network security analysis can be improved while the network security analysis time is reduced.

The invention discloses an industry-oriented context omission question-answering method. According to the method, an industry knowledge graph is constructed according to structured and unstructured knowledge in industry data, the industry knowledge graph comprises triad information, and when a system determines a certain theme through a client problem, the theme and attributes related to the client problem in a triad are both identified as a dialogue state; and based on the industry knowledge graph and the determined dialogue state, the system performs dialogue state management after receivingthe client question, including solving noise interference through a historical state question and answer mechanism and a context omission question and answer judgment mechanism, emptying the system state caused by non-industry question and answer, and answering non-asked questions.

The invention provides a water industry emergency decision generation method and device. The method comprises: collecting water industry knowledge; wherein the water industry knowledge comprises waterindustry expert knowledge and water industry historical disaster emergency plan knowledge; constructing a water industry knowledge base according to the water industry knowledge; performing contextual case extraction on the current disaster event to generate an emergency case of the current disaster event; and generating an emergency decision of the current disaster event according to the generated emergency case and the constructed water industry knowledge base. According to the method, effective organization and utilization of unstructured experience, knowledge and data in the water industry are realized. Historical process recording of water industry emergency cases can be achieved in a scene mode, meanwhile, historical experience and similar case emergency measures can be combined with scenes to be pushed in a dynamic mode, and a more convenient and accurate information management method and decision-making means are provided for the industry.

The invention relates to a government affair knowledge building method and knowledge retrieval system based on ontology, in particular to the field of knowledge service, and particularly relates to a government affair knowledge ontology building model and government affair knowledge retrieval software. The government affair knowledge ontology building model comprises a basic concept and a core concept, and has the interrelationship between the concepts; the core concept description includes information resource associated rules. The government affair knowledge retrieval system mainly provides service such as knowledge ontology content maintenance, ontology and information resource associated rule maintenance, knowledge ontology inquiry and information resource retrieval dispatching. The invention aims at providing an ontology building method, an ontology retrieval technology and an information resource retrieval dispatching technology for solving the problems that the government affair knowledge cannot be easily teased out and cannot be easily associated, and the retrieval effect is poor. By using the method and the system, the efficiency and the quality of externalization building and internalization application of the government affair knowledge can be greatly improved.

An entertaining ball-rolling table game that generates the desire to understand and use the physics, dynamics and geometry incorporated in the game is provided. The game may include a game table providing a sloped table surface forming two vortical holes. The game is played by rolling one ball bearing at a time along the table surface with the purpose of rolling the ball bearing into a predetermined vortical hole. At the beginning of a player's experience with the game, it will seem extremely difficult to aim the ball with enough precision to guarantee that the ball will fall into one hole rather than the other. The precision and subtlety of the surface of the game table and its interface with the ball bearing makes it uniquely hard to understand, but uniquely challenging, and thus uniquely gratifying to master, and so generate the desire to problem solve and understand the STEM knowledge at play. Further, the system that embodies the game may provide further analysis and knowledge-building by representing physical parameters from previous rolls for the participants to observe and apply to future rolls.

The embodiment of the invention discloses a domain knowledge base construction method and device, and the method comprises the steps: obtaining entity data according to a preset expert knowledge base,and the entity data comprises the concepts and attributes of entities and the relation between the entities; performing text information extraction on the entity data by using a preset extraction technology, and taking the extracted text information as ontology data; and carrying out knowledge construction on the ontology data by adopting the created reasoning knowledge base, and forming a new domain knowledge base according to new knowledge obtained by knowledge construction. Through the scheme of the embodiment, a knowledge base which is low in cost and based on knowledge reasoning is established, an automatic decision-making process is realized, the data quality and flexibility of the map are improved, and the data governance difficulty and cost are reduced.

The invention relates to a first-aid knowledge question-answering method based on a multi-modal knowledge graph and a system thereof, and the method comprises the steps: obtaining first-aid related knowledge based on the Internet, and constructing the multi-modal first-aid knowledge graph according to the first-aid related knowledge; acquiring a question input by a user, and extracting entities and relationships in the question by using the entity and relationship joint extraction model; positioning entities in the multi-modal first-aid knowledge graph according to the entities in the question, and determining matched entities; calculating the similarity of all relationships between the entities in the question and the matched entities by using a deep learning model; determining answers to the questions according to the similarity; and inputting the answer into the machine translation model according to the target language selected by the user, and outputting the translated answer. According to the first-aid knowledge question-answering method based on the multi-modal knowledge graph and the system thereof, first-aid knowledge learning can be carried out online, the learning convenience and the first-aid effect of social citizens are improved, multi-language translation can be carried out, and the first-aid efficiency is improved.