Abstract: A system is equipped with an audio data obtaining unit that obtains audio data of an explanation given to a patient by a physician, a data converting unit that converts the audio data obtained by the audio data obtaining unit into text data, a keyword extracting unit that extracts keywords which are set in advance from the text data converted by the data converting unit, a summary template storage unit that stores a plurality of summary templates in which explanations given to patients by physicians are summarized, and a summary template evaluating unit that evaluates the plurality of summary templates based on the keywords extracted by the keyword extracting unit.