Intelligent feature identification and presentation
A method and system for providing one or more suggested application features to a user of an application may include receiving an indication of a user action in a document, accessing contextual document data associated with the document, providing at least one of information about the user action or the contextual document data as input to a machine-learning (ML) model to predict a desired intent for the document, obtaining the predicted desired intent as an output from the ML model, identifying based on the predicted desired intent one or more application features that fulfil the desired intent, and providing data about the one or more application features for display.
1. A data processing system comprising:
a processor; and
a memory in communication with the processor, the memory comprising executable instructions that, when executed by the processor, cause the data processing system to perform functions of:
receiving a user request from within a content pane displaying a document;
in response to the user request, generating a user interface element on the content pane, the document being a currently open document in an application, and the user interface element being a selectable input box for receiving one or more search terms;
displaying the user interface element on the content pane;
receiving user selection of the input box from a user to select the user interface element;
in response to receiving the user selection, accessing contextual document data associated with the document;
providing content of the document, user-specific information for the user, one or more recent actions of the user and the contextual document data as input to a machine-learning (ML) model to predict a desired intent for completing a task with respect to the document;
obtain the predicted desired intent as an output from the ML model;
identify a command provided by the application for achieving the predicted desired intent;
displaying a selectable user interface menu on the content pane for selecting the identified command
receiving an indication of selection of the identified command; and
responsive to receiving the indication of the selection, completing a task associated with the predicted desired intent.
2. The data processing system of claim 1 , wherein the user input from the user to select the user interface element initiates a zero-term search.
3. A method for completing a task in an application, comprising:
receiving a user request from within a content pane displaying a document;
in response to the user request, generating a user interface element on the content pane, the document being a currently open document in the application, and the user interface element being a selectable input box for receiving one or more search terms;
displaying the user interface element on the content pane;
receiving user selection of the input box from a user to select the user interface element;
in response to receiving the user selection, accessing contextual document data associated with the document;
providing content of the document, user-specific information for the user, one or more recent actions of the user and the contextual document data as input to a machine-learning (ML) model to predict a desired intent for completing a task with respect to the document;
obtain the predicted desired intent as an output from the ML model;
identify a command provided by the application for achieving the predicted desired intent;
displaying a selectable user interface menu on the content pane for selecting the identified command
receiving an indication of selection of the identified command; and
responsive to receiving the indication of the selection, completing a task associated with the predicted desired intent.
4. The method of claim 3 , wherein the user input from the user to select the user interface element initiates a zero-term search.
5. A non-transitory computer readable medium on which are stored instructions that, when executed, cause a programmable device to:
receiving a user request from within a content pane displaying a document;
in response to the user request, generating a user interface element on the content pane, the document being a currently open document in an application, and the user interface element being a selectable input box for receiving one or more search terms;
displaying the user interface element on the content pane;
receiving user selection of the input box from a user to select the user interface element;
in response to receiving the user selection, accessing contextual document data associated with the document;
providing content of the document, user-specific information for the user, one or more recent actions of the user and the contextual document data as input to a machine-learning (ML) model to predict a desired intent for completing a task with respect to the document;
obtain the predicted desired intent as an output from the ML model;
identify a command provided by the application for achieving the predicted desired intent;
displaying a selectable user interface menu on the content pane for selecting the identified command
receiving an indication of selection of the identified command; and
responsive to receiving the indication of the selection, completing a task associated with the predicted desired intent.
6. The non-transitory computer readable medium of claim 5 , wherein the user input from the user to select the user interface element initiates a zero-term search.