Information Technology Reference
In-Depth Information
Fig. 1.
Dynamic baysian network for mood estimation
of the behavior network comes from DBNs output, which consists of user and the
agents internal (or a remote user) mood and local time. There are three goals
in this behavior network, imitation, feedback and special time. The imitation
goal triggers the character to emulate his or her partner's mood. The feedback
goal intends to give feedback for the user's mood. The special time goal greets
the user about the time change. The special time goal is triggered when there
is a change in the time period, such as morning afternoon and evening. The
feedback goal will be triggered only when there is a prominent user's mood that
reaches a certain threshold, otherwise the imitation goal will be activated. In
the feedback mode, the personality of the partner is considered and represented
by the animation speed. The behavior network will determine the animation
of the character behavior, and the animation speed of the character depend on
the personality of the partner. The more extrovert the partner is, the faster the
animation of the character will move. The designed behavior network is shown
in 2.
2.3 Visualization of the Working Process of the System
In order to demonstrate the generated behaviors of artificial companion, an
experiment with two partners is performed. The reason for choosing a second
real user (partner) is to attribute the artificial agent's mood to a real user.
Artificial agents with anthropomorphic features could be perceived more natural
and realistic [2]. The first five sets of the mood data from the user, and its partner
with the respective animated agent's behavior is shown in figure3. The proposed
AI is applied in a smartphone Android app and the prototype screen shot is
shown in Figure 3f.
