| 摘要 |
<p>A speech recognition unit (2) performs speech recognition on a speech of an utterer input by a speech input unit (1), specifies possible words which are represented by the speech, and the scores thereof, and a natural language analyzer (3) specifies parts of speech of the words and supplies word data representing the words to an agent processing unit (7). The agent processing unit (7) stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a weighting factor to the transition, and executes a flow represented generally by the process item data and the wires to thereby control devices belonging to an input/output target device group (6) in such a way as to adequately grasp a demand of the utterer and meet the demand.</p> |
