公开(公告)号：US20250103636A1

公开(公告)日：2025-03-27

申请号：US18474878

申请日：2023-09-26

Applicant: Dropbox, Inc.

Inventor： Richard Chan ,  Devin Mancuso ,  Sateesh Srinivasan ,  Yidi Zhang

IPC: G06F16/34 ,  G06F16/335 ,  G06F16/338

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and providing an aggregated feed interface that includes or presents aggregate summaries for thread data across multiple data feeds of a user account. In some embodiments, the disclosed systems generate an aggregate summary by extracting digital communications and other thread data from a variety of data feeds across multiple computer applications and by utilizing a summary generation model to generate an aggregate summary that combines and condenses the thread data from the different data feeds. For example, the disclosed systems determine topics associated with thread data from various data feeds and generates different aggregate summaries for different topics. The disclosed systems can further rank aggregate summaries and/or other digital communications to present within the aggregated feed interface according to an account-specific ranking algorithm resulting a customized per-account presentation of the aggregated feed interface.

公开(公告)号：US20250111149A1

公开(公告)日：2025-04-03

申请号：US18478066

申请日：2023-09-29

Applicant: Dropbox, Inc.

Inventor： Vasanth Krishna Namasivayam ,  Devin Mancuso ,  Geoff Hulten ,  Shubham Goel ,  Sateesh Srinivasan ,  Tony Xu

IPC: G06F40/20 ,  G06F11/34

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating composite actions for a user account. In particular, in one or more embodiments, the disclosed systems determine a set of tasks performable by the user account using software tools on a client device. In some embodiments, the disclosed systems generate a task initialization prompt to provide to a large language model. Additionally, in some implementations, the disclosed systems generate a composite action comprising a hybridized combination of the set of tasks performable by the user account along with a set of content items relevant to the set of tasks. Moreover, in some embodiments, the disclosed systems provide access to the composite action and the set of content items via a user interface of the client device. Furthermore, in some implementations, the disclosed systems generate and insert predicted content into a content item without user input.

公开(公告)号：US20250111148A1

公开(公告)日：2025-04-03

申请号：US18478061

申请日：2023-09-29

Applicant: Dropbox, Inc.

Inventor： Vasanth Krishna Namasivayam ,  Devin Mancuso ,  Geoff Hulten ,  Shubham Goel ,  Sateesh Srinivasan ,  Tony Xu

IPC: G06F40/20

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating composite actions for a user account. In particular, in one or more embodiments, the disclosed systems determine a set of tasks performable by the user account using software tools on a client device. In some embodiments, the disclosed systems generate a task initialization prompt to provide to a large language model. Additionally, in some implementations, the disclosed systems generate a composite action comprising a hybridized combination of the set of tasks performable by the user account along with a set of content items relevant to the set of tasks. Moreover, in some embodiments, the disclosed systems provide access to the composite action and the set of content items via a user interface of the client device. Furthermore, in some implementations, the disclosed systems generate and insert predicted content into a content item without user input.