US 7,490,122 B2
Methods for and applications of learning and inferring the periods of time until people are available or unavailable for different forms of communication, collaboration, and information access
Eric J. Horvitz, Kirkland, Wash. (US); Carl M. Kadie, Bellevue, Wash. (US); and Andrew W. Jacobs, Seattle, Wash. (US)
Assigned to Microsoft Corporation, Redmond, Wash. (US)
Filed on Jan. 31, 2005, as Appl. No. 11/47,527.
Application 11/047527 is a division of application No. 09/894087, filed on Jun. 28, 2001.
Prior Publication US 2005/0132006 A1, Jun. 16, 2005
Int. Cl. G06F 15/16 (2006.01)
U.S. Cl. 709—200  [709/204; 709/205; 706/11; 706/45; 706/46; 706/52; 706/61] 13 Claims
OG exemplary drawing
 
1. A communications system providing fine-grained inferences of a user, comprising:
a processor communicatively coupled to a memory having stored therein a first component that reasons about the amount of time until a user will be available for at least one of a type of interaction or a communications with a message sender, the first component reasons by learning statistics about at least a state of the user from one or more context information sources and building one or more prediction models from the statistics, wherein the one or more prediction models infer the user availability;
a second component that automatically responds to the message sender in relation to the reasoning of the first component, tracks the automatic responses communicated to the message sender and based on identity of the message sender provides updates with a recommendation about another channel of communication to the message sender if the reasoning of the first component fails; wherein the first component determining when a user will be available to be interrupted with a particular class of alert or notification; and wherein the determination is based on at least one of patterns of availability, inferences about a workload or associated cost of an interruption.