Remembrance Agent: A Continuously Running Automated Information Retrieval System

The Remembrance Agent (RA) is a program which augments human memory by displaying a list of documents which might be relevant to the user’s current context. Unlike most information retrieval systems, the RA runs continuously without user intervention. Its unobtrusive interface allows a user to pursue or ignore the RA’s suggestions as desired. The Remembrance Agent Most of a desktop computer’s time is spent waiting: waiting for the user to hit the next keystroke, waiting for the user to read the next page, and waiting for the next packet to come down the network. The remembrance agent uses those wasted CPU cycles constructively by performing continuous searches for information that might be of use in its user’s current situation. For example, while an engineer reads email about a project the remembrance agent reminds her of project schedules, status reports, and other resources related to the project in question. When she stops reading email and starts editing a file, the RA automatically changes it recommendations accordingly. These suggestions are presented in the form of one-line summaries at the bottom of the screen. Here they can be easily monitored, but won’t distract from the primary work at hand. The full text of a suggestion can be brought up with a single keystroke. Most applications for augmenting human memory, e.g. those developed by (Jones 1986) and (Lamming & Flynn 1994), have concentrated on recall-on-demand. For example, they can answer questions such as "when is that conference paper deadline?". However, they do not address situations where a user does not remember enough to realize he or she has forgotten something in the first place. This associative form of recall is what reminds a user that an important conference exists at all. The Remembrance Agent augments this continuous, associative form of recall. Beyond simple memory enhancement, the RA also suggests alternative ways to organize knowledge. The connection between a suggested document and the user’s current context may not be obvious to the user until pointed out. In this way the RA both helps the user organize their own datafiles into new categories, and helps create continuous brainstorming session where new ideas and possible connections are suggested.