公开(公告)号：US20240420252A1

公开(公告)日：2024-12-19

申请号：US18485747

申请日：2023-10-12

Applicant: Snap Inc.

Inventor： Nathan Kenneth Boyd ,  Marc Brown ,  Shuaiqing Luo ,  Wenjie Ma ,  Rasana Manandhar ,  Anton Shevchenko ,  Alexander Vodovoz ,  Yilin Yang

IPC: G06Q50/00 ,  G06F3/0482 ,  G06T7/20 ,  G06V20/40 ,  G06V40/16

Abstract: A technique for deriving a mashup is described. Given a collection of media content items for sequential playback, a subset of the media content items are selected for inclusion in a mashup, based on selection criteria specified in a template associated with the featured story. The subset of media content items are then arranged in a mashup, which is prepended to the story. By automatically generating a mashup—an abbreviated version of a story—the mashup will increase user engagement and encourage sharing, because the mashup condenses the content into a more digestible and captivating format. By using optimized content selection criteria, the mashup will include only the best and most impactful moments, highlights, or key elements of the story. The shorter version grabs the viewer's attention, maintaining their interest and prompting them to share the condensed experience with others, enticing them to discover the full story.

公开(公告)号：US20250047969A1

公开(公告)日：2025-02-06

申请号：US18362644

申请日：2023-07-31

Applicant: Snap Inc.

Inventor： Matthew Mahar ,  Vineet Kapil ,  Kaveh Anvaripour ,  Ranidu Lankage ,  Anton Shevchenko ,  Xin Su ,  Benjamin Lin ,  Noam Lerner ,  Rasana Manandhar ,  Prasad Tare ,  Dustin Kendall

IPC: H04N23/63 ,  G06F3/0482

Abstract: Aspects of the present disclosure involve a system comprising a storage medium storing a program and method for providing a template for media content generation. The program and method provide for receiving, from a first device of a first user, an indication of first user input setting properties to create a template for combining user-selected media with an audio track, the properties specifying the audio track, a sequence of media slots, a duration for each media slot, and predefined edits for applying to the media slots; causing display of a user interface on a second device of a second user, the user interface for assigning a respective video or photo to each media slot; and receiving, from the second device, a media content item generated based on second user input provided via the user interface, the second user input assigning the respective video or photo to each media slot.

公开(公告)号：US20240395286A1

公开(公告)日：2024-11-28

申请号：US18484326

申请日：2023-10-10

Applicant: Snap Inc.

Inventor： Marc Brown ,  Shuaiqing Luo ,  Matthew Mahar ,  Anton Shevchenko ,  Yin Tang

IPC: G11B27/031

Abstract: A video montage is assembled by one or more processors by selecting a number of media items for use in the video montage from a collection of media items. An audio track having a theme parameter corresponding to a theme parameter of the number of media items is identified, and a video montage incorporating the media items and the audio track is generated. A data structure may specify an identity and order of the media items and a start location of the audio track, and the video montage may be created by generating individual video segments from each media item in the number of media items, and assembling the individual video segments into the video montage based on an order specified in the data structure. Updates or edits to the video montage are represented as changes to the data structure, which is used to generate an updated video montage.

公开(公告)号：US20240193482A1

公开(公告)日：2024-06-13

申请号：US18535551

申请日：2023-12-11

Applicant: Snap Inc.

Inventor： Eric Portes dos Santos ,  Matthew Mahar ,  Christie Marie Heikkinen ,  Anton Shevchenko ,  Hanbo Chen ,  Xin Su

IPC: G06N20/00 ,  G06T11/00

CPC classification number: G06N20/00 ,  G06T11/00 ,  G06T2200/24

Abstract: A system includes one or more hardware processors and at least one memory storing instructions that cause the one or more hardware processors to perform operations including receiving, via a client device, a selection of a photographic filter or a virtual lens. The operations additionally include deriving, via a model, a date, or a combination thereof, a music recommendation, a sound recommendation, or a combination thereof, for the selection of the photographic filter or the virtual lens, and providing the music recommendation, the sound recommendation, or the combination thereof, to the client device.