Abstract: A method comprises constructing, for a specific activity, a decision model based on action data of one or more actions, each action having an identifier of an activity performed with a computer application, use data being operated on by the computer application, and a timestamp, the decision model including a rule specifying a first activity as a next activity or a probabilistic classifier that accepts use data being operated on via the specific activity and outputs an identifier of an activity to be performed as a next activity with a probability. The method comprises detecting performance of the specific activity, when the decision model for the specific activity includes the rule, automatically applying the rule, and when the decision model for the specific activity includes the probabilistic classifier and no applicable rule: executing the probabilistic classifier to obtain a list of candidate next activities and an associated list of probabilities.

Abstract: A system for predicting and automatically performing activities related to computer applications is disclosed. In some embodiments, the system is programmed to monitor user interactions with computer applications and detect use events that represent computer-related activities that can be sequentially performed based on information regarding the previous activity in the sequence. The system is programmed to create, for each use event, an action that indicates an activity performed using a computer application, use data being operated on by the computer application, and a timestamp. The system is programmed to then build a decision model for each activity that predicts the next activity with a probability. Subsequently, the system is programmed to detect a current use event, create a current action indicating the current activity, apply the decision model for the current activity, create the next action based on the application result, and automatically effect the next use event.