Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
MODEL ACQUISITION METHOD, APPARATUS AND SYSTEM
Document Type and Number:
WIPO Patent Application WO/2024/041563
Kind Code:
A1
Abstract:
The present disclosure relates to the technical field of communications, and relates to a model acquisition method, apparatus and system, and a computer-storable storage medium. The model acquisition method, executed by a model training logical function (MTLF) network element, comprises: receiving a first model request message from an analytics logical function (AnLF) network element, wherein the first model request message comprises an analytics identifier, input information identifier and output information identifier of current analytics; on the basis of the analytics identifier, the input information identifier and the output information identifier, acquiring a machine learning model for the current analytics; and transmitting a first model request response message to the AnLF network element, wherein the first model request response message comprises the machine learning model for the current analytics.

Inventors:
YU MENGHAN (CN)
LI PENGYU (CN)
Application Number:
PCT/CN2023/114429
Publication Date:
February 29, 2024
Filing Date:
August 23, 2023
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
CHINA TELECOM CO LTD (CN)
International Classes:
H04L41/14; G06N20/00
Domestic Patent References:
WO2022164225A12022-08-04
WO2022041947A12022-03-03
Foreign References:
CN112784992A2021-05-11
US20220237521A12022-07-28
Other References:
NOKIA, NOKIA SHANGHAI BELL: "Corrections to ML model provisioning and AnLF / MTLF split functionality", 3GPP DRAFT; S2-2107250, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG2, no. e-meeting; 20211018 - 20211022, 11 October 2021 (2021-10-11), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052061479
Attorney, Agent or Firm:
CCPIT PATENT AND TRADEMARK LAW OFFICE (CN)
Download PDF: