Method of sensing-enabled combination mode signaling

Abstract

The present disclosure describes methods of using the pre-configured AI / ML (artificial intelligence / machine learning) combination mode with the sensing-enabled model operation in wireless mobile communication system including base station e.g., gNB, TRP, TN, NTN and mobile station e.g., UE. In AI / ML model is applied to radio access network, model performance is significantly impacted due to sensing-based data collection. Therefore, model operation e.g., model training / inferencing / monitoring / updating is adaptively set up between network and UE by using combination mode of sensing and model operation.

Description

[0001] 202403438

[0002] - 1 -

[0003] TITLE

[0004] Method of sensing-enabled combination mode signaling

[0005] TECHNICAL FIELD

[0006] The present disclosure relates to AI / ML based model operation with sensing-enabled model signaling, where techniques for pre-configuring and signaling the specific information about sensing-based combination mode operation applicable to radio access network are presented.

[0007] BACKGROUND

[0008] 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.

[0009] 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) 202403438

[0010] - 2 - 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.

[0011] 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 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, TRP) 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.

[0012] US 2023069342 describes how to assist determination of the model update time in consideration of cost for the update of a model.

[0013] US2023022737 explains supporting generation of machine learning model when a certain machine learning model is changed.

[0014] US 2019012876 provides projections, predictions, and recommendations for computing system. 202403438

[0015] - 3 -

[0016] US 2023276208 describes UE context scenario indication-based configurations in a wireless communication network where UE identifies, based on the sensor data, a context scenario associated with a surrounding environment of the UE or a user status.

[0017] US 2024022927 explains that sensing agents communicate with UEs or nodes using one of multiple sensing modes through non-sensing-based or sensing-based links, and / or Al agents communicate with UEs or nodes using one of multiple Al modes through non-AI-based or Al-based links.

[0018] The present disclosure solves the cited problem by the proposed embodiments and describes methods of using the pre-configured AI / ML (artificial intelligence / machine learning) combination mode with the sensing-enabled model operation in wireless mobile communication system including base station e.g., gNB, TRP, TN, NTN and mobile station e.g., UE. In AI / ML model is applied to radio access network, model performance is significantly impacted due to sensing-based data collection.

[0019] Therefore, model operation e.g., model training / inferencing / monitoring / updating is adaptively set up between network and UE by using combination mode of sensing and model operation.

[0020] In some embodiments of the method according to the first aspect is characterized by that the method of sensing-enabled combination mode signaling in a wireless communication system by configuring a list of modes having combinations of associating ML model operation types with sensing modes for sensing-capable ML model activation, comprises the step presetting look-up table(s) of activating any specific combination of ML model operation type and sensing mode; including the associated ID information to be pre-configured in assistance information to be associated with the selected combination mode index for the related parameter set or characteristics such as model ID, dataset ID and / or sensing ID; categorizing device capabilities as sensing-capable only, ML-capable only and dual sensing / ML-capable. 202403438

[0021] - 4 -

[0022] In some embodiments of the method according to the first aspect, the method is characterized by, that the look-up table is used to associate the number of available sensing modes in the set with ML model operation types and sent via RRC signaling.

[0023] In some embodiments of the method according to the first aspect, the method is characterized by, that that different number of look-up tables are configured to support various device categories with sensing / ML capabilities.

[0024] In some embodiments of the method according to the first aspect, the method is characterized by, that sending mode indication message is used for specific mode activation via L1 / L2 or RRC signaling.

[0025] In some embodiments of the method according to the first aspect, the method is characterized by, that either NW-based or UE autonomous-based decision for selection of specific combination mode is available for combination mode activation.

[0026] In some embodiments of the method according to the first aspect, the method is characterized by, that ML model operation type and the associated sensing mode is enabled or switched simultaneously.

[0027] In some embodiments of the method according to the first aspect, the method is characterized by, that combination mode switching or adaptation is triggered based on implementation-specific scenarios such as model performance accuracy level or sensing data quality in association with environmental conditions or mobility.

[0028] In some embodiments of the method according to the first aspect, the method is characterized by, that measurement configuration information is provided to UE so as to perform on-device measurement of ML / sensing related metrics.

[0029] In some embodiment of the method according to the first aspect, the network configures UE to measure the metrics such as inference latency time (in ms) from sensor input arrival to ML output, reported via RRC measurement report and signal-to-noise ratio (SNR) as quality of the sensing signal reception included in 202403438

[0030] - 5 -

[0031] Layer 1 measurement report. UE performs these measurements at intervals defined by the network (e.g. every 100 ms) and reports back the results in extended measurement reports so that the network can adapt combination modes based on performance or sensing quality.

[0032] In some embodiments of the method according to the first aspect, the method is characterized by, that both sides of entities are aligned about model ID, dataset collection ID, LCM phase and sensing activities for enabling any specific combination mode between network side and UE side.

[0033] In some embodiments of the method according to the first aspect, the method is characterized by, that the same ML operation type is used with sensing mode switching based on a separate look-up table to be configured for switching sensing mode only.

[0034] In some embodiments of the method according to the first aspect, the method is characterized by, that a separate look-up table about switching ML operation type only is configured so that independent combination mode switching is executed between sensing mode and ML operation type.

[0035] In some embodiments of the method according to the first aspect, the method is characterized by, that multiple pairs of NW-UE links is set up along with either dedicated or common model ID to be applied.

[0036] In some embodiments of the method according to the first aspect, the method is characterized by, that Tx-Rx entity switching is set up along with the assigned model ID to be applied.

[0037] In some embodiments of the method according to the first aspect, the method is characterized by, that switching of combination mode is executed dynamically or semi-statically depending on deployment scenarios or use cases.

[0038] In some embodiments of the method according to the first aspect, the method is characterized by, that UE grouping based combination mode activation is set up 202403438

[0039] - 6 - using common model ID to be applied (e.g., the same model ID used across UE group or dedicated model ID of each UE to be paired with the same NW-side model together with bi-static sensing mode).

[0040] In some embodiments of the method according to the first aspect, the method is characterized by, that sensing-capable only device supports sensing mode-based operation without performing ML operation.

[0041] In some embodiments of the method according to the first aspect, the method is characterized by, that ML-capable only device supports ML operation (LCM phase based) without performing sensing mode operation.

[0042] In some embodiments of the method according to the first aspect, the method is characterized by, that dual sensing / ML-capable device supports both sensing modebased operation and ML operation together.

[0043] In some embodiments of the method according to the first aspect, the method is characterized by, that device type is further sub-categorized into multiple levels of capabilities according to supportability of sensing and ML operation.

[0044] In some embodiments of the method according to the first aspect, the method is characterized by, that device (sub-) categorization of supporting sensing and ML operation is indexed with multiple levels of sensing mode / ML operation type capabilities.

[0045] In some embodiments of the method according to the first aspect, the method is characterized by, that either NW-based or UE autonomous-based decision for combination mode activation is made based on network configuration, which depends on valid combination mode selections.

[0046] According to a second aspect, the present disclosure relates to an apparatus for sensing-enabled combination mode signaling in a wireless communication system by configuring a list of modes having combinations of associating ML model operation 202403438

[0047] - 7 - types with sensing modes for sensing-capable ML model activation, 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 according to the first aspect.

[0048] According to a third aspect, the present disclosure relates to an user Equipment comprising an apparatus according to the second aspect.

[0049] According to a fouth aspect, the present disclosure relates to an gNB comprising an apparatus according to the second aspect.

[0050] Wireless communication system for sensing-enabled combination mode signaling by configuring a list of modes having combinations of associating ML model operation types with sensing modes for sensing-capable ML model activation, wherein the wireless communication systems comprises user equipment according to third aspect , gNB according the fourth aspect, whereby the user Equipment and the gNB each comprises at least a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps according to the first aspect.

[0051] BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is an exemplary look-up table of combination modes.

[0053] Figure 2 is an exemplary block diagram of applying combination mode for ML / sensing activation.

[0054] Figure 3 is an exemplary block diagram of multi-pairing of NW-UE links.

[0055] Figure 4 is an exemplary block diagram of Tx-Rx entity switching.

[0056] Figure 5 is an exemplary block diagram of UE grouping based mode activation. 202403438

[0057] - 8 -

[0058] Figure 6 is an exemplary flow chart of configuring combination mode at network side.

[0059] Figure 7 is an exemplary flow chart of activating combination mode at UE side.

[0060] DETAILED DESCRIPTION

[0061] 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.

[0062] 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.

[0063] 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. 202403438

[0064] - 9 -

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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 202403438

[0069] - 10 - over some radio channel. And in the following the transmitter or receiver could be either gNodeB (gNB), or UE.

[0070] 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.

[0071] 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.

[0072] 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

[0073] 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. 202403438

[0074] - 11 -

[0075] 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.

[0076] 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”)).

[0077] 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 202403438

[0078] - 12 - 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.

[0079] 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 fimctions / acts specified in the flowchart diagrams and / or block diagrams

[0080] 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.

[0081] 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 202403438

[0082] - 13 - 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.

[0083] 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).

[0084] 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.

[0085] 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. 202403438

[0086] - 14 -

[0087] 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.

[0088] 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.

[0089] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs.

[0090] 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.

[0091] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0092] 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.

[0093] 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. 202403438

[0094] - 15 -

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0101] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.

[0102] Model download means Model transfer from the network to UE.

[0103] 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 202403438

[0104] - 16 - identification may or may not be applicable and regarding the AI / ML model may be shared during model identification.

[0105] Model monitoring is A procedure that monitors the inference performance of the AI / ML model.

[0106] 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.

[0107] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.

[0108] Model update is process of updating the model parameters and / or model structure of model.

[0109] Model upload is Model transfer from UE to the network.

[0110] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0111] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0112] 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.

[0113] Online field data is the data collected from field and used for online training of the AI / ML model. 202403438

[0114] - 17 -

[0115] 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.

[0116] 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.

[0117] 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.

[0118] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

[0119] Supervised learning is a process of training model from input and its corresponding labels.

[0120] 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.

[0121] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.

[0122] Unsupervised learning is a process of training model without labelled data. 202403438

[0123] - 18 -

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 202403438

[0130] - 19 - 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The disclosure is related to wireless communication system, which may be for 202403438

[0135] - 20 - 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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 202403438

[0140] - 21 - 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.

[0141] 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.

[0142] 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. 202403438

[0143] - 22 -

[0144] 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 identification of UE-side or UE-part of two-sided models, ML operation using model activation for LCM phases can be degraded or unreliable when sensing-based data collection is interfered due to environmental change and / or mobility.

[0145] In this method, a list of modes having combinations of associating ML model operation types with sensing modes are configured for sensing-capable ML model activation. To support combination modes, look-up table(s) of activating any specific combination of ML model operation type and sensing mode can be preset and sent via RRC signaling where it can be used to associate the number of available sensing modes in the set with ML model operation types so as to speed up sensing-capable ML model activation. And different number of look-up tables can be configured to support various device categories with sensing / ML capabilities. Sending mode indication message can be used for specific mode activation via L1 / L2 or RRC signaling.

[0146] The associated ID information can be preset to be included in assistance information when selecting combination mode index for the related parameter set or characteristics such as model ID, dataset ID and / or sensing ID. For selection of specific combination mode, either network(NW)-based or UE autonomous-based decision can be available for combination mode activation where it can depend on valid combination mode selections. When any specific combination mode is indicated via L1 / L2 or RRC signaling, ML model operation type and the associated sensing mode can be enabled or switched simultaneously. 202403438

[0147] - 23 -

[0148] For combination mode index, a unique numeric identifier (e.g. an 8-bit index) is used to select one entry in a pre-configured look-up table of ML operation type and sensing-mode pairs. Also combination mode index is used in signaling messages (L1 / L2 or RRC) so that both UE and network refer to the exact ML and sensing configuration.

[0149] In LCM stages, the stage of an ML model’s on-device lifecycle includes at least one of training (initial model parameter learning), inferencing (real-time model execution), updating (e.g. weight refinement or fine-tuning), and monitoring (performance / health reporting). For example, a specific LCM stage is explicitly conveyed as part of associated ID information so the network knows whether UE is to train, infer, update, or monitor.

[0150] For bi-static sensing, a sensing arrangement in which the Tx (e.g. gNB) and Rx (e.g. UE) are spatially distinct nodes. In NW-to-UE bi-static sensing, network node transmits sensing signal and UE receives reflected / scattered signal. In UE-to-NW bi-static sensing, UE transmits and network node receives it. For mono-static sensing, same node transmits and receives.

[0151] Using look-up table for combination mode based indication signaling can speed up sensing-capable ML model activation and different number of look-up tables with the associated mode size can be configured to support various device categories with sensing / ML capabilities. Combination mode switching or adaptation can be triggered based on implementation-specific scenarios such as model performance accuracy level or sensing data quality in association with environmental conditions or mobility. Measurement configuration information is provided to UE so as to perform on-device measurement of ML / sensing related metrics where measurement feedback can be sent if applicable. UE can then send on-device sensing capability and ML capability to network side so that those capability information can be used to configure the relevant combination mode set for UE. After determining specific combination mode set information as part of configuration information, indication message can be sent to UE and UE can then activate the indicated combination mode for ML and sensing operation together. 202403438

[0152] - 24 -

[0153] When enabling any specific combination mode between network side and UE side, both sides need to be aligned about model ID, dataset collection ID, LCM phase and sensing activities. When the same ML operation type is maintained with no change, sensing mode can be only switched or changed as well. In this case, a separate lookup table can be configured for sensing mode only version. If necessary, another separate look-up table about ML operation type only can be also configured so that independent combination mode switching can be executed. Multiple pairs of NW-UE links can be set up along with either dedicated or common model ID to be applied where the same model ID of UE side (common model ID) is paired with different NW- side models or the separate model ID of UE side (dedicated model ID) is paired with each cell or TRP. When there are multiple cells or TRPs connected with UE having NW-side models and UE-side model, respectively, model ID pairs between each link can be configured for ML model activation and also sensing mode of bi-static can be enabled such as NW-UE or UE-NW bi-static in association with model ID in use. The collected dataset via sensing mode operation can then be used for ML model operation with specific LCM phase(s) such as model training, inferencing, updating, or monitoring etc. Tx-Rx entity switching can be set up along with the assigned model ID to be applied.

[0154] When initially TRP-UE link has combination mode with NW-UE bi-static and UE-side model, it can be switched into other combination mode of UE-NW bi-static with two- side model based on any implementation-specific triggering method or the configured threshold value. Switching of combination mode can happen dynamically or semi- statically depending on deployment scenarios or use cases. UE grouping based mode activation can be set up using common model ID to be applied where the same model ID is used across UE group together with NW-UE bi-static.

[0155] As another example, dedicated model ID of each UE can be paired with the same NW-side model so that either NW-UE bi-static or UE-NW bi-static can be enabled. Depending on various scenarios, any specific combination mode table can be configured for use between network side and UE(s). Device categories can be defined such as 1 ) sensing-capable only, 2) ML-capable only, and 3) dual 202403438

[0156] - 25 - sensing / ML-capable, where sensing-capable only device supports sensing modebased operation without performing ML operation and ML-capable only device supports ML operation (LCM phase based) without performing sensing mode operation while dual sensing / ML-capable device supports both sensing mode-based operation and ML operation together.

[0157] Device type can be further sub-categorized into multiple levels of capabilities according to supportability of sensing and ML operation. Device (sub-)categorization of supporting sensing and ML operation can be indexed with multiple levels of sensing mode / ML operation type capabilities so that any requested combination mode can be executed. Either NW-based or UE autonomous-based decision for combination mode activation can be made based on network configuration, which can also depend on valid combination mode selections.

[0158] Figure 1 shows an exemplary look-up table of combination modes. In this example, look-up table(s) of activating any specific combination of ML model operation type and sensing mode to be preset (that can be sent via RRC) can be preset and shared with UE. When any specific combination mode is indicated via L1 / L2 or RRC signaling, ML model operation type and the associated sensing mode can be enabled or switched simultaneously. Using look-up table for combination mode based indication signaling can speed up sensing-capable ML model activation.

[0159] Different number of look-up tables with the associated mode size for different number of combinations can be configured to support various device categories with sensing / ML capabilities. Combination mode switching or adaptation can be triggered based on implementation-specific scenarios such as model performance accuracy level or sensing data quality in association with environmental conditions or mobility.

[0160] Figure 2 shows an exemplary block diagram of applying combination mode for ML / sensing activation. In this example, measurement configuration information is provided to UE so as to perform on-device measurement of ML / sensing related metrics where measurement feedback can be sent if applicable. UE can then send on-device sensing capability and ML capability to network side so that those information can be used to configure the relevant combination mode set for UE. After 202403438

[0161] - 26 - determining specific combination mode set information as part of configuration information, indication message can be sent to UE. UE can then activate the indicated combination mode for ML and sensing operation together. When enabling any specific combination mode between network side and UE side, both sides need to be aligned about model ID, dataset collection ID, LCM phase and sensing activities. When the same ML operation type is maintained with no change, sensing mode can be only switched or changed as well. In this case, a separate look-up table can be configured for sensing mode only version. If necessary, another separate look-up table about ML operation type only can be also configured so that independent combination mode switching can be executed.

[0162] Figure 3 shows an exemplary block diagram of multi-pairing of NW-UE links. In this example, multiple pairs of NW-UE links can be set up along with either dedicated or common model ID to be applied where the same model ID of UE side (common model ID) is paired with different NW-side models of TRPs or the separate model ID of UE side (dedicated model ID) is paired with each TRP. When there are multiple TRPs connected with UE having NW-side models and UE-side model, respectively, model ID pairs between each link of TRP and UE can be configured for ML model activation and also sensing mode of bi-static can be enabled such as NW-UE or UE- NW bi-static in association with model ID in use. The collected dataset via sensing mode operation can then be used for ML model operation with specific LCM phase(s) such as model training, inferencing, updating, or monitoring etc.

[0163] Figure 4 shows an exemplary block diagram of Tx-Rx entity switching. In this example, Tx-Rx entity switching can be set up along with the assigned model ID to be applied. When initially TRP-UE link has combination mode with NW-UE bi-static and UE-side model, it can be switched into other combination mode of UE-NW bi- static with two-side model based on any implementation-specific triggering method or the configured threshold value. Switching of combination mode can happen dynamically or semi-statically depending on deployment scenarios or use cases.

[0164] Figure 5 shows an exemplary block diagram of UE grouping based mode activation.

[0165] In this example, UE grouping based mode activation can be set up using common 202403438

[0166] - 27 - model ID to be applied where the same model ID is used across UE group together with NW-UE bi-static. As another example, dedicated model ID of each UE can be paired with the same NW-side model so that either NW-UE bi-static or UE-NW bistatic can be enabled. Depending on various scenarios, any specific combination mode table can be configured for use between network side and UE(s).

[0167] Figure 6 shows an exemplary flow chart of configuring combination mode at network side. In this example, a list of modes having combinations of associating ML model operation types with sensing modes for sensing-capable ML model activation are configured at network side. In addition, the associated ID information can be preset to be included in assistance information when selecting combination mode index for the related parameter set or characteristics such as model ID, dataset ID and / or sensing ID. The pre-configured combination modes can be sent to UE via system information or dedicated RRC signaling where one or more types of different combination mode set can be generated and sent if applicable.

[0168] Figure 7 shows an exemplary flow chart of activating combination mode at UE side. In this example, device categories can be defined such as 1 ) sensing-capable only, 2) ML-capable only, and 3) dual sensing / ML-capable, where sensing-capable only device supports sensing mode-based operation without performing ML operation and ML-capable only device supports ML operation (LCM phase based) without performing sensing mode operation while dual sensing / ML-capable device supports both sensing mode-based operation and ML operation together. Device type can be further sub-categorized into multiple levels of capabilities according to supportability of sensing and ML operation.

[0169] Device (sub-)categorization of supporting sensing and ML operation can be indexed with multiple levels of sensing mode / ML operation type capabilities so that any requested combination mode can be executed. Sensing capability can indicate a set of supported sensing modes with different types of sensing signals or devices. ML capability can indicate a set of supported models and ML features with available on- device resource, supportability of LCM phases (e.g., training, inferencing, updating, monitoring, etc.). Either NW-based or UE autonomous-based decision for 202403438

[0170] - 28 - combination mode activation can be made based on network configuration, which can also depend on valid combination mode selections.

Claims

202403438- 29 -CLAIMS1. Method of sensing-enabled combination mode signaling in a wireless communication system by configuring a list of modes having combinations of associating ML model operation types with sensing modes for sensing-capable ML model activation, comprising:• Presetting look-up table(s) of activating any specific combination of ML model operation type and sensing mode;• Including the associated ID information to be pre-configured in assistance information to be associated with the selected combination mode index for the related parameter set or characteristics such as model ID, dataset ID and / or sensing ID;• Categorizing device capabilities as sensing-capable only, ML-capable only and dual sensing / ML-capable.

2. The method according to previous claim 1 , wherein look-up table is used to associate the number of available sensing modes in the set with ML model operation types and sent via RRC signaling.

3. The method according to one of the previous claims, wherein different number of look-up tables are configured to support various device categories with sensing / ML capabilities.

4. The method according to one of the previous claims, wherein sending mode indication message is used for specific mode activation via L1 / L2 or RRC signaling.

5. The method according to one of the previous claims, wherein either NW-based or UE autonomous-based decision for selection of specific combination mode is available for combination mode activation.202403438- 30 -6. The method according to one of the previous claims, wherein ML model operation type and the associated sensing mode is enabled or switched simultaneously.

7. The method according to one of the previous claims, wherein combination mode switching or adaptation is triggered based on implementation-specific scenarios such as model performance accuracy level or sensing data quality in association with environmental conditions or mobility.

8. The method according to one of the previous claims, wherein measurement configuration information is provided to UE so as to perform on-device measurement of ML / sensing related metrics.

9. The method according to one of the previous claims, wherein both sides of entities are aligned about model ID, dataset collection ID, LCM phase and sensing activities for enabling any specific combination mode between network side and UE side.

10. The method according to one of the previous claims, wherein the same ML operation type is used with sensing mode switching based on a separate look-up table to be configured for switching sensing mode only.

11. The method according to one of the previous claims, wherein a separate look-up table about switching ML operation type only is configured so that independent combination mode switching is executed between sensing mode and ML operation type.

12. The method according to one of the previous claims, wherein multiple pairs of NW-UE links is set up along with either dedicated or common model ID to be applied.

13. The method according to one of the previous claims, wherein Tx-Rx entity switching is set up along with the assigned model ID to be applied.202403438- 31 -14. The method according to one of the previous claims, wherein switching of combination mode is executed dynamically or semi-statically depending on deployment scenarios or use cases.

15. The method according to one of the previous claims, wherein UE grouping based combination mode activation is set up using common model ID to be applied (e.g., the same model ID used across UE group or dedicated model ID of each UE to be paired with the same NW-side model together with bi-static sensing mode).

16. The method according to one of the previous claims, wherein sensing-capable only device supports sensing mode-based operation without performing ML operation.

17. The method according to one of the previous claims, wherein ML-capable only device supports ML operation (LCM phase based) without performing sensing mode operation.

18. The method according to one of the previous claims, wherein dual sensing / ML- capable device supports both sensing mode-based operation and ML operation together.

19. The method according to one of the previous claims, wherein device type is further sub-categorized into multiple levels of capabilities according to supportability of sensing and ML operation.

20. The method according to one of the previous claims, wherein device (sub-) categorization of supporting sensing and ML operation is indexed with multiple levels of sensing mode / ML operation type capabilities.21 . The method according to one of the previous claims, wherein either NW-based or UE autonomous-based decision for combination mode activation is made based on network configuration, which depends on valid combination mode selections.202403438- 32 -22. Apparatus for sensing-enabled combination mode signaling in a wireless communication system by configuring a list of modes having combinations of associating ML model operation types with sensing modes for sensing-capable ML model activation, 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 21.

23. User Equipment comprising an apparatus according to claim 22.

24. gNB comprising an apparatus according to claim 2.

25. Wireless communication system for sensing-enabled combination mode signaling by configuring a list of modes having combinations of associating ML model operation types with sensing modes for sensing-capable ML model activation, wherein the wireless communication systems comprises user equipment according to claim 23, gNB according to claim 24, 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 implement steps of the claims 1 to 21 .

Images