Increasing efficiency of inferencing digital videos utilizing machine-learning models
US12067499B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 2, 2020 |
| Grant date | Aug 20, 2024 |
| Priority date | — |
| Expiry date | Jun 22, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/01
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
This disclosure describes one or more implementations of a video inference system that utilizes machine-learning models to efficiently and flexibly process digital videos utilizing various improved video inference architectures. For example, the video inference system provides a framework for improving digital video processing by increasing the efficiency of both central processing units (CPUs) and graphics processing units (GPUs). In one example, the video inference system utilizes a first video inference architecture to reduce the number of computing resources needed to inference digital videos by analyzing multiple digital videos utilizing sets of CPU/GPU containers along with parallel pipeline processing. In a further example, the video inference system utilizes a second video inference architecture that facilitates multiple CPUs to preprocess multiple digital videos in parallel as well as a GPU to continuously, sequentially, and efficiently inference each of the digital videos.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.