| 摘要 |
<p>A system (10) for automatically responding to an inquiry from a user comprises a dialogue manager (50), which executes a machine-controlled human-machine dialogue to determine a plurality of pre-determined query items. The dialogue manager (50) retrieves a plurality of information items from a storage (52) in dependence on the query items. The system further comprises a presentation manager (90) which determines an intention of the user, reflecting a preferred way of presenting the information items. The presentation manager (90) selects a presentation scenario from a predetermined set of presentation scenarios (96) in dependence on the determined intention. At least one natural language phrase is generated to present the obtained information items according to the selected presentation scenario. A speech generator (60) verbally presents the generated phrase(s) to the user.</p> |
