A Recommendation-type Dialogue System Responding to Potential Requests in Consideration of Personal Attributes

A dialogue system that responds mechanically to given queries can be used for public relations prospective university students. However, as a user-specific problem, collecting information from first-time entrances and passive examinations is difficult, conventional may not collect sufficient information. Therefore, we developed recommendation-type supports gathering by evoking potential user requests. Based on the preference analysis results using previous real-time query histories recommended universities, in form of users when considering their personal attributes. We evaluated presence or absence recommendation function implemented an introduction evaluation targeting those who wish enroll university. The average number increases requests, supported.