Method of training mode adaptation signaling

Abstract

The present application describes methods of using the pre-configured AI / ML (artificial intelligence / machine learning) based model training modes 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 capability elements.

Description

[0001] TITLE

[0002] Method of training mode adaptation signaling

[0003] TECHNNICAL FIELD

[0004] The present disclosure relates to AI / ML based model class tiering, where techniques for pre-configuring and signaling the specific information about model training capability elements applicable to radio access network are presented.

[0005] BACKGROUND

[0006] 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.

[0007] 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 (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, 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.).

[0008] Model information can be signaled to pair both network-side 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.

[0009] 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.

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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.

[0014] The present disclosure solves the cited problem by the proposed embodiments and describes as first aspect a method of training mode adaption signaling in a wireless communication system by configuring a set of model training capability elements, comprising, defining a list of model training capability elements; presetting Table type-1 and Table type-2 using the pre-determined model training capability elements; determining combination sets of training capability elements for indication of subset(s) of model training capability elements; generating mapping relation between the pre-determined model training capability elements and the associated configuration information (e.g., parameter setting); providing model training configuration information to UE.

[0015] In some embodiments of the method according to the first aspect the method is characterized by, a set of model training capability elements can be adjusted for any given specific ML applications or use cases that can be associated with varying ML functionalities such that different sets of model training capability elements can be preset for different ML applications or use cases.

[0016] In some embodiments of the method according to the first aspect the method is characterized by, that exemplary list of model training capability elements can be dataset collection and / or model transfer and / or model proprietary use and / or reference model generation and / or training parameter exchange.

[0017] The method according to one of the previous claims, wherein the pre-determined model training capability elements can be identified and indicated as index or ID signaling between network side and UE side via system information or dedicated RRC message.

[0018] In some embodiments of the method according to the first aspect the method is characterized by, that the configured set of model training capability elements can be used to indicate UE ML capability to support part of model training procedure.

[0019] In some embodiments of the method according to the first aspect the method is characterized by, that the configured combination sets of training capability elements can be used to indicate subset(s) of model training capability elements.

[0020] In some embodiments of the method according to the first aspect the method is characterized by, that the configured combination sets of training capability elements can be signaled via RRC reconfiguration message (alternatively broadcast via system information if applicable).

[0021] In some embodiments of the method according to the first aspect the method is characterized by, that the configured combination sets of training capability elements can be signaled broadcast via system information if applicable.

[0022] In some embodiments of the method according to the first aspect the method is characterized by, that mapping relation between a set of model training capability elements and combination sets of training capability elements can be configured using index or ID information depending on different scenarios for deployment.

[0023] In some embodiments of the method according to the first aspect the method is characterized by, that Table type-1 represents characteristics information for list of training capability elements.

[0024] In some embodiments of the method according to the first aspect the method is characterized by, that Table type-2 represents combination sets of training capability elements to indicate support of list of model training modes.

[0025] In some embodiments of the method according to the first aspect the method is characterized by, that diverse training modes can be implementation-specific such as dataset collection, online / offline training, joint / separate training, collaborative training, training parameter exchange, training reference model transfer, etc.

[0026] In some embodiments of the method according to the first aspect the method is characterized by, that different combinations of available training modes can be collaboratively configured to execute model training operation based on network side decision.

[0027] In some embodiments of the method according to the first aspect the method is characterized by, that activating model training based on training capability elements can be indicated via MAC CE or RRC signaling.

[0028] In some embodiments of the method according to the first aspect the method is characterized by, that multiple versions of preset tables for Table type-1 and type-2 can be generated depending on specific implementation scenarios.

[0029] In some embodiments of the method according to the first aspect the method is characterized by, that any updates or additional preset tables of type-1 / 2 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 the associated configuration information, whereby the configuration information are parameter setting, with model training capability elements can be either binary or quantized format depending on implementation scenarios.

[0030] In some embodiments of the method according to the first aspect the method is characterized by, that parameter settings are dataset size and / or training parameter type and / or model transfer type / structure for each model training capability elements can be included in ML configuration information and can be sent via RRC signaling.

[0031] In some embodiments of the method according to the first aspect the method is characterized by, that the pre-determined model training capability elements and the associated configuration information, which could be the parameter setting, can be configured as mapping relation with index or ID information.

[0032] In some embodiments of the method according to the first aspect the method is characterized by, that quantization method is applied to represent model training capability elements with the associated configuration information depending on device ML capability.

[0033] In some embodiments of the method according to the first aspect the method is characterized by, that indication of any updates about model training capability elements / combination sets can be sent in periodic or non-periodic way depending on application scenarios via L1 / L2 or RRC signaling.

[0034] In some embodiments of the method according to the first aspect the method is characterized by, that the configured set of model training capability elements and / or the configured combination sets of training capability elements can be provided to UE so that full set of training capability elements are identified at UE side.

[0035] According to a second aspect the present disclosure solves the cited problem by the proposed embodiments and described by an apparatus for method of training mode adaption signaling in a wireless communication system by configuring a set of model training capability elements 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.

[0036] 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.

[0037] 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.

[0038] According to a fifth aspect, the present disclosure relates to a wireless communication system for training mode adaption signaling by configuring a set of model training capability elements, wherein the wireless communication systems comprises at least a user equipment according to the thirs aspect, at least a gNB according to the third aspect, whereby the user Equipment and the gNB each comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to carry out steps according to the first aspect.

[0039] 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.

[0040] 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.

[0041] BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is an exemplary block diagram of relationship across training capability elements and combinations with training modes.

[0043] Figure 2 is an exemplary block diagram of a list of model training capability elements.

[0044] Figure 3 is an exemplary block diagram of mapping relation between training capability elements and the associated parameter values.

[0045] Figure 4 is an exemplary table of type-1 mapping relation information.

[0046] Figure 5 is an exemplary table of type-2 mapping relation information.

[0047] Figure 6 is an exemplary flow chart of configuring model training at network side. Figure 7 is an exemplary flow chart of configuring model training at UE side.

[0048] Figure 8 is an exemplary signaling flow of model training setup with UE autonomous decision for model training mode activation.

[0049] Figure 9 is an exemplary signaling flow of model training setup with network decision of activating model training mode.

[0050] DETAILED DESCRIPTION

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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”)).

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0079] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature. Model download means Model transfer from the network to UE.

[0080] 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.

[0081] Model monitoring is a procedure that monitors the inference performance of the AI / ML model.

[0082] 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.

[0083] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.

[0084] Model update is Process of updating the model parameters and / or model structure of model.

[0085] Model upload is Model transfer from UE to the network.

[0086] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0087] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0088] 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.

[0089] 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.

[0090] 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-training may be done via online or offline training. This note could be removed when we define the term fine-tuning.

[0091] 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.

[0092] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

[0093] Supervised learning is a process of training model from input and its corresponding labels.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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, a set of model training capability elements are pre-configured for any given specific ML applications or use cases (e.g., adjustment of pre-configuration) that can be associated with varying ML functionalities. Exemplary list of model training capability elements can be {dataset collection, model transfer, model proprietary use, reference model generation, training parameter exchange, etc.}. The additional elements in the list may be defined based on implementation needs. Different sets of model training capability elements can be preset for different ML applications or use cases.

[0108] The pre-determined model training capability elements can be identified and indicated as index or ID signaling between network side and UE side via system information or dedicated RRC message. The configured set of model training capability elements can be used to indicate UE ML capability to support part of model training procedure and the configured combination sets of training capability elements can be used to indicate subset(s) of model training capability elements where it can be signaled via RRC reconfiguration message (alternatively broadcast via system information if applicable).

[0109] Depending on different scenarios for deployment, mapping relation between a set of model training capability elements and combination sets of training capability elements can be configured using index or ID information. Additionally, Table type-1 and Table type-2 are also configured using the pre-determined model training capability elements where Table type-1 represents characteristics information for list of training capability elements and Table type-2 represents combination sets of training capability elements to indicate support of list of model training modes. Here, more training modes can be implementation-specific such as dataset collection, online / offline training, joint / separate training, collaborative training, training parameter exchange, training reference model transfer, etc. Activating model training based on training capability elements can be indicated via MAC CE or RRC signaling. Multiple versions of preset tables for Table type-1 and type-2 can be generated depending on specific implementation scenarios and any updates or additional preset tables of type-1 / 2 can be indicated via L1 / L2 or RRC signaling. The associated configuration information (e.g., parameter setting) with model training capability elements can be either binary or quantized format depending on implementation scenarios where parameter settings (e.g., dataset size, training parameter type, model transfer type / structure, etc.) for each model training capability elements can be included in ML configuration information that is sent via RRC signaling where the pre-determined model training capability elements and the associated configuration information (e.g., parameter setting) can be configured as mapping relation with index or ID information. Depending on device ML capability, quantization method is applied to represent model training capability elements with the associated configuration information. Indication of any updates about model training capability elements / combination sets can be sent in periodic or non-periodic way depending on application scenarios via L1 / L2 or RRC signaling. Either the configured set of model training capability elements or the configured combination sets of training capability elements can be sent when full set of training capability elements are identified at UE side. Or both can be sent together if applicable.

[0110] Figure 1 shows an exemplary block diagram of relationship across training capability elements and combinations with training modes. In this example, the configured set of model training capability elements can be used to indicate UE ML capability to support part of model training procedure and the configured combination sets of training capability elements can be used to indicate subset(s) of model training capability elements. Depending on different scenarios for deployment, mapping relation between a set of model training capability elements and combination sets of training capability elements can be configured using index or ID information. Model training modes can be implementation-specific such as dataset collection, online / offline training, joint / separate training, collaborative training, training parameter exchange, training reference model transfer, etc. different combinations of available training modes can be collaboratively configured to execute model training operation based on network side decision.

[0111] Figure 2 shows an exemplary block diagram of a list of model training capability elements. In this example, different sets of model training capability elements can be preset for different ML applications or use cases. There can be flexible number of model training capability elements and each element can be identified with specific ID or index information if applicable. Depending on application scenarios, any subset of full list of model training capability elements can be pre-configured for use.

[0112] Figure 3 shows an exemplary block diagram of mapping relation between training capability elements and the associated parameter values. In this example, different sets of model training capability elements can be preset for different ML applications or use cases. The pre-determined model training capability elements can be identified and indicated as index or ID signaling between network side and UE side via system information or dedicated RRC message. The associated configuration information (e.g., parameter setting) with model training capability elements can be either binary or quantized format depending on implementation scenarios where parameter settings (e.g., dataset size, training parameter type, model transfer type / structure, etc.) for each model training capability elements can be included in ML configuration information that is sent via RRC signaling. Therefore, the predetermined model training capability elements and the associated configuration information (e.g., parameter setting) can be configured as mapping relation with index or ID information.

[0113] Figure 4 shows an exemplary table of type-1 mapping relation information. In this example, Table type-1 represents characteristics information for list of training capability elements. Multiple versions of preset tables for Table type-1 can be generated depending on specific implementation scenarios and any updates or additional preset tables of type-1 can be indicated via L1 / L2 or RRC signaling.

[0114] Figure 5 shows an exemplary table of type-2 mapping relation information. In this example, Table type-2 represents combination sets of training capability elements to indicate support of list of model training modes. Multiple versions of preset tables for Table type-2 can be generated depending on specific implementation scenarios and any updates or additional preset tables of type-2 can be indicated via L1 / L2 or RRC signaling. Figure 6 shows an exemplary flow chart of configuring model training at network side. In this example, model training capability elements with Table type 1 and / or type 2 are configured at network side so that model training configuration information can be sent to UE side via system information or dedicated RRC signaling. Mapping relation information across training capability elements and combinations with training modes can be also shared with UE when model training configuration information is sent by network.

[0115] Figure 7 shows an exemplary flow chart of configuring model training at UE side. In this example, UE can receive Table type-1 only or both Table type-1 and type-2 depending on implementation use cases. If both Table type-1 and type-2 are received, UE can decide candidate model training mode(s) autonomously if applicable. If Table type-1 only is received, UE selects the supported capability element(s) and feedback indication message to network side.

[0116] Figure 8 shows an exemplary signaling flow of model training setup with UE autonomous decision for model training mode activation. In this example, based on ML configuration information about model training, UE determine the supported model training capability elements and / or combination set(s) so that any specific training mode can be activated by UE autonomously.

[0117] Figure 9 shows an exemplary signaling flow of model training setup with network decision of activating model training mode. In this example, ML configuration with model training capability elements / combination sets are provided to UE after signaling exchange of ML conditions and / or ML capability so that UE can select the supported training capability element(s) or combination set and send the indication message about the selection. Network side then can determine any specific training mode for activation.

Claims

CLAIMS1. A method of training mode adaption signaling in a wireless communication system by configuring a set of model training capability elements at the network node, comprising:• Defining a list of model training capability elements;• Presetting Table type-1 and Table type-2 using the pre-determined model training capability elements;• Determining combination sets of training capability elements for indication of subset(s) of model training capability elements;• Generating mapping relation between the pre-determined model training capability elements and the associated configuration information (e.g., parameter setting);• Providing model training configuration information to UE.

2. The method according to previous claim 1 , wherein a set of model training capability elements are adjusted for any given specific ML applications or use cases that are associated with varying ML functionalities such that different sets of model training capability elements are preset for different ML applications or use cases.

3. The method according to one of the previous claims, wherein exemplary list of model training capability elements are dataset collection and / or model transfer and / or model proprietary use and / or reference model generation and / or training parameter exchange.

4. The method according to one of the previous claims, wherein the pre-determined model training capability elements are identified and indicated as index or ID signaling between network side and UE side via system information or dedicated RRC message.

5. The method according to one of the previous claims, wherein the configured set of model training capability elements are used to indicate UE ML capability to support part of model training procedure.

6. The method according to one of the previous claims, wherein the configured combination sets of training capability elements are used to indicate subset(s) of model training capability elements.

7. The method according to one of the previous claims, wherein the configured combination sets of training capability elements are signaled via RRC reconfiguration message (alternatively broadcast via system information if applicable).

8. The method according to one of the previous claims, wherein the configured combination sets of training capability elements are signaled broadcast via system information if applicable.

9. The method according to one of the previous claims, wherein mapping relation between a set of model training capability elements and combination sets of training capability elements are configured using index or ID information depending on different scenarios for deployment.

10. The method according to one of the previous claims, wherein Table type-1 represents characteristics information for list of training capability elements.

11. The method according to one of the previous claims, wherein Table type-2 represents combination sets of training capability elements to indicate support of list of model training modes.

12. The method according to one of the previous claims, wherein diverse training modes are implementation-specific such as dataset collection, online / offline training, joint / separate training, collaborative training, training parameter exchange, training reference model transfer, etc.

13. The method according to one of the previous claims, wherein different combinations of available training modes are collaboratively configured to execute model training operation based on network side decision.

14. The method according to one of the previous claims, wherein activating model training based on training capability elements are indicated via MAC CE or RRC signaling.

15. The method according to one of the previous claims, wherein multiple versions of preset tables for Table type-1 and type-2 are generated depending on specific implementation scenarios.

16. The method according to one of the previous claims, wherein any updates or additional preset tables of type-1 / 2 are indicated via L1 / L2 or RRC signaling.

17. The method according to one of the previous claims, wherein the associated configuration information, whereby the configuration information are parameter setting, with model training capability elements are either binary or quantized format depending on implementation scenarios.

18. The method according to one of the previous claims, wherein parameter settings are dataset size and / or training parameter type and / or model transfer type / structure for each model training capability elements are included in ML configuration information and are sent via RRC signaling.

19. The method according to one of the previous claims, wherein the pre-determined model training capability elements and the associated configuration information, which could be the parameter setting, are configured as mapping relation with index or ID information.

20. The method according to one of the previous claims, wherein quantization method is applied to represent model training capability elements with the associated configuration information depending on device ML capability.21 . The method according to one of the previous claims, wherein indication of any updates about model training capability elements / combination sets are sent in periodic or non-periodic way depending on application scenarios via L1 / L2 or RRC signaling.

22. The method according to one of the previous claims, wherein the configured set of model training capability elements and / or the configured combination sets of training capability elements are provided to UE so that full set of training capability elements are identified at UE side.

23. Apparatus for method of training mode adaption signaling in a wireless communication system by configuring a set of model training capability elements 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 22.

24. User Equipment comprising an apparatus according to claim 23.

25. gNB comprising an apparatus according to claim 23.

26. Wireless communication for training mode adaption signaling by configuring a set of model training capability elements, wherein the wireless communication systems comprises at least a user equipment according to claim 24, at least a gNB according to claim 25, whereby the user Equipment and the gNB each comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to carry out the steps of the claims 1 to 22.

Images