101 results about "Question analysis" patented technology

The invention provides an implement method of an FAQ Chinese question answering system in the tourism field. The implement method comprises the steps of FAQ collection and organization, construction of a tourism field knowledge base, user query, question analysis, answer extraction and the like, thereby realizing the FAQ Chinese question answering system in the tourism field. The implement method constructs the tourism field knowledge base-field knowledge network with the help of the idea of ontology, utilizes the KDML language to define and describe the terms and the relations of the tourism field and realizes the integration of the tourism field knowledge network and a general knowledge base-knowledge network. The invention proposes a calculation method of similarity of tourism questions on the basis, the method realizes the calculation of the similarity of the questions with the help of the characteristics of the questions of the tourism field and the combination of morphological relations, the syntactic dependency relations and the field concept semantic relations in the questions, and the method further searches the related question from a candidate question set and extracts the answer of the question based on the similarity calculation. The test result of a Yunnan tourism FAQ question answering system proves that the method is feasible and has better effect.

A system for providing receipt inspection reporting (RIR) allows for entry, modification, searching and reporting of RIR data. The RIR data is stored in a database and accessible online to facilitate tracking and analysis of defects and other problems. Searches and custom reports also may be generated to provide RIR tracking and analysis of problems. Logging and tracking of defects allows for root cause analysis using RIR data stored in a database to improve the RIR resolution process.

The invention discloses an automatic question answering method and a system thereof. The automatic question answering method comprises the following steps: step A, the information of a question is acquired through the analysis of the question; step B, the query criterion is generated according to the analysis results of the question for retrieval by using the search engine in knowledge source, thus searching out the file collection relating to the query criterion; the file collection is divided into paragraph collections; step C, paragraph collections relating to the query criterion are retrieved in a centralized way from the paragraphs by using the paragraph retrieval method according to the file retrieval results; and the answer of the question is returned from the paragraph collections. The automatic question answering method and the system improve the accuracy of answers and the precision of returning correct results.

A method for implementing a question answering system based on a question-answer pair comprises the following steps: question analysis, question retrieval and answer selection. After a user submits aquestion expressed in natural language to the question answering system, the question answering system uses question vectorization, keyword extraction, keyword extension and other natural language processing techniques to understand the questioning intent of a user, and then uses the engine searching method in the question-answer pair database to obtain the question-related candidate question-answer pair set, and uses a matching algorithm and sorting algorithm to accurately select the best answer from the candidate sets. The invention obtains the function of the matching degree score between the question and the answer by learning by synthesizing different algorithms and models, the method of choosing the best answer from the candidate question-answer pairs is realized, and an answer selection method based on convolution neural network and Xgboost feature fusion is completed, which provides a better method for the answer selection of the question answering system.

The invention discloses a method for answering with natural language, which is used for instantly and effectively answering the questions of users. The method comprises the following steps of: (1) performing question analysis on a question input by a user; (2) answering the question by use of the question analysis result and the corpus of community questions and answers; (3) answering the question by use of the question analysis result and the encyclopedia corpus; and (4) verifying and selecting the answers returned by the steps (2) and (3), and finally returning the best answer to the user.

The invention discloses a method and equipment for constructing an intelligent question-answering system through a question generation data set. The method comprises the following steps: constructinga tourism domain knowledge graph; performing question analysis on natural language questions proposed by a user, performing word segmentation and word vector training on the questions, and in a word segmentation process, using a jaeba tool and adding a tourism domain dictionary set in advance; performing entity extraction on the natural language questions by using a Bert-BiLSTM+CRF model; matchingthe extracted entities with entities in a knowledge graph; if a matched entity exists in the knowledge graph, selecting the entity; if no matched entity exists in the knowledge graph, performing semantic similarity calculation, and selecting the closest entity; matching the selected entities and attributes with triples in a knowledge graph; and returning the corresponding attribute value as an answer to the question to be provided for the user. The invention also provides a device for realizing the method, a terminal and a readable storage medium. According to the invention, the information required by the user can be returned conveniently and accurately.

The invention discloses an automatic questioning and answering method and an automatic questioning and answering system, comprising the following steps: 1) a question analyzing step: separating the words of a natural question sentence and then identifying the words obtained after the words are separated by a question point/premise point identifying model so as to identify the question point and premise point of the question sentence; 2) an information retrieving step: querying an information resource library via the identified question point and premise point and extracting the query result. The information resource library is a structural information resource library. In the step 2), the question point in the question point/premise point data structure is used as a field for SQL query, and the premise point is used as a premise for SQL query. The automatic questioning and answering method and the automatic questioning and answering system enable people to understand the question better and provide correct answers by querying the structural information resource library via logic relationship of the question point and the premise point.

A Harmonized Tariff Schedule Classification system and method is disclosed using an integrated Trade Compliance System (TCS) that includes a decision tree for classifying products based on HTS codes. In one aspect, an analyst may access the TCS and select a commodity group appropriate for the product to be imported. Thereupon, the analyst may navigate through a decision tree which includes questions regarding the nature of the product (e.g., function, composition, etc.). The analyst finally arrives at a specific HTS code, which is assigned to the product. In other aspect, a company utilizing an internal classification system for its products creates an internal-to-commodity group map, thereby enabling an analyst to associate an internal classification with a relevant commodity group for classification purposes. In other aspect, the internal classifications may be mapped directly to an HTS code rather than to a commodity group.

Provided is a question answering method facing a specific field. The invention relates to the question answering method facing the specific field. The goal is to solve a problem that in the prior art, identification of entities such as personal name, geographic name and organization name is accurate, but identification of proper names in the specific field is inaccurate is inaccurate. The process comprises a first step of constructing a word list in a specific field, and utilizing the word list to segment input questions; a second step of performing question analysis on the input questions having been divided; a third step of performing semantic questions and character string layer extension on question components, and obtaining answer candidate words; a fourth step of performing answer candidate word-attribute retrieval in a knowledge base, and obtaining answer candidate paragraphs; and a fifth step of screening candidate answer sentences from the answer candidate paragraphs. The question answering method is used for question answering in the specific field.

The invention relates to the technical field of internet information processing, in particular to an associated data visualization display method. The method comprises: abstracting associated information of target information into sub-nodes of a corresponding level number, and adding directed edges among the nodes according to pointing relationships among the associated information; and constructing an associative relationship map with the directed edges among the nodes taking the target information as a starting point by using a visualization tool. According to the method, other information associated with the target information can be analyzed from massive associated information data, and an associative mode between an associative path and the nodes is visually displayed by adding the corresponding directed edges among the nodes; and the path is clear, visual and easy to understand, so that the manpower and time costs of users in related data arrangement and analysis are greatly reduced, a reference basis is provided for target information background analysis and mining and related question analysis and tracking, and the method has wide application prospects in the fields of information mining and information processing.

Embodiments of the invention provide a method for analyzing a question based on a knowledge base. The method comprises following steps: receiving a question input by a user; detecting phrases of the question and determining candidate phases; mapping the candidate phases in a resource item in the knowledge base; further determining the values of observation predicates and the possible question analysis space; performing uncertainty reasoning and calculating the confidence coefficient of each proposition set in the possible question analysis space according to the values of the observation predicates and values of implicit predicates; acquiring a set of true propositions in the proposition sets whose confidence coefficients meet preset conditions; and generating a formalized query statement according to the set of the true propositions. According to the embodiments, by means of the observation predicate and the implicit predicate, the uncertainty reasoning is performed, and a natural language question can be converted into a formalized query statement. Furthermore, the uncertainty reasoning method can be applied to the knowledge base of any field, the method can be widely applied to multiple fields, and conversion rules are not required to be manually configured for the knowledge bases.

The embodiment of the invention discloses a question-answering method and system based on multi-model fusion. The method comprises the following steps: constructing a knowledge base and a knowledge graph, conducting question analysis on input original questions in combination with the knowledge base and the knowledge graph, obtaining question analysis data, retrieving the question analysis data based on a matching method indicated by a fusion model, and obtaining question answers corresponding to the original questions. According to the method, higher efficiency can be achieved on the premisethat accuracy is guaranteed in the process of searching for the answers corresponding to the original questions through the fusion model, the deep learning model is increasingly robust along with increase of the data volume, the overall model understands semantics more accurately, and real intelligence can be injected to the robot.

The invention discloses a method and system for searching for a question and displaying an answer. The method comprises the steps of obtaining the test question, and obtaining test question analysis of the test question from a database, wherein the test question analysis comprises a vignette, a question solving idea and answer analysis; displaying the vignette and the question solving idea; determining that the displaying time of the vignette and the question solving idea is greater than or equal to a preset time threshold value, and displaying the answer analysis. According to the method and system for searching for the question and displaying the answer, the question analysis obtained from the database is categorized into the vignette, the question solving idea and the answer analysis, and the vignette, the question solving idea and the answer analysis are divided into two parts for display when the question analysis is displayed to a user, so that the user has to look through the vignette and the question solving idea carefully before looking at the answer analysis, and the user is guided to think about the test question independently and sufficiently before looking at the answer analysis.

The invention discloses a cardiovascular and cerebrovascular knowledge map questioning and answering method based on electronic medical records. The method comprises the following three parts: 1, constructing a crawler to extract encyclopedia and cardiovascular and cerebrovascular medical knowledge, fusing medical record data to construct a cardiovascular and cerebrovascular domain dictionary andcarrying out electronic medical record desensitization treatment; 2, constructing a knowledge graph based on an electronic medical record, namely realizing entity relationship extraction by using a language model, a bidirectional long-short-term memory network, a conditional random field and a convolutional neural network, screening entity relationships by using word2vec, and storing the entity relationships in Neo4j; and 3, constructing a question-answering method based on a traditional rule, constructing an ACTree and a question template by using the medical feature word set and the domain dictionary to perform question analysis and intention recognition, generating a Cypher query statement, and returning an answer. Based on the electronic medical record and the online knowledge base, cardiovascular and cerebrovascular knowledge graph construction and knowledge graph-based user complaint questioning and answering are realized.

The invention provides an information processing device and an information processing method, wherein the input of retrieval questions is received from the outside; the processing results of the retrieval questions are grouped; and then the result of grouping is output. The information processing device is provided with: a question analysis and retrieval item generation module (1300) for analyzing a retrieval question and generating a retrieval item; a document retrieval module (1400) for receiving the retrieval item generated by the question analysis and retrieval item generation module (1300) and performing document retrieval; a result extracting/filtering module (1500) for extracting the results of retrieval and filtering the results; and a result grouping module (1600) for grouping the filtered results.

The invention relates to a question and answer system implementation method based on Web. The method comprises the steps of S1, performing question analysis: analyzing questions raised by users, specifically, classifying the questions and extracting keywords; and meanwhile, vectorizing the questions, and retrieving existing question and answer pairs similar to the questions; S2, performing information retrieval: generating different query links according to the questions and different search engines, and then obtaining corresponding web pages by requesting the links; and S3, performing answerextraction: finding out optimal answers from web page fragments returned in the information retrieval step according to inquiry intentions of the users; and when the answers are extracted, extractinga plurality of possible candidate answers, and then obtaining the optimal answers by scoring and sorting the candidate answers. According to the method, the accuracy of answer extraction is improved from two aspects of candidate answer extraction and candidate answer sorting; and models and rules are used for optimizing the extraction process of the Chinese answers.

The invention relates to an examination question duplicate checking and judging method and device. The method comprises the following steps: acquiring the information of examination questions; matching the acquired information of the examination questions with the examination questions in a question bank; if the matching degree of the examination questions is lower than minimum repetition rate of the examination questions, submitting the examination questions to on-line manual answering process for treatment to acquire to-be-pushed examination question analysis; if the matching degree of the examination questions is greater than or equal to minimum repetition rate of the examination questions, confirming whether to submit the examination questions to manual duplicate judging process for treatment or not; if the examination questions are submitted to the manual duplicate judging process, pushing the corresponding examination question analysis in the question bank when the duplicate judging result is repetitive; submitting the examination questions to the on-line manual answering process for treatment to acquire to-be-pushed examination question analysis when the duplicate judging result is not repetitive; otherwise, pushing the corresponding examination question analysis in the question bank. Through the combination of two manners of an image recognition technology and manual duplicate judging, the problem that teachers answer repetitive examination questions and repetitive examination questions are accumulated in the question bank due to immaturity of current image recognition technologies is solved; burden of manual answering questions is reduced; the method and device can be applied to educational electronic products of learning machines, and the like.

The present invention relates to a social media question and answer service, and discloses a social media issue processing device and method. The method includes a question analyzing unit which analyzes a question type of an input question through a question pattern dictionary which is stored in advance; a social media analyzing unit which performs issue period recognition for the question, question type based analysis, question based summary creation, and question based reliability calculation; and a report creating unit which creates a summary in accordance with at least one of correlation between the question type and the question based summary, correlation between the issue period and the question type based analysis result, and correlation between the reliability and the question based summary.

The invention relates to a mathematical subject step-by-step demonstration method suitable and a and computer system suitable for self-adaptive learning, which comprises the following steps of: carrying out knowledge point matching processing conducting knowledge points matching and processing according to the received user's learning level information and pushing corresponding learning questions;monitoring whether or not receive the feedback information in real time and processing according to different feedback information, specifically: when receiving a first feedback information, carryingout an answer matching processing and generating and displaying a question analysis; when receiving a second feedback information, generating and displaying prompt information; when receiving a thirdfeedback information,displaying a problem solving step of the learning problem, and each time of receiving the third feedback, displaying only one solution step in sequence until all the solution steps are displayed; and when receiving a fourth feedback information, generating and displaying a reference answer information. Compared with the prior art, the invention has the advantages of effectively improving the learning efficiency of the user and the like.

The invention discloses an animation teaching method and system. The method comprises the following steps: pushing exercises; acquiring question types of the exercises; reading animation templates corresponding to the question types; using the animation templates to produce question analyzing animation corresponding to question analysis of the exercises. According to the invention, after the exercises are pushed to a user, in accordance with difference in presenting the animation required by question analysis of different types of exercises, through the acquisition of types of the exercises, the animation templates corresponding to the types of the exercises are utilized to generate the question analyzing animation corresponding to the question analysis of the exercises. For different types of exercises, only the corresponding animation templates need to be extracted so as to produce the question analyzing animation corresponding to the question analysis of the exercises in a simple and rapid manner, and exercises that belong to a same type only requires one corresponding template which makes the production of question analyzing animation simple and rapid and low in manufacturing cost.

The invention relates to a self-adaptive Web honeypot system based on an intelligent question and answer technology. The self-adaptive Web honeypot system is used for deep complete attack chain capture. An intelligent question-answering technology is utilized, the system is composed of three main algorithm models, question analysis is carried out on attacker messages based on an LSTM model of an attention mechanism, and key attack vectors in the attacker messages are extracted; dynamically generating deception feedback according to the attack vector based on a sensitive information counterfeiting model of the SeqGAN; the Web application learning model based on external observation uses an external observation mode to self-adaptively learn application features. According to the honeypot system, context semantics are used for replacing traditional honeypot spoofing, and generative intelligent question and answer response can be carried out.

The present disclosure relates to an apparatus and method of allocating a question according to a question type or question feature. A question allocating apparatus for the same may include a question analysis unit generating at least one of question type information and question feature information of a current question; and a question allocating unit determining an answer generating unit suitable for the current questions among a plurality of answer generating units based on at least one of the question type information, and the question feature information, and allocating the current question to at least one answer generating including the determined answer generating unit.