126 results about "Knowledge retrieval" patented technology

The present invention is directed to an integrated implementation framework and resulting medium for knowledge retrieval, management, delivery and presentation. The system includes a first server component that is responsible for adding and maintaining domain-specific semantic information and a second server component that hosts semantic and other knowledge for use by the first server component that work together to provide context and time-sensitive semantic information retrieval services to clients operating a presentation platform via a communication medium. Within the system, all objects or events in a given hierarchy are active Agents semantically related to each other and representing queries (comprised of underlying action code) that return data objects for presentation to the client according to a predetermined and customizable theme or “Skin.” This system provides various means for the client to customize and “blend” Agents and the underlying related queries to optimize the presentation of the resulting information.

A system for generating and retrieving relevant electronic information required by a user initiating an electronic search on the system. The system comprise a user-interactive search engine and a knowledge database, which stores knowledge information that is formatted. Additionally, the system includes a plurality of functional software modules that enables a user to complete an interactive search and find a solution to a task based on entered context information and keywords. A list of keywords are displayed to the user and the user selects those keywords that are relevant to the solution desired. The search engine looks for the articles containing the identified keywords. If no article is found with the search terms, the search is expanded to the Internet. The user may then modify the information returned from the Internet, format the information and save the information as a new recipe.

The invention discloses an enhanced question answering interaction system and method for a universal mapping knowledge domain on the basis of deep learning. The system comprises an expanded mapping knowledge domain hybrid question answering module, a knowledge base question generation module, a web interaction module, a mapping knowledge domain question answering module and a knowledge depth reasoning module, wherein the expanded mapping knowledge domain hybrid question answering module is used for obtaining an expanded mapping knowledge domain; the knowledge base question generation module independently generates answers corresponding to different questions to enable generate a plurality of question-answer pairs; the web interaction interface is used for obtaining a user question; the mapping knowledge domain question answering module obtains the type of an answer corresponding to the user question, and obtains a numerical value vector corresponding to the user question; and the knowledge depth reasoning module is used for carrying out knowledge retrieval and reasoning on the type of the answer corresponding to the user question and the numerical value vector corresponding to theuser question, and obtaining the target answer of the user question according to retrieval and reasoning results and a plurality of question-answer pairs. By use of the system, the performance, the operability, the semantic comprehension analysis ability, the comprehensive question answering expansion ability and the universal technology sharing ability of the question answering system can be effectively improved, and answer generation accuracy is improved.

A semantically integrated knowledge retrieval, management, delivery and presentation system.

The present invention describes a method and system for informing a customer service agent of the details of a service user's interaction with a voice-based knowledge retrieval system. More particularly the invention is directed to a method of informing a customer service agent of details of a user's interaction with a voice retrieval system including the steps of providing a user of a voice retrieval system with a list of one or more information items, playing the one or more information items to the user in response to one or more user inputs, storing a transcript of the user's interaction with the one or more information items, transferring the user from the voice retrieval system to a customer service agent in response to the one or more user inputs; and providing the customer service agent with the transcript of the user's interaction with the one or more information items.

A semantically integrated knowledge retrieval, management, delivery and presentation system.

The invention discloses a man-machine interaction question-answering method and system based on complex intention intelligent recognition, and the method comprises the steps: obtaining an original question sentence of a user, carrying out the sentence segmentation and part-of-speech tagging, and obtaining the part-of-speech information of each component word of the question sentence; performing dependency syntax analysis on the question sentence to obtain a dependency syntax tree; carrying out industry entity identification to obtain industry entities and the number, and extracting a core dependency tree to simplify questions; carrying out industry question relation classification on the questions, carrying out Chinese multi-intention question rewriting, and then carrying out knowledge retrieval on the questions; and selecting and generating answers for knowledge retrieval results, and returning the answers to the user. According to the method and system, multi-intention complex questions can be effectively simplified in any industrial scene, the intention of the user can be accurately understood, the industrial knowledge can be more naturally fed back to the user, the user can more accurately and quickly obtain the required industrial knowledge, the user experience is improved, and the method and system are particularly suitable for man-machine interaction intelligent questions and answers in the medical industry.

The invention relates to a historic building conservation technical information management system and a method based on domain knowledge, which aim to solve the problems that electronic data are numerous but knowledge is little in the historic building conservation process. The system comprises six parts: a data management unit, a historic building conservation knowledge base, a historic building conservation database, a historic building conservation knowledge management platform, an outside knowledge service unit, a data index unit and the like. The method comprises the following steps that: a knowledge engineer constructs a historic building conservation domain knowledge base; a historic building conservation worker uploads structured data and unstructured data to the historic building conservation database in different ways according to the domain knowledge classification and manages the data; and historic building conservation knowledge retrieval services based on WebService are provided for the public by adopting a mode of the free combination of elementary knowledge services. The invention can effectively utilize the knowledge of the historic building conservation field to increase the use efficiency of large amount of existing historic building conservation technical relevant data and information, thereby creating generous economic benefits for the industry.

A semantically integrated knowledge retrieval, management, delivery and presentation system.

The invention discloses a knowledge retrieving method. High retrieval matching needs comprehensive representation of structure and semantic meaning of knowledge; the similarity is computed with the combination of the semantic distance and the semantic attribute; therefore, a body-based knowledge representation process, a body-based knowledge retrieval model and a body-based knowledge retrieval algorithm are provided. According to the knowledge retrieving method, the provided body-based knowledge retrieval algorithm is matched and applied to the provided knowledge retrieval model, and the similarity computation is performed by aiming to the semantic distance of a concept and the concept attribute, so that the obtained result is closer to user demands, and the retrieving efficiency and the knowledge reusability are improved.

The invention belongs to the technical field of clinical diagnosis, and discloses a clinical diagnosis aid decision-making system and a medical knowledge graph accumulation method. The system comprises a vital sign acquisition module, a medical image acquisition module, a central control module, a diagnosis analysis module, a treatment scheme recommendation module, a medical knowledge retrieval module, an atlas creation module, a data storage module and a display module. According to the invention, the model is trained by using historical data of various disease types through the diagnosis analysis module, so the effect of pre-diagnosing a plurality of disease types by only one model can be achieved, the system is very suitable for clinical diagnosis management and maintenance, and the diagnosis analysis result is accurate; meanwhile, the medical knowledge graph is created through the graph creation module, and the medical data is managed through the medical knowledge graph, so when the medical data is used, the medical data can be extracted through the medical knowledge graph, and the convenience of using the medical data can be improved to a certain extent.

The invention relates to a use method of a combat knowledge system based on knowledge engineering and a combat decision auxiliary method. The use method comprises the following steps: mining a new rule from battlefield experiment data by using a data mining engine; carrying out object and attribute extraction on the new rule and the existing rule through a rule engine so as to construct a combat rule base; performing rule reasoning calling on the combat rule base by utilizing a Rete algorithm through the rule engine to generate a reasoning result; forming a knowledge ontology library from the acquired battlefield experiment data by three elements of entities, relationships and attributes through a knowledge engine; and performing knowledge retrieval and knowledge recommendation on the multi-party information by using the knowledge engine according to the knowledge ontology library and a reasoning result generated by the rule engine so as to generate combat decision support. According to the invention, deeper analysis, research and judgment work is carried out on the combat factor information, so that weapons are associated with each piece of intelligence information, the data of informatization combat are fused and standardized, and the command efficiency is improved.

The invention discloses a 95598 knowledge base system. The 95598 knowledge base system comprises a knowledge sorting module, a knowledge consulting module, a knowledge consulting query module, a knowledge collecting module, a knowledge collecting query module, a knowledge maintaining module, a knowledge retrieving module and an index re-establishing module. The knowledge consulting module is used for generating work orders of a corresponding power supply company unit according to the power supply company unit selected by a user, issuing the work orders to the corresponding unit, and configuring a time limit. The knowledge sorting module maintains and displays knowledge in a tree catalog structure, and knowledge is divided into services of new addition, updating and the like of knowledge catalogs and catalog hierarchical relationships according to services. The knowledge collecting module is used for screening and perfecting knowledge consulting information and typing the information in the system according to knowledge types and the conditions of the applicable unit. A knowledge element neutral network is established, a knowledge structure professionally divided can be provided for related personnel, and the knowledge retrieval effective rate and accuracy are improved.

The disclosure generally relates to knowledge retrieval using a knowledgebase storing general and/or expert knowledge. In particular, the disclosure relates to using complex retrieval techniques to implement an enhanced troubleshooting system that provides relevant information. Aspects of the disclosure retrieve relevant documents to assist in troubleshooting by reasoning with stored representations about the faulty system and its operating environment. After receiving a description of the symptoms and/or other information related to the problem, the system may recommend textual and/or non-textual documents with relevant information for identifying the cause of the problem and restoring operation.

The invention relates to an engineering technical and economic knowledge retrieval platform based on a knowledge graph and method thereof. The platform comprises a technical and economic knowledge library, a semantic processing unit, and an interaction unit, and the technical and economic knowledge library and the interaction unit are connected with the semantic processing unit. The technical andeconomic knowledge library is used for storing project management knowledge, technical and economic knowledge, cost knowledge, engineering technology knowledge, law and regulation knowledge and actualcases; the semantic processing unit generates a corresponding retrieval formula according to a retrieval statement input by a user so as to retrieve from the technical and economic ontology knowledgebase to obtain a related knowledge graph; and the interaction unit is used for a user to carry out input operation of retrieval statements, and visually presenting the related knowledge graph obtained by retrieval to the user. Compared with the prior art, the technical and economic knowledge library is constructed, semantic retrieval is combined, a user can accurately and rapidly retrieve neededknowledge, and engineering professional cooperation efficiency can be improved.

The present invention discloses a knowledge search method and apparatus embedded in a search engine and a search engine. The method comprises: acquiring search input information input by a user; determining whether the search engine is in a learning mode; if the search engine is in the learning mode, acquiring an entity in the search input information according to the search input information; and according to the entity, performing knowledge searching to acquire a first class search result and first class relevant result information, and providing the first class search result and the first class relevant result information to the user. According to the method, by setting the learning mode in the search engine, utilizing the features of the search engine and perfectly fusing online learning and the search engine, students are helped to search knowledge, the students can be avoided being in contact with unhealthy information when using the search engine and the students can freely search knowledge in a pure and closed cyberspace.

Systems and methods for pre-training and fine-tuning of neural-network-based language models are disclosed in which a neural-network-based textual knowledge retriever is trained along with the language model. In some examples, the knowledge retriever obtains documents from an unlabeled pre-training corpus, generates its own training tasks, and learns to retrieve documents relevant to those tasks. In some examples, the knowledge retriever is further refined using supervised open-QA questions. The framework of the present technology provides models that can intelligently retrieve helpful information from a large unlabeled corpus, rather than requiring all potentially relevant information to be stored implicitly in the parameters of the neural network. This framework may thus reduce the storage space and complexity of the neural network, and also enable the model to more effectively handle new tasks that may be different than those on which it was pre-trained.