WO2024045866 - SYSTEM AND METHOD FOR CROSS-MODAL INTERACTION BASED ON PRE-TRAINED MODEL
National phase entry is expected:
Publication Number
WO/2024/045866
Publication Date
07.03.2024
International Application No.
PCT/CN2023/104350
International Filing Date
30.06.2023
Title **
[English]
SYSTEM AND METHOD FOR CROSS-MODAL INTERACTION BASED ON PRE-TRAINED MODEL
[French]
SYSTÈME ET PROCÉDÉ D'INTERACTION INTERMODALE SUR LA BASE D'UN MODÈLE PRÉ-ENTRAÎNÉ
Applicants **
HUAWEI TECHNOLOGIES CO., LTD.
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
Inventors
XU, Hang
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
HOU, Lu
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
LU, Guansong
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
NIU, Minzhe
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
LI, Zhenguo
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
HUANG, Runhui
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
YAO, Lewei
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
XU, Chunjing
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
LIANG, Xiaodan
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
Priority Data
17/900,592
31.08.2022
US
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 |
CNIPA
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| 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 | Stages | Total | |
|---|---|---|---|
| China | Filing | 1264 | |
| EPO | Filing, Examination | 7972 | |
| Japan | Filing | 587 | |
| South Korea | Filing | 574 | |
| USA | Filing, Examination | 2710 |
Total: 13107 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
A method is provided for data processing performed by a processing system. The method comprises determining a set of first tokens for first data and a set of second token for second data, each token comprising information associated with a segment of the respective data, determining pair-wise similarities between the set of first tokens and the set of second tokens, each pair comprising a first token in the set of first tokens and a second token in the set of second tokens, determining, for each first token in the set of first tokens, a maximum similarity based on the determined pair-wise similarities between the respective first token and the second tokens in the set of second tokens, and determining a first similarity between the first data and the second data by aggregating the maximum similarities corresponding to the first tokens in the set of first set of tokens.[French]
L'invention concerne un procédé de traitement de données mis en œuvre par un système de traitement. Le procédé consiste à : déterminer un ensemble de premiers jetons pour des premières données et un ensemble de deuxièmes jetons pour des deuxièmes données, chaque jeton comprenant des informations associées à un segment des données respectives ; déterminer des similarités par paire entre l'ensemble de premiers jetons et l'ensemble de deuxièmes jetons, chaque paire comprenant un premier jeton dans l'ensemble de premiers jetons et un deuxième jeton dans l'ensemble de deuxièmes jetons ; déterminer, pour chaque premier jeton dans l'ensemble de premiers jetons, une similarité maximale sur la base des similarités par paire déterminées entre le premier jeton respectif et les deuxièmes jetons dans l'ensemble de deuxièmes jetons ; et déterminer une première similarité entre les premières données et les deuxièmes données par agrégation des similarités maximales correspondant aux premiers jetons dans l'ensemble de premiers jetons.