123 results about "Knowledge question" patented technology

The invention relates to a conversation robot system. The system comprises a multimedia processing module, a multi-channel access module, a scene decision module, a daily conversation subsystem, a question-answer subsystem, an active conversation system, a task conversation subsystem and a state management module. According to the system, besides the abilities of daily conversation, knowledge questioning and answering and task conversation, a conversation robot further can actively trigger a series of specific conversation skills according to specific scenes, chat with a user, collect and verify answers of the user and execute corresponding service commands.

The invention provides a question pushing method and system, which are implemented based on pre-established user models, and the user models include at least two of the following models: an interest model, an attribute model, a behavior model and a relation model, wherein the interest model is established by exploiting questions asked by users and answers thereof, the attribute model is established based on user attributes, the behavior model is established by carrying out statistics on user behaviors, and the relation model is established based on relations between different users. The method comprises the following steps: A, carrying out text analysis on a question to be answered so as to extract question features; B, matching with the user models by using the extracted question features, and carrying out sequencing on users according to the matching degree of the question features with the users in each user model and a preset sequencing weight of each user model; and C, pushing the question to be answered to the front M users in the obtained sequence, wherein M is a preset positive integer. Through the method and system disclosed by the invention, the answer providing efficiency and quality of a knowledge questioning and answering system can be improved.

This invention relates to a knowledge question quick speed process system based on artificial intelligence including a user, a network station interaction system, a communication platform including an instant communication platform, a mobile communication platform and an E-mail platform, a knowledge library used in storing large numbers of knowledge data information, a user library used in storing user data information, an artificial intelligent server set between the network interaction system, the communication platform and the knowledge library, at least 4 engines: one for judgment, one for intelligent sort, one for searching for similar questions and one for summing up solutions and an information transmission engine set between the communication platform and the user library to be associated with the artificial intelligent server.

The invention relates to a Tibetan language entity knowledge information extraction method, which comprises the following steps that: Tibetan and Chinese comparable language material information is extracted from Tibetan and Chinese text language material information; entity equivalence pairs are extracted from the Tibetan and Chinese comparable language material information; the Tibetan and Chinese cross-language entity relationship is extracted from the entity equivalence pairs; a Tibetan language "entity-attribute-value" triad is extracted from the Tibetan and Chinese cross-language entity relationship; and the triad is stored into a Tibetan language entity knowledge semantic resource library. The Tibetan language entity knowledge information extraction method solves the problem of Tibetan language training language material deficiency to a certain degree, promotes the knowledge sharing among different languages, and provides support for the study in the fields of Tibetan and Chinese cross-language knowledge questions, information retrieval, machine translation and the like.

The invention discloses a multi-strategy fusion knowledge question and answer method and system, and the method comprises an offline part and an online part, the offline part is mainly used for data preparation and model training, and the online part is mainly used for system service, and the method comprises the steps: receiving a statement input by a user, and correcting a spelling error; Performing word segmentation and part-of-speech tagging on the statement input by the user; Extracting entity information in the user statement, and linking the entity to the knowledge graph node; Obtainingan executable query statement through a multi-strategy fusion semantic analysis step according to the result of the entity recognition and connection process; Executing a query on a knowledge graph by the executable query statement to obtain an answer, and then generating a corresponding natural language reply user according to the answer through a reply generation mode combined by multiple methods, so that the question and answer system is suitable for question query of general and domain knowledge graphs, the system robustness is improved, and meanwhile, the good interpretability and controllability are achieved.

The invention discloses an automatic question generation method based on deep learning. The method comprises the following steps: constructing a training set (articles, answers and questions), a verification set (articles, answers and questions) and a prediction set (articles and answers); creating Encoder-based construction by using deep learning framework tensorflow A sequence of decoders to a sequence neural network model; Carrying out word segmentation, word list making and word embedding operations on sentences in the data set; Wherein the data set comprises a training set, a verificationset and a prediction set; The training set is used for training the model, the verification set is used for detecting whether the currently trained model is over-fitted or not, and if over-fitting isachieved, stopping training; Otherwise, continuing training; And decoding the prediction set by using the trained model to generate a problem. The method is good in generalization effect and low in labor cost, the generated questions are better matched with articles and answers, and the method can be widely applied to the fields of intelligent teaching, intelligent questions and answers, knowledge question and answer games and the like.

The invention discloses a teaching method and system based on cross-media dynamic knowledge graph. The method comprises the following steps of constructing the cross-media dynamic knowledge graph; storing entity related information in the knowledge graph, and returning attribute values corresponding to entities through subject knowledge questions and answers; obtaining feedback information of students and knowledge points, calculating the knowledge point recommendation degree and the learning resource recommendation value score, and therefore, constructing a knowledge point recommendation listand a learning resource recommendation list and returning the lists to learners; constructing a course knowledge card; recommending friends, and recommending other users with similar learning progress and learning conditions to the current user. The teaching system comprises a data layer, a data analysis layer, an application layer and a user layer. The teaching method can be realized through a computer-readable storage medium. The problem that in the prior art, a teaching scheme cannot be formulated in a targeted mode according to learning characteristics is solved, the individualized teaching can be achieved, and the teaching level is effectively improved.

The invention relates to a domain event graph construction method and device fusing multiple types of facts and entity knowledge. The method comprises the following steps: performing cause relationship extraction and instance cause element extraction on a domain corpus to form an instance cause logic knowledge base; constructing an abstract concept knowledge base with hierarchy; performing entityword abstraction and predicate abstraction on instance events in the instance cause logic knowledge base by utilizing the abstract concept knowledge base to form an abstract cause graph; carrying outentity linking on instance events in the instance cause logic knowledge base by utilizing the entity knowledge graph and adopting an entity linking technology, and fusing event knowledge and entity knowledge to form a cause knowledge graph; and combining the abstract factorial map with the factorial knowledge map to form a domain event map. The advantages of static entity knowledge and action event knowledge can be integrated, the application range of knowledge questions and answers can be widened, and the domain event graph can be used as a common knowledge base to expand domain language resources.

A method and system for user authentication based on speech recognition and knowledge questions. The method comprises receiving a speech recognition result derived from ASR processing of a received utterance. A reference information element is obtained for the utterance. Then, the method determines at least one similarity metric indicative of a degree of similarity between the speech recognition result and the reference information element. A feature vector is determined from the at least one similarity metric, and a score is computed based on the elements of the feature vector. A classifier may be used to process the elements of the feature vector, with the classifier having been trained to tend to produce higher scores when processing training feature vectors derived from utterances known to convey associated reference information elements than when processing training feature vectors derived from utterances known not to convey said associated reference information elements.

The invention discloses a text interaction matching method and device for financial knowledge questions and answers, belongs to the field of natural language processing, and provides a method for mapping user questions to standard questions in order to accurately judge the matching degree of the financial knowledge questions of a user and the standard financial knowledge questions, and the methodcomprises the following steps: 1, constructing a question pair knowledge base; s2, constructing a question pair matching model training data set; s3, constructing a question pair matching model, comprising the following steps: S301, constructing a character mapping conversion table; s302, constructing an input layer; s303, constructing a character vector mapping layer; s304, constructing a text coding model of an attention mechanism; s305, constructing a text interaction matching layer; and S4, training a question pair matching model and question selections with the intention. (2) The devicecomprises a question pair knowledge base construction unit, a question pair matching model training data set generation unit, a question pair matching model construction unit and a question pair matching model training unit.

The invention discloses a question method, an answer method and an interactive knowledge question-answer system, belonging to the communication field. The method comprises the following steps: receiving a question request transferred by an instant communication client corresponding to a question user; inquiring an interactive knowledge question-answer strategy from an interactive knowledge question-answer management server according to a target user mark; displaying the question information to a target user who has the knowledge question-answer strategy which can accept the question information according to the instant communication client corresponding to the target user mark, wherein the question request carries the question information and the target user mark. The system comprises the instant communication client, an instant communication platform and the interactive knowledge question-answer management server. By questioning the target user chosen by the question user, the invention not only can enhance the accuracy rate of the answer but also satisfies the demands of users for personality and greatly improves the user experience.

The invention discloses a knowledge questioning-answering system based on ontology reasoning, and a working method of the knowledge questioning-answering system. The system comprises a language database management unit, a knowledge management unit, a knowledge reasoning unit, a comprehensive knowledge database unit and a knowledge questioning-answering interaction unit, wherein the language database management unit and the knowledge management unit are connected with each other and are respectively connected with the knowledge reasoning unit; the knowledge reasoning unit is connected with the comprehensive knowledge database unit; the comprehensive knowledge database unit is connected with the knowledge questioning-answering interaction unit. The working method of the system comprises the following steps: acquisition of web crawlers and acquisition of data of relational databases; keywords input of a user on a knowledge questioning-answering interface of the knowledge questioning-answering interaction unit for questioning; reasoning after questioning and answering guidance, query preprocessing, sentence model matching and model algorithm matching, generating of knowledge and result showing. According to the system and the working method of the system, a knowledge storage and organization standardization method is established by applying an ontology reasoning technology, therefore, the system is guaranteed to be simple and practical, and the accuracy of the system is improved.

The invention belongs to the technical field of artificial intelligence, and provides a method and device for identifying an encyclopedic knowledge question. The method for identifying the encyclopedic knowledge question includes the steps of identifying an entity in the question; identifying an attribute name of the entity in the question; identifying the sentence type of the question; inquiring information related to the entity or the attribute name in a graph database according to the sentence type of the question, processing the inquired information, and obtaining an answer of the question. By means of the method and device for identifying the encyclopedic knowledge question, the accuracy of answering the encyclopedic-knowledge-related question can be improved.

The invention discloses a method, a device and a system for establishing a knowledge questioning and answering sharing platform and a method for realizing a search engine. The method for establishing the knowledge questioning and answering sharing platform comprises the following steps: presetting a classification structure used for classifying knowledge questioning and answering information, wherein the sorting structure comprises at least one stage, and each stage comprises at least one unit classification; and dynamically generating a main-stage mark and a secondary-stage mark under the unit classification and establishing the upper and lower stage incidence relation between the main-stage mark and the secondary-stage mark according to the real-time analysis result of additional questioning information under the unit classification of the classification structure. The invention can flexibly respond hot questioning information and new questioning information and can also further correct the search range from a classification range to a mark range, thereby assisting users in precisely hitting a target.

The invention discloses a knowledge question-answer system established on basis of a Wiki semantic network, and an intelligent retrieval method and relates to the technical fields such as text semantic analysis, intelligent retrieval and machine learning. According to the invention, semi-structuralized text data grasped by vertical field Wiki in an oriented manner is used; knowledge elements are extracted automatically according to a pre-defined knowledge ontology; further, a deep learning algorithm can be used to train and establish an ontology semantic comprehension model; and thus, semantic comprehension of clustering relations and inference relations of the knowledge elements could be achieved. According to the invention, advantages of machine learning including automatic theme inference based on context semantic understanding and expert knowledge oriented optimization are synthesized; matched retrieval results matched through rational semantic association and expansion as well as inferred retrieval results are returned to a retrieval word input by a user; and in combination with definition of expert knowledge, accuracy and depth of the information retrieval can be increased effectively, and knowledge navigation can be achieved. The system and method are applicable to a medical-themed mapping knowledge domain, knowledge questioning and answering and a content recommendation system.

The invention discloses a knowledge question and answer retrieval method and device based on a tourism domain knowledge graph, and the method comprises the following steps: crawling tourism website information through employing a Python program, and constructing the tourism domain knowledge graph; enabling a user to input a natural language question related to travel; analyzing a natural languagequestion proposed by the user, performing word segmentation on the natural language, and performing part-of-speech tagging on each word; storing the knowledge graph in an entity-attribute-attribute value form, and linking the questions with the knowledge graph; and querying related triples from the knowledge graph according to the linked entities and attributes, and returning attribute values. Theinvention further discloses a device for realizing the method, terminal equipment and a computer readable storage medium, and convenient and effective tourism information query service can be provided for tourists.

The invention relates to a knowledge question answering system and method based on a same-root double-chain blockchain, and relates to the technical field of blockchain application. The system comprises a plurality of blockchain node formation networks used for network formation, wherein each blockchain node comprises a creation block; the creation block comprises a creation block timestamp, an initial Hash secret value and an initial kernel parameter; the rear end of the creation block establishes two data chains which are mutually in a parallel relationship and independently contain a plurality of blocks, wherein one data chain is a recording chain, and the other chain is a discussion chain; and the data in the discussion chain is screened and input into the recording chain. By use of the shareability, the traceability and the tamperability of a blockchain technology, a knowledge sharing solution of extensive participation, common evaluation, contribution exchange equity, fairness and public benefit can be realized, and the co-construction, sharing and co-inheritance knowledge question answering system is established.

The present invention relates to the field of online knowledge question / answer technology, and particularly to a method and an apparatus for establishing specialized knowledge question / answer system. The method for establishing a specialized knowledge question / answer system according to the present invention comprises: establishing classification information of a specialized knowledge question / answer system, wherein each piece of classification information comprises at least one question database and at least one expert information database; for each piece of classification information, storing pre-sorted questions into the question database of the classification information and storing pre-sorted expert information into the expert information database of the classification information; and when a user raises a question for one piece of classification information, using at least one expert corresponding to the expert information to answer the question. According to the method and apparatus for establishing a specialized knowledge question / answer system provided by the present invention, a specialized knowledge question / answer system for a specific industry can be created quickly, thereby saving a large amount of time and manpower and reducing a large amount of expense.

The invention provides a method and device for forming a question and a server end of a knowledge question-answering system, wherein the method comprises the steps of: A, providing a page including a preset question link for a user; B, when one question link is clicked, skipping to a question template page appointed by the clicked question link; C, obtaining key information input by the user at a to-be-added information part of the question template page; and D, generating a question by using the question template page input with the key information. Through simple clicking operation and key information input by the user, the invention can complete the question without inputting integral question information, and improves the convenience of realizing the knowledge question-answering service for a user terminal of a mobile phone inflexibly inputting characters.

The invention provides a method for constructing a knowledge question answering system in the field of elderly health, comprising the following steps: (1) establishing a data model in the field of elderly health; (2) knowledge acquisition in the field of elderly health; (3) the integration of knowledge in the field of elderly health; (4) the storage of knowledge in the field of elderly health; (5)The algorithm of automatic question answering system. The invention has the advantages of high accuracy and strong professionalism according to the medical health knowledge and health suggestion thatcan be provided for the retrieval user.

The invention discloses a heuristic voice interaction method and device. The method comprises the following steps: acquiring questioning requests input by a user; carrying out voiceprint recognition according to questioning voices; carrying out voice recognition according to the questioning voices; carrying out natural language understanding processing on questioning voice data; acquiring questiondata corresponding to the questioning voice data according to knowledge question graph; judging input times of same questioning voices input by the user according to user identification; generating corresponding guiding type rhetorical question data according to the questioning voice data when a user age group is matched with difficulty attributes of the questioning voice data; and receiving reply voices input by the user based on the guiding type rhetorical question data and judging whether the reply voices are correct or not. According to the heuristic voice interaction method and device disclosed by the invention, thinking of children is inspired and guided by adopting the heuristic voice interaction method, and the defect that intelligent equipment interacts with the user so as not tocarry out guidance education on thinking modes in the prior art is solved.

The invention discloses a knowledge-question matching method and device for an intelligent question-answering system. In the matching method, two similarity evaluation systems, namely the weight similarity evaluation system and the vector similarity evaluation system, are integrated so as to make up for system errors existing in a single similarity evaluation mode; moreover, according to the method and device, before the weight similarity and the vector similarity are calculated, word segmentation results are preprocessed, stop words in the word segmentation results are removed, and the unintended activation rate is reduced; besides, the weight of the knowledge words obtained after preprocessing is subjected to normalization, so that the threshold of the weight is equal to or larger than 0 and equal to or smaller than 1, the weight similarity calculating deviation caused by great weight difference due to different knowledge words is reduced, accordingly, the weights of the similarities of questions and alternative knowledge are more accurate, so that the accuracy of the total similarity is improved, and the knowledge-question matching accuracy of the intelligent question-answering system is further improved.

The invention discloses a knowledge graph-based financial domain knowledge question-answering method, which comprises the following steps: firstly, crawling financial data to establish a knowledge base, vectorizing entities through Word2vec, and calculating similarity among the entities by using a cosine similarity algorithm; based on a financial dictionary, adopting a maximum forward traversal method to traverse, cut and analyze questions raised by a user, then carrying out classification training on questions in the financial field through an RNN neural network, and carrying out data retrieval according to question categories; extracting words with higher similarity with the question keywords in the corpus by using a similarity algorithm to expand the vocabularies of the question sentences, and finally completing matching of database query sentences according to a template matching method; returning the queried result as an answer to the question to the user, and realizing visualization of the relationship between the financial entity attribute data and the entities through ECharts. According to the method disclosed in the invention, through the neural network training model andsimilarity comparison adaptive parameter adjustment, the accuracy of the question-answering system is effectively improved.

The invention relates to a knowledge question answering method, a knowledge question answering system and a computer-readable storage medium. The method comprises the following steps: a question answering request is received; the question answering request carries the active question text information; Determining a query language according to the source question text information and a preset question label template; Query the recommended entity group matching the query language from the dynamically updated knowledge management database, and generate knowledge map based on the recommended entity group; Sending knowledge map. The invention provides a knowledge question answering method, A knowledge question answer system and a computer-readable storage medium, The preset question label template can check the integrity of query language, improve the accuracy of query language, query language and knowledge management database together ensure the accuracy and real-time of recommended entitygroup, knowledge map form unified recommended entity group, to provide users with professional knowledge answers.

The invention relates to the technical field of big data processing and discloses an intelligent logistics knowledge question answering system. The system comprises a question answering interaction module and an expert assistant subsystem. The question answering interaction module is used for receiving questions from clients; the expert assistant subsystem comprises an expert management module and an expert information pushing module, the expert management module is used for expert portraying based on expert data, and the expert information pushing module is used for pushing questions according to expert portraits and transmitting answers given by experts to the clients through an original route. The invention further discloses an intelligent logistics knowledge question answering method. By big data analysis and data mining, question answering knowledge is summarized, the intelligent logistics knowledge question answering system is developed to realize intelligent question answering of industry knowledge, and the problem of failure of an existing question answering system in high-quality solving of questions asked by clients including employees in the field of logistics is solved.

The invention discloses a knowledge graph construction system and method, being characterized in that firstly, different ontology libraries are constructed for different data sources and data types; then all the ontology libraries are mapped into a global ontology library; then entity alignment and entity linking are conducted on the global ontology library, serving as a knowledge base, of all thesources, and the constructed multi-data fusion ideological and political knowledge graph is perfected and expanded. The knowledge graph construction system and method construct an ideological and political knowledge graph to complete multiple functions such as ideological and political knowledge system display, ideological and political knowledge questioning and answering and ideological and political knowledge reasoning, and can effectively overcome the defect that in the prior art, a traditional data management and display mode cannot enable students to well learn ideological and politicalknowledge and understand an ideological and political knowledge system.

The invention discloses a multi-round dialogue method and device in a knowledge question-answering system. The multi-round dialogue method comprises the following steps: acquiring a historical entityand a historical relationship of a current question sentence; screening out candidate entities according to the current questions; performing weighting processing on the features of the candidate entities to obtain a main entity; forming a candidate path according to the adjacent relationship between the main entity and the historical entity in the knowledge base and the adjacent entities; performing weighting processing on the features of the candidate paths to obtain a final path; obtaining an answer according to the final path and returning the answer to the user; and obtaining all entitiesand all relationships of the final path as historical entities and historical relationships of the next round of questions and answers. Through the method, the historical information of the previousquestion sentence is completely added into the current question and answer, so that the historical information acquisition accuracy is ensured, and a large amount of labor cost is avoided.

The invention provides a method and a device acquiring and searching for relevant knowledge information. The method comprises: analyzing a search log to mine a hot-spot search query with a doubt requirement; forming a question by using the mined query and issuing the question on a page of a knowledge question and answer platform; and acquiring relevant knowledge information about the question through the page of the knowledge question and answer platform. When a query input by a user is received, a page matching with a keyword of the query is searched. If the page matching with the keyword of the query is found on the knowledge question and answer platform, the page matching with the keyword of the query on the knowledge question and answer platform is carried in a search result of the query and returned to the user. Through the present invention, relevant knowledge information can be rapidly and accurately provided for the user, and the user does not need to log in to the knowledge question and answer platform to issue a question and acquire relevant knowledge information until the question is answered.

The invention discloses an entity alignment method based on weighted neighbor information coding, and the method specifically comprises the steps: 1), carrying out the preprocessing of data in two knowledge bases needing to be aligned, and extracting two knowledge base triples, entities and neighbor information thereof, and entities and type information thereof; 2) based on all currently discovered matching entity pairs, obtaining a vector representation corresponding to each entity through triple-based knowledge representation learning, weighted neighbor information coding and cross-knowledge-base entity-type graph embedding; 3) reasoning matching entity pairs in combination with three different vector representations of the entity; and 4) forming new training data by the discovered matching entity pairs and the priori aligned seed entity pairs, repeating the steps 1)-4) until the specified iteration times are reached, and outputting the discovered matching entity pairs. According tothe method, fewer entities appearing in the triad can be more accurately matched, and the method has a wide application prospect in the fields of knowledge fusion, knowledge questions and answers andthe like.

The invention discloses a somatic sensing interaction knowledge question answering system which is characterized in that the somatic sensing interaction knowledge question answering system comprises a control room; a main control computer is arranged in the control room; a projection screen is hung in the front of the control room; a somatic sensor is arranged above the projection screen; a somatic sensing identification region is formed on the ground over against the projection screen; two cameras are arranged above the somatic sensing identification region; a projector I and a projector II are also arranged above the somatic sensing identification region. The somatic sensing interaction knowledge question answering system adopts the simple principle and is convenient to use; knowledge questions are projected into the projection screen by the projector I, option buttons are projected into the projection identification region by the projector II, then a knowledge question answering participant can select correct answers in the projection identification region by movement of the body and the feet, and the main control computer judges whether the selections are right according to signals captured by the somatic sensor and the two cameras and displays a judgment result on the projection screen, and thus, the somatic sensing interaction knowledge question answering system has high practicality and entertainment.