Semantic selection and purpose facilitation

摘要

Computer-implemented methods for proposing actions to a user to select based on the user's predicted purpose for selecting content are provided. In one aspect, a method includes receiving an identifier of a referent entity associated with user-selectable content, identifying, based on a prediction of a purpose in selecting the content, at least one action to be executed that is associated with the entity, and providing, for display, at least one identifier of the at least one action to the device for selection by a user. Systems, graphical user interfaces, and machine-readable media are also provided.

主权项

1. A computer-implemented method for proposing actions to a user to select based on the user's predicted purpose for selecting content, the method comprising:
receiving an identifier of a referent entity from a device, the referent entity selected from a list of suggested entities identified from content displayed on the device, at least one of the suggested entities being associated with a weight value indicating a likelihood that the at least one suggested entity is a referent of the content; identifying at least one descriptor associated with the referent entity; identifying, based on a context in which the referent entity is selected by a user from the list of suggested entities, at least one action to be executed for the referent entity that is selected from a list of actions associated with the descriptor and the referent entity, the at least one action added to the list of actions in response to a previous action taken by the user or another user after the referent entity has been identified; and providing, for display, at least one identifier of the at least one action to the device for selection by the user.