WO2026099669 - DELIVERY OF AI/ML MODEL PARAMETERS
National phase entry is expected:
Publication Number
WO/2026/099669
Publication Date
15.05.2026
International Application No.
PCT/IB2025/060622
International Filing Date
17.10.2025
Title **
[English]
DELIVERY OF AI/ML MODEL PARAMETERS
[French]
DISTRIBUTION DE PARAMÈTRES DE MODÈLE D'IA/ML
Applicants **
NOKIA TECHNOLOGIES OY
Inventors
TAN, Yi
LADDU, Keeth Saliya Jayasinghe
GOLD, Dimitri
HEJSELBAEK, Johannes
Priority Data
63/717,699
07.11.2024
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 | 2657 | |
| EPO | Filing, Examination, Granting | 18196 | |
| Japan | Filing, Examination, Granting | 2763 | |
| South Korea | Filing, Examination, Granting | 3199 | |
| USA | Filing, Examination, Granting | 11140 |
Total:
37,955
Contact Us
Abstract[English]
Example embodiments of the present disclosure are directed to delivery of AI/ML model parameters. A method comprises obtaining, from a second apparatus, accuracy level information indicating parameter quantization for an artificial intelligence and machine learning (AI/ML) model, the accuracy level information indicating at least one accuracy level; obtaining, from the second apparatus, indication information of at least one set of parameters of the AI/ML model corresponding to the at least one accuracy level; and generating, the at least one set of parameters based on the indication information and the at least one accuracy level.[French]
Des modes de réalisation donnés à titre d'exemple de la présente divulgation concernent la distribution de paramètres de modèle d'IA/ML. Un procédé consiste à : obtenir, à partir d'un second appareil, des informations de niveau de précision indiquant une quantification de paramètres pour un modèle d'intelligence artificielle et d'apprentissage automatique (IA/ML), les informations de niveau de précision indiquant au moins un niveau de précision ; obtenir, à partir du second appareil, des informations d'indication d'au moins un ensemble de paramètres du modèle d'IA/ML correspondant à l'au moins un niveau de précision ; et générer ledit au moins un ensemble de paramètres sur la base des informations d'indication et de l'au moins un niveau de précision.