公开(公告)号：US20240403597A1

公开(公告)日：2024-12-05

申请号：US18763972

申请日：2024-07-03

Applicant: Dropbox, Inc.

Inventor： Devin Mancuso

IPC: G06N3/02 ,  H04L51/216

Abstract: This disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that can utilize language neural networks to automatically generate draft electronic communications for a user account. For example, the disclosed systems leverage composition parameters of a user account (determined from historical electronic communications of the user account, digital content items corresponding to the user account, and/or other application data) with a neural network to automatically generate draft electronic communications that reflect a composition style of a user account and accurately addresses a context of a communication thread. In addition, the disclosed systems can generate electronic communications using the communication generation neural network and save the electronic communication as a draft (e.g., for review by a user of the user account) and/or automatically transmit the electronic message to a recipient user account.

公开(公告)号：US20240403086A1

公开(公告)日：2024-12-05

申请号：US18342469

申请日：2023-06-27

Applicant: Dropbox, Inc.

Inventor： Devin Mancuso ,  Jason Stakelon ,  Richard Chan

IPC: G06F9/451 ,  G06N3/042 ,  G06N3/0455

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating and providing an intelligent assistant interface that integrates with a large language model and a knowledge graph to adaptively change its appearance for presenting and interacting with different content items from various sources. In some embodiments, the disclosed systems provide an intelligent assistant interface that includes a set of interface elements selectable to interact with a large language model. Based on an input intent, the disclosed systems can utilize the large language model to analyze a knowledge graph for accessing and/or generating content items for display within the intelligent assistant interface.

公开(公告)号：US12033050B1

公开(公告)日：2024-07-09

申请号：US18339833

申请日：2023-06-22

Applicant: Dropbox, Inc.

Inventor： Devin Mancuso

IPC: G06N3/02 ,  H04L51/216

CPC classification number: G06N3/02 ,  H04L51/216

Abstract: This disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that can utilize language neural networks to automatically generate draft electronic communications for a user account. For example, the disclosed systems leverage composition parameters of a user account (determined from historical electronic communications of the user account, digital content items corresponding to the user account, and/or other application data) with a neural network to automatically generate draft electronic communications that reflect a composition style of a user account and accurately addresses a context of a communication thread. In addition, the disclosed systems can generate electronic communications using the communication generation neural network and save the electronic communication as a draft (e.g., for review by a user of the user account) and/or automatically transmit the electronic message to a recipient user account.

公开(公告)号：US20240202349A1

公开(公告)日：2024-06-20

申请号：US18068161

申请日：2022-12-19

Applicant: Dropbox, Inc.

Inventor： Devin Mancuso ,  Benjamin Joseph Calabrese ,  Austin Sung ,  Jason Stakelon ,  Bonita Leung

IPC: G06F21/62

CPC classification number: G06F21/6218

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating content clusters from topic data and focus data, generating content collections from content clusters, storing and restoring desktop scene layouts, and storing and arranging video call scenes. In some embodiments, the disclosed systems generate content clusters based on topic data and focus data associated with content items within a content management system and/or accessed via the internet. The disclosed systems can also generate content collections for a user account of the content management system from the content clusters. In some embodiments, the content scene system can further store and restore desktop scene layouts for arranging application windows presenting content items. Further, the disclosed systems can store and arrange particular desktop scene layouts for video call scenes.

公开(公告)号：US20240202250A1

公开(公告)日：2024-06-20

申请号：US18068132

申请日：2022-12-19

Applicant: Dropbox, Inc.

Inventor： Devin Mancuso ,  Benjamin Joseph Calabrese ,  Austin Sung ,  Jason Stakelon ,  Bonita Leung

IPC: G06F16/906 ,  G06F11/14 ,  G06F16/9535

CPC classification number: G06F16/906 ,  G06F11/1469 ,  G06F16/9535 ,  G06F2201/84

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating content clusters from topic data and focus data, generating content collections from content clusters, storing and restoring desktop scene layouts, and storing and arranging video call scenes. In some embodiments, the disclosed systems generate content clusters based on topic data and focus data associated with content items within a content management system and/or accessed via the internet. The disclosed systems can also generate content collections for a user account of the content management system from the content clusters. In some embodiments, the content scene system can further store and restore desktop scene layouts for arranging application windows presenting content items. Further, the disclosed systems can store and arrange particular desktop scene layouts for video call scenes.

公开(公告)号：US20240201831A1

公开(公告)日：2024-06-20

申请号：US18591382

申请日：2024-02-29

Applicant: Dropbox, Inc.

Inventor： Devin Mancuso ,  Benjamin Joseph Calabrese ,  Austin Sung ,  Jason Stakelon ,  Bonita Leung

IPC: G06F3/04842 ,  G06F3/0481 ,  H04L65/1069

CPC classification number: G06F3/04842 ,  G06F3/0481 ,  H04L65/1069 ,  G06F2203/04803

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating content clusters from topic data and focus data, generating content collections from content clusters, storing and restoring desktop scene layouts, and storing and arranging video call scenes. In some embodiments, the disclosed systems generate content clusters based on topic data and focus data associated with content items within a content management system and/or accessed via the internet. The disclosed systems can also generate content collections for a user account of the content management system from the content clusters. In some embodiments, the content scene system can further store and restore desktop scene layouts for arranging application windows presenting content items. Further, the disclosed systems can store and arrange particular desktop scene layouts for video call scenes.

公开(公告)号：US20230315972A1

公开(公告)日：2023-10-05

申请号：US17657573

申请日：2022-03-31

Applicant: Dropbox, Inc.

Inventor： Arunsunai Anbukarasi Anbalagapandian ,  Devin Mancuso ,  Rituparna Vincent ,  Viksit Gaur

IPC: G06F40/106

CPC classification number: G06F40/106

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that dynamically capture, organize, and utilize digital media clips. For example, in one or more implementations, the disclosed systems can capture and generate digital media clips of content items that include both content metadata of the content items as well as contextual metadata of contextual signals surrounding the content item. Additionally, in some implementations, the disclosed systems analyze contextual metadata to search, retrieve, discover, and organize new and existing digital media clips. Further, in various implementations, the disclosed systems facilitate generating digital media clip libraries as well as the creation of digital media collections, where different types of digital media clips can be combined in a cohesive interactive graphical user interface.

公开(公告)号：US11762898B1

公开(公告)日：2023-09-19

申请号：US17657572

申请日：2022-03-31

Applicant: Dropbox, Inc.

Inventor： Arunsunai Anbukarasi Anbalagapandian ,  Devin Mancuso ,  Rituparna Vincent ,  Viksit Gaur

IPC: G06F16/435 ,  G06F16/44 ,  G06F16/45

CPC classification number: G06F16/435 ,  G06F16/44 ,  G06F16/45

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that dynamically capture, organize, and utilize digital media clips. For example, in one or more implementations, the disclosed systems can capture and generate digital media clips of content items that include both content metadata of the content items as well as contextual metadata of contextual signals surrounding the content item. Additionally, in some implementations, the disclosed systems analyze contextual metadata to search, retrieve, discover, and organize new and existing digital media clips. Further, in various implementations, the disclosed systems facilitate generating digital media clip libraries as well as the creation of digital media collections, where different types of digital media clips can be combined in a cohesive interactive graphical user interface.