US 7,519,676 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. 11/47,210.
Application 11/047210 is a division of application No. 09/894087, filed on Jun. 28, 2001, granted, now 7,409,423.
Prior Publication US 2005/0132005 A1, Jun. 16, 2005
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 15/16 (2006.01)
U.S. Cl. 709—207  [709/204] 16 Claims
OG exemplary drawing
 
1. An information transfer system, comprising a processor and a computer readable storage medium having stored thereon the following components:
a predictive component to estimate when a user will likely be in a setting have access to a messaging system to review one or more messages; and
an answering component to automatically provide an adaptive message reply in association with the predictive component relating to when the user is likely to have access to the messaging system to review the one or more messages wherein the adaptive message reply includes dynamically computed user availability status comprising a confidence measure that the user will return in an expected timeframe, the dynamically computed user availability status, includes a forecast of an expected time for at least one of until the user will likely review the messages, be available to review the messages, or be in a particular situation wherein the expected time is computed as a sum of times, weighted by different likelihoods of expected time of return and the confidence measure is updated over time as new information is received from one or more context information sources.