WO2025210138A1

WO2025210138A1 - Method of multi-training model operation signaling

Info

Publication number: WO2025210138A1
Application number: PCT/EP2025/059112
Authority: WO
Inventors: Hojin Kim
Original assignee: Continental Automotive Technologies GmbH
Current assignee: Aumovio Germany GmbH
Priority date: 2024-04-04
Filing date: 2025-04-03
Publication date: 2025-10-09
Anticipated expiration: 2026-10-04

Abstract

The present disclosure describes methods of using the pre-configured AI/ML (artificial intelligence/machine learning) based model training operation types in wireless mobile communication system including base station (e.g., gNB, TN, NTN) and mobile station e.g., UE. In AI/ML model is applied to radio access network, model training performance can be degraded depending on UE ML condition or capability changes. Therefore, model operation (e.g., model training/inferencing/monitoring/updating) can be set up between network and UE by configuring model training operation types.

Description

TITLE

Method of multi-training model operation signaling

TECHNNICAL FIELD

The present disclosure relates to AI/ML based model training operation types, where techniques for pre-configuring and signaling the specific information about model training operation types applicable to radio access network are presented.

BACKGROUND

In 3GPP (Third 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 (Technical Specification Group) RAN (Radio Access Network) meeting #94e. The official title of AI/ML study item is “Study on AI/ML for NR Air Interface”. 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 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 framework are included as one of key work scopes. 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. Also in 3GPP, two-sided (AI/ML) model is defined as a paired AI/ML model(s) over which joint inference is performed, where joint inference comprises AI/ML Inference whose inference is performed jointly across the UE and the network. Also for one-sided (AI/ML) model, UE-side (AI/ML) model is defined as an AI/ML model whose inference is performed entirely at the UE and network-side (AI/ML) model is defined as an AI/ML model whose inference is performed entirely at the network. Currently, AI/ML specification work is at the stage of work item discussion for Release 19. Earlier, in 3GPP TR 37.817 for Release 17, titled as Study on enhancement for Data Collection for NR and EN-DC, UE (user equipment) 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 (Al)/Machine 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, RAN-based AI/ML model is considered very significant for both network and UE to meet any desired model operations (e.g., model training, inference, selection, switching, update, monitoring, etc.). Model information can be signaled to pair both networkside and UE-side models for various lifecycle management (LCM) operations. However, signaling overhead indicating model information can be very high especially when model based LCM is processed between base station (BS/gNB) and multiple UEs.

In LCM, model training is one of the most important parts for model deployment and currently there is no specification defined for signaling methods and network-UE behaviors so as to identify the required dataset when model updating/re-training as any activated model can be also impacted due to model/data drift. When ML condition changes, the enabled AI/ML model(s) can be impacted for model performance due to data/model drift. In this case, model re-training/updating can be executed.

WO20231 44831 A1 describes a method to perform life cycle management of at least one machine learning, ML, model for telecommunications dimensioning in a network where the method includes performing to determine that a performance of a current ML model is not acceptable for a forecast of telecommunications dimensioning with selecting minimal informative dataset.

WO2023173296A1 describes that a device is selectively included or excluded from participating in an online training procedure based on the device's currently reported learning capabilities in order to provide a tradeoff between overhead reductions and training performance. US2022116764A1 shows that the base station receives, from each of the number of UEs, a machine learning processing capability report and the base station groups a number of UEs in accordance with the machine learning processing capability reports, to receive gradient updates to the machine learning model.

US2022360973A1 shows that the UE may transmit to the network, based on the request to report the UE capability, an indication of one or more of an Al capability, an ML capability, a radio capability associated with the at least one of the Al procedure or the ML procedure, or a core network capability associated with the at least one of the Al procedure or the ML procedure.

W02022008037A1 shows that the terminal informs the network that the terminal is in the inability state if the terminal indicated the capability and the terminal is in the inability state, wherein, in the inability state, the terminal is not able to execute and/or train the machine learning model, or the terminal is not able to execute and/or train the machine learning model at least with a predefined performance.

For AI/ML model operation of one-sided or two-sided models between network and UE, there can be multiple types of model training methods such as joint training or separate training. However, different UEs have model training constraints to support any specific model training method (e.g., private model not allowed for joint training). With the limited number of target UEs for training due to UE's training capability constraints, training convergence can be slow or not efficient to apply any specific type of model training.

This problem is solved by configuring multiple types of model training operations such that two or more types of model training operations can be collaborated together for the same target model training.

This solution beneficially leads to increase target UEs for model training regardless of multiple model training types and to improve model training performance such as convergence rate. The present disclosure solves the cited problem by the proposed embodiments and describes as first aspect a method of multi-training model operation signaling for configuring multiple types of model training operations in a wireless communication system, comprising, grouping target UEs for specific type of model training operation; defining information for exchange between model training operations; determining specific bits for signaling of selective/combining model training; presetting mapping relationship information to support various types of model training operations.

In some embodiments of the method according to the first aspect the method is characterized by, that two or more types of model training operations can be collaborated for the same target model training.

The method according to one of the previous claims, wherein grouping of target UEs for model training can be based on device training capability information for a specific model training operation type.

In some embodiments of the method according to the first aspect the method is characterized by, that UE can be assigned to operate two or more types of model training operations depending on network side decision or UE autonomous decision.

In some embodiments of the method according to the first aspect the method is characterized by, that two or more model training operation types can be enabled simultaneously for one-sided or two-sided model training between network side and UE side.

In some embodiments of the method according to the first aspect the method is characterized by, that model training updates can be exchanged each other across different UE groups.

In some embodiments of the method according to the first aspect the method is characterized by, that /V-bit signaling is used to enable either selective model training or combining model training. In some embodiments of the method according to the first aspect the method is characterized by, that selective model training can enable selection of single type of model training operation between network and UE for activation.

In some embodiments of the method according to the first aspect the method is characterized by, that combining model training can enable selection of multiple types of model training operation between network and UE for activation such that two or more different types of model training operations are performed in parallel.

In some embodiments of the method according to the first aspect the method is characterized by, that the exchanged model training information across those training types can be combined for model training.

In some embodiments of the method according to the first aspect the method is characterized by, that specific content of training update information can vary depending on different model training operation types and/or application scenarios.

In some embodiments of the method according to the first aspect the method is characterized by, that exchange of training update information can be configured using ML configuration information via L1/L2 or RRC signaling.

In some embodiments of the method according to the first aspect the method is characterized by, that mapping relationship between model training operation types and the associated parameter value set for information exchange can be preset available via system information or dedicated RRC signaling based on ML deployment scenarios with different model applications/functionalities.

In some embodiments of the method according to the first aspect the method is characterized by, that any updates about mapping relationship table (containing model training operation types and the associated parameter value set for information exchange) can be indicated via L1/L2 or RRC signaling. In some embodiments of the method according to the first aspect the method is characterized by, that a set of model training operation types can be configured by including one-sided model and two-sided model scenarios such that model training can be performed jointly or independently between network side and UE side.

In some embodiments of the method according to the first aspect the method is characterized by, that the associated parameter value set with each model training operation types can be pre-defined in mapping relationship table.

In some embodiments of the method according to the first aspect the method is characterized by, that UE can provide the configured parameter value information related to each model training operation types to network side based on mapping relationship table format.

In some embodiments of the method according to the first aspect the method is characterized by, that different model training operation types can be determined for different UE groups.

In some embodiments of the method according to the first aspect the method is characterized by, that network side can coordinate what combinations of model training types can be enabled for model training across multiple UE groups.

In some embodiments of the method according to the first aspect the method is characterized by, that indication message can be sent via L1/L2 or RRC signaling with broadcast or multicast transmission to enable specific model training operation type for each UE group.

In some embodiments of the method according to the first aspect the method is characterized by, that a single network-sided model can be enabled to perform two- sided model training with UE groups having UE-sided models based on the preconfigured model training operation types. In some embodiments of the method according to the first aspect the method is characterized by, that UE can enable two or more model training operation types to support the configured two-sided model training.

In some embodiments of the method according to the first aspect the method is characterized by, that the number of UE groups can be flexible to determine target UEs with their associated UE-sided models for use.

In some embodiments of the method according to the first aspect the method is characterized by, that multiple network-sided models can be enabled to perform two- sided model training with UE groups having UE-sided models.

In some embodiments of the method according to the first aspect the method is characterized by, that the configured multiple network-sided models supporting specific model training operation type(s) can be located in the same network side location or distributed across different locations with network interface connection.

In some embodiments of the method according to the first aspect the method is characterized by, that each network-sided models can activate specific model training operation types with the determined UE groups.

In some embodiments of the method according to the first aspect the method is characterized by, that model training can be collaborated across different networksided models that are associated with their own UE groups.

In some embodiments of the method according to the first aspect the method is characterized by, that mapping relationship between model training operation types and the associated parameter value set for information exchange can be preset based on ML deployment scenarios with different model applications/functionalities at network side. In some embodiments of the method according to the first aspect the method is characterized by, that grouping of target UEs for model training based on device training capability information can be determined by network side.

In some embodiments of the method according to the first aspect the method is characterized by, that UE can receive ML model training configuration information from network side including mapping relationship between model training operation types and the associated parameter value set for information exchange.

In some embodiments of the method according to the first aspect the method is characterized by, that UE can provide the configured parameter value information to network side based on mapping relationship table after activation of specific model training operation type(s).

According to a second aspect the present disclosure solves the cited problem by the proposed embodiments and described by an apparatus for of multi-training model operation signaling for configuring multiple types of model training operations in a wireless communication system, the apparatus comprising a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to carry out the steps of the first aspect.

According to a third aspect the present disclosure solves the cited problem by the proposed embodiments and described by a user equipment comprising an apparatus according to the second aspect.

According to a fourth aspect the present disclosure solves the cited problem by the proposed embodiments and described by gNB comprising an apparatus according to the second aspect. According to a fifth aspect, the present disclosure relates to a wireless communication of multi-training model operation signaling for configuring multiple types of model training operations, wherein the wireless communication systems comprises at least a user equipment according according to the third aspect, at least a gNB according to the fourth aspect, whereby the user Equipment and the gNB each comprises a processor coupled with a memory in which computer program instructions are stored.

According to a sixth aspect, the present disclosure relates to a computer program product comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to the first aspect said at least one processor to carry out a method for exchanging data according to any one of the embodiments of the present disclosure. The computer program product can use any programming language, and can be in the form of source code, object code, or in any intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.

According to a sixth aspect, the present disclosure relates to a computer-readable storage medium comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to any one of the embodiments of the present disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

Figure 1 is an exemplary block diagram of exchanging training update information between type 1 and type 2 model training operations.

Figure 2 is an exemplary table of mapping relationship between model training operation types and the associated parameter value set for information exchange.

Figure 3 is an exemplary block diagram of assigning model training types for multi- UE groups.

Figure 4 is an exemplary block diagram of enabling model training types for single network-sided model with multiple UE-sided models. Figure 5 is an exemplary block diagram of enabling model training types for multiple network-sided models with multiple UE-sided models.

Figure 6 is an exemplary flow chart of configuring model training operation types at network side.

Figure 7 is an exemplary flow chart of configuring model training operation types at UE side.

DETAILED DESCRIPTION

The detailed description set forth below, with reference to annexed drawings, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In particular, although terminology from 3GPP 5G NR may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the invention.

Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and/or is implied from the context in which it is used. All references to a/an/the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and/or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

In some embodiments, a more general term “network node” may be used and may correspond to any type of radio network node or any network node, which communicates with a UE (directly or via another node) and/or with another network node. Examples of network nodes are NodeB, MeNB, ENB, a network node belonging to MCG or SCG, base station (BS), multi-standard radio (MSR) radio node such as MSR BS, eNodeB, gNodeB, network controller, radio network controller (RNC), base station controller (BSC), relay, donor node controlling relay, base transceiver station (BTS), access point (AP), transmission points, transmission nodes, RRU, RRH, nodes in distributed antenna system (DAS), core network node (e.g. Mobile Switching Center (MSC), Mobility Management Entity (MME), etc), Operations & Maintenance (O&M), Operations Support System (OSS), Self Optimized Network (SON), positioning node (e.g. Evolved- Serving Mobile Location Centre (E-SMLC)), Minimization of Drive Tests (MDT), test equipment (physical node or software), etc.

In some embodiments, the non-limiting term user equipment (UE) or wireless device may be used and may refer to any type of wireless device communicating with a network node and/or with another UE in a cellular or mobile communication system. Examples of UE are target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine (M2M) communication, PDA, PAD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, UE category Ml, UE category M2, ProSe UE, V2V UE, V2X UE, etc. Additionally, terminologies such as base station/gNodeB and UE should be considered non-limiting and do in particular not imply a certain hierarchical relation between the two; in general, “gNodeB” could be considered as device 1 and “UE” could be considered as device 2 and these two devices communicate with each other over some radio channel. And in the following the transmitter or receiver could be either gNodeB (gNB), or UE.

As will be appreciated by one skilled in the art, aspects of the embodiments may be embodied as a system, apparatus, method, or program product. Accordingly, embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects.

For example, the disclosed embodiments may be implemented as a hardware circuit comprising custom very-large-scale integration (“VLSI”) circuits or gate arrays, off- the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed embodiments may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, or the like. As another example, the disclosed embodiments may include one or more physical or logical blocks of executable code which may, for instance, be organized as an object, procedure, or function.

Furthermore, embodiments may take the form of a program product embodied in one or more computer readable storage devices storing machine readable code, computer readable code, and/or program code, referred hereafter as code. The storage devices may be tangible, non- transitory, and/or non-transmission. The storage devices may not embody signals. In a certain embodiment, the storage devices only employ signals for accessing code.

Any combination of one or more computer readable medium may be utilized. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing the code. The storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

More specific examples (a non-exhaustive list) of the storage device would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (“RAM”), a read-only memory (“ROM”), an erasable programmable read-only memory (“EPROM” or Flash memory), a portable compact disc readonly memory (“CD-ROM”), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

Code for carrying out operations for embodiments may be any number of lines and may be written in any combination of one or more programming languages including an object- oriented programming language such as Python, Ruby, Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language, or the like, and/or machine languages such as assembly languages. The code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (“LAN”), wireless LAN (“WLAN”), or a wide area network (“WAN”), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider (“ISP”)).

Furthermore, the described features, structures, or characteristics of the embodiments may be combined in any suitable manner. In the following description, numerous specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a thorough understanding of embodiments. One skilled in the relevant art will recognize, however, that embodiments may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of an embodiment. Reference throughout this specification to “one embodiment,” “an embodiment,” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in one embodiment,” “in an embodiment,” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment, but mean “one or more but not all embodiments” unless expressly specified otherwise. The terms “including,” “comprising,” “having,” and variations thereof mean “including but not limited to,” unless expressly specified otherwise. An enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms “a,” “an,” and “the” also refer to “one or more” unless expressly specified otherwise.

Aspects of the embodiments are described below with reference to schematic flowchart diagrams and/or schematic block diagrams of methods, apparatuses, systems, and program products according to embodiments. It will be understood that each block of the schematic flowchart diagrams and/or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and/or schematic block diagrams, can be implemented by code. This code may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart diagrams and/or block diagrams.

The code may also be stored in a storage device that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the storage device produce an article of manufacture including instructions which implement the function/act specified in the flowchart diagrams and/or block diagrams.

The code may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer implemented process such that the code which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart diagrams and/or block diagrams.

The flowchart diagrams and/or block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of apparatuses, systems, methods, and program products according to various embodiments. In this regard, each block in the flowchart diagrams and/or block diagrams may represent a module, segment, or portion of code, which includes one or more executable instructions of the code for implementing the specified logical function(s).

It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Other steps and methods may be conceived that are equivalent in function, logic, or effect to one or more blocks, or portions thereof, of the illustrated Figures.

Although various arrow types and line types may be employed in the flowchart and/or block diagrams, they are understood not to limit the scope of the corresponding embodiments. Indeed, some arrows or other connectors may be used to indicate only the logical flow of the depicted embodiment. For instance, an arrow may indicate a waiting or monitoring period of unspecified duration between enumerated steps of the depicted embodiment. It will also be noted that each block of the block diagrams and/or flowchart diagrams, and combinations of blocks in the block diagrams and/or flowchart diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and code.

The description of elements in each figure may refer to elements of proceeding figures. Like numbers refer to like elements in all figures, including alternate embodiments of like elements.

AI/ML Model is a data driven algorithm that applies AI/ML techniques to generate set of outputs based on set of inputs.

AI/ML model delivery is a generic term referring to delivery of an AI/ML model from one entity to another entity in any manner. Note is An entity could mean network node/function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.

AI/ML model Inference is a process of using trained AI/ML model to produce set of outputs based on set of inputs.

AI/ML model testing is a subprocess of training, to evaluate the performance of final AI/ML model using dataset different from one used for model training and validation. Differently from AI/ML model validation, testing does not assume subsequent tuning of the model.

AI/ML model training is a process to train an AI/ML Model [by learning the input/output relationship] in data driven manner and obtain the trained AI/ML Model for inference.

AI/ML model transfer is a delivery of an AI/ML model over the air interface in manner that is not transparent to 3GPP signalling, either parameters of model structure known at the receiving end or new model with parameters. Delivery may contain full model or partial model. AI/ML model validation is a subprocess of training, to evaluate the quality of an AI/ML model using dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

Data collection is a process of collecting data by the network nodes, management entity, or UE for the purpose of AI/ML model training, data analytics and inference.

Federated learning I federated training is a machine learning technique that trains an AI/ML model across multiple decentralized edge nodes e.g., UEs, gNBs each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples.

Functionality identification is a process/method of identifying an AI/ML functionality for the common understanding between the NW and the UE. Note is Information regarding the AI/ML functionality may be shared during functionality identification. Where AI/ML functionality resides depends on the specific use cases and sub use cases.

Model activation means enable an AI/ML model for specific AI/ML-enabled feature.

Model deactivation means disable an AI/ML model for specific AI/ML-enabled feature.

Model download means Model transfer from the network to UE.

Model identification is A process/method of identifying an AI/ML model for the common understanding between the NW and the UE. The process/method of model identification may or may not be applicable and regarding the AI/ML model may be shared during model identification.

Model monitoring is a procedure that monitors the inference performance of the AI/ML model.

Model parameter update is Process of updating the model parameters of model. Model selection is the process of selecting an AI/ML model for activation among multiple models for the same AI/ML enabled feature. Model selection may or may not be carried out simultaneously with model activation.

Model switching is deactivating currently active AI/ML model and activating different AI/ML model for specific AI/ML-enabled feature.

Model update is Process of updating the model parameters and/or model structure of model.

Model upload is Model transfer from UE to the network.

Network-side (AI/ML) model is an AI/ML Model whose inference is performed entirely at the network.

Offline field data is the data collected from field and used for offline training of the AI/ML model.

Offline training is an AI/ML training process where the model is trained based on collected dataset, and where the trained model is later used or delivered for inference. Note is This definition only serves as guidance. There may be cases that may not exactly conform to this definition but could still be categorized as offline training by commonly accepted conventions.

Online field data is the data collected from field and used for online training of the AI/ML model.

Online training is an AI/ML training process where the model being used for inference) is (typically continuously) trained in (near) real-time with the arrival of new training samples. Note is the notion of (near) real-time vs. non real-time is context- dependent and is relative to the inference time-scale. This definition only serves as guidance.

There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Note is Fine- tuning/re-train ing may be done via online or offline training. This note could be removed when we define the term fine-tuning.

Reinforcement Learning (RL) is a process of training an AI/ML model from input (a.k.a. state) and feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with.

Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

Supervised learning is a process of training model from input and its corresponding labels.

Two-sided (AI/ML) model is a paired AI/ML Model(s) over which joint inference is performed, where joint inference comprises AI/ML Inference whose inference is performed jointly across the UE and the network, i.e, the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.

UE-side (AI/ML) model is an AI/ML Model whose inference is performed entirely at the UE.

Unsupervised learning is a process of training model without labelled data.

Proprietary-format models is ML models of vendor-Zdevice-specific proprietary format, from 3GPP perspective. They are not mutually recognizable across vendors and hide model design information from other vendors when shared.

Open-format models is ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually recognizable between vendors and do not hide model design information from other vendors when shared. The detailed description set forth below, with reference to the figures, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. For instance, although 3GPP terminology, from e.g., 5G NR, may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the present disclosure.

The disclosure is related to wireless communication system, which may be for example a 5G NR wireless communication system. More specifically, it represents a RAN of the wireless communication system, which is used exchange data with UEs via radio signals. For example, the RAN may send data to the UEs (downlink, DL), for instance data received from a core network (CN). The RAN may also receive data from the UEs (uplink, UL), which data may be forwarded to the CN.

In the examples illustrated, the RAN comprises one base station, BS. Of course, the RAN may comprise more than one BS to increase the coverage of the wireless communication system. Each of these BSs may be referred to as NB, eNodeB (or eNB), gNodeB (or gNB, in the case of a 5G NR wireless communication system), an access point or the like, depending on the wireless communication standard(s) implemented.

The UEs are located in a coverage of the BS. The coverage of the BS corresponds for example to the area in which UEs can decode a PDCCH transmitted by the BS.

An example of a wireless device suitable for implementing any method, discussed in the present disclosure, performed at a UE corresponds to an apparatus that provides wireless connectivity with the RAN of the wireless communication system, and that can be used to exchange data with said RAN. Such a wireless device may be included in a UE. The UE may for instance be a cellular phone, a wireless modem, a wireless communication device, a handheld device, a laptop computer, or the like. The UE may also be an Internet of Things (loT) equipment, like a wireless camera, a smart sensor, a smart meter, smart glasses, a vehicle (manned or unmanned), a global positioning system device, etc., or any other equipment that may run applications that need to exchange data with remote recipients, via the wireless device.

The wireless device comprises one or more processors and one or more memories. The one or more processors may include for instance a central processing unit (CPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc. The one or more memories may include any type of computer readable volatile and non-volatile memories (magnetic hard disk, solid-state disk, optical disk, electronic memory, etc.). The one or more memories may store a computer program product, in the form of a set of programcode instructions to be executed by the one or more processors to implement all or part of the steps of a method for exchanging data, performed at a UE’s side, according to any one of the embodiments disclosed herein.

The wireless device can comprise also a main radio, MR, unit. The MR unit corresponds to a main wireless communication unit of the wireless device, used for exchanging data with BSs of the RAN using radio signals. The MR unit may implement one or more wireless communication protocols, and may for instance be a 3G, 4G, 5G, NR, WiFi, WiMax, etc. transceiver or the like. In preferred embodiments, the MR unit corresponds to a 5G NR wireless communication unit.

The following explanation will provide the detailed description of the mechanism about pre-configuring and signaling the specific information about model online training by configuring a set of UE behaviors. AI/ML based techniques are currently applied to many different applications and 3GPP also started to work on its technical investigation to apply to multiple use cases based on the observed potential gains. AI/ML lifecycle can be split into several stages such as data collection/pre- processing, model training, model testing/validation, model deployment/update, model monitoring etc., where each stage is equally important to achieve target performance with any specific model(s). In applying AI/ML model for any use case or application, one of the challenging issues is to manage the lifecycle of AI/ML model. It is mainly because the data/model drift occurs during model deployment/inference and it results in performance degradation of AI/ML model. Fundamentally, the dataset statistical changes occur after model is deployed and model inference capability is also impacted with unseen data as input. In a similar aspect, the statistical property of dataset and the relationship between input and output for the trained model can be changed with drift occurrence. In this context, model training or re-training is one of key issues for model performance maintenance as model performance such as inferencing and/or training is dependent on different model execution environment with varying configuration parameters. To handle this issue, collaboration between UE and gNB is highly important to track model performance and re-configure model corresponding to different environments. AI/ML model needs model monitoring after deployment because model performance cannot be maintained continuously due to drift and update feedback is then provided to re- train/update the model or select alternative model.

When AI/ML model enabled wireless communication network is deployed, it is then important to consider how to handle AI/ML model in activation with re-configuration for wireless devices under operations such as model training, inference, updating, etc. For AI/ML model operation of one-sided or two-sided models between network and UE, For AI/ML model operation of one-sided or two-sided models between network and UE, Model training performance (e.g., training in LCM) can be degraded depending on ML condition changes.

In this method, multiple types of model training operations are configured such that two or more types of model training operations can be collaborated for the same target model training. Grouping of target UEs for model training can be based on device training capability information for a specific model training operation type, where UE can be assigned to operate two or more types of model training operations depending on network side decision or UE autonomous decision. Two or more model training operation types can be enabled simultaneously for one-sided or two-sided model training between network side and UE side. Model training updates can be exchanged each other across different UE groups. /V- bit signaling (e.g., 1 -bit) is used to enable either selective model training or combining model training. Specifically, selective model training can enable selection of single type of model training operation between network and UE for activation. As an example, when type-1 model training operation is performed, it can be switched into type-2 model training operation based on the pre-configured threshold or metric information. On the other hand, combining model training can enable selection of multiple types of model training operation between network and UE for activation. As an example, two or more different types of model training operations are performed in parallel so that the exchanged model training information across those training types can be combined for model training. Specific content of training update information can vary depending on different model training operation types and/or application scenarios.

However, exchange of training update information is configured using ML configuration information via L1/L2 or RRC signaling. Mapping relationship between model training operation types and the associated parameter value set for information exchange is preset based on ML deployment scenarios with different model applications/functionalities. Mapping relationship table can be sent via system information or dedicated RRC signaling. Also any updates about mapping relationship table can be indicated via L1/L2 or RRC signaling. A set of model training operation types are configured by including one-sided model and two-sided model scenarios where model training can be performed jointly or independently between network side and UE side. The associated parameter value set with each model training operation types can be also pre-defined in mapping relationship table where parameter values can be related to or part of {input dataset/feature, training output, target/reference training model, etc.}.

At UE side, UE provides the configured parameter value information to network side based on mapping relationship table.

Different model training operation types can be determined for different UE groups. Network side coordinates what combinations of model training types can be enabled for model training across multiple UE groups. To enable specific model training operation type for each UE group, indication message is sent via L1/L2 or RRC signaling with broadcast or multicast transmission. Based on the pre-configured model training operation types, a single network-sided model is enabled to perform two-sided model training with UE groups having UE-sided models. UE can enable two or more model training operation types to support the configured two-sided model training. The number of UE groups can be flexible to determine target UEs with their associated UE-sided models for use. Based on the pre-configured model training operation types, multiple network-sided models can be enabled to perform two-sided model training with UE groups having UE-sided models. In this scenario, the configured multiple network-sided models can be located in the same network side location or distributed across different locations with network interface connection. Each network-sided models can activate specific model training operation types with the determined UE groups. Model training can be collaborated across different network-sided models that are associated with their own UE groups.

Mapping relationship between model training operation types and the associated parameter value set for information exchange is preset based on ML deployment scenarios with different model applications/functionalities at network side. Grouping of target UEs for model training based on device training capability information can be also determined by network side. Two or more model training operation types can be enabled simultaneously for one-sided or two-sided model training between network side and UE side. UE receives ML model training configuration information from network side including mapping relationship between model training operation types and the associated parameter value set for information exchange. UE provides the configured parameter value information to network side based on mapping relationship table after activation of specific model training operation type(s).

Figure 1 shows an exemplary block diagram of exchanging training update information between type 1 and type 2 model training operations. In this example, two model training operations are enabled in parallel so that training update information from model training operation type 1 is provided to model training operation type 2 and vice versa. Specific content of training update information can vary depending on different model training operation types and/or application scenarios. However, exchange of training update information is configured using ML configuration information via L1/L2 or RRC signaling.

Figure 2 shows an exemplary table of mapping relationship between model training operation types and the associated parameter value set for information exchange. In this example, mapping relationship between model training operation types and the associated parameter value set for information exchange is preset based on ML deployment scenarios with different model applications/functionalities. Mapping relationship table can be sent via system information or dedicated RRC signaling. Also any updates about mapping relationship table can be indicated via L1/L2 or RRC signaling. A set of model training operation types are configured by including one-sided model and two-sided model scenarios where model training can be performed jointly or independently between network side and UE side. The associated parameter value set with each model training operation types can be also pre-defined in mapping relationship table where parameter values can be related to or part of {input dataset/feature, training output, target/reference training model, etc.}. At UE side, UE provides the configured parameter value information to network side based on mapping relationship table.

Figure 3 shows an exemplary block diagram of assigning model training types for multi-UE groups. In this example, different model training operation types can be determined for different UE groups. Network side coordinates what combinations of model training types can be enabled for model training across multiple UE groups. To enable specific model training operation type for each UE group, indication message is sent via L1/L2 or RRC signaling with broadcast or multicast transmission.

Figure 4 shows an exemplary block diagram of enabling model training types for single network-sided model with multiple UE-sided models. In this example, based on the pre-configured model training operation types, a single network-sided model is enabled to perform two-sided model training with UE groups having UE-sided models. UE can enable two or more model training operation types to support the configured two-sided model training. The number of UE groups can be flexible to determine target UEs with their associated UE-sided models for use.

Figure 5 shows an exemplary block diagram of enabling model training types for multiple network-sided models with multiple UE-sided models. In this example, based on the pre-configured model training operation types, multiple network-sided models can be enabled to perform two-sided model training with UE groups having UE-sided models. In this scenario, the configured multiple network-sided models can be located in the same network side location or distributed across different locations with network interface connection. Each network-sided models can activate specific model training operation types with the determined UE groups. Model training can be collaborated across different network-sided models that are associated with their own UE groups.

Figure 6 shows an exemplary flow chart of configuring model training operation types at network side. In this example, mapping relationship between model training operation types and the associated parameter value set for information exchange is preset based on ML deployment scenarios with different model applications/functionalities at network side. Grouping of target UEs for model training based on device training capability information can be also determined by network side. Two or more model training operation types can be enabled simultaneously for one-sided or two-sided model training between network side and UE side.

Figure 7 shows an exemplary flow chart of configuring model training operation types at UE side. In this example, UE receives ML model training configuration information from network side including mapping relationship between model training operation types and the associated parameter value set for information exchange. UE provides the configured parameter value information to network side based on mapping relationship table after activation of specific model training operation type(s).

This application provides fundamental mechanisms of interworking and data information flow in radio access network collaboration for AI/ML support, especially in supporting model training operation types based model operations aspect. Based on the proposed methods, gNB-UE behaviors for supporting AI/ML operation for wireless communication with the configured model training operation types are greatly improved with the potential scenarios.

Claims

1. A method performed by a network node for multi-training model operation signaling to configure multiple types of model training operations in a wireless communication system, comprising:

• Grouping target UEs for specific type of model training operation;

• Defining information for exchange between model training operations;

• Determining specific bits for signaling of selective/combining model training;

• Presetting mapping relationship information to support various types of model training operations.

2. The method according to previous claim 1 , wherein two or more types of model training operations are collaborated for the same target model training.

3. The method according to one of the previous claims, wherein grouping of target UEs for model training are based on device training capability information for a specific model training operation type.

4. The method to one of the previous claims, wherein UE are assigned to operate two or more types of model training operations depending on network side decision or UE autonomous decision.

5. The method to one of the previous claims, wherein two or more model training operation types are enabled simultaneously for one-sided or two-sided model training between network side and UE side.

6. The method to one of the previous claims, wherein model training updates are exchanged each other across different UE groups.

7. The method to one of the previous claims, wherein /V-bit signaling is used to enable either selective model training or combining model training.

8. The method to one of the previous claims, wherein selective model training can enable selection of single type of model training operation between network and UE for activation.

9. The method to one of the previous claims, wherein combining model training can enable selection of multiple types of model training operation between network and UE for activation such that two or more different types of model training operations are performed in parallel.

10. The method to one of the previous claims, wherein the exchanged model training information across those training types are combined for model training.

11 . The method to one of the previous claims, wherein specific content of training update information can vary depending on different model training operation types and/or application scenarios.

12. The method to one of the previous claims, wherein exchange of training update information are configured using ML configuration information via L1/L2 or RRC signaling.

13. The method to one of the previous claims, wherein mapping relationship between model training operation types and the associated parameter value set for information exchange are preset available via system information or dedicated RRC signaling based on ML deployment scenarios with different model applications/functionalities.

14. The method to one of the previous claims, wherein any updates about mapping relationship table (containing model training operation types and the associated parameter value set for information exchange) are indicated via L1/L2 or RRC signaling.

15. The method to one of the previous claims, wherein a set of model training operation types are configured by including one-sided model and two-sided model scenarios such that model training are performed jointly or independently between network side and UE side.

16. The method to one of the previous claims, wherein the associated parameter value set with each model training operation types are pre-defined in mapping relationship table.

17. The method to one of the previous claims, wherein UE provides the configured parameter value information related to each model training operation types to network side based on mapping relationship table format.

18. The method to one of the previous claims, wherein different model training operation types are determined for different UE groups.

19. The method to one of the previous claims, wherein network side can coordinate what combinations of model training types are enabled for model training across multiple UE groups.

20. The method to one of the previous claims, wherein indication message are sent via L1/L2 or RRC signaling with broadcast or multicast transmission to enable specific model training operation type for each UE group.

21 . The method to one of the previous claims, wherein a single network-sided model are enabled to perform two-sided model training with UE groups having UE-sided models based on the pre-configured model training operation types.

22. The method to one of the previous claims, wherein UE can enable two or more model training operation types to support the configured two-sided model training.

23. The method to one of the previous claims, wherein the number of UE groups are flexible to determine target UEs with their associated UE-sided models for use.

24. The method to one of the previous claims, wherein multiple network-sided models are enabled to perform two-sided model training with UE groups having UE-sided models.

25. The method to one of the previous claims, wherein the configured multiple network-sided models supporting specific model training operation type(s) are located in the same network side location or distributed across different locations with network interface connection.

26. The method to one of the previous claims, wherein each network-sided models can activate specific model training operation types with the determined UE groups.

27. The method to one of the previous claims, wherein model training are collaborated across different network-sided models that are associated with their own UE groups.

28. The method to one of the previous claims, wherein mapping relationship between model training operation types and the associated parameter value set for information exchange are preset based on ML deployment scenarios with different model applications/functionalities at network side.

29. The method to one of the previous claims, wherein grouping of target UEs for model training based on device training capability information are determined by network side.

30. The method to one of the previous claims, wherein two or more model training operation types are enabled simultaneously for one-sided or two-sided model training between network side and UE side.

31. The method to one of the previous claims, wherein UE can receive ML model training configuration information from network side including mapping relationship between model training operation types and the associated parameter value set for information exchange.

32. The method to one of the previous claims, wherein UE can provide the configured parameter value information to network side based on mapping relationship table after activation of specific model training operation type(s).

33. Apparatus for of multi-training model operation signaling for configuring multiple types of model training operations in a wireless communication system, 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 32.

34. User Equipment comprising an apparatus according to claim 33.

35. gNB comprising an apparatus according to claim 33.

36. Wireless communication of multi-training model operation signaling for configuring multiple types of model training operations, wherein the wireless communication systems comprises at least a user equipment according to claim 34, at least a gNB according to claim 35, whereby the user Equipment and the gNB each comprises a processor coupled with a memory in which computer program instructions are stored.