公开(公告)号：US20220392011A1

公开(公告)日：2022-12-08

申请号：US17337989

申请日：2021-06-03

Applicant: Micron Technology, Inc.

Inventor： Yunju Lee ,  Shwetha Vure ,  Barbara J. Bailey

IPC: G06T1/00 ,  G06K9/00 ,  G06K9/62 ,  A47L15/42 ,  A47L15/46 ,  A47L15/37 ,  A47L15/44 ,  G06N20/00

Abstract: A method includes receiving, at an artificial intelligence (AI) accelerator of a computing system, image data of one or more objects from an image sensor and performing an AI operation on the image data at the AI accelerator of the computing system using an AI model. The method further includes determining a custom cleaning cycle at the AI accelerator in response to performing the AI operation.

公开(公告)号：US20230200696A1

公开(公告)日：2023-06-29

申请号：US17564647

申请日：2021-12-29

Applicant: Micron Technology, Inc.

Inventor： Yunju Lee ,  Sue-Fern Ng ,  Bhumika Chhabra

IPC: A61B5/16 ,  G06N20/00 ,  A61B5/00 ,  G16H20/70 ,  G16H20/30

CPC classification number: A61B5/165 ,  G06N20/00 ,  A61B5/4803 ,  G16H20/70 ,  G16H20/30

Abstract: Methods, devices, and systems associated with audio and visual input analysis are described. A method can include recording audio during production of artwork using a microphone, storing the audio recording in tiered memory, generating an image of the artwork using an image sensor, storing the image of the artwork in the tiered memory, receiving a reference library including a number of audio recordings and a number of images of artwork, comparing the image of the artwork to the number of images of artwork and the audio recording to the number of audio recordings, and providing an output in response to at least one of: the image of the artwork matching one of the number of images of artwork or the audio recording matching one of the number of audio recordings.