摘要 |
This conversation-sentence generation device: accepts input information consisting of a conversation sentence from a user to an agent, first hint information for extrapolating the physical and mental state of the agent, and second hint information for extrapolating the physical and mental state of the user; stores an agent state consisting of the physical and mental state of the agent; stores a user state consisting of the physical and mental state of the user; uses the input information and the agent state to extrapolate a new agent state; uses the input information and the user state to extrapolate a new user state; uses the input information, the agent state, and the user state to generate an utterance intent, i.e. the intent of an utterance from the agent to the user; uses the input information, the agent state, the user state, and the utterance intent to generate a conversation sentence from the agent to the user; and outputs said conversation sentence. |