Personalizing user interfaces across operating systems

Abstract

A user-centered interface agent eases the problem of unfamiliar user interfaces on host computers. The agent operates by learning user preferences and typical behaviors and predicting the user's preferred user interface for different types of host computers. Most of the agent's learning is through observation, requiring minimal-initialization by the user. The interface agent consists of a learning program which operates on the user's primary computer, a shadow program which is installed on a Personal Digital Assistant (PDA), and a remote program which operates on host computers. The role of the PDA includes the transfer of data between the primary and remote machines, and the PDA can also be the user's primary computer. On the primary computer, the agent learns a user's preference by observing the user's actions. The user may run agent-training module or directly query and modify the agent's current state of knowledge, but the user is not forced to explicitly teach the agent. The learning algorithm may be statistical, rule-based, case-based, neural network, or employ any other technique for reasoning under uncertainty. The automated way of reaching a usable configuration has a particular advantage for individuals with disabilities who require configuration before they can use a new computer system.

Dependencies are inferred from the claim text.