Apparatus and method for selecting training ue in a mobile communication system

Patent metadata

Field	Value
Publication number	US-2023262487-A1
Application number	US-202318099761-A
Country	US
Kind code	A1
Filing date	Jan 20, 2023
Priority date	Jan 21, 2022
Publication date	Aug 17, 2023
Grant date	—

Abstract

A method and an apparatus for selecting UE through steps of requesting analytics for selecting the UE to participate in an AI/ML operation from an NWDAF in a core network and selecting the UE based on the analytics.

First claim

What is claimed is:

1 . A method for selecting user equipment (UE), the method comprising:
requesting analytics for selecting the UE participating in artificial intelligence (AI) / machine learning (ML) operation from a network data analytics function (NWDAF) in a core network; and selecting the UE based on the analytics.

2 . The method of claim 1 , wherein the requesting the analytics comprises
requesting QoS Sustainability analytics from the NWDAF.

3 . The method of claim 2 , wherein the requesting the QoS Sustainability analytics from the NWDAF comprises
transmitting a target of a report of the analytics as a granularity of a UE level to the NWDAF.

4 . The method of claim 1 , wherein the analytics includes at least one of service experience, UE mobility, UE communication pattern, user data congestion, QoS sustainability, and/or abnormal behavior.

5 . The method of claim 1 , wherein the requesting the analytics comprises
requesting the analytics from the NWDAF via an AI/ML assistance NF in the core network.

6 . The method of claim 5 , wherein the requesting the analytics from the NWDAF via an AI/ML assistance NF in the core network comprises
requesting the analytics from the NWDAF via one of a first AI/ML assistance NF or a second AI/ML assistance NF when the first AI/ML assistance NF that determines a plurality of AI/ML-related tasks of the AI/ML operation and the second AI/ML assistance NF that proposes candidate AI/ML training members for the AI/ML-related tasks are within the core network.

7 . The method of claim 1 further comprising:
transferring a global model of the AI/ML operation to the selected UE; and
receiving an update result of local training for the global model from the UE that has received the global model.

8 . The method of claim 1 further comprising collecting information required for the AI/ML operation from at least one UE through a user plane.

9 . The method of claim 8 , wherein the information required for the AI/ML operation includes at least one of battery charging/consumption pattern, mobility pattern, and/or application usage pattern of the at least one UE.

10 . A network data analytics function (NWDAF) in a core network, comprising:
a processor, a memory, and a communication device, wherein the processor executes a program stored in the memory to perform:
receiving a request for analytics in user equipment (UE) level granularity from an application function (AF);
collecting data from at least one UE, a network function (NF), and OAM (operations, administration, and maintenance) in the core network; and
providing the analytics derived based on the data to the AF.

11 . The NWDAF of claim 10 , wherein when collecting the data, the processor performs
collecting RAN Throughput per UE and QoS flow retainability per UE from the OAM.

12 . The NWDAF of claim 10 , wherein when collecting the data, the processor performs
collecting at least one of throughput for downlink (DL) and uplink (UL) per UE, packet delay for the DL and the UL per radio access bearer (RAB)/data radio bearer (DRB) per UE, packet loss rate for the DL and the UL per the RAB/DRB from the OAM at the UE level granularity.

13 . The NWDAF of the claim 10 , wherein when collecting the data, the processor performs
collecting quality of experience (QoE) metric about success rate of model distribution or upload success rate of results of local update from the at least one UE.

14 . The NWDAF of claim 10 , wherein when collecting the data, the processor performs
collecting a customized mean opinion score (MOS) about success rate of model distribution or upload success rate of results of local update from the AF.

15 . The NWDAF of claim 10 , wherein when receiving the request for analytics in the UE level granularity from the AF, the processor performs
receiving the request for the analytics from the AF in the core network.

16 . The NWDAF of claim 15 , wherein when providing the analytics derived based on the collected data to the AF, the processor performs
providing the analytics to the AF.

17 . A method for providing assistance information for selection of user equipment (UE), the method comprising:
transferring a request for analytics with in UE level granularity to a network data analytics function (NWDAF) in a core network when the analytics is requested from an application function (AF); and transferring the assistance information collected from at least one UE and a network function (NF) of the core network and the analytics received from the NWDAF to the AF.

18 . The method of claim 17 , wherein the transferring the request for the analytics to the NWDAF comprises
confirming a UE that has agreed to participate in an artificial intelligence (AI) / machine learning (ML) operation based on subscription information stored in a unified data management function (UDM).

19 . The method of claim 18 , wherein the transferring the request for the analytics to the NWDAF comprises
transmitting information of the UE that has agreed to participate in the AI/ML operation to the NWDAF as a target of the analytics.

Assignees

• Electronics & Telecommunications Res Inst

Inventors

• Sung Jihoon
• Lee Soohwan
• Shin Myung Ki

Classifications

• H04W88/18

  Service support devices; Network management devices · CPC title

• H04W84/02

  Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop] · CPC title

• H04W92/02

  Inter-networking arrangements · CPC title

• H04W8/24

  Transfer of terminal data · CPC title

• H04W8/18

  Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data · CPC title