244 results about "Question generation" patented technology

A system and method for detecting and processing fraud and credit abuse is disclosed. One embodiment of the present invention comprises a method for detecting and processing fraud and credit abuse. The method may comprise: receiving a telephone call from a caller concerning a credit account; identifying one or more potential fraud-related problems by searching the credit account data for conditions that match one or more predetermined qualifiers and quantifiers; presenting the caller with a series of questions and soliciting, from the caller, responses to the series of questions, wherein each question in the series is generated based on the one or more potential fraud-related problems and further based on the caller's responses to earlier questions in the series; and determining a fraud status associated with the credit account based on a computerized analysis of the solicited responses.

An authentication challenge system for performing secondary authentication for an account associated with an online store is described. In one embodiment, the authentication challenge system includes a question generation engine, which can derive a series of questions based upon activity associated with a user account of an online store; a network interface, which can transport the series of one or more questions derived by the question generation engine to authenticate the user to the online store; a confidence engine, which can determine a required confidence level for a successful authentication, and can compute a confidence score of the user identity; and a quality engine, which can adjust the question generation engine and the confidence engine based upon an analysis of question and answer metrics across multiple accounts of the online store. The online store can include digital media, such as music, movies, books or applications for electronic computing devices.

Disclosed herein is a transmission apparatus for distributing a content to a client, including: a question generation section configured to generate question information representative of a question regarding liking of a user of the client; and a transmission section configured to transmit the question information and provider side answer information in the form of a bit string representative of an answer set by a provider which provides the content to the question regarding the liking of the user to the client.

Disclosed herein is a transmission apparatus for distributing a content to a client, including a question generation section configured to generate question information representative of a question regarding liking of a user of the client, and a transmission section configured to transmit the question information and provider side answer information representative of an answer set by a provider which provides the content to the question regarding the liking of the user to the client.

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 question answering system includes a similar-question generation unit, a first search unit, a second search unit, and an answer selection unit. The similar-question generation unit selects a feature word from an input question to generate a transformational question in which the feature word is replaced with another word. The first search unit executes a first search process based on the transformational question. The second search unit selects a word included in a first search result acquired as an extension word and executes a second search process with using the selected extension word. The answer selection unit analyzes a correspondence relation among extension words included in a second search result, determines the feature word and a constructive part of an answer equivalent word in the second search result based on an analysis result, and selects a word determined to be an answer.

Method and apparatus for providing a personalized self-support service to a user of an online application coupled with an online community forum. Embodiments include obtaining a plurality of questions from the online community forum and obtaining historical user data. Embodiments further include identifying one or more part-of-speech words in the plurality of questions and generating a high-dimensional vector for each question of the plurality of questions based on a frequency of the one or more part-of-speech words. Embodiments further include identifying one or more user features of the plurality of users based on the historical user data and establishing, based on the historical user data, one or more statistical correlations between user features and part-of-speech words. Embodiments further include training a predictive model based on the one or more statistical correlations. Embodiments further include using the predictive model to predict to provide one or more relevant questions 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.

Disclosed herein is a transmission apparatus for distributing a content to a client, including: a question generation section configured to generate question information representative of a question regarding liking of a user of the client; and a transmission section configured to transmit the question information and provider side answer information in the form of a bit string representative of an answer set by a provider which provides the content to the question regarding the liking of the user to the client.

A system and method provide the ability to control an architecture, engineering, and construction (AEC) project workflow. AEC data regarding a quality of construction is obtained. A set of classifiers and machine learning models are obtained. The AEC data is augmented based on the set of classifiers and machine learning models. A risk metric is generated for one or more issues in the AEC data based on the augmented AEC data. The risk metric is interactively generated and presented on a display device. Work, project resourcing, and / or training are prioritized based on the risk metric.

The invention discloses a generation system and method for a Chinese similar problem. The system comprises a preprocessing module, a naming entity identification module, a problem classification module and a similar semantic problem generation module, wherein the preprocessing module is used for receiving a given problem and carrying out preprocessing, wherein the preprocessing comprises word segmentation, stop word removal, part-of-speech tagging for obtained segmented words; the naming entity identification module is used for identifying the given problem to obtain a naming entity to be identified; the problem classification module is used for classifying given problems according to semantics; the similar semantic problem generation module is used for generating a semantic similar problems by aiming at the given problems; and the similar semantic problem generation module comprises a similar semantic problem generation submodule based on a rule and a similar semantic problem generation submodule based on machine learning. By use of the system, the matching degree and the rationality of the generated problem question and an original problem can be effectively improved.

The invention provides a dialogue system construction method and a semantic controlled response method and device. A dialogue system comprises a first question-answer model and a second question-answer model. When a user inputs a question, firstly, an introducer associated with question semanteme is obtained from the question; then, the first question-answer model is used for generating a first response to the question, wherein the first response comprises partial response content of the dialogue system to the question; then, the second question-answer model is used for generating a second response to the question, wherein the second response comprises all responses of the dialogue system to the question. The introducer can control the output of a first response model and the output of a second response model, so that the semanteme of the first response and the semanteme of the second response are controlled. Therefore, by means of the semantic controlled response method, the semanticassociation degree of the responses generated for unknown questions and the questions is high; in addition, along with the change of the introducer, the responses generated for the unknown questions can also be changed, so that the diversity of the question responses is improved.

The invention provides a common sense question answering method based on question generation and a convolutional neural network. According to the method, content-problems are encoded into a vector sequence through a BERT language model; the vector sequence is sent to a problem generation module, and then is sent to a shared BERT language model; a triple composed of content, questions and answers passes through a BERT language model, an output content-question-answer coding sequence is transmitted to an answer selection module and classified through a convolutional neural network, and finally,an optimal option is selected as a candidate answer selected by the model according to scores obtained by the model.

The invention provides a computer test-question generating method and a system, relating to a method and a system which adopt computer information technology to realize automatic computer test-question generation and automatic answer generation. The method and the system can be used on a computer platform, such as a desktop PC, a notebook PC, a palm PC, a personal digital assistant device and a mobile communication device. The method and the system are characterized in that the inventor proposes a method model of subject description and computer automatic test-question generation. The test-question generation and test paper generation system formed by the method can automatically and changefully generate test questions, can automatically generate standard answers for objective questions and also can automatically correct and mark the test and generate reference answer or marking standard for subjective questions, thus effectively overcoming a plurality of defects of test-question generation by people and leading the test paper to be more standard and scientific so as to reflect the actual knowledge level of examinees objectively, really and roundly and to enhance the rationality, the authority, the safety and the equity of testing.

The invention discloses a network questionnaire generation method and a network questionnaire generation device, used for collecting more data in questions as few as possible, thus improving data recovery efficiency and a network resource utilization rate of a questionnaire. The network questionnaire method comprises the steps of receiving a response message of accepting a network questionnaire invitation submitted by user equipment; determining weights corresponding to selectable questions included in a question library according to a preset assessment parameter; selecting the preset quantity of selectable questions according to the weights in a descending order; generating a network questionnaire according to required questions included in the question library and the selected selectable questions; and returning the generated network questionnaire back to the user equipment.

The invention discloses an intelligent question generation method and device and a computer-readable storage medium, which are used for automatically generating questions for an input article, and outputting the same. The method comprises the steps of: S1, utilizing a seq2seq model for extraction of key contents on the article; S2, carrying out syntactic analysis and named-entity identification oneach sentence in the key contents to establish a corresponding grammar tree of each sentence; S3, utilizing the grammar tree for matching with question templates in a pre-established question template database, and if a matched question template exists, converting a sentence, which corresponds to a grammar tree, into a questioning sentence based on the matched question template, and thus generating a question; and S4, utilizing a neural network to sort the generated questions, and then outputting the same.

A system for creating a personalized, dynamic, multi-sport training plan for a user comprises a question generating module; a user input module which accepts user answers to questions generated by the question generating module and accepts other inputs relating to the user; and a processing module which collects and analyzes the answers to the questions and the inputs and thereafter, based at least in part on a calculation of an exponential moving average (“EMA”) of said answers, creates a training schedule for each sport, which is dynamically linked to all previous user inputs; wherein the question generating module, by way of an intelligent link to all previous user inputs and feedback direction from the processing module, creates a plurality of further questions for the user to enable modifications to be made to training schedule for each sport.

The embodiment of the invention provides a problem generation method and device and a computer readable storage medium. The problem generation method comprises the steps of identifying a text type ofa to-be-processed document according to a text structure; Selecting a generation model corresponding to the text type, wherein the generation model comprises at least one of an explicit question generation model, a structured and semi-structured question generation model and a natural language question generation model; And generating a problem for the to-be-processed document by using the selected generation model. According to the embodiment of the invention, aiming at the characteristics of different text types, the most suitable generation model is selected for the whole document or each part of text of the whole document, so that the problem generation accuracy is improved.

The invention discloses a neural network question generation method based on answers and answer position information, and a neural network model is from a sequence to a sequence and consists of an encoder and a decoder. Wherein the encoder model mainly learns characteristics in an original text, and the decoder is used for generating a question sentence corresponding to an answer by using the characteristics. The complete generation process of the question sentence is divided into three modes, namely a question word generation mode, a dictionary word generation mode and a copy mode. Wherein the question word generation mode uses an answer-based model, participates in model calculation through context vectors irrelevant to position information of answers in an original text, and generates question words corresponding to the answers from a limited question word dictionary; Wherein the question word generation mode adopts context vectors related to position information of answers in an original text for calculation; The probability distribution of the copy mode directly uses an attention distribution related to location information of the answer in the original text.

The embodiment of the invention discloses an FAQ question and answer pair automatic construction method and device, computer equipment and a storage medium. The method belongs to the technical field of artificial intelligence and natural language processing, and comprises the steps of obtaining a to-be-read document; analyzing the document to be read and segmenting the analyzed document to obtaina segmented document as a target document; according to the to-be-answered question and a preset screening model, screening out a paragraph matched with the to-be-answered question from the target document as a target paragraph; and generating an FAQ question and answer pair based on a preset reading understanding model according to the target paragraph and the to-be-answered question. According to the embodiment of the invention, the target paragraph matched with the to-be-answered question is screened out; the FAQ question-answer pair is generated according to the target paragraph and the to-be-answered question, and the non-target paragraph does not need to be processed, so that interference information brought by the non-target paragraph when the FAQ question-answer pair is generated is reduced to a certain extent, and the matching accuracy of the generated FAQ question-answer pair is higher.

The invention discloses a kind of test question generating system and method, which is used in data processing device. The test question generating system includes: database, researching module and adjusting module. The test question generating method includes: creates database which can contain at least several test question library, selection rule of test question and the adjusting rule for the rate of test question; searches the corresponding testing questions from the database according to the selection rule of test question; and researches the test question according with the conditions from database according to the answer result and the adjusting rule for the rate of test question. The test question generating system and method in invention can adjust the ratio of test question according to the answer result for testing question library, and provides test question according to the user answer.

The invention discloses a visual question and answer enhancement method based on graph convolution. The method comprises the following steps: the step 1, respectively extracting feature representations of a picture and a problem; the step 2, extracting a relationship between targets in a picture generated based on the problem; and the step 3, generating the picture with the problem information into graph, selecting a most relevant target for each vertex, generating a new feature representation for each vertex, and performing maximum pooling and classification on the graph. According to the method, high-level semantics are explored by utilizing the relationship between the GCN network and the object in the picture, and the method has great significance for a visual question-answering technology.

The invention is applicable to the technical field of a computer and provides an examination question pushing method and device. The method comprises the steps of receiving a examination question generation request input by a user, wherein the examination question generation request comprises an identification number of a video learning file, and the identification number is used for identifying the video learning file; obtaining a referred subject of the video learning file and matching corresponding examination questions in a preset examination question library according to the referred subject; and selecting the examination questions of the corresponding number for the referred subject from the matched examination questions and outputting the selected examination questions to the user. The examination question pushing automatic and intelligent degree is improved, the availability of the output examination questions is effectively improved, and the learning efficiency of the user is improved.

The embodiment of the invention belongs to the field of artificial intelligence, and relates to a problem generation model training method, a problem generation method and related equipment. The method comprises the following steps: pre-training an initial model to obtain a pre-trained language model, and adjusting a mask matrix in pre-training to realize three language models; obtaining questionand answer information including a question text and an answer text; extracting a key entity related to the question text from the answer text; setting a network in the pre-trained language model to adapt to Chinese text generation; inputting the key entity and the answer text into a pre-training language model to obtain a prediction question text; determining a prediction error according to the prediction problem text and the problem text; and adjusting the model according to the prediction error to obtain a problem generation model. Data annotation does not need to depend on manpower. In addition, the invention also relates to a blockchain technology, and the prediction problem text can be stored in the blockchain node.

Mechanisms are provided for dynamically selecting a subset of candidate answer sources for use by a question and answer (QA) system. The QA system receives an input question for which an answer is sought and generates one or more queries based on the input question. The QA system selects a subset of candidate answer sources, from a group of candidate answer sources, based on a ranked listing of candidate answer sources. The ranked listing of candidate answer sources is generated based on characteristics of previous candidate answers generated by the QA system for previously input questions. The QA system applies the one or more queries to the subset of candidate answer sources and generates at least one candidate answer for the input question based on results of applying the one or more queries to the subset of candidate answer sources.