Abstract: Systems and processes for navigating and performing device tasks using a search interface are provided. For example, a first user input including at least one character is received. Based on the first user input, a first task among a plurality of tasks is displayed, wherein the first task is associated with a confidence value exceeding a threshold confidence value. A second input corresponding to an activation on the first task is received. In accordance with a determination that the activated task corresponds to a predetermined task type performance of the activated task is initiated, and a respective interface corresponding to the initiated task is displayed. In accordance with a determination that the activated task does not correspond to the predetermined task type, the system causes the activated task to be performed without displaying the respective interface.

Abstract: Systems and processes for operating an intelligent automated digital assistant on an electronic device are provided. In particular, this paper describes the automatic registration of voice-activated shortcuts for a particular application at a vocabulary engine associated with the intelligent automated digital assistant. In some embodiments the automatic registration can be performed during installation or update of an application. Automatic registration can also be initiated after entry of particular types of data into the application or a determination that a particular feature of the application is being commonly used.

Abstract: A system for determining relevant information based on user interactions may include a processor configured to receive application data from one or more applications, the application data including features related to user activity from the one or more applications, the one or more application including applications local to the device that are stored in the memory and applications external to the device. The processor may be further configured to provide, using a machine learning (ML) model, a relevance score for each of one or more user interface (UI) elements based on each of the features. The processor may be further configured to sort one or more UI elements based on a ranking of the relevance scores. The processor may be further configured to provide, as output, the one or more UI elements based at least in part on the ranking.

Abstract: A system for determining relevant information based on user interactions may include a processor configured to receive application data from one or more applications, the application data including features related to user activity from the one or more applications, the one or more application including applications local to the device that are stored in the memory and applications external to the device. The processor may be further configured to provide, using a machine learning (ML) model, a relevance score for each of one or more user interface (UI) elements based on each of the features. The processor may be further configured to sort one or more UI elements based on a ranking of the relevance scores. The processor may be further configured to provide, as output, the one or more UI elements based at least in part on the ranking.

Abstract: A system for determining relevant information based on user interactions may include a processor configured to receive application data from one or more applications, the application data including features related to user activity from the one or more applications, the one or more application including applications local to the device that are stored in the memory and applications external to the device. The processor may be further configured to provide, using a machine learning (ML) model, a relevance score for each of one or more user interface (UI) elements based on each of the features. The processor may be further configured to sort one or more UI elements based on a ranking of the relevance scores. The processor may be further configured to provide, as output, the one or more UI elements based at least in part on the ranking.