WO2024154113 - MACHINE LEARNING MODEL SELECTION IN WIRELESS COMMUNICATION SYSTEMS
National phase entry is expected:
Publication Number
WO/2024/154113
Publication Date
25.07.2024
International Application No.
PCT/IB2024/051689
International Filing Date
21.02.2024
Title **
[English]
MACHINE LEARNING MODEL SELECTION IN WIRELESS COMMUNICATION SYSTEMS
[French]
SÉLECTION DE MODÈLE D'APPRENTISSAGE AUTOMATIQUE DANS DES SYSTÈMES DE COMMUNICATION SANS FIL
Applicants **
LENOVO (SINGAPORE) PTE. LTD.
Inventors
POURAHMADI, Vahid
HINDY, Ahmed
KOTHAPALLI, Venkata Srinivas
NANGIA, Vijay
Priority Data
63/486,057
21.02.2023
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 |
EPO
* |
| 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 | 2328 | |
| EPO | Filing, Examination, Granting | 11420 | |
| Japan | Filing, Examination, Granting | 2353 | |
| South Korea | Filing, Examination, Granting | 2327 | |
| USA | Filing, Examination, Granting | 4740 |
Total:
23,168
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
Various aspects of the present disclosure relate to methods, apparatuses, and systems that support model selection in wireless systems. For instance, implementations provide ways for efficient selection of a machine learning model, such as based on system state. For example, different models are pretrained based on different system states and the described techniques enable a best-fit pretrained model to be selected based on a current system state. A selected model can be used for various purposes, such as encoding and decoding data pertaining to wireless communications, e.g., channel state information (CSI).[French]
Divers aspects de la présente divulgation concernent des procédés, des appareils et des systèmes qui prennent en charge la sélection de modèle dans des systèmes sans fil. Par exemple, des mises en œuvre fournissent des moyens pour une sélection efficace d'un modèle d'apprentissage automatique, par exemple en fonction d'un état de système. Par exemple, différents modèles sont préformés en fonction de différents états de système et les techniques décrites permettent de sélectionner un modèle préformé de meilleur ajustement en fonction d'un état de système actuel. Un modèle sélectionné peut être utilisé à diverses fins, telles que le codage et le décodage de données concernant des communications sans fil, par exemple, des informations d'état de canal (CSI).