24 results about "Question selection" patented technology

A system and method for generating a human expert-like fully interactive interview via an artificial intelligence agent system is provided. The method may include the steps of: analyzing a job post to extract skill and behavior traits of the job post via a job benchmark analysis module running on a computing platform; analyzing a candidate resume of a candidate to extract skills and work proof via a candidate resume analysis module running on the computing platform; curating a plurality of questions and an interview structure based on data of the candidate resume and the extracted skill and behavior traits of the job post via a question selector and plan generator module running on the computing platform; generating the artificial intelligence agent on a client device via an interactive interview agent module running on the computing platform; and conducting an interview of the candidate via the artificial intelligence agent.

The present teaching relates to a Q&A framework for quality controlling of automatically generated answers via AI. Based on a question on a subject matter received from a user, at least one machine expert is selected to answer the question based on past performances of multiple machine experts for generating respective candidate answers to the question. Each selected machine expert creates a candidate answer based on a reference from a source. Quality assessment is performed with respect to each candidate answer from a respective machine expert and is relied on to determine a candidate answer as the answer to the question. Such determined answer is provided to the user as a response to the question.

The invention relates to a casting field question and answer data enhancement method based on a large language model, electronic equipment and a storage medium. The method comprises the following steps: constructing a comprehensive knowledge base of the casting field by gathering professional literatures from the casting field; generating a first number of initial questions from the comprehensive knowledge base based on one or more large language models in combination with an advanced prompt engineering strategy; performing semantic duplicate removal processing on the first number of initial questions to obtain a second number of unique and diversified questions; inputting the second number of questions into a plurality of different large language models so as to obtain a plurality of candidate answers for each question; performing systematic evaluation on the plurality of candidate answers of each question by using an evaluation large language model with high evaluation ability, and selecting an optimal answer for each question according to an evaluation result to form a second number of question and answer pairs; and performing diversification and data enhancement on the second number of question and answer pairs.

The invention relates to the technical field of psychological assessment, and particularly discloses a dynamic psychological assessment question selection method and system based on a factor integrity principle, and the method comprises the steps: creating a session, collecting the psychological attention field of a user, mapping the psychological attention field of the user into a corresponding psychological factor, carrying out the duplicate removal, and generating a target psychological factor set; all questions corresponding to each psychological factor are retrieved and loaded from the database, preset answering time and actual answering time are obtained according to the number of the questions and preset average answering time of each question, psychological credibility indexes of the user are analyzed, answers to each question of the user and question fields are obtained, and an answering data set is generated; whether the user completes all target questions or not is verified through the score integrity verification module, score calculation is performed after integrity verification is passed, and the priority of the psychological attention field of the user is determined in combination with the psychological credibility index, so that the reliability of the evaluation data is ensured, and the user experience and the practical value of the evaluation result are also improved.

The invention relates to the field of safety training, in particular to a safety talent training resource sharing system and method based on cloud computing, and the method comprises the steps: determining a test question obtaining mode according to the number of historical training times and effective duration corresponding to a generation request; the test question obtaining mode is that when test questions are obtained based on the calibrated training test questions, the calibrated training test questions are selected based on the label support proportion determination basis processing evaluation value or the label subordinate learning degree; according to a position change reference value corresponding to a first-class standard selection box in a test question video corresponding to the calibrated training test question, determining that the video feature difference degree is a second-class standard selection box influence quantity difference value or a first-class standard selection box surrounding area difference value; according to the video feature difference degree corresponding to the to-be-selected test questions and the calibrated training test questions, primary training is selected; when the test question obtaining mode is test question obtaining based on the rotation number, the current training test question is selected according to the rotation number corresponding to the test question to be selected; the selection precision of the training test questions is improved.

There is provided a computer implemented method of dynamic generation of audio content of a panel including questions asked by a moderator and responses by responders, comprising: accessing user interest(s) of a target user, accessing a social network graph that includes the target user, selecting questions correlated with the user interest(s) of the target user, selecting responses to questions by responders, wherein the responders are linked to the target user in the social network graph, wherein the responders are associated with user interests correlated with the user interest(s) of the target user, dynamically assembling audio content(s) from voice records and / or from audio recordings generating by converting text to voice, each audio content including a sub-set of the selected questions and a sub-set of the responses, and providing dynamically assembled audio content(s) for selection thereof for playing on a speaker.

The application relates to a question and answer method and system based on a text-knowledge expansion graph collaborative reasoning network, which comprises the following steps: step A: collecting user questions and answer records in a question and answer platform, and labeling the true labels of each question-answer pair to build a training set DS; step B: using the training set DS and a knowledge graph to train a deep learning network model M based on the text-knowledge expansion graph collaborative reasoning network, so as to analyze a given question through the model M and give a corresponding answer; and step C: inputting a user question into the trained deep learning network model M to output a matched answer. The method and system are favorable for improving the accuracy of selecting answers for given questions.

The invention belongs to the technical field of deep learning, reinforcement learning, brain-computer interfaces, adaptive learning, computational psychology and electroencephalogram signal processing, and relates to an adaptive learning system and method based on deep reinforcement learning and electroencephalogram analysis. The cognitive load score is accurately mapped into a cognitive load score; the individualized multi-dimensional base line calibration module is used for calculating an exclusive optimal cardiac flow cognitive load value of the user and a cognitive inertia coefficient and a cognitive sensitivity coefficient for representing cognitive dynamic characteristics of the user; and the question selection module based on deep reinforcement learning selects the optimal next question according to the cognitive load score of the user, the individualized dynamic model and the available question bank state, and the learning target is to maximize long-term accumulated rewards. According to the method, how the user enters and leaves different states is concerned, and personalized learning process adaptation from static state to dynamic state is realized.

The application provides a question adaptation method and device, wherein the question adaptation method comprises the following steps: obtaining question selection condition information of a target user, and selecting at least one candidate question from a question library based on the question selection condition information; obtaining learning condition information of the target user and candidate question information of each candidate question, and determining a target matching degree of the candidate question information of each candidate question and the learning condition information, wherein the learning condition information is generated based on historical answering information of the target user; and adapting each candidate question according to each target matching degree, to obtain a title question corresponding to each candidate question. The accuracy of the generated title question and the degree of conformity with the actual situation of the user are improved. The same question can be avoided from being generated for users with different learning conditions in the case that the question selection conditions of different users are the same, so that the generated question meets the individualized needs of the user.

The present application relates to the technical field of computer application, and provides a computer adaptive test method and system, an electronic device and a storage medium, which first determines the current ability information of a target subject for a target subject; then inputs the historical answering information and the current ability information of the target subject for the target subject into a question selection model to obtain test resources output by the question selection model. When the basic model is trained to obtain the question selection model, a first loss function is introduced to ensure that the knowledge coverage rate of the test resources output by the question selection model is overall for the target subject, and a second loss function is introduced to ensure that the knowledge point correlation of the test resources output by the question selection model is overall small, so that the credibility of the test resources can be improved, the target subject can be comprehensively tested, the test efficiency can be improved, the subsequent test result is more accurate, and accurate recommendation of learning resources can be realized.

The invention relates to the technical field of computers, and discloses a correction method and device for adding character phonetic notation, electronic equipment and a storage medium, and the method provided by the invention comprises the following steps: obtaining a to-be-corrected picture; identifying the to-be-corrected picture to obtain each small question in the Chinese character added phonetic notation question, the added Chinese character of each small question and the answer result of the added Chinese character; identifying the added character of each small question and the answering result of the added character to obtain a target added character and a target answering phonetic notation; determining a target phonetic notation corresponding to the target point-added character based on a corresponding relationship between the character and the phonetic notation; and based on a comparison result of the target phonetic notation and the target answering phonetic notation, determining a correction result of the Chinese character adding phonetic notation question. According to the method, rules do not need to be used for question cutting, the operation efficiency is high, question positioning is more accurate, a question bank does not need to be prepared in advance, and the efficiency of adding character phonetic notation correction can be improved.

An object of the present disclosure is to improve a technique of presenting a portfolio of asset management according to a subject. An information processing apparatus includes a question selection unit that selects a question to be presented next from among unpresented questions included in a question group based on an answer to a question selected from the question group for determining a portfolio of asset management and presented to a subject, and a presentation control unit that presents, to the subject, a portfolio according to an answer of the subject to each of the selected and presented questions. According to this information processing apparatus, it is possible to support the decision making of the subject for asset management.

Provided is a technique for recommending a question suitable for use in future study to a learner. Included are a correct answer rate prediction unit that estimates a predicted correct answer rate of a question by using a learned neural network from an input vector obtained from a test result of a learner of K questions or by using a decoder of a learned neural network from a latent variable vector obtained from an input vector obtained from the test result of the learner of the K questions, and a question selection unit that selects a question to be recommended to the learner from among selection candidate questions by using a reference predicted correct answer rate that is a predicted correct answer rate to be a reference for recommending a question to be solved and predicted correct answer rates of the selection candidate questions among the K questions.

Provided is a technique for recommending a question suitable for use in future study to a learner. Included are, setting a first latent variable vector as a latent variable vector obtained from an input vector obtained from test results of a learner of K questions using an encoder of a learned neural network, a first decoder unit that calculates a first predicted correct answer rate vector from the first latent variable vector using a decoder of the learned neural network, a latent variable vector generation unit that generates a second latent variable vector by a predetermined method from the first latent variable vector, a second decoder unit that calculates a second predicted correct answer rate vector from the second latent variable vector using the decoder of the learned neural network, and a question selection unit that preferentially selects an element having a larger value from elements of a vector obtained by subtracting the first predicted correct answer rate vector from the second predicted correct answer rate vector, and obtains a question corresponding to the index of the selected element as a question to be recommended to the learner.

To provide review by which facility-related knowledge can be acquired in an early stage.SOLUTION: The control device 16 of the facility-related knowledge acquisition system 10 includes the representative action recognition section 19, which recognizes an answering action of the representative 1 for a problem displayed on the first display device 11 in the learning area 4 on the basis of the digital apparatus 13, and the most frequent person action recognition section 20, which recognizes an answering action performed by each individual in a group including the representative 1 and the companion 2 for the problem and recognizes a most frequent person answering action, which is an answering action of a majority in the group 3. The device has a correct / incorrect determination part 21 for storing the result of determination in a storage device 15, and a question selection part 18 for displaying a question whose result of determination of the maximum number of persons answering operation is incorrect on a second display device 14 of a review area 5.SELECTED DRAWING: Figure 1

The application discloses a kind of multi-modal online test question recommendation method, system and medium based on end cloud cooperation.The method obtains the test record of user, question attribute and expression information in the process of answering by obtaining the device end, carries out cognitive diagnosis to obtain user knowledge radar chart diagnosis result in the device end, and realizes adaptive test question recommendation according to diagnosis result.To solve the limitation of device end recommendation question bank, cloud end question selection strategy and device end question selection strategy are designed, and a variety of questions can be selected from the angle of question type and quality according to user demand, which are downloaded to the user by the cloud, and the redundant questions in the device end are removed.The method of the application realizes adaptive examination under the cooperation of end and cloud, accurately diagnoses by fusing user expression information, and realizes personalized test question recommendation according to diagnosis result, solves the problem that traditional method cannot be applied to large-scale question bank, and has the advantages of good recommendation effect, accurate diagnosis and the like.

A textbook text question and answer method and system based on multi-level attention, the method comprising: inputting the question text and the corresponding chapter context paragraph into the first attention model after tokenization and coding, performing self-attention calculation and pooling within the sentence to obtain the sentence representation vector; calculating the cosine similarity of the question sentence representation vector and the representation vector of all context paragraph sentences, retaining only the representation vector corresponding to the sentence with the maximum similarity of each paragraph as the context representation vector of each paragraph corresponding to the question; inputting the question and the context representation vector of each paragraph corresponding to the question into the second attention model, performing self-attention calculation and pooling between the paragraphs and the question to obtain the answer representation vector corresponding to the question as the input of the classifier; outputting the answer options by the classifier, and obtaining the context paragraph of the answer text corresponding to the chapter. The application can select more accurate answer options for textbook text questions.

This application provides a method and system for randomly generating exam papers. The method includes: obtaining exam paper generation requirements; randomly selecting and matching questions from a target exam paper according to a preset two-dimensional array and the exam paper generation requirements to obtain a proposed exam paper question set; wherein, the preset two-dimensional array is generated based on a preset question bank and is used to store all question information in the preset question bank; the proposed exam paper question set and a preset exam paper template are used to assemble the target exam paper, and the target exam paper is output. This invention utilizes a preset two-dimensional array to store question information from a question bank, greatly improving exam paper generation efficiency while ensuring the randomness of question selection.

The application discloses an intelligent question and answer method based on multi-view answer representation, comprising the following steps: 1. constructing a question and answer data and preprocessing; 2. constructing a text coding module, obtaining a word vector matrix and a sentence vector of the text; 3. constructing a responder professional ability representation module, obtaining a representation of the professional ability of a responder to a question; 4. constructing an LSTM module based on an attention mechanism, obtaining information interaction of answers under the same question; 5. constructing an answer representation module based on a question description text sentence vector, weighting word vectors of an answer body by using vector representation of a question description text; 6. constructing an answer representation module based on a question and answer work graph, obtaining answer representation based on a concept graph; 7. constructing an answer representation fusion module, obtaining multi-view-based answer representation; and 8. constructing a prediction module, predicting a matching score of a question and an answer. The application can select the best answer for a question.

The present invention discloses a multi-strategy knowledge graph question-answering method. The method includes classifying question types according to question content, identifying question entities using an entity recognition model, linking question entities to graph nodes using fuzzy queries, converting the required search content into Cypher statements based on the question, selecting different query strategies for different question types, obtaining triples corresponding to the question, matching similar graph nodes to question entities using fuzzy queries, matching relevant nodes and edges to question relationships using the BERT model, and selecting the node or edge most similar to the question using a semantic similarity model, and outputting the node or edge as the answer to the question. The present invention provides an attribute query retrieval method for static questions and a temporal reasoning or statistical query retrieval method for dynamic questions. Different question-answering strategies are proposed for different question types, thereby enabling answer retrieval for dynamic questions.

The invention relates to the technical field of answering systems, in particular to an ideological and political answering system and method based on a mobile terminal. The system comprises a user login management unit, the user login management unit carries out user authentication based on Hash encryption, and a user inputs a user name and a password through a mobile terminal to log in an ideological and political answering system; the topic selection management unit manages and maintains topics in a question bank through a question bank management module; the judgment and feedback unit is responsible for judging and analyzing the answer result of the user and sending the judgment and analysis result to the topic selection management unit for an intelligent recommendation module so as to optimize a topic recommendation mechanism; and the user interaction unit is used for providing interaction input between a user and each unit. An autonomous incremental learning mechanism is adopted, learning efficiency and a time decay factor are introduced to adjust a learning progress updating algorithm, the actual learning state of a user is accurately reflected, and a question sorting set is dynamically adjusted according to the latest learning progress.

To improve a technique for presenting a portfolio of asset management corresponding to an object person.SOLUTION: An information processing device includes a question selection unit that selects a question to be presented next from unpresented questions included in a group of questions based on an answer to a question selected from the group of questions for determining a portfolio of asset management and presented to a subject, and a presentation control unit that presents a portfolio according to the answer to the selected and presented question to the subject. In addition, according to the information processing apparatus, it is possible to support decision-making of a subject who manages assets.SELECTED DRAWING: Figure 1

The application discloses an education-based common error question image generation method. It relates to the technical field of image processing. The education-based common error question image generation method comprises the following steps: screening common error questions for educating students from an error question set according to a teacher's question selection requirement, wherein the common error questions are used to indicate error questions selected by multiple students; generating a text image of the common error questions; performing fusion processing on the text image and an identification image used for identifying the error questions to generate a common error question image; and displaying the common error question image to an expected arrangement object of the teacher.

A system is provided.SOLUTION: A system comprising: means for selecting a relevant lecture video based on user input interests and challenges; means for summarizing content of the selected lecture video; means for generating a concrete action plan based on the summarized content; and means for providing the generated action plan to a user.SELECTED DRAWING: Figure 1