Patent · US Active

Video recommendation with multi-gate mixture of experts soft actor critic

US11922287B2 · kind B2 · utility

1Cited by
3References
17Claims
0Family size

Assignees

Inventors

Key dates

Filing dateJul 15, 2020
Grant dateMar 5, 2024
Priority date
Expiry dateOct 29, 2042

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04N21/4826
  • WIPO fieldAudio-visual technology
  • WIPO sectorElectrical engineering

Abstract

Described herein are embodiments of a reinforcement learning based large-scale multi-objective ranking system. Embodiments of the system may be used for optimizing short-video recommendation on a video sharing platform. Multiple competing ranking objective and implicit selection bias in user feedback are the main challenges in real-world platform. In order to address those challenges, multi-gate mixture of experts (MMoE) and soft actor critic (SAC) are integrated together into a MMoE_SAC system. Experiment results demonstrate that embodiments of the MMoE_SAC system may greatly reduce a loss function compared to systems only based on single strategies.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.