WO2023193169 - METHOD AND APPARATUS FOR DISTRIBUTED INFERENCE

National phase entry:
Publication Number WO/2023/193169
Publication Date 12.10.2023
International Application No. PCT/CN2022/085490
International Filing Date 07.04.2022
Title **
[English] METHOD AND APPARATUS FOR DISTRIBUTED INFERENCE
[French] PROCÉDÉ ET APPAREIL D'INFÉRENCE DISTRIBUÉE
Applicants **
HUAWEI TECHNOLOGIES CO.,LTD. Huawei Administration Building, Bantian, Longgang District Shenzhen, Guangdong 518129, CN
Inventors
ZHANG, Huazi Huawei Administration Building, Bantian, Longgang District Shenzhen, Guangdong 518129, CN
GE, Yiqun Huawei Administration Building, Bantian, Longgang District Shenzhen, Guangdong 518129, CN
TONG, Wen Suite 400, 303 Terry Fox Drive, Kanata Ottawa, Ontario 231, CA
front page image
Application details
Total Number of Claims/PCT *
Number of Independent Claims *
Number of Priorities *
Number of Multi-Dependent Claims *
Number of Drawings *
Pages for Publication *
Number of Pages with Drawings *
Pages of Specification *
*
*
International Searching Authority
*
Applicant's Legal Status
*
*
*
*
*
Entry into National Phase under
*
Translation

Recalculate

* The data is based on automatic recognition. Please verify and amend if necessary.

** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.

Quotation for National Phase entry

Country StagesTotal
China Filing1640
EPO Filing, Examination11302
Japan Filing596
South Korea Filing482
USA Filing, Examination6710
MasterCard Visa

Total: 20730

The term for entry into the National Phase has expired. This quotation is for informational purposes only

Abstract[English] Aspects of the present disclosure relate to inference and, in particular, to distributed inference representative of a machine learning process. It is expected that inferencing will be a key service in 6G wireless networks. Aspects of the present application relate to applying aspects of coding theory to distributed inference to introduce redundancy which improves accuracy and robustness of inference. Methods of decoding outputs from a distributed inference process are also provided.[French] Des aspects de la présente invention concernent l'inférence et, en particulier, une inférence distribuée représentative d'un processus d'apprentissage automatique. Il est attendu que l'inférence soit un service clé dans les réseaux sans fil 6G. Des aspects de la présente invention concernent l'application d'aspects de théorie de codage à une inférence distribuée afin d'introduire une redondance qui améliore la précision et la robustesse d'inférence. L'invention concerne également des procédés de décodage de sorties provenant d'un processus d'inférence distribué.
An unhandled error has occurred. Reload 🗙