Resumen
This article focuses on the working of intelligent software agents in computers. Researchers feel that they should have the ability to inter appropriate high-level goals from user actions and requests and take action to achieve these goals. The system described here called Apple Data Detectors, meets the criteria of being unobtrusive, being able to infer user needs, and doing useful work. Apple Data Detectors is a first step toward extracting semantics from everyday documents without asking users to create documents in new ways. Such an intelligent agent redefines "document" from a stream of characters to a data structure containing specific, known kinds of structures that can play specific, known roles in user interactions. Researchers have used machine learning techniques to track user actions and construct models of user preferences, create explicit models of user knowledge and skill levels in an attempt to anticipate user actions, misconceptions, and information needs, and implement planning systems to leap from a user's stated intention to the specific actions required to achieve that intention. Apple Data Detectors is an open extensible system allowing the recognition and parsing of complex structures.