WO2024174561 - M2M WITH GENERATIVE PRETRAINED MODELS
National phase entry is expected:
Publication Number
WO/2024/174561
Publication Date
29.08.2024
International Application No.
PCT/CN2023/127173
International Filing Date
27.10.2023
Title **
[English]
M2M WITH GENERATIVE PRETRAINED MODELS
[French]
M2M AVEC MODÈLES PRÉFORMÉS GÉNÉRATIFS
Applicants **
HUAWEI TECHNOLOGIES CO., LTD.
Inventors
TONG, Wen
GE, Yiqun
ZHANG, Qifan
MA, Jianglei
Priority Data
63/448,167
24.02.2023
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 | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
CNIPA
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* 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, Examination, Granting | 1689 | |
| EPO | Filing, Examination, Granting | 12115 | |
| Japan | Filing, Examination, Granting | 2039 | |
| South Korea | Filing, Examination, Granting | 1770 | |
| USA | Filing, Examination, Granting | 4740 |
Total:
22,353
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
Aspects of the present application relate to a UE transmitting, to a cloud, one or more attentions rather than transmitting raw sensor information. To allow the UE to transmit the attentions, it is proposed to implement an encoding network at the UE. The UE may then employ the encoding network to determine embeddings encoded by the raw sensor information, both spatial and temporal, collected at a plurality of sensors. On the basis of the embeddings, the UE may then determine the attentions, e.g., self-attention matrices and/or cross-attention matrices. The UE may then transmit, to the cloud, the attentions. At the cloud, the attentions may be processed to obtain actions. The cloud may then transmit, to the UE, instructions for carrying out the actions. Upon receipt of the instructions, the UE may carry out the actions.[French]
Des aspects de la présente demande concernent un UE transmettant, à un nuage, une ou plusieurs atténuations plutôt que de transmettre des informations de capteur brutes. Pour permettre à l'UE de transmettre les attentions, il est proposé de mettre en œuvre un réseau de codage au niveau de l'UE. L'UE peut ensuite utiliser le réseau de codage pour déterminer les intégrations codées par les informations brutes des capteurs, à la fois spatiales et temporelles, collectées au niveau d'une pluralité de capteurs. D'après les intégrations, l'UE peut ensuite déterminer les attentions, par exemple des matrices d'auto-attention et/ou des matrices d'attention croisée. L'UE peut ensuite transmettre les attentions au nuage. Au niveau du nuage, les attentions peuvent être traitées afin d'obtenir des actions. Le nuage peut ensuite transmettre, à l'UE, des instructions permettant d'effectuer les actions. Lors de la réception des instructions, l'UE peut effectuer les actions.