Abstract: This application relates to a computing system and method for an automated program error repair. In one aspect, the computing system includes a storage, a preprocessing processor, and an automated error repair processor. The storage stores a program code. The preprocessing processor acquires the program code from the storage and preprocesses the program code. Preprocessing includes tokenizing the program code with tokens, converting the tokens into vectors, and adding location information for the tokens. The automated error repair processor receives the preprocessed program code as an input from the preprocessing processor, detects an error in the preprocessed program code, corrects the detected error, and outputs the error-corrected program code. Detecting and correcting the error are performed based on a deep learning result and the location information for the tokens.

Abstract: This application relates to a computing system and method for an automated program error repair. In one aspect, the computing system includes a storage, a preprocessing processor, and an automated error repair processor. The storage stores a program code. The preprocessing processor acquires the program code from the storage and preprocesses the program code. Preprocessing includes tokenizing the program code with tokens, converting the tokens into vectors, and adding location information for the tokens. The automated error repair processor receives the preprocessed program code as an input from the preprocessing processor, detects an error in the preprocessed program code, corrects the detected error, and outputs the error-corrected program code. Detecting and correcting the error are performed based on a deep learning result and the location information for the tokens.

Abstract: A user adaptive conversation apparatus generating a talk for a conversation based on emotional and ethical states of a user. A voice recognition unit converts a talk of the user in a conversational situation into a natural language script form to generate talk information. An artificial visualization unit generates situation information by recognizing talking situation from a video and generates intention information indicating an intention of the talk. A natural language analysis unit converts the situation information and the intention information into the natural language script form. A natural language analysis unit analyzes the talk information, the intention information, and the situation information.

Abstract: A user adaptive conversation apparatus generating a talk for a conversation based on emotional and ethical states of a user. A voice recognition unit converts a talk of the user in a conversational situation into a natural language script form to generate talk information. An artificial visualization unit generates situation information by recognizing talking situation from a video and generates intention information indicating an intention of the talk. A natural language analysis unit converts the situation information and the intention information into the natural language script form. A natural language analysis unit analyzes the talk information, the intention information, and the situation information.

Abstract: The present disclosure provides a method and apparatus for enabling an early treatment of a health abnormality by analyzing a health condition of a user periodically and accumulating history information of user condition data. In the health care apparatus, instructions stored in a memory causes a processor to: load history information for a user from a memory; acquire an image and a voice of the user through the audio unit; perform a diagnosis process by analyzing the history information and the image and voice information of the user, and provide reference information to the user or perform a corresponding action depending on a diagnosis result; and update the history information stored in the memory by adding the image and voice information of the user, the diagnosis result, and the reference information or information of the corresponding action.

Abstract: Provided is a method for servicing queried contents using a Simple Object Access Protocol (SOAP) operation. The method includes transmitting a request message of a SOAP query operation to which a request element field type is added in order to request various content searches through a complex operation, and extracting a query result expression value corresponding to a table field designated in the request field type element, and adding the extracted query expression value to a query result element to transmit the added value by a response message of the SOAP operation, when the request message includes the request element field type designating a query request result value.

Abstract: Provided is a method for searching contents using a Simple Object Access Protocol (SOAP) operation. The method includes adding a request element field type in order to request various content searches through a comparison operation in a SOAP query operation, and transmitting a request message of the SOAP query operation to which the request element field type is added to a content service server. The method adds an operator associated with a comparison operation to a corresponding query request field which requests the search result of various contents to a SOAP query operation, thereby enabling to perform a content search by a complex operation expression.