公开(公告)号：US12289495B2

公开(公告)日：2025-04-29

申请号：US18172740

申请日：2023-02-22

Applicant: Snap Inc.

Inventor： Jacob Andreou ,  Sheldon Chang ,  Donald Giovannini

IPC: H04N21/4545 ,  G06Q50/00 ,  H04N21/239 ,  H04N21/258 ,  H04N21/2743 ,  H04N21/435 ,  H04N21/45

Abstract: Systems and methods described herein relate to generation of media collections in a messaging system. The media collection may be created by the user, other users, or an entity. Example embodiments further allow users to set access criteria through privacy settings assigned to one or more media content items themselves, as well as to a media collection, such that some or all of the media collection may only be viewed by users authorized by the user sharing the media content item or media collection (e.g., only to one or more users designated by the user as a “friend”).

公开(公告)号：US20250133181A1

公开(公告)日：2025-04-24

申请号：US18987380

申请日：2024-12-19

Applicant: Snap Inc.

Inventor： Kaveh Anvaripour ,  Laurent Desserrey

IPC: H04N5/262 ,  H04N23/63

Abstract: Disclosed is a method for providing custom visual settings on a device including a display and a camera. The method comprises displaying an existing video that includes data specifying augmentation effects that were applied to the existing video, and an effects indicator. Selection of the effects indicator applies the augmentation effects to a video feed from the camera. Also displayed with the existing video is an audio context indicator identifying an audio track playing with the existing video. Selection of the audio context indicator provides a user interface option to capture a new video with the audio track accompanying the new video.

公开(公告)号：US20250133088A1

公开(公告)日：2025-04-24

申请号：US19005414

申请日：2024-12-30

Applicant: Snap Inc.

Inventor： Nicholas Richard Allen ,  Sheldon Chang

IPC: H04L9/40 ,  H04L51/222 ,  H04L51/52 ,  H04W4/02 ,  H04W4/021 ,  H04W4/029 ,  H04W4/18 ,  H04W12/06 ,  H04W12/63 ,  H04W12/64

Abstract: A system includes a communication module that receives a request to post content to an event gallery associated with an event. The request in turn includes geo-location data for a device sending the content, and identification data identifying the device or a user of the device. The system further has an event gallery module to perform a first authorization operation that includes determining that the geo-location data corresponds to a geo-location fence associated with an event. The event gallery module also performs a second authorization operation that includes using the identification data to verify an attribute of the user. Finally, based on the first and second authorization operations, the event gallery module may selectively authorize the device to post the content to the event gallery.

公开(公告)号：US20250133050A1

公开(公告)日：2025-04-24

申请号：US18940030

申请日：2024-11-07

Applicant: Snap Inc.

Inventor： Haim Shoham ,  Gavin Shriver ,  Jason Varbedian ,  Zhichao Yang

IPC: H04L51/216 ,  G06F16/955 ,  H04L51/043 ,  H04L51/234

Abstract: A system to automatically increment read-watermarks based on a set of predefined rules and criteria and configured to perform operations that include: accessing a message thread that comprises a plurality of messages; detecting a display of a message from among the plurality of messages at a client device, the message corresponding with an identification number from among a plurality of sequentially assigned identification numbers associated with the plurality of messages; applying the identification number that corresponds with the message from among the plurality of messages to a data object within a database associated with the message thread, the data object indicating a most recent message read by a user of the client device based on the identification number; detecting a trigger event; and automatically incrementing the identification number associated with the data object within the database responsive to the trigger event.

公开(公告)号：US20250131624A1

公开(公告)日：2025-04-24

申请号：US18634588

申请日：2024-04-12

Applicant: Snap Inc.

Inventor： Nathan Kenneth Boyd ,  Evan Spiegel ,  Celia Nicole Mourkogiannis

IPC: G06T11/60 ,  G06F16/532 ,  G06F40/40

Abstract: Methods and systems are disclosed for suggesting scenarios for an image using one or more machine learning models based on an output of an LLM. The methods and systems generate, by a device of a user, a first prompt comprising a demographic of a person and a date, and process the first prompt by a large language model (LLM) to generate a plurality of ideas relevant to the person on that date, each idea comprising a respective description and vibe. The methods and systems generate a second prompt comprising a selected idea from the plurality of ideas and a request for a plurality of scenarios that are relevant to the selected idea, process the second prompt by the LLM to generate the plurality of scenarios that are relevant to the selected idea, and present an individual content item corresponding to an individual scenario of the plurality of scenarios.

公开(公告)号：US20250131584A1

公开(公告)日：2025-04-24

申请号：US19006543

申请日：2024-12-31

Applicant: Snap Inc.

Inventor： Matan Zohar ,  Yanli Zhao ,  Brian Fulkerson ,  Itamar Berger

IPC: G06T7/70 ,  G06F18/214 ,  G06F18/24 ,  G06T19/00 ,  G06V40/10

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for performing operations comprising: receiving a video that depicts a person. The operations further include identifying a set of skeletal joints of the person. The operations further include identifying a pose of the person depicted in the video based on positioning of the set of skeletal joints (or detecting a hand pose, detecting a mirror frame, or detecting a mobile device). The operations further include determining, based on the pose of the person (or detecting a hand pose, detecting a mirror frame, or detecting a mobile device), that the video comprises a mirror reflection of the person. The operations further include, in response to determining that the video comprises the mirror reflection of the person, causing display of a 3D virtual object in the video.

公开(公告)号：US20250127282A1

公开(公告)日：2025-04-24

申请号：US19007302

申请日：2024-12-31

Applicant: Snap Inc.

Inventor： Christine Barron ,  Virginia Drummond ,  Jean Luo ,  Alek Matthiessen ,  Celia Nicole Mourkogiannis ,  Jonathan Solichin ,  Olesia Voronova

IPC: A45D44/00 ,  G06F3/04817 ,  G06F3/04842 ,  G06Q30/0601 ,  G06T11/00 ,  G09B19/00

Abstract: Systems, methods, and computer readable media for augmented reality beauty product tutorials are disclosed. Methods disclose displaying on a first portion of a screen a beauty product tutorial including pre-recorded images of a presenter applying a beauty product to a body part of the presenter and determining first effects indicating changes to make to live images of a user to simulate applying the beauty product to the body part of the user, where the first effects are determined based on second effects indicating changes to the pre-recorded images from applying the beauty product to the body part of the presenter. Methods further disclose processing the live images of the user to add the first effects and indications of motion of the beauty product and displaying the processed live images of the user on a second portion of the screen.

公开(公告)号：US12284324B2

公开(公告)日：2025-04-22

申请号：US17888948

申请日：2022-08-16

Applicant: Snap Inc.

Inventor： Tianying Chen ,  Timothy Chong ,  Sven Kratz ,  Fannie Liu ,  Andrés Monroy-Hernández ,  Olivia Seow ,  Yu Jiang Tham ,  Rajan Vaish ,  Lei Zhang

IPC: H04N13/111 ,  G06T3/60 ,  G06V10/44 ,  G06V10/764 ,  G06V20/20

Abstract: Augmented reality (AR) systems, devices, media, and methods are described for generating AR experiences including interactions with virtual or physical prop objects. The AR experiences are generated by capturing images of a scene with a camera system, identifying an object receiving surface and corresponding surface coordinates within the scene, identifying an AR primary object and a prop object (physical or virtual), establishing a logical connection between the AR primary object and the prop object, generating AR overlays including actions associated with the AR primary object responsive to commands received via a user input system that position the AR primary object adjacent the object receiving surface responsive to the primary object coordinates and the surface coordinates within the scene and that position the AR primary object and the prop object with respect to one another in accordance with the logical connection, and presenting the generated AR overlays with a display system.

公开(公告)号：US12284107B2

公开(公告)日：2025-04-22

申请号：US18601790

申请日：2024-03-11

Applicant: Snap Inc.

Inventor： Zahra Ferdowsi ,  Michael Cieslak ,  Michael David Marr ,  Aysegul Cansizoglu ,  Xiaolin Shi ,  Hussein Mehanna ,  Caleb Ogden ,  Yi Xu

IPC: H04L43/55 ,  H04L41/0893 ,  H04L41/50 ,  H04L67/1087 ,  H04L67/125

Abstract: Clustering a plurality of client devices running an application as a function of a data structure such that the plurality of client devices are each assigned a cluster. Client devices having similar performance metrics are assigned the same cluster. An operation of the application is modified as a function of the performance metrics of the client device. The modification of application operation is performed by turning certain features of the application on and off using a rule based on device cluster.

公开(公告)号：US12283276B2

公开(公告)日：2025-04-22

申请号：US17646271

申请日：2021-12-28

Applicant: Snap Inc.

Inventor： Alex Edelsburg ,  Kyle Goodrich ,  Pedram Javidpour ,  Andrew James McPhee ,  Daniel Moreno ,  Jeremy Baker Voss

IPC: G06F3/04886 ,  G06F3/0481 ,  G06F3/04883 ,  G06F3/16 ,  G10L15/26 ,  H04L51/10

Abstract: A messaging system, which hosts a backend service for an associated messaging client application, includes a voice notes system that addresses the technical problem of serving an audio message to the recipient in a manner that permits the recipient to consume the message in a text format as a transcription. A chat user interface (UI) provided with the voice notes system permits a user to play an audio message or request generation of the transcription of the audio message on-demand to prevent unnecessary cluttering of the UI real estate.