| 摘要 |
The present invention relates to a program that allows a conversation to be performed with a user in a natural and human-like manner. Each of response candidate generating modules 54a through 54c generates response candidate data based on its own rule, in response to voice data input from the outside through an input module 51 and a response selecting module 52, and calculates a score of the response candidate data based on the response candidate data, the voice data and internal status data recorded in an internal status recording module 55, and then supplies the score to a response selecting module 52. In response to the supplied score, the response selecting module 52 selects, as response data responsive to the input voice data, one piece of response candidate data, and outputs the one piece of response candidate data through a response output module 53. The present invention is applicable to a voice interactive apparatus mounted on a robot, etc.
|
