Abstract: An electronic device and an method of the electronic device are provided, where the electronic device maintains a context that does not reflect a request for a secret conversation, in response to the request for the secret conversation being received from a first user, and generates a response signal to a voice signal of a second user based on the maintained context, in response to an end of the secret conversation with the first user.

Abstract: A wearable device includes first and second electronic modules, a connection module configured to electrically connect the first electronic module to the second electronic module, and a length adjusting module of which length is adjustable to bring the connection module in contact with a user. The length adjusting module comprises first and second fastening units configured to be assembled and disassembled and configured to be locked together in a fastened position when assembled. When the first and second fastening units are assembled, the first fastening unit is electrically connected to the second fastening unit and a length of the length adjusting module is adjusted.

Abstract: Encoding an image using a non-encoding region of the image, a block-based encoding region of the image, and a pixel-based encoding region of the image.

Abstract: A processor-implemented response inference method and apparatus are disclosed. The response inference apparatus receives an input, generates a latent variable vector in a latent variable region space by encoding the input, generates a validation vector with a predetermined phase difference from the latent variable vector, generates an output response by decoding the latent variable vector, generates a validation response by decoding the validation vector, and validates the output response by comparing the output response to the validation response.

Abstract: Provided are a video encoding method and apparatus having temporal scalability, and a video decoding method and apparatus having temporal scalability. The video encoding method includes: splitting pictures included in a picture sequence into temporal sub-layers; classifying, as a first temporal layer access picture or a second temporal layer access picture, a temporal layer access picture based on whether a picture encoded after the temporal layer access picture is capable of referring to a picture encoded before the temporal layer access picture; and adding, to transmission unit data including the temporal layer access picture, type syntax information for identifying the first temporal layer access picture and the second temporal layer access picture, wherein the picture encoded after the temporal layer access picture belongs to a same temporal sub-layer as the temporal layer access picture or belongs to an upper temporal sub-layer to the temporal layer access picture.

Abstract: Provided is in-loop filtering technology using a trained deep neural network (DNN) filter model. An image decoding method according to an embodiment includes receiving a bitstream of an encoded image, generating reconstructed data by reconstructing the encoded image, obtaining information about a content type of the encoded image from the bitstream, determining a deep neural network (DNN) filter model trained to perform in-loop filtering by using at least one computer, based on the information about the content type, and performing the in-loop filtering by applying the reconstructed data to the determined DNN filter model.

Abstract: Provided is a prediction image generating technology using a deep neural network (DNN). Provided is an image decoding method including: receiving a bitstream of an encoded image; determining at least one block split from the encoded image; determining neighboring blocks for predicting a current block among the at least one block; generating prediction data of the current block by applying the neighboring blocks to a DNN learning model configured to predict a block of an image by using at least one computer; extracting residual data of the current block from the bitstream; and reconstructing the current block by using the prediction data and the residual data.

Abstract: Provided are an image compressing method including determining a compressed image by performing downsampling using a deep neural network (DNN) on an image; determining a prediction signal by performing prediction based on the compressed image; determining a residual signal based on the compressed image and the prediction signal; and generating a bitstream comprising information about the residual signal, wherein the DNN has a network structure that is predetermined according to training of a downsampling process using information generated in an upsampling process, and an image compressing device for performing the image compressing method. Also, provided are an image reconstructing method of reconstructing a compressed image by using a DNN for upsampling, the compressed image having been compressed by the image compressing method, and an image reconstructing device for performing the image reconstructing method.

Abstract: An operation method of a dialog agent includes obtaining an utterance history including at least one of an outgoing utterance to be transmitted to request a service or at least one of an incoming utterance to be received to request the service, updating a requirement specification including items requested for the service based on the utterance history, generating utterance information to be used to request the service based on the updated requirement specification, and outputting the generated utterance information.

Abstract: Provided is a method, performed by a terminal, of providing content includes determining whether at least one content is included in preference content, based on information about the at least one content provided to the terminal and preference information of a user of the terminal about content; content, which is not included in the preference content, is present in the at least one content, transmitting, to a server, a request to change the first content to second content included in the preference content based on previously stored information about the preference content; and outputting the second content received from the server, in response to the request.

Abstract: Provided is a method of encoding an image, the method including: determining a subjective quality of the image when the image is compressed; determining at least one degree of compression that changes the subjective quality and is from among degrees of compression indicating how much the image is compressed; and encoding the image by compressing a residual signal of the image, based on compression information according to the determined degree of compression, wherein the subjective quality is determined for each frame by using a Deep Neural Network (DNN). Provided are an image decoding method and an image decoding apparatus for performing the image decoding method for decoding an image by using information encoded according to an image encoding method.

Abstract: An operation method of a dialog agent includes obtaining an utterance history including at least one of an outgoing utterance to be transmitted to request a service or at least one of an incoming utterance to be received to request the service, updating a requirement specification including items requested for the service based on the utterance history, generating utterance information to be used to request the service based on the updated requirement specification, and outputting the generated utterance information.

Abstract: Provided is a prediction image generating technology using a deep neural network (DNN). Provided is an image decoding method including: receiving a bitstream of an encoded image; determining at least one block split from the encoded image; determining neighboring blocks for predicting a current block among the at least one block; generating prediction data of the current block by applying the neighboring blocks to a DNN learning model configured to predict a block of an image by using at least one computer; extracting residual data of the current block from the bitstream; and reconstructing the current block by using the prediction data and the residual data.

Abstract: A method and apparatus with natural language processing is disclosed. The method includes determining a first similarity between an input sentence of a user and a select first database query sentence and dependent on a determination that the first similarity fails to meet a first threshold, determining a second similarity between a portion of the input sentence, less than all of the input sentence, and a select second database query sentence, and in response to the second similarity meeting a second threshold, outputting a response sentence corresponding to the second database query sentence as a response to the input sentence.

Abstract: A processor-implemented method includes performing speech recognition of a speech signal, generating a plurality of first candidate sentences as a result of the performing of the speech recognition, identifying a respective named entity in each of the plurality of first candidate sentences, determining a standard expression corresponding to the identified respective named entity using phonemes of the corresponding named entity, determining whether to replace the identified named entity in each of the plurality of first candidate sentences with the determined standard expression based on a similarity between the named entity and the standard expression corresponding to the named entity and determining a plurality of second candidate sentences based on the determination result; and outputting a final sentence selected from the plurality of second candidate sentences.

Abstract: Provided are an image compressing method including determining a compressed image by performing downsampling using a deep neural network (DNN) on an image; determining a prediction signal by performing prediction based on the compressed image; determining a residual signal based on the compressed image and the prediction signal; and generating a bitstream comprising information about the residual signal, wherein the DNN has a network structure that is predetermined according to training of a downsampling process using information generated in an upsampling process, and an image compressing device for performing the image compressing method. Also, provided are an image reconstructing method of reconstructing a compressed image by using a DNN for upsampling, the compressed image having been compressed by the image compressing method, and an image reconstructing device for performing the image reconstructing method.

Abstract: A processor-implemented response inference method and apparatus are disclosed. The response inference apparatus receives an input, generates a latent variable vector in a latent variable region space by encoding the input, generates a validation vector with a predetermined phase difference from the latent variable vector, generates an output response by decoding the latent variable vector, generates a validation response by decoding the validation vector, and validates the output response by comparing the output response to the validation response.

Abstract: According to an embodiment of the present disclosure, an electronic device for transmitting data comprises a memory storing the data, a processor, and a coil. The processor may perform controls to detect a data receiving device configured to detect a magnetic field corresponding to the data and apply a voltage or a current corresponding to the data to the coil in response to the detection of the data receiving device.

Abstract: A structure of an electric sunshade and a sunroof may include glass sleds which both open and close a sunroof glass by sliding in a longitudinal direction along mechanism rails disposed at both sides of a roof panel of a vehicle, wherein a front sled and a rear sled are rotatably coupled to both end portions of each of glass sleds, respectively, main cable devices which are connected to a driving motor by a cable, and movable along the mechanism rails, and separately include a cable protrusion slidably accommodated in glass grooves formed in lateral surfaces of the front sled, the rear sled, and the glass sled, and sunshade sleds which are selectively coupled to the main cable devices, and slide to open or close the sunshade.

Abstract: A processor-implemented speech recognition method includes: applying, to an input layer of a neural network, a frame of a speech sequence; obtaining an output of a hidden layer of the neural network corresponding to the frame; calculating a statistical value of at least one previous output of the hidden layer corresponding to at least one previous frame of the speech sequence; normalizing the output based on the statistical value; applying the normalized output to a subsequent layer of the neural network; and recognizing the speech sequence based on the applying of the normalized output.