Contextual prediction of user words and user actions

摘要

An operating sequence for a handheld computing device manages the device to automatically detect cues describing the device's environmental and user actions performed with the device, learn which cues and cue combinations are relevant to predict user actions, and then in response to occurrence of the relevant cues, predictively implementing the appropriate user action or configuring the device in anticipation of user action.

主权项

1. A handheld computing device, comprising:
a user interface; a digital data processor coupled to the user interface and programmed to perform operations comprising:
over time, monitoring and recording cues describing the device environment and monitoring and recording user performed actions of configuring the device and operating its application programs;learning which if any of the recorded cues and combinations of recorded cues are relevant predictors of which of the recorded user actions;for each user action having a learned relevant predictor, planning one or more of the following types of machine-executed actions:
configuring the device to streamline user performance of the user action;causing the device to perform the user action;responsive to occurrence of learned relevant predictors of user actions, performing the machine-executed actions planned for the learned relevant predictors that occurred;the operations further comprising prioritizing interpretation of inherently ambiguous user-entered text input by favoring a disambiguated interpretation consistent with the present environment of the device, where the present environment of the device includes detected geographic location and the prioritizing operation comprises planning a disambiguation operation comprising favoring interpretations of user-entered text input consistent with said geographic location.