Invention Grant
- Patent Title: Automatic generation of events using a machine-learning model
-
Application No.: US17404773Application Date: 2021-08-17
-
Publication No.: US12056929B2Publication Date: 2024-08-06
- Inventor: Kristina Bohl , Joe Agajanian , Lily Berg , Brian Potetz , Keegan Mosley , Shinko Cheng
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: IP Spring
- Main IPC: G06V20/40
- IPC: G06V20/40 ; G06F18/21 ; G06F18/214 ; G06F18/23 ; G06T11/60 ; G06V20/30 ; G06V40/16

Abstract:
A media application segments a library of media associated with a user account into episodes, wherein each episode is associated with a corresponding time period. The media application generates, using an event machine-learning model, an event signal that indicates a likelihood that an event occurred in each episode, wherein the event machine-learning model is a classifier that receives the media as input. The media application generates an event significance score for each episode. The media application determines one or more events from the episodes based on the event signal and a corresponding event significance score exceeding a threshold event significance value. The media application provides a user interface that includes corresponding media from the one or more events.
Public/Granted literature
- US20220366191A1 AUTOMATIC GENERATION OF EVENTS USING A MACHINE-LEARNING MODEL Public/Granted day:2022-11-17
Information query