Abstract: An example electronic device includes a display, a communication circuit, a memory, and at least one processor configured to, based on a signal for requesting transmission of identification information including a call word for using first mode of an artificial intelligence assistant function of the electronic device being received, from another electronic device, through the communication circuit using first communication method, control the display to display a user interface for requesting user confirmation for transmission of the identification information; control the communication circuit to transmit the identification information to the another electronic device as a result of user confirmation through the user interface; and receive information for using a second communication method from the another electronic device.

Abstract: The disclosure is for a video caption generation apparatus and method thereof to generate a natural language sentence explaining a video used as input. The disclosure is configured by including an embedding unit to perform a video embedding and a category information embedding, a stack embedding encoder block unit to select a feature by utilizing the embedded video vector and category vector, a video-category attention unit to receive a result of the stack embedding encoder, to generate a similarity matrix and a feature matrix for a video and category information, and to provide a final encoding result, and a decoder module to generate a sentence by utilizing the final encoding result.

Abstract: A device for detecting a morpheme tagging corpus error, of the present invention, includes: an attribute generating unit for generating attributes for word phrases included in an input corpus, by using a kernel to which a rough set theory is applied; and an attribute statistics processing unit for generating part-of-speech tagging corpus error data through the calculation of attributes and frequency count for the same word phrases by counting attributes for the same word phrase among the word phrases, and thus the present invention can detect, quantify, and modify errors included in a corpus (learning data) required in learning for classifier generation and recognition for natural language processing.

Abstract: A device for detecting a morpheme tagging corpus error, of the present invention, includes: an attribute generating unit for generating attributes for word phrases included in an input corpus, by using a kernel to which a rough set theory is applied; and an attribute statistics processing unit for generating part-of-speech tagging corpus error data through the calculation of attributes and frequency count for the same word phrases by counting attributes for the same word phrase among the word phrases, and thus the present invention can detect, quantify, and modify errors included in a corpus (learning data) required in learning for classifier generation and recognition for natural language processing.

Abstract: An apparatus and method summarize a user's daily life information. The apparatus includes an information collection unit, an analysis unit, a story generator, and a display unit. The information collection unit collects log information including user's daily life information, from at least one electronic device. The analysis unit analyzes the log information collected from the information collection unit and decides at least one topic representing the user's daily life information. The story generator generates at least one sentence representing the user's daily life information using the at least one topic decided in the analysis unit. The display unit displays the at least one sentence generated in the story generator.

Abstract: An apparatus and method summarize a user's daily life information. The apparatus includes an information collection unit, an analysis unit, a story generator, and a display unit. The information collection unit collects log information including user's daily life information, from at least one electronic device. The analysis unit analyzes the log information collected from the information collection unit and decides at least one topic representing the user's daily life information. The story generator generates at least one sentence representing the user's daily life information using the at least one topic decided in the analysis unit. The display unit displays the at least one sentence generated in the story generator.

Abstract: A method and system for assessing a user reputation and/or a content reliability on contents sharing web sites is provided. In one embodiment, the method includes defining a networked association between users based on social activity information related to the users' social activities on a contents sharing web site, the users' social activities including social activities between the users and/or social activities of the users on the contents sharing web site; obtaining a link relation for at least one of the users based on the networked association; and computing a user reputation for the at least one of the users based on the link relation. The method may further include computing a content reliability of the at least one user-created contents based on the computed user reputation.

Abstract: A method and system for assessing a user reputation and/or a content reliability on contents sharing web sites is provided. In one embodiment, the method includes defining a networked association between users based on social activity information related to the users' social activities on a contents sharing web site, the users' social activities including social activities between the users and/or social activities of the users on the contents sharing web site; obtaining a link relation for at least one of the users based on the networked association; and computing a user reputation for the at least one of the users based on the link relation. The method may further include computing a content reliability of the at least one user-created contents based on the computed user reputation.