| 摘要 |
A method for authoring content of a computer-controlled agent includes the steps of identifying a potential context of the agent to an author; receiving content for the agent in the potential context from the author; and storing the content such that it can be accessed by a run-time agent. The run-time agent uses the content to control behavior of the agent in an actual context that matches the potential context. Context is typically presented to the author via a graphical user interface that allows the author to enter content without having any technical understanding of the run-time engine or the system's computer code. When the agent is authored using the authoring method, it can interact with a user through dialogue and gestures that are specific to contexts defined by user input, internal states or events of the agent, or input from other systems. For example, the agent responds to user questions differently when in different moods, and the agent's moods change in response to user statements or actions the agent performs.
|
