| 摘要 |
<p>A method for providing recommendations to a user based on user activity. A plurality of activity data tracking a plurality of activities of a user is obtained. The activity data may be obtained over a wide area net network such as the Internet or downloaded from a data card (30) which stores activity data whenever the user participates in an activity. The activity data is either stored on the data card (26) or transmitted over the network (14) whenever the user uses a card when participating in any activity such as when making a purchase of goods, paying for services, watching television, etc. The activity data is processed to identify a plurality of user patterns. The user patterns are used to form a user profile (48) and may include user habit data. Recommendations specific to the user based on the user patterns are then created for and provided to the user. The recommendations are provided to a user when the user logs onto a computer network such as the Internet. Electronic mail, electronic pager or other methods may alsalso provide the recommendations. The recommendations are provided by various data analysis techniques including rule based inference engines and other forms of artificial intelligence.</p> |
