Abstract: An apparatus for processing natural language according to an embodiment includes a collection module that collects documents having tags, a parsing module that extracts text from the collected documents and extracts tag-related information on the tag surrounding each extracted text, and a preprocessing module that generates tokens of a preset unit by tokenizing each extracted text, generates token position information for each token in full text of the document, and sets the token and the token position information as training data in matching with the tag-related information.

Abstract: An automated guided vehicle for transporting an object to a facility according to an embodiment of the present disclosure includes a main body, a shaft provided in the main body for guiding movement of the object to the facility and to face a front direction of the main body, a camera provided at one end of the shaft for photographing a front direction of the main body, and a position adjustment module for decoding an identifier when an image photographed by the camera includes the identifier displayed on the facility, and using a result of the decoding to adjust a position, toward which the one end of the shaft is directed.

Abstract: A method for providing a task automation service, performed by at least one computing device is provided. The method may include collecting information on an object, in which a user's input occurs, by using a recording engine, generating an object information list for the object based on the information collected by the recording engine, determining first object information corresponding to the user's input based on a result of comparing a plurality of kinds of candidate object information included in the object information list, and automatically generating an activity corresponding to the user's input based on the first object information and predefined pattern information.

Abstract: A method of creating a Robotic Process Automation (RPA) scenario is provided. The method may include: receiving input from a user that designates a target application or an RPA object within the target application, identifying and displaying one or more RPA objects that belong to the target application, receiving input from the user that selects a target RPA object and a user activity associated with the target RPA object, and transforming the selected user activity into a corresponding RPA activity sequence and displaying the corresponding RPA activity sequence.

Abstract: There is provided a communication device. The communication device may comprise one or more processors; a communication interface; and a memory that stores a computer program executed by the one or more processors, wherein the computer program includes instructions for operations of: forming a general security channel according to a first transport layer security (TLS) protocol that does not support a post-quantum cryptography algorithm with another communication device; forming a communication channel of an application layer (L7) with another communication device through the general security channel; forming a quantum security channel by performing a handshake procedure according to a second TLS protocol that supports the post-quantum cryptography algorithm with another communication device through the communication channel; and communicating with another communication device through the quantum security channel.

Abstract: The disclosure relates to a method, an apparatus, a system, and a computer program for identifying and responding to quantum vulnerability with respect to an application by using a dynamic analysis agent and, specifically, as a method of identifying quantum vulnerability with respect to an application by using a computing apparatus, the disclosure may include an operation of identifying one or more cryptographic associated functions performed in an application based on analysis of a code, executed while the application is in an operating state, by using a dynamic analysis agent corresponding to the application, an operation of calculating, based on the one or more cryptographic associated functions, a cryptography algorithm list used in the application, and an operation of identifying, based on the cryptography algorithm list, quantum vulnerability with respect to the application.

Abstract: An apparatus for training a reinforcement learning model according to an embodiment includes a starting point determinator configured to determine starting points from an input value of a combinatorial optimization problem, a multi-explorer configured to generate exploration trajectories by performing exploration from each of the starting points using a reinforcement learning model, a trajectory evaluator configured to calculate an evaluation value of each of the exploration trajectories using an evaluation function of the combinatorial optimization problem, a baseline calculator configured to calculate a baseline for the input value from the evaluation value of each exploration trajectory, an advantage calculator configured to calculate an advantage of each of the exploration trajectories using the evaluation value of each exploration trajectory and the baseline, and a parameter updater configured to update parameters of the reinforcement learning model by using the exploration trajectories and the advantage

Abstract: Provided is a method performed by a computing system for providing an integrated chatbot-based service. The method includes receiving, by an integrated chatbot, a query from a user device; extracting a main keyword from the query; transmitting the extracted main keyword to a first chatbot and a second chatbot; receiving, from the first chatbot and the second chatbot, a content search result corresponding to the extracted main keyword; and providing a response to the query to the user device based on the received content search result.

Abstract: The present disclosure relates to a message notification method of an online messenger, and a computing device using the same. The message notification method of the online messenger according to an embodiment of the present disclosure includes determining, when a new message is received, the importance of the new message based on keywords included in the new message; identifying a user status configured within the online messenger; and controlling a notification display indicating reception of the new message based on the importance of the new message and the user status.

Abstract: A method for searching a content includes receiving a predefined user input with respect to a text region; extracting, in response to the predefined user input, at least one word from the text region; creating a search condition based on the extracted at least one word; and displaying a list of contents searched based on the created search condition.

Abstract: A learning with errors (LWE) instance management method according to an embodiment may include obtaining, from one or more user devices among a plurality of user devices, one or more learning with errors (LWE) instances and one or more extended LWE instances including reuse tags associated with the LWE instances, storing the one or more extended LWE instances, receiving, from a first device among the plurality of user devices, a request for an LWE instance produced by a second device among the plurality of user devices, and identifying, based on a reuse tag included in each of the one or more extended LWE instances, a target extended LWE instance including an LWE instance produced by the second device among the one or more extended LWE instances, and providing the LWE instance included in the target extended LWE instance to the first device.

Abstract: A ciphertext comparison method according to an embodiment is performed by a processor in a computing apparatus, and the method includes an operation of segmenting a first ciphertext and a second ciphertext into m part bitstreams (in this instance, m is a natural number satisfying 1<m), respectively; an operation of extracting a value corresponding to a j?1th part bitstream (in this instance, j=i+1, i is a natural number satisfying 0?i?m?1) of the first ciphertext and a j?1th part bitstream of the second ciphertext, as a jth intermediate value between a first value and a second value in a first lookup table including the first value and the second value of which Hamming weights are identical; an operation extracting a value corresponding to the jth intermediate value and a j?1th result value, as a jth result value between a third value and a fourth value in a second lookup table including the third value and the fourth value of which Hamming weights are identical; and in a case of j?m, an operation of repea

Abstract: The disclosure relates to a method for synchronizing messages between a plurality of messenger client devices, and a messenger client device using the same, and the method for synchronizing messages between a plurality of messenger client devices to which a user account is shared according to an embodiment of the disclosure may include: accessing a pre-configured public repository and downloading public data including a previous chat list shared between the plurality of messenger client devices by a messenger client device; and generating merged data by merging the public data and local data including a previous chat list stored in a local repository of the messenger client device by the messenger client device.

Abstract: A method for providing a video conference service is provided. The method may include receiving status data of a plurality of terminals logged in with an account of a first participant; determining video priorities of the plurality of terminals based on the received status data; selecting a first terminal, among the plurality of terminals, to transmit a video of the first participant based on the video priorities; and transmitting the video of the first participant received from the first terminal to terminals of other participants.

Abstract: The present disclosure according to at least one embodiment provides a method of processing operations of a polynomial-based security algorithm, the method being performed by a computing system. The method comprises identifying a plurality of operations using secret information in the polynomial-based security algorithm, generating a random index to be applied to the identified operations, and performing the operations using the random index.

Abstract: There is provided a cloud-based application programming interface (API) service providing system. The system may comprise a cloud management console issuing authentication information for a requested API among a plurality of APIs, an API manager receiving a call message for a specific API, which comprises authentication information, from a user's terminal, performing authentication using the authentication information in the call message, and requesting the execution of the specific API based on the authentication result and an API execution engine generating the result of executing the specific API in response to a request from the API manager, wherein the cloud management console is a module belonging to a control plane, and the call message is received by the API manager belonging to a data plane without via the control plane.

Abstract: The present disclosure according to at least one embodiment provides a software development platform, a software development platform comprising a config manager receiving config information of target software through a graphical user interface (GUI)-based config interface—the config information including config information on a plurality of items, at least some of which are for configuring a common component—, a code generator generating a code of the target software based on the config information; and an execution engine executing the generated code by using the common component in which the config information of the at least some of the items is reflected.

Abstract: A logistics center layout generation method and a device therefor are provided. The logistics center layout generation method includes: receiving basic configuration information for generating a layout of the logistics center; generating, based on an inventory history of the logistics center, storage cells configured to store items handled in the logistics center; arranging, based on an outgoing history of the logistics center, the storage cells in each stacking area according to possible combinations of types and arrangement directions of the items; and generating, multiple alternative layouts based on combinatorial optimization, multiple alternative layouts, comparing outgoing times of the alternative layouts, and providing a recommended layout among the multiple alternative layouts.

Abstract: A method for providing a cloud-based application programming interface (API) service is provided. The method may include issuing an authentication key corresponding to an application for some of a plurality of API services, performing authentication for a first user using the issued authentication key in response to a call for a first API service by the first user, and executing the first API service based on a result of the authentication.

Abstract: A method for an anomaly detection is provided. The method may include acquiring a score predictor trained using normal time-series data, wherein the score predictor is a deep learning model configured to output a conditional score for previous time-series data and the conditional score represents a gradient of data density, extracting data for a specific time and data segments corresponding to a period before the specific time from target time-series data, and predicting a conditional score for the data segments through the trained score predictor and conducting an anomaly determination for the data for the specific time using the predicted conditional score.