Conceptual clustering of structured objects: a goal-oriented approach
Artificial Intelligence
Experience with a learning personal assistant
Communications of the ACM
Proceedings of the 5th international conference on Intelligent user interfaces
GOOSE: A Goal-Oriented Search Engine with Commonsense
AH '02 Proceedings of the Second International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems
Active preference learning for personalized calendar scheduling assistance
Proceedings of the 10th international conference on Intelligent user interfaces
Enabling rich human-agent interaction for a calendar scheduling agent
CHI '05 Extended Abstracts on Human Factors in Computing Systems
A goal-oriented interface to consumer electronics using planning and commonsense reasoning
Proceedings of the 11th international conference on Intelligent user interfaces
Conflict negotiation among personal calendar agents
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Automating to-do lists for users: interpretation of to-dos for selecting and tasking agents
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
| Hi-index | 0.01 |
Personal event management involves planning when, where and how events should occur, making sure the event's prerequisites are satisfied, and developing contingencies for when things go wrong. Conventional calendar and project management tools, however, only record and visualize explicit human decisions regarding event specifics. We present Event Minder, a calendar program that takes into account the goals for which the events are scheduled. Users can input descriptions of events in natural language, mixing high-level objectives, concrete time and place decisions, and omit "obvious" common sense details. A commonsense knowledge base provides sensible defaults, and machine learning refines these defaults with experience. We can make recommendations for alternative plans, including alternatives that satisfy higher-level goals in different ways as well as those that meet immediate constraints. Our current system covers dining-related events, integrating commonsense with domain knowledge about specific restaurants, bars and hotels.