Abstract: A method of generating an application by using an artificial neural network model includes a data processing step of pre-processing training data, a model training step of training the artificial neural network model based on the preprocessed training data, and an application making step of receiving an input for editing one or more components included in the application and an input for setting a connection relationship between the one or more components. The one or more components include the artificial neural network model.

Abstract: A device for providing an interface for managing contact scenarios for one or more respondents may provide a first interface for inputting contact information of one or more respondents to be contacted, provide a second interface for inputting a scenario of the contact, and provide a third interface for displaying on a screen a contact simulation according to the scenario.

Abstract: A method of generating a speaker-labeled text from voice data including voices of at least two speakers includes converting the voice data into text to generate a first text, determining a speaker of each of one or more second texts obtained by dividing the first text in a predetermined unit, and providing an editing interface for displaying the one or more second texts and a speaker of each of the one or more second texts.

Abstract: A device for providing an interface for managing contact scenarios for one or more respondents may provide a first interface for inputting contact information of one or more respondents to be contacted, provide a second interface for inputting a scenario of the contact, and provide a third interface for displaying on a screen a contact simulation according to the scenario.

Abstract: Provided is a method of controlling display of a consultation session by integrating and displaying at least one consultation session managed by an individual respondent. The method includes receiving, from a server, data about the at least one consultation session to be displayed; displaying a consultation session window for each of the at least one consultation session; and displaying in a preset manner a session window of a consultation session in which details of consultation satisfy a certain condition for a consultant's intervention. The consultation session window includes a history of conversation in each of the at least one consultation session.

Abstract: A method of generating a voice for each speaker from audio content including a section in which at least two or more speakers simultaneously speak is provided. The method includes dividing the audio content into one or more single-speaker sections and one or more multi-speaker sections, determining a speaker feature value corresponding to each of the one or more single-speaker sections, generating grouping information by grouping the one or more single-speaker sections based on a similarity of the determined speaker feature value, determining a speaker feature value for each speaker by referring to the grouping information, and generating a voice of each of multiple speakers in each section from each of the one or more multi-speaker sections by using a trained artificial neural network and the speaker feature value for each individual speaker.

Abstract: The present disclosure relates to a system and method of generating a sentence similar to a basis sentence for machine learning. For the same, the similar sentence generating method includes: generating a first similar sentence by using a word similar to a word included in a basis sentence; generating a second similar sentence of the basis sentence or the first similar sentence based on a speaker feature; and determining whether or not the first similar sentence and the second similar sentence are valid.

Abstract: 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.

Abstract: The present disclosure relates to a system and method of sentence learning based on an unsupervised learning method. For the same, a sentence learning method may include: enhancing a basis sentence corpus by using a word similar to a word included in a basis sentence; performing learning for the basis sentence included in the basis sentence corpus based on an unsupervised learning method; and removing an abnormal sentence among at least one similar sentence obtained by performing of the sentence learning.

Abstract: A queue processing method and a router perform cache update and queue processing based upon whether or not the packet capacity stored in the queue exceeds a rising threshold, or whether the packet capacity stored in the queue is below a falling threshold after the packet capacity stored in the queue has exceeded the rising threshold. This queue processing method and router makes it possible to eliminate overhead associated with the update of flow information by using two caches, while concomitantly removing the inequality of packet flows via RED queue management with the expedient of using two caches.

Abstract: A queue processing method and a router perform cache update and queue processing based upon whether or not the packet capacity stored in the queue exceeds a rising threshold, or whether the packet capacity stored in the queue is below a falling threshold after the packet capacity stored in the queue has exceeded the rising threshold. This queue processing method and router makes it possible to eliminate overhead associated with the update of flow information by using two caches, while concomitantly removing the inequality of packet flows via RED queue management with the expedient of using two caches.

Abstract: A router for performing queue management for packet transmission is provided, which includes a first storage unit for storing and outputting packets input to request transmission from a source device to a destination device; a second storage unit for storing information on the packets stored in the first storage unit; and a packet-processing determination unit for determining whether the input packets are to be stored in the first storage unit, based on whether there is a available storage capacity in the first storage unit, and updating information on the packets into the second storage unit.