Abstract: Provided are a device and method for recommending educational content. The method includes acquiring a user's search information, acquiring a candidate webpage set on the basis of the search information, classifying candidate webpages included in the candidate webpage set into a first webpage group and a second webpage group, determining a target webpage on the basis of classification results, and transmitting the determined target webpage.

Abstract: A method of tracking a dialogue state according to an embodiment of the present application includes: acquiring a trained dialogue state tracking model; acquiring target dialogue data; acquiring dialogue summary data from the target dialogue data using the dialogue state tracking model; and generating a dialogue state template from the dialogue summary data, in which the dialogue state tracking model includes an input layer for receiving the target dialogue data, an output layer for outputting the dialogue summary data, and a hidden layer having a plurality of nodes connecting the input layer and the output layer, and is trained using a training set that includes dialogue data and a dialogue summary sentence generated from dialogue state data related to the dialogue data.

Abstract: A method of learning a task model and a language model according to an embodiment of the present application includes: acquiring log data for each user for a content set consumed by a plurality of users and content included in the content set; acquiring text embedding for the content included in the content set through a pretrained language model (PLM); acquiring an output value related to a task from the text embedding and the log data through a task model; updating a weight of the task model based on the output value and a target value of the task; and acquiring back-propagation information for training the language model from the task model, and training the language model based on the back-propagation information.

Abstract: Provided is a method of training a neural network model for calculating an uncertainty index, the method including: obtaining a reference answering data set of a plurality of reference users, calculating expected score information of the reference user from the reference answering data set; obtaining actual score information of the reference user; obtaining a training set on the basis of the reference answering data set, the expected score information, and the actual score information, the training set including label information that is defined as a difference between the expected score information and the actual score information; and training a first neural network model for calculating an uncertainty index related to accuracy of the expected score information of the reference user from the reference answering data set using the training set.

Abstract: Provided are a method of recommending preceding educational content and an educational content recommendation device for recommending preceding educational content. The method includes acquiring a language model of which training has been completed, updating the language model by tuning the language model to acquire a target language model, and determining preceding educational content through the target language model. The acquirement of the target language model includes acquiring an educational data set including first clustering data and second clustering data and updating the language model to predict a probability that the first clustering data is a next token of the second clustering data.

Abstract: The present disclosure relates to a method of recommending a diagnostic test question for user evaluation by an electronic device, including: generating a first matrix indicating whether users answer all questions correctly; generating a second matrix based on the first matrix using knowledge tracing (KT); and selecting the diagnostic test question using Lasso regression based on the second matrix.

Abstract: The present disclosure relates to a method of reducing a size of an artificial intelligence model by an electronic device, including: inputting an input value for training to a first model; training the first model for performing a specific task based on the input value; inputting the input value to a second model; and training the second model based on an output value of the first model, in which the first model may be an artificial intelligence model larger in size than the second model.

Abstract: The present disclosure relates to a method of predicting a user's score on a question by an electronic device. The method includes: training a DP-multi tasking learning (DP-MTL) model; verifying the DP-MTL model; receiving choice selection information related to the question from the user through the terminal, and predicting 1) a probability that the user answers the question correctly and 2) the user's score related to the question using the verified DP-MTL model based on the choice selection information, and the DP-MTL model may be a model for predicting the user's score based on 1) information on whether the user answers the question correctly, 2) information on which incorrect answer is selected among choices of the question when the user selects an incorrect answer, and 3) a skill level of the user.

Abstract: In the present specification, a method of performing pre-training using an automated machine learning (AutoML) model by a server includes: using a first model for performing a first task to generate a second model for a second task; inputting, to the Auto ML model, a preset feature based on 1) components of the first model and the second model and 2) an element obtainable from training of the first model and generating of the second model as a state value; and changing the first model using the AutoML model.

Abstract: Provided are a device and method for assessing a user's learning ability. The method includes acquiring target assessment data of a target user and a reference user related to a target domain, wherein the target assessment data includes question data related to the target domain and answer data of each of the target user and the reference user for the question data, acquiring a target neural network model of which training has been completed, acquiring comparison information representing the target user's ability in relation to the reference user's ability in the target domain through the target neural network model, and calculating the target user's virtual score in the target domain on the basis of the comparison information.

Abstract: A method of providing learning to a user by a terminal includes the steps of: receiving user information from the user; displaying a first area for delivering information provided by a server to the user on the basis of the user information; displaying a second area for delivering a learning journey of the user to the user, wherein the second area includes a first icon representing a score predicted through a first test, one or more second icons representing a score predicted for each learning cycle, and a third icon representing a target score of the user; displaying an icon representing a learning cycle being performed by the user in the second area; and displaying a third area for delivering information related to the learning cycle being performed by the user.

Abstract: A method for predicting a test score of a user through an artificial intelligence model by a terminal, includes: delivering training data of the user to a first layer for embedding; embedding the training data through the first layer; delivering an embedding vector from the first layer to a second layer including a compressive transformer; delivering an output value from the second layer to a third layer for predicting the test score; and outputting a prediction value for predicting the test score from the third layer.

Abstract: Provided are a device and method for recommending educational content. The method includes acquiring a target user's learning data which includes log data including question data related to a question previously answered by the target user and answer data related to the target user's answer to the question, acquiring a question database including at least one candidate question, calculating the target user's predicted correct answer rate information for the candidate question on the basis of the candidate question and the learning data, acquiring the target user's ability information related to at least some of the log data, and determining recommendation content on the basis of the target user's ability information.

Abstract: A method for scheduling a task for AutoML (Automated Machine Learning) by a terminal, includes: setting a ratio of 1) a first task requiring a plurality of arithmetic devices and 2) a second task requiring one arithmetic device, in a cluster connected with the terminal; allocating a third task for the AutoML on the basis of the set ratio; receiving a request for allocation of a session from a user; inspecting whether the session is allocable on the basis of the ratio of the second task; and allocating the session to the arithmetic device associated with the second task on the basis of the ratio of the second task when the session is allocable.

Abstract: Provided are a method of training a neural network for calculating a learning ability and a method of calculating a user's learning ability. The method of training a neural network includes acquiring an assessment database including data, which includes question information answered by a user at a second time point earlier than a first time point, the user's answer information to the question information, and the user's score information in a second assessment system, acquired from the second assessment system different from a first assessment system, generating an answer sequence from the assessment database by matching the answer information with the score information to prepare a training set, preparing a neural network for calculating the user's score information in the second assessment system on the basis of the answer information in the second assessment system, and training the neural network with the training set.

Abstract: According to an embodiment of the present invention, a method of recommending educational content includes acquiring search information of a user, extracting searched question information based on the search information, acquiring a solution content set related to the question information, the solution content set including first solution information and second solution information, calculating learning ability information of the user based on the search information, calculating an index related to an expected educational effect based on the learning ability information and the solution content set, selecting target solution content from the solution content set based on the index, and transmitting the target solution content.

Abstract: According to an embodiment of the present invention, a method of recommending educational content may include acquiring search information of a user; acquiring a candidate webpage set based on the search information, the candidate webpage set including a first webpage and a second webpage; calculating knowledge level information of the user based on the search information; calculating a first index related to an expected educational effect when the first webpage is provided to the user based on the knowledge level information and first content information included in the first webpage; calculating a second index related to an expected educational effect when the second webpage is provided to the user based on the knowledge level information and second content information included in the second webpage; selecting a target webpage based on the first index and the second index; and transmitting the target webpage.

Abstract: Provided are a device and method for recommending educational content. The method includes acquiring a user's learning data, wherein the learning data includes at least one of the user's first learning ability information at a first time point, the user's second learning ability information at a second time point, and the user's question answering information, acquiring the user's target learning ability information on the basis of the learning data, determining a neural network model on the basis of the target learning ability information, distributing resources corresponding to the determined neural network model, and acquiring educational content to be recommended to the user through the determined neural network model.

Abstract: According to an embodiment of a recommending educational content method includes: acquiring search information of target user; acquiring learning set information based on the search information; acquiring a search database of a plurality of users based on the leaning set information, the search database including user identification information and a reference value allocated according to whether the user searches for a question included in the learning set information; allocating a feature value according to whether to search for at least one question included in the learning set information based on the search information; generating a first matrix based on the reference value of the search database and the feature value related to the target user; transforming the first matrix into a second matrix based on similarity of the reference value and the feature value; and calculating a learning ability score of the target user based on the second matrix.

Abstract: According to an aspect of the present specification, a method in which a terminal recommends a word to a user includes: receiving recommended word information from a server, wherein the recommended word information includes word information that the user is predicted not to know in an AI (Artificial Intelligence) model of the user on the basis of training data of the user; displaying a first window including the word information on the basis of the recommended word information; receiving operation of dragging the first window from the user; displaying an icon representing whether to add the word information to a vocabulary list of the terminal on the basis of a direction of the dragging operation; and including the word information in the vocabulary on the basis of the direction of the dragging operation.