2. Topic 4: Overview
• Agents & Intelligent Agents
• Agent Models
• Bene
fi
ts of user adaptivity
• Usability challenges
• Collecting data from users
• Future needs in IUI’s
2
3. Agents & Intelligent Agents
• Complex systems: Arti
fi
cial vs. Natural
• Intelligent Agents: autonomous & cooperative
• Environment as the problem space: deterministic
vs. stochastic
• Uses a perception of the environment status to take
decisions
• Uses and provides functions
4. Agents & Intelligent Agents
• Important characteristics of agents include:
• Rationality; agent acts to achieve goals, taking
the right decision in every situation
• Behaviour depends on (a) performance
measure, (b) knowledge of environment, (c)
sequence of perceptions
• Autonomy; agent takes initiative with a non-trivial
degree of control over its actions
5. Agent Models
• Simple Re
fl
ex; decision based on current perception
• Model-based Re
fl
ex; when the world is not fully observable
• Goal-based; agent is wholly dedicated to achieving end
goals, no matter how complex
• Utility-based; similar to goal-based but agent knows the
utility function
• Learning; knowledge is expanded learning from past
experiences
7. Agent Environment Space
The Design Perspective
• Basic - agents access their deployment
context directly
• Abstraction -
fi
lling in conceptual gap between
agent abstraction and deployment context
• Interaction/Mediation - supporting both
perspectives and support coordination
between agents
8. Agent Interactions
Agent viewed as ‘the one who acts’
• Situated; being immersed in an environment
• Social; reconciles individual cognitive processes
and social coordinations
• Simulated; dynamic processes of agent interaction
repeated over time
9. Interface Agents
Why design them?
• To improve communication between humans and
computers.
• To enhance the
fl
exibility, usability, and power of
human-computer interaction for all users.
HCI scientists exploit knowledge of users, tasks,
tools, and content, as well as devices for supporting
interaction within different contexts of use.
9
10. In simple terms, an intelligent interface agent provides
a way for a system to learn something about each
individual user and adapt its behaviour to them in
some nontrivial way.
11. • Amazon adapts its recommendation system to the
user’s previous history of purchase. Depending on
their function and form, systems that adapt to their
users have been given labels ranging from
adaptive interfaces through user modelling
systems to software agents or intelligent agents.
• However a common property binding these
systems or agents is user-adaptivity
12. Systems where the
intelligence lies mainly in UIs
• Systems with adaptive user interfaces that are automatically
adapted to the inferred capabilities or needs of the user.
• Multimodal systems that aim to enable more natural, human-like
forms of input and output.
• Systems with human-like virtual characters that enable the user to
interact with a system in a way that is partly similar to human-
human interaction.
• Smart environments in which embedded objects interact
intelligently with their users.
• Personalised websites, in which the displayed content is adapted
to the inferred interests of the user.
13. Systems where the intelligence
lies mainly behind UIs
• Recommender systems, which present products, documents, or other items that
are expected to be of interest to the current user.
• Systems that employ intelligent technology to support information retrieval.
• Learning environments that offer learning assistance on the basis of assessments
of each learner’s capabilities and needs.
• Interface agents that perform complex or repetitive tasks with some guidance from
the user.
• Situated assistance systems that monitor and support a user’s daily activities.
• Systems for capturing knowledge from domain experts who are not knowledge
engineers.
• Games that make use of AI technology to create the opponents against which the
human players play.
14. General schema for the processing in a user adaptive
system
(Dotted arrows: use of information; solid
arrows: production of results.)
15. • A user-adaptive agent system can be de
fi
ned as:
An interactive system that adapts its behaviour to
individual users on the basis of processes of user
model acquisition and application that involve
some form of learning, inference, or decision
making
18. Bene
fi
ts of user-adaptivity:
Functions: supporting system use
• Taking over parts of routine tasks;
• Adapting the interface;
• Helping with system use;
• Mediating interaction with the real world;
• Controlling a dialog;
19. Bene
fi
ts of user-adaptivity:
Functions: supporting information acquisition
• Helping users
fi
nd information;
• Recommending products;
• Tailoring information presentation;
• Supporting collaboration;
• Supporting learning;
20. Use of Data Collected
• The key difference between user-adaptive systems and
other interactive systems is the inclusion of some
method for acquiring and exploiting a user model.
• What is needed are (a) some implementation of the
adaptation algorithm, not necessarily embedded in any
interactive system; and (b) a database of behavioural
data from a number of users who have used a relevant
nonadaptive system. The researcher can then apply the
modelling method to the data in order to determine how
well the system would adapt to the users in question.
21. Future of User-adaptive
Systems
• Growing need for user-adaptivity;
• Diversity of Users and Contexts of Use
• Number and Complexity of Interactive Systems
• Scope of Information to Be Dealt With
22. Future of User-adaptive
Systems
• Increasing Feasibility of Successful Adaptation
• Ways of Acquiring Information About Users
• Advances in Techniques for Learning, Inference,
and Decision
• Attention to Empirical Methods