公开(公告)号：US20230409615A1

公开(公告)日：2023-12-21

申请号：US18334235

申请日：2023-06-13

Applicant: Meta Platforms, Inc.

Inventor： Piyush Khemka ,  Brandon Ramos ,  Ryan Wolff ,  Stephen Chee-Ching Wu ,  Ashley Gustafson ,  Gabrielle Catherine Moskey ,  Hyundong Cho ,  Andrea Madotto ,  Zhaojiang Lin ,  Satwik Kottur ,  Chinnadhurai Sankar ,  Ashish Vishwanath Shenoy ,  Jiangning Chen ,  Rahim Manji ,  Bing Liu ,  Xin Liu ,  Ziyun Zhang

IPC: G06F16/332 ,  G06F9/451 ,  G06V20/68 ,  G10L15/18

CPC classification number: G06F16/3329 ,  G06F9/451 ,  G06V20/68 ,  G10L15/1822

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

公开(公告)号：US11348032B1

公开(公告)日：2022-05-31

申请号：US16120279

申请日：2018-09-02

Applicant: Meta Platforms, Inc.

Inventor： Jurgen Anne Francois Marie Van Gael ,  Yu Ning ,  Hao Shi ,  Fei Xie ,  Bingyue Peng ,  Shyamsundar Rajaram ,  Xin Liu ,  Zhen Yao ,  Peng Yang ,  Robert Oliver Burns Zeldin ,  Piyush Bansal

IPC: G06N20/00 ,  G06F8/30

Abstract: Machine-trained models are generated based on a model description that defines parameters for training the model and that can inherit parameters from parent model descriptions. When a parent model description changes, the changes made to the parent model description are applied to the model description automatically. When a target model is re-generated, a description of the set of parameters for generating the target model is received. The parent model is then identified from the received description, and a description of the set of parameters for generating the parent model is retrieved. Using the description for the target model and the parent model, a pipeline for generating the target model is generated. Finally, the pipeline is executed to generate the target model.

公开(公告)号：US20250077977A1

公开(公告)日：2025-03-06

申请号：US18822593

申请日：2024-09-03

Applicant: Meta Platforms, Inc.

Inventor： Satyajeet Singh Ahuja ,  Zhaodong Wang ,  Mohammad Noormohammadpour ,  Yuhui Zhang ,  Thomas Fuller ,  Mengcheng Wang ,  Muhammet Mustafa Ozdal ,  Abhinav Triguna ,  Abishek Gopalan ,  Jian Yang ,  Xin Liu ,  Ying Zhang ,  Gregory Robbins Steinbrecher ,  James Williams ,  Steve Politis

IPC: G06N20/00

Abstract: Methods, systems, and storage media for running unified simulations on clusters. Exemplary implementations may include: receiving simulation parameters for a simulation of a cluster; generating synthesized workload events based the simulation parameters of the cluster; determining a memory latency associated with the cluster; determining a reliability and availability of resources in the cluster for a predetermined duration of time; simulating events for jobs in the cluster based on the reliability and availability of resources in the cluster, each job associated with one or more synthesized workload events; and outputting simulation results based on the synthesized workload, the memory latency, and the events.