Search

EP-4740392-A1 - METHOD OF ADVANCED ML REPORT SIGNALING

EP4740392A1EP 4740392 A1EP4740392 A1EP 4740392A1EP-4740392-A1

Abstract

The method of data-driven AI/ML model signaling for ML status reporting with machine learning model operation in wireless mobile communication system including base station (e.g., gNB) and mobile station (e.g., UE) is described, furthermore the mapping relationship is measured for different types of model operation between network and UE so that this measurement can be applied to varying applications with priority index for ML status update based on prioritization.

Inventors

  • KIM, HOJIN
  • SHAH, Rikin
  • ANDRAE, ANDREAS

Assignees

  • AUMOVIO Germany GmbH

Dates

Publication Date
20260513
Application Date
20240701

Claims (15)

  1. 1. A method of forming a mapping relationship between machine learning, ML, status update and a priority index, comprising: • Pre-configuring the priority index for different ML application scenarios and associated ML features with one or multiple applicable models; • Configuring ML status update content that is one of an life cycle management, LCM, operation mode update and/or an ML applicable condition update; • Mapping of ML models with application scenarios and associated ML status update content; • Setting mapping relationship tables with the priority index; • Transmitting the pre-configured mapping relationship information including priority index.
  2. 2. The method according to claim 1 , wherein transmitting the pre-configured mapping relationship information is performed through one of common RRC signaling or dedicated RRC signaling.
  3. 3. The method according to any previous claim, further including reporting ML status update signaling.
  4. 4. The method according to claim 3, wherein reporting ML status update signaling comprises one of: • Deciding on network side to send the priority index with an indication message by the gNB, or • autonomously deciding by the UE to send the priority index.
  5. 5. The method according to claim 4, wherein sending the priority index with an indication message by the gNB is performed through one of MAC CE or other available L1/L2 signaling.
  6. 6. The method according to any previous claim, further comprising: configuring the mapping relationship information between ML status reporting and priority index by a gNB or the network side, and sending an indication message to a UE through L1/L2 signaling based on a network side decision of sending the priority index.
  7. 7. The method according to any previous claim, wherein the preferred priority index is determined by the network side for particular ML status update reception.
  8. 8. The method according to claim 4, wherein the UE determines the priority index to report any particular ML status update and the UE sends the determined priority index with the associated ML status update to the network side.
  9. 9. The method according to claim 1 , wherein depending on the configured LCM operation mode between network and UE, ML status reporting is split into high priority and low priority levels and a set of key elements contain one of ML application scenarios, ML features, ML functionalities, ML models, LCM phases, and attribute data sets that represent different combinations of the associated configuration, scenario, deployment, model, etc. or applicable conditions required to support LCM/model operations for any particular ML application scenarios.
  10. 10. The method according to any previous claim, wherein the signaling flow of ML status reporting with priority index for one of a periodic case and an event-trigger case comprises one of: • A periodic case, in which ML status reporting is performed periodically for different LCM operations enabled by UE. For example, finite list of ML status updates for specific LCM operations can be reported to network in different periodic settings based on prioritized order. • An event-trigger case in which ML status reporting is triggered with the preconfigured threshold based on applicable condition change or attribute data change belonging to ML status update content for facilitating that network side receives a report for selected ML status update with the associated priority index.
  11. 11 . The method according to any previous claim, wherein UE grouping based multicast can be used for sending priority index as indication message for requesting specific ML status update and the same priority index is sent to more than one single UE for ML status update request by grouping multiple UEs based on using common mapping relationship information applicable to those UEs.
  12. 12. Apparatus for forming mapping relationship between ML status update and priority index, the apparatus comprising a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 11 .
  13. 13. User Equipment comprising an apparatus according to claim 12.
  14. 14. Base station comprising an apparatus according to claim 12.
  15. 15. Wireless communication system, wherein the gNB comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of one of claims 1 to 11 , and wherein the UE comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of one of the claims 1 to 11 .

Description

TITLE Method of advanced ML report signaling TECHNNICAL FIELD The present disclosure relates to AI/ML based model status update report signaling, where techniques for pre-configuring and signaling the specific information about status update of machine learning model operation with different types are presented. BACKGROUND In 3GPP (3rd Generation Partnership Project), one of the selected study items as the approved Release 18 package is AI/ML (artificial intelligence/machine learning) as described in the related document (RP-213599) addressed in 3GPP TSG RAN (Technical Specification Group Radio Access Network) meeting #94e. The official title of AI/ML study item is “Study on AI/ML for NR Air Interface”, and currently RAN WG1 and WG2 are actively working on specification. The goal of this study item is to identify a common AI/ML framework and areas of obtaining gains using AI/ML based techniques with use cases. According to 3GPP, the main objective of this study item is to study an AI/ML framework for air-interface with target use cases by considering performance, complexity, and potential specification impact. In particular, AI/ML model, terminology and description to identify common and specific characteristics for the framework will be one of key work scope. Regarding AI/ML framework, various aspects are under consideration for investigation, and one of key items is about lifecycle management of AI/ML model where multiple stages are included, as mandatory for model training, model deployment, model inference, model monitoring, model updating etc. Earlier, in 3GPP TR 37.817 for Release 17, titled as Study on enhancement for Data Collection for NR and EN-DC, UE mobility was also considered as one of AI/ML use cases and one of scenarios for model training/inference is that both functions are located within RAN node. Followingly, in Release 18 the new work item of “Artificial Intelligence (AI)ZMachine Learning (ML) for NG-RAN” was initiated to specify data collection enhancements and signaling support within existing NG-RAN interfaces and architecture. For the above active standardization works, currently there is no specification defined for signaling methods or network (e.g., gNB) I mobile station (e.g., UE) behaviors about supporting UE status update reporting about AI/ML model operation when multiple LCM (lifecycle management) operations are enabled on a device such as model training and inferencing and/or updating, etc. for one or more particular application scenarios with different set of ML features/functionalities. Since applicable conditions to support the enabled LCM operations can dynamically change due to indevice condition change and/or external condition change, the network side also need to be aware of accurate information about the reported ML status update for those LCM operations. For various use cases/scenarios with ML operation, it is expected that the model performance can be significantly degraded with an applicable condition change, as the associated ML status update could not be reported to network accurately and/or with delay. US 2021326701 A1 describes the method of transmitting the measurements to other node for neural network training and a method of reporting a UE capability to a server and configuring neural network parameters. US 2022400373A1 shows a method, performed by a UE, for transmitting, to a BS, UE capability information indicating at least one radio capability of the UE and at least one machine learning (ML) capability of the UE and receiving, from the BS, based on the UE capability information, ML configuration information indicating at least one neural network function. US 2022330012A1 shows the performance of a ML procedure based on at least one initial ML capability of the UE and determination of at least one updated ML capability for the ML procedure corresponding to an update to the at least one initial ML capability. WO2023272718A1 shows that a UE indicates a support for an end-to-end multi-block machine learning application with block of the multi-block machine learning application. US 2022377844A1 shows a network transmission of an ML model training request to activate the ML model training and a device transmission, based on receiving the ML model training request, ML model training results indicative of a trained ML model. The object of the invention is to improve the performance of such known communication systems. This object is solved by the subject matter of the independent claims. Further embodiments of the invention are defined in the dependent claims. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is an exemplary block diagram of ML status reporting with priority index. Figure 2 is an exemplary table #1 of mapping relationship table for priority index. Figure 3 is an exemplary table #2 of mapping relationship table for priority index. Figure 4 is a flowchart of procedure of ML status update report at network side. Figure 5 is a flowchart of procedure o