Abstract: A computing system can provide enhanced control responsive to ambient interactions from a user. The computing system can obtain context data including an ambient audio signal. The computing system can generate a command path based at least in part on the context data. The command path can include an ordered one or more command actions. The computing system can provide an interactive user interface element depicting the command path to the user. The interactive user interface element can enable the user to select a selected command action of the ordered one or more command actions for performance by the computing system. The computing system can, in response to providing the command path to the user, receive, from the user, the selected command action of the ordered one or more command actions.

Abstract: An annotating system aids a user in mapping a large number of queries to tasks to obtain training data for training a search component. The annotating system includes a query log containing a large quantity of queries which have previously been submitted to a search engine. A task list containing a plurality of possible tasks is stored. A machine learning component processes the query log data and the task list data. For each of a plurality of query entries corresponding to the query log, the machine learning component suggests a best guess task for potential query-to-task mapping as a function of the training data. A graphical user interface generating component is configured to display the plurality of query entries in the query log in a manner which associates each of the displayed plurality of query entries with its corresponding suggested best guess task.