Abstract: An example controlling method includes receiving an input utterance, determining whether domain information and intent information are able to be extracted by analyzing the input utterance, based on at least one of the domain information and the intent information not being extracted, broadcasting a signal requesting previous utterance related information to one or more external devices connected to a same network as the electronic device, receiving the previous utterance related information from the at least one external device, extracting the domain information and the intent information based on the received previous utterance related information and the input utterance, and obtaining and outputting a response result based on the extracted domain information and intent information.

Abstract: Disclosed are an electronic device, a system, and a controlling method thereof. The controlling method includes: receiving an input utterance, determining whether domain information and intent information are able to be extracted by analyzing the input utterance, based on at least one of the domain information and the intent information not being extracted, broadcasting a signal requesting previous utterance related information to one or more external devices connected to a same network as the electronic device, receiving the previous utterance related information from the at least one external device, extracting the domain information and the intent information based on the received previous utterance related information and the input utterance, and obtaining and outputting a response result based on the extracted domain information and intent information.

Abstract: An electronic device and a method for controlling thereof are provided. The electronic device includes a display, a memory storing at least one instruction, and a processor, wherein the processor is configured to, by executing the at least one instruction, extract a plurality of texts displayed on a chat window of a message application and collect the texts, input the plurality of collected texts into a trained first neural network model and align the plurality of texts in order, input the plurality of texts aligned in order into a trained second neural network model and identify whether additional information for acquiring event information from the plurality of texts is necessary, and acquire event information from the plurality of texts based on the identification result.

Abstract: An electronic device and a method for controlling thereof are provided. The electronic device includes a display, a memory storing at least one instruction, and a processor, wherein the processor is configured to, by executing the at least one instruction, extract a plurality of texts displayed on a chat window of a message application and collect the texts, input the plurality of collected texts into a trained first neural network model and align the plurality of texts in order, input the plurality of texts aligned in order into a trained second neural network model and identify whether additional information for acquiring event information from the plurality of texts is necessary, and acquire event information from the plurality of texts based on the identification result.

Abstract: An electronic apparatus and a controlling method thereof are provided. The method of controlling an electronic apparatus according to an embodiment includes: obtaining first text information including a plurality of words, identifying a security level of the first text information based on at least one of a source from which the first text information is obtained or a type of the first text information, obtaining second text information by converting at least one of the plurality of words included in the first text information based on the identified security level, and obtaining first summary sentence information summarizing the second text information through a summary module.

Abstract: Disclosed is an electronic device. The electronic device may execute an application for transmitting and receiving at least one of text data or voice data with another electronic device using the communication module, in response to occurrence of at least one event, based on receiving at least one of text data or voice data from the another electronic device, identify that a confirmation is necessary using the digital assistant based on at least one of text data or voice data being generated based on a characteristic of ab utterance using a digital assistant, generate a notification to request confirmation using the digital assistant based on confirmation being necessary, and output the notification using the application. A method for identifying that a confirmation is necessary may include identifying using voice data or text data that is received from another electronic device using a rule-based or AI algorithm.

Abstract: The disclosure refers to electronic apparatuses and controlling methods thereof. In an embodiment, an electronic apparatus includes an input interface, an output interface, and a processor that is communicatively coupled to the input interface and the output interface. The processor is configured to control the input interface to receive conversation data including one or more texts and one or more images. The processor is further configured to extract a first text and an image from the conversation data. The processor is further configured to identify a meaning of the conversation data based on at least one of the first text and the image. The processor is further configured to control the output interface to output the meaning of the conversation data.

Abstract: Disclosed is an electronic device. The electronic device may execute an application for transmitting and receiving at least one of text data or voice data with another electronic device using the communication module, in response to occurrence of at least one event, based on receiving at least one of text data or voice data from the another electronic device, identify that a confirmation is necessary using the digital assistant based on at least one of text data or voice data being generated based on a characteristic of ab utterance using a digital assistant, generate a notification to request confirmation using the digital assistant based on confirmation being necessary, and output the notification using the application. A method for identifying that a confirmation is necessary may include identifying using voice data or text data that is received from another electronic device using a rule-based or AI algorithm.

Abstract: Disclosed are an electronic device, a system, and a controlling method thereof. The controlling method includes: receiving an input utterance, determining whether domain information and intent information are able to be extracted by analyzing the input utterance, based on at least one of the domain information and the intent information not being extracted, broadcasting a signal requesting previous utterance related information to one or more external devices connected to a same network as the electronic device, receiving the previous utterance related information from the at least one external device, extracting the domain information and the intent information based on the received previous utterance related information and the input utterance, and obtaining and outputting a response result based on the extracted domain information and intent information.

Abstract: A control method of an electronic apparatus includes clustering words included in a plurality of domains respectively into a plurality of clustering groups based on information corresponding to the plurality of domains; obtaining an embedding vector between the words and the plurality of clustering groups based on learning data corresponding to respective domains, the words, and mass text learning data; and generating one or more final clustering groups of the words based on the obtained embedding vector and the plurality of clustering group.

Abstract: Provided are an electronic device for correcting a speech input, and an operating method thereof. The method may include receiving a first speech signal; obtaining first text; obtaining an intent of the first speech signal and a confidence score of the intent, by inputting the first text to a natural language understanding model; identifying a plurality of correction candidate semantic elements capable of being correction targets in the first text; receiving a second speech signal; obtaining second text; identifying whether the second speech signal is a speech signal for correcting the first text; comparing the plurality of correction candidate semantic elements in the first text with a semantic element in the second text, based on the confidence score; and correcting at least one of the plurality of correction candidate semantic elements in the first text.

Abstract: A mobile device includes: a location sensor configured to detect a location of the mobile device; a timer; a microphone configured to receive an utterance input of a user; a communication interface; a memory; and a processor. The processor is configured to execute one or more instructions stored in the memory to extract, from the utterance input of the user, element information corresponding to a command controlling a target device and detection condition information of the target device; detect first context information using the location sensor and the timer; determine whether the detected first context information satisfies the detection condition information of the target device; and process the command corresponding to the element information of the command, based on a result of the determination.

Abstract: Disclosed is a method for controlling an electronic apparatus. A method for controlling an electronic apparatus includes: obtaining a speech signal; obtaining a first sentence based on the speech signal and obtaining a first feature value for the first sentence by inputting the first sentence to a natural language understanding module; obtaining first semantic information corresponding to the first sentence and obtaining a second feature value for the first semantic information by inputting the first semantic information to a natural language generation module; and training the natural language understanding module and the natural language generation module to provide the first feature value and the second feature value within a predetermined distance in a vector space.

Abstract: Artificial intelligence for machine learning to provide an optimized response sentence in reply to an input sentence.

Abstract: An electronic apparatus is provided. The electronic apparatus includes a memory storing information regarding a plurality of voice assistants, and a processor. The processor may be configured to, based on a voice of a user being input via a microphone, identify a voice assistant among the plurality of voice assistants based on the user's voice, and identify whether the identified voice assistant is able to provide a response to the voice, by inputting a text converted from the user's voice to an artificial intelligence model trained based on texts recognizable by the identified voice assistant, based on the identified voice assistant being identified to be unable to provide a response to the voice, obtain a response to the voice from at least one of the plurality of voice assistants other than the identified voice assistant, and output at least one of the plurality of obtained responses as a response to the voice.

Abstract: An electronic apparatus and a controlling method thereof are provided. The method of controlling an electronic apparatus according to an embodiment includes: obtaining first text information including a plurality of words, identifying a security level of the first text information based on at least one of a source from which the first text information is obtained or a type of the first text information, obtaining second text information by converting at least one of the plurality of words included in the first text information based on the identified security level, and obtaining first summary sentence information summarizing the second text information through a summary module.

Abstract: Disclosed is a method for controlling an electronic apparatus. A method for controlling an electronic apparatus includes: obtaining a speech signal; obtaining a first sentence based on the speech signal and obtaining a first feature value for the first sentence by inputting the first sentence to a natural language understanding module; obtaining first semantic information corresponding to the first sentence and obtaining a second feature value for the first semantic information by inputting the first semantic information to a natural language generation module; and training the natural language understanding module and the natural language generation module to provide the first feature value and the second feature value within a predetermined distance in a vector space.

Abstract: Disclosed is an electronic device. The electronic device may execute an application for transmitting and receiving at least one of text data or voice data with another electronic device using the communication module, in response to occurrence of at least one event, based on receiving at least one of text data or voice data from the another electronic device, identify that a confirmation is necessary using the digital assistant based on at least one of text data or voice data being generated based on a characteristic of abutterance using a digital assistant, generate a notification to request confirmation using the digital assistant based on confirmation being necessary, and output the notification using the application. A method for identifying that a confirmation is necessary may include identifying using voice data or text data that is received from another electronic device using a rule-based or AI algorithm.

Abstract: Artificial intelligence for machine learning to provide an optimized response sentence in reply to an input sentence.

Abstract: A speech recognition device and a method thereof are disclosed. The speech recognition method includes detecting an error word of a recognized received speech, separately encoding a right part and a left part with respect to the detected error word, and decoding while correcting the error word based on a vector of the encoded right and left parts, a last character of the encoded right part, and a last character of the left part.