公开(公告)号：US20250158940A1

公开(公告)日：2025-05-15

申请号：US18505875

申请日：2023-11-09

Applicant: Snap Inc.

Inventor： Dennis Jin

IPC: H04L51/02 ,  G06F40/166 ,  H04L51/10 ,  H04L51/52

Abstract: A system and method for generating contextually relevant reply suggestions for media posts is disclosed. The system analyzes media content to identify visual objects, scenes, text, and metadata attributes using computer vision techniques. Identified objects and attributes are incorporated into structured prompt templates to construct detailed natural language descriptions of the media context. The prompts are provided to a text generation artificial intelligence (AI) that outputs a plurality of contextual reply suggestions based on the media analysis. Suggestions are displayed as selectable options adjacent to the media post. Users can cycle through suggestions and select a reply to send. Selections are logged to improve the AI model. Feedback on suggestion quality can also be collected. By integrating computer vision and AI generation driven by engineered prompts, the system produces highly relevant, personalized responses tailored to media content. The techniques enhance user engagement with media posts through intelligent AI reply suggestions.

公开(公告)号：US20250157234A1

公开(公告)日：2025-05-15

申请号：US18505916

申请日：2023-11-09

Applicant: Snap Inc.

Inventor： Dennis Jin ,  Kaveh Anvaripour

IPC: G06V20/70 ,  G06T19/00 ,  H04N21/2187

Abstract: A system and method for automatically generating captions for images and videos using artificial intelligence is disclosed. The system receives image or video data and analyzes the pixels to detect visual features including objects, people, text, and backgrounds. These detected features are used to generate a prompt summarizing the contents. The prompt is provided to a trained natural language processing model which outputs caption text describing the image/video data. The system can incorporate contextual factors to enhance relevance of the generated captions. The captions are ranked using relevance, diversity, and quality metrics then displayed to the user as an overlay on the media or in a separate interface pane. Users can cycle through different generated captions having varying tones and styles. The techniques combine computer vision, natural language processing, and deep learning to automatically generate context-relevant captions without manual user input.

公开(公告)号：US20240281125A1

公开(公告)日：2024-08-22

申请号：US18110842

申请日：2023-02-16

Applicant: Snap Inc.

Inventor： Dennis Jin ,  Daniel Moreno

IPC: G06F3/04845 ,  G06F3/01 ,  G06F3/0488

CPC classification number: G06F3/04845 ,  G06F3/016 ,  G06F3/0488

Abstract: A user interface comprising a message composition area is presented at a user device. Commencement of a resizing gesture is detected. A location of the resizing gesture within the user interface is tracked while the resizing gesture is in progress. The location of the resizing gesture is adjustable to cause resizing of message content in the message composition area. Responsive to detecting ending of the resizing gesture, a size of the message content is checked. Transmission of the message content to a recipient is based on a size of the message content relative to a base size.

公开(公告)号：US12112025B2

公开(公告)日：2024-10-08

申请号：US18110842

申请日：2023-02-16

Applicant: Snap Inc.

Inventor： Dennis Jin ,  Daniel Moreno

IPC: G06F3/048 ,  G06F3/01 ,  G06F3/04845 ,  G06F3/0488

CPC classification number: G06F3/04845 ,  G06F3/016 ,  G06F3/0488

Abstract: A user interface comprising a message composition area is presented at a user device. Commencement of a resizing gesture is detected. A location of the resizing gesture within the user interface is tracked while the resizing gesture is in progress. The location of the resizing gesture is adjustable to cause resizing of message content in the message composition area. Responsive to detecting ending of the resizing gesture, a size of the message content is checked. Transmission of the message content to a recipient is based on a size of the message content relative to a base size.

公开(公告)号：US20240419315A1

公开(公告)日：2024-12-19

申请号：US18818362

申请日：2024-08-28

Applicant: Snap Inc.

Inventor： Dennis Jin ,  Daniel Moreno

IPC: G06F3/04845 ,  G06F3/01 ,  G06F3/0488

Abstract: A user interface with a message composition area is presented at a user device. The message composition area includes message content presented in a base size. The user interface further includes a resizing graphical element presented at a base position within the user interface. A resizing gesture commences at the base position. While the resizing gesture is in progress, the resizing gesture is tracked and the message content is dynamically resized as positioning of the resizing gesture changes relative to the base position. Transmission of a message is caused when ending of the resizing gesture is detected at an adjusted position relative to the base position. The message includes the message content in an adjusted size relative to the base size.

公开(公告)号：US20230419417A1

公开(公告)日：2023-12-28

申请号：US18096357

申请日：2023-01-12

Applicant: Snap Inc.

Inventor： Jacob Catalano ,  Dennis Jin ,  Mengyao Li ,  Daniel Marcos Schwaycer ,  Joshua Siegel ,  Evan Spiegel

IPC: G06Q50/00

CPC classification number: G06Q50/01

Abstract: A system to display a route of a user over a period of time is configured to perform operations that include: causing display of a map image that depicts a location; accessing user profile data associated with a user profile, the user profile data comprising a user identifier and location data associated with the user profile; identifying a sequence of locations associated with the user profile based on the user profile data; and causing display of a presentation of a trail indicating the sequence of locations associated with the user profile, the trail terminating at a display of the user identifier.