67 results about "Question selection" patented technology

A dynamic system and method for efficiently measuring organizational compliance with multiple, overlapping, selected sources of compliance requirements by making associations of individual source controls and survey questions with a limited set of discrete compliance objectives, and by enabling creation of compliance surveys and analysis of survey answer sets based on user-selected criteria that may include selection of a specific source or sources; one or more discrete compliance objectives, and/or a choice of questions from a master question pool. Custom surveys with weighted questions and dynamic reporting enables responses to compliance audits to be analyzed against a pre-determined benchmark result, against responder's own prior results, or against other responders.

An active learning framework is operative to identify informative questions that should be added to existing question-answer (Q&A) pairs that comprise a training dataset for a learning model. In this approach, the question—answer pairs (to be labeled as “true” or “false”) are automatically selected from a larger pool of unlabeled data. A spatial-directed clustering algorithm partitions the relevant question-answer space of unlabeled data. A margin-induced loss function is then used to rank a question. For each question selected, a label is then obtained, preferably by assigning a prediction for each associated question-answer pair using a current model that has been trained on labeled question-answer pairs. After the questions are labeled, an additional re-sampling is performed to assure high quality of the training data. Preferably, and with respect to a particular question, this additional re-sampling is based on a distance measure between correct and incorrect answers.

The invention provides a method for question selection of a network education test. The method includes the following steps: obtaining input question selection parameters; seeking metadata matched with the question selection parameters in metadata corresponding to preset test questions according to the question selection parameters; and obtaining the test questions corresponding to the metadata. In addition, a device for the question selection of the network education test, a method and a device for on-line tests and a method and a device for on-line test assessment are further provided. The method and the device for the question selection of the network education test enables the question selection parameters input by the user to be more flexible, so that the user can conduct question selection conveniently.

A system, method and computer readable medium that performs data analyses, such as economic forecasting, in accordance with the configured needs of one or more users. The system may maintain local information on which its various analyses are based, and may supplement or replace this local information with information retrieved from a remote data sources containing a desired type of data, such as time series data. Preferably, the system includes the ability to search for databases within an associated information network, such as the Internet. The system records information in an index about each database it finds, including whether the database contains data of a desired type. The particular type of data sought by the system depends upon configurable settings and relates to the type of analyses for which it has been configured. Thereafter, the system may use the index to retrieve data from many different databases when performing an analysis, relieving it from the need to store such data locally. The system may use the indexed information to check remote databases for changes or updates. The system can update any affected analyses, or alert users whose analyses are affected by such changes. A variety of mathematical models may be included in the system, and it can select the best model or models for a given user problem.

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 test question generation system and an implementation method thereof, which are applied to handheld electronic education equipment. The test question generation system comprises a database, an intelligent controller, a display unit and an input unit, wherein the database, the display unit and the input unit are all connected with the intelligent controller, the database comprises a test question database and a user record database, the test question database can carry out intelligent question selection, random question selection and question selection for review according to user demands, the intelligent question selection refers to supplying proper test questions suitable for the current learning of the user according to the comprehensive information of the user, the random question selection refers to preferably selecting new questions and supplying to the user, and the question selection for review refers to preferably selecting wrongly-solved questions and supplying to the user. By adopting the handheld electronic education equipment of the test question generation system provided by the invention, the user can acquire the test questions meeting the requirements of current learning by selecting corresponding display icons in a test question management module, so that the students can learn in a better pertinence way, and the learning effect can be enhanced rapidly.

A method, implemented on at least one computing device, each of which has at least one processor, storage, and a communication platform connected to a network for classifying a question is disclosed. A question is received from a person. A question pattern is determined. A model selected based on the question is retrieved. Further, a decision is made as to whether the question is a personal question based on the question pattern and the selected model.

The invention relates to the technical field of micro expressions, and provides a question and answer process optimization method and device, a computer device and a storage medium. The method comprises the steps of obtaining the question and answer video data and question and answer audio data of a user answering a first question, carrying out face detection on a picture frame in the question andanswer video data to obtain a facial expression image; analyzing to obtain a micro-expression analysis result, carrying out voice recognition on the question and answer audio data, obtaining an answer judgment result according to a preset answer, adjusting a user question and answer strategy by combining the micro-expression analysis result and the answer judgment result, and selecting a second question answered by the user according to a corresponding question selection rule. During the whole process, the micro-expression analysis is performed on the facial expression of the user in the process of answering the first question, the answer of the question and answer is judged, the judgment result and the micro-expression analysis result are combined to adjust the question and answer strategy and select the second question answered by the user, so that a more real and effective question and answer result is obtained, and the optimization of the whole question and answer process is realized.

Disclosed herein is an information processing apparatus including: a user answer evaluation section configured to determine whether a user answer to a question selected from a plurality of questions is correct or wrong; a user answer analysis block configured to compute at least a user wrong-answer percentage by use of the user answer evaluation result; a questioning condition setting block configured to compute a degree of similarity between the plurality of questions on the basis of the user wrong-answer percentage and, at the same time, compute an evaluation value of each of the plurality of questions by use of the degree of similarity; and a question selection section configured to select a question to be set from the plurality of questions on the basis of the evaluation value and a user correct-answer percentage in one of a predetermined period and a predetermined number of questions.

The invention discloses an answer selection method, comprising: acquiring a preset recognition model of context information and session information that at least includes questions to be answered; recognizing context in the session information according to the preset recognition model of context information so as to determine related context information in the session information; subjecting the related context information to word segmentation, and calculating TF-IDF (term frequency-inverse document frequency) value of each term in the related context information; extracting a preset number ofkeywords from the related context information according to the TF-IDF values; selecting corresponding answers through preset question selection rules according to the extracted keywords and a retrieval knowledge base of questions to be answered. The invention also discloses an answer selection device and a computer-readable storage medium. The answer selection method and device and the computer-readable storage medium can provide increased answer selection rate.

The invention discloses an examination paper generating system which comprises a question bank module, an input module, an automatic question selection module, a score setting module and a checking and adjusting module, wherein the question bank module is used for storing lots of examination questions; the input module is used for inputting a ratio of examination points to the examination question difficulty for a responsible teacher; the automatic topic selection module is used for automatically selecting questions and generating examination paper according to the ratio of examination points to the examination question difficulty input by the teacher; the score setting module is used for setting scores of the generated questions; and the checking and adjusting module is used for checking and manually adjusting the automatically generated examination paper by the teacher. Due to the mode, the examination paper can be generated automatically according to the ratio of examination points to the examination question difficulty, and in addition, the examination question library can be updated and can be synchronized with update of teaching materials.

The present invention provides an automatic questions selecting method of an examination system on a network based on a layered genetic algorithm. A key point of the invention is introducing characteristics of the layered genetic algorithm into the automatic questions selection of the examination system on the network. The method can select questions which are best matched with a question requirement to generate examination paper rapidly and satisfy the rapid and high-efficiency question requirement by the high capacity item bank of the examination system according to the crucial attributes of investigation scope and difficulty of paper etc. with respect to users. The automatic questions selecting method based on the layered genetic algorithm can integrate situations such as questions difficulty of various levels, total difficulty of the paper and questions that have already been used in examines, so that a question selection efficiency of the examination system can be greatly enhanced, a matching degree between the paper and the question selection requirement can be improved, and a checking efficiency can be increased.

The invention discloses an intelligent service method and system based on an innovation and entrepreneurship platform, and belongs to the technical field of innovation and entrepreneurship service platforms. The method comprises the following steps of: S1, introducing a multi-source heterogeneous big data access technology, and constructing an innovation and entrepreneurship resource library; S2,introducing a knowledge graph technology to form a knowledge base supporting brain-like services; S3, performing abstract generation, label extraction and text generation technologies based on a deepneural network; S4, recommending and matching various eligible service resources of a platform for entrepreneurs through an unsupervised adaptive recommendation algorithm; and S5, providing low-cost and automatic consultation services based on an intelligent question-answering technology of the knowledge graph; and S6, providing automatic consultation services for help selection and professional guidance based on the intelligent question-answering technology of the knowledge graph. Therefore, the platform can serve customers with high efficiency and high quality and solve customer business problems, and machine learning of artificial intelligence continues to be optimized while a result is selected.

A questionnaire apparatus includes: a question storage unit that holds plural questions; a selection condition reception unit that receives a selection condition for selecting a question; and a question selection unit that selects a next question from among the questions stored in the question storage unit, based on a question, an answer to the question and a selection condition received by the selection condition reception unit.

A computer executable training system and method for making foreign language sentences within limited time is disclosed. Said system is composed of a sentence type database, a question selection module for randomly selecting sentence type as question, randomly sorting them, and receiving an answer for comparison, a timing processing module for storing a question setting time table, dividing the antimation archives and generating a play time table, a play display module for storing the animation archives, playing a fragment of animation, down counting of playing time, and displaying it, and aninput comparing module for inputting user answer and making a parison.

A knowledge base correction system includes a question generator configured to detect incomplete knowledge data of a knowledge base, and to generate a question, an answer to which is used to correct the incomplete knowledge data; a user information storage configured to store level information about a plurality of users; and a question selector configured to determine a number of questions and questions to be assigned to each of the plurality of users, based on the level information of the plurality of users.

The invention is suitable for the technical field of network education, and provides a question selection method and device, terminal equipment and a readable storage medium, and the method comprisesthe steps: obtaining a question image comprising at least one question, carrying out the recognition of an area where a target question in the at least one question is located, and generating an areaselection box; adjusting the area selection box according to the detected adjustment operation to generate a box selection area completely covering the target question; and cutting the title image according to the frame selection area to obtain a cut title image. An area where a target topic is located is identified; a region select box is generated, the area selection box is adjusted according tothe adjustment operation; the frame selection area completely covering the target topic is generated according to the target topic, finally, the clipped topic image matched with the frame selection area is obtained through clipping, the storage space occupied by the clipped topic image is smaller than that occupied by the non-clipped topic image, the time spent on sending the clipped topic imageto the server is shortened, and the efficiency of retrieving the target topic is improved.

The invention discloses a Chinese reading comprehension intelligent test and intelligent tutoring system and method. The system is an application of emerging technologies such as the Internet and artificial intelligence in the field of Chinese reading comprehension teaching and evaluation. The system comprises an intelligent question selection subsystem based on a Chinese reading comprehension ability model, an automatic Chinese reading comprehension evaluation subsystem based on artificial intelligence, a personalized and hierarchical tutoring subsystem for Chinese reading comprehension, anda Chinese reading comprehension teaching auxiliary subsystem based on data mining. The system can intelligently select questions according to the reading ability of learners, and can automatically score and evaluate Chinese reading understanding questions, including subjective questions; and on the basis of accurately mastering the specific reading comprehension learning condition of each learner,targeted and individual intelligent tutoring is further implemented, so that individual teaching of Chinese reading comprehension is realized. In addition, the system can also provide assistance foroffline teaching through the generated data.

An approach to automatically generating a survey. The approach collects input information from a survey designer and uses the input to generate sections for the survey. The approach then selects question from related archived surveys and generates new questions from internal and/or external data sources to assemble the survey. The approach can perform the section generation analysis and the question selection/generation automatically and/or tuned by a survey designer. The approach distributes the completed survey to survey takers and feedback is provided based on metrics associated with characteristics exhibited by the survey takers while taking the survey. The feedback allows the approach to improve survey quality.

The invention discloses a personalized question recommendation method and system using a machine learning model, and the method comprises the steps: collecting the related questions of a student, building a question bank, carrying out the multi-target estimation of each question in the question bank through the machine learning model, scoring the questions in the question bank according to the estimated targets and the contribution value of each question to the total score of the student, selecting a first number of questions according to the scores, establishing a first question set, sortingthe questions in the first question set under each estimated target, converting the corresponding rank into scores, and performing fusion sorting; and selecting a second number of questions in the fusion sorting result according to set question selection factors and recommending the questions to the students. According to the invention, personalized questions can be provided for students, maximized question solving efficiency is achieved, and powerful support is provided for score improvement.

A computer implemented system, method and computer program product for identifying a user's design categories for one or more products offered by one or more sellers of products. A plurality of questions can be displayed. Each question is associated with a plurality of choices. A user can be permitted to select one or more choices to the plurality of questions. An indication of at least one of the selected choices to one or more of the plurality of questions can be received. The selected choices comprise lifestyle preferences for the user. Multiple user design categories can be identified based on the user's lifestyle preferences. The user's multiple design categories can be displayed. Access can be provided to an incentive for the purchase products associated with the user's design categories. The incentive is activatable at a seller's retail location.

The invention discloses an interactive learning method and system based on augmented reality. The method comprises the following steps: S1, receiving a question selection instruction that is input bya user through terminal equipment; S2, acquiring question data corresponding to the question selection instruction from a question database, wherein the question data includes at least one question voice and virtual model data; S3, displaying a virtual scene and a radar chart to the terminal equipment; S4, playing each question voice in the at least one question voice until the at least one question voice is completely played; S5, receiving a shooting instruction that is sent by the user through shooting equipment; and S6, determining whether a virtual balloon corresponding to the current question voice is shot according to the shooting instruction, if the balloon is shot, displaying correct prompt information, and jumping to the step S4, and otherwise, displaying error prompt information,and jumping to the step S4. The interactive learning method and system disclosed by the invention have the beneficial effects that the augmented reality technology and learning are combined to provide a new learning method, and the user can deeply experience the fun of learning.

The invention discloses a combined type history teaching system, which includes a server, and a teacher terminal, a student terminal and a teaching terminal which realize communication with the serverthrough the Internet. A target data acquisition module and a puzzling problem collection module are arranged in the server. The teaching terminal includes a teaching material display module which isinternally provided with a normalized display module and a holographic projection module and is used for displaying teaching data; and a control command acquisition module which is used for acquiringvarious control commands and sending the acquired control commands to the corresponding module for execution. In the teaching process, the learning interest of students is greatly improved through a holographic projection technology; after-class exercise is performed in a random question selection mode, and thus students' learning efficiency can be better improved; and an aided teaching link can effectively solve the problems of students in the learning process, and while improving teaching efficiency, sharing of teaching materials and teachers is realized.

An off-line response card having a plurality of sensors is provided with a replaceable cover, where the cover is provided with a plurality of questions and choices for questions. The choices are arranged into the cover so that each choice corresponds to one sensor in the response card when the cover is placed on the response card. The sensor is adapted to sense whether the choice in the cover is influenced (selected) and output identifying information of said sensor as a result of the influence.