Ensure consistency for machine learning procedure

Abstract

At step 1, a network apparatus (NW) receives a capability report from a user equipment (UE) which may indicate consistency between a first machine learning (ML) phase and a second ML phase. At step 2,

Description

FIELDS

[0001] Various example embodiments of the present disclosure generally relate to the field of telecommunication and in particular, to methods, devices, apparatuses and computer readable storage medium for ensuring consistency for artificial intelligence (AI) / machine learning (ML) procedure. BACKGROUND

[0002] With developments in the integration of AI / ML within the 5G and emerging 6G new radio (NR) air interface, a new frontier in network adaptability and efficiency is being explored. The 3rd generation partner project (3GPP) Release-18 study item and 3GPP Release-19 work item emphasize the importance of model generalization across various network scenarios, addressing the need for AI / ML models to maintain robust performance under diverse conditions. This includes the strategic incorporation of additional conditions to refine model training, ensuring models are well-suited to both network-side and user equipment-side requirements. There may be a plurality of phases during a life cycle of an ML model. It is important to ensure the consistency between different phases such as training and inference. SUMMARY

[0003] In a first aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to: receive, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator; and determine, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

[0004] In a second aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus to: determine, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network; and transmit, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

[0005] In a third aspect of the present disclosure, there is provided a method. The method comprises: receiving, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator; and determining, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

[0006] In a fourth aspect of the present disclosure, there is provided a method. The method comprises: determining, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network; and transmitting, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

[0007] In a fifth aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises means for receiving, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator; and means for determining, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

[0008] In a sixth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises means for determining, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network; and means for transmitting, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

[0009] In a seventh aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the third aspect.

[0010] In an eighth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the fourth aspect.

[0011] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Some example embodiments will now be described with reference to the accompanying drawings, where:

[0013] FIG. 1A illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0014] FIG. IB illustrates another example communication environment in which example embodiments of the present disclosure can be implemented;

[0015] FIG. 2 illustrates a signaling flow of inference procedure according to some example embodiments of the present disclosure.

[0016] FIG. 3A and FIG. 3B illustrate signaling flows of data collection procedure according to some example embodiments of the present disclosure.

[0017] FIG. 4 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0018] FIG. 5 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0019] FIG. 6 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0020] FIG. 7 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0021] FIG. 8 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0022] FIG. 9 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0023] Throughout the drawings, the same or similar reference numerals represent the same or similar element. DETAILED DESCRIPTION

[0024] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0025] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same mean as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0026] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0027] It shall be understood that although the terms “first,” “second,”..., etc. in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0028] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0029] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0030] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0031] As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0032] This definition of circuitry applies to all uses of this term in this application, 5 including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor 10 integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0033] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), 15 High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), the sixth generation (6G) communication protocols, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0034] As used herein, the term “network device” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU) at an IAB donor node. An IAB node comprises a Mobile Terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0035] As used herein, the term “network device” also may refer to a core network (CN) entity / node / function / apparatus / device. Example core network nodes may such as include functions of one or more of a location management function (LMF), mobile switching center (MSC), mobility management entity (MME), home subscriber server (HSS), access and mobility management function (AMF), session management function (SMF), authentication server function (AUSF), subscription identifier de-concealing function (SIDF), unified data management (UDM), security edge protection proxy (SEPP), network exposure function (NEF), and / or a user plane function (UPF) and so on.

[0036] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0037] As used herein, the term “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other combination of the time, frequency, space and / or code domain resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0038] The term “transmission reception point (TRP)” used herein may be defined as an antenna array, with one or more antenna elements, available to the network located at a specific geographical location for a specific area. In some embodiments, the TRP may be implemented at a network device. The term “condition registered in a network side” used herein may refer to a condition at network side which include additional information to assist terminal units to improve consistency between training and inference model. The term “condition registered in a network side”, the term “condition registered in a second apparatus” and the term “network (NW) side additional condition” may be used interchangeable. The process of model identification pinpoints what are known as 5 “additional conditions”, which may include, for example, training dataset category, site-related information, timestamps, implicit identification information (such as, labels for specific gNB / UE implementation details), statistical information (e.g., delay spread, angular spread, line of sight (LOS) / None-LOS data and so on), and other factors. The term “condition registered in a UE side” used herein may refer to a condition at UE side which 10 include additional information to improve consistency between training and inference model. The term “condition registered in a UE side”, the term “condition registered in a first apparatus” and the term “UE side additional condition” may be used interchangeable.

[0039] 3GPP has started to provide supports for AI / ML positioning with the following objectives. - Positioning accuracy enhancements, encompassing: o Direct AI / ML positioning: ■ (1st priority) Case 1: UE-based positioning with UE-side model, direct AI / ML positioning ■ (2nd priority) Case 2b: UE-assisted / location management function (LMF)-based positioning with LMF-side model, direct AI / ML positioning ■ (1st priority) Case 3b: NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning o AI / ML assisted positioning ■ (2nd priority) Case 2a: UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning ■ (1st priority) Case 3a: NG-RAN node assisted positioning with gNB-side model, AI / ML assisted positioning o Specify necessary measurements, signalling / mechanism(s) to facilitate life circle management (LCM) operations specific to the Positioning accuracy enhancements use cases, if any o Investigate and specify the necessary signalling of necessary measurement enhancements (if any) o Enabling method(s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE for relevant positioning sub use cases 15

[0040] Further, network (NW)-side additional conditions are being prioritized if compared to UE-side additional conditions. For NW-side additional conditions, it has investigated a variety of scenarios for model generalization considering the following scenarios: Model generalization'. To investigate the model generalization capability, at least the following aspect(s) are considered for the evaluation for AI / ML based positioning: - Different drops: Training dataset from drops {Ao, Ai,..., An-i}, test dataset from unseen drop(s) (i.e., different drop(s) than any in {Ao, Ai,..., An-i}). Here N>1. - Clutter parameters, e.g., training dataset from one clutter parameter (e.g., {40%, 2m, 2m{), test dataset from a different clutter parameter (e.g., {60%, 6m, 2m}); - Network synchronization error, e.g., training dataset without network synchronization error, test dataset with network synchronization error; - UE / gNB RX and TX timing error; - The baseline non-AI / ML method may enable the Rel-17 enhancement features (e.g., UE Rx TEG, UE RxTx TEG). - InF scenarios, e.g., training dataset from one indoor factory scenario (e.g., indoor factory-dense high, InF-DH), test dataset from a different InF scenario (e.g., Indoor Factory with High Tx and High Rx, InF-HH) - The following issues related to measurements on the positioning accuracy of the AI / ML model. The simulation assumptions reflecting these issues are up to companies. - SNR mismatch (i.e., SNR when training data are collected is different from SNR when model inference is performed). - Time varying changes (e.g., mobility of clutter objects in the environment) - Channel estimation error For both direct AI / ML approach and AI / ML assisted approach, for a given AI / ML model design (e.g., input, output, single-TRP vs multi-TRP), identify the generalization aspects where model fme-tuning / mixed training dataset / model switching is necessary.

[0041] To facilitate the discussion, it studies the model identification type A with more details related to use cases. To facilitate the discussion, it also studies the following options as starting point for model identification type B with more details related to all use cases: 5 •Option 1: Model identification with data collection related configuration(s) and / or indication(s); • Option 2: Model identification with dataset transfer; • Option 3: Model identification in model transfer from NW to UE; • Option 4. Model identification via standardization of reference models, (for CSI 10 compression); • Option 5. Model identification via model monitoring.

[0042] Regarding Option 1 (i.e., model identification with data collection related configuration(s) and / or indication(s)) of model identification type B, RANI further studies the following aspects: relationship between model ID and data collection related configuration(s) and / or indication(s); information transmitted from NW to UE (if any); information transmitted from UE to NW (if any); the associated procedure; usage / applicable use case(s) of Option 1.

[0043] From RANI perspective, for UE-sided model(s) developed (e.g., trained, updated) at UE side, following procedure is an example (noted as AI-Examplel) of MI-Optionl for further study (including the feasibility / necessity): • A: For data collection, NW signals the data collection related configuration(s) and it / their associated ID(s), o Associated IDs for each sub use case in relation with NW-sided additional conditions, • B: UE(s) collects the data corresponding to the associated ID(s), • C: AI / ML models are developed (e.g., trained, updated) at UE side based on the collected data corresponding to the associated ID(s). • D: UE reports information of its AI / ML models corresponding to associated IDs to the NW. Model ID is determined / assigned for each AI / ML model, o relationship between model ID(s) and the associated ID(s), o How model ID(s) is determined / assigned, e.g., ■ Alt. 1: NW assigns Model ID, ■ Alt.2: UE assigns / reports Model ID, ■ Alt.3: Associated ID(s) is assumed as model ID(s), • “Model ID is determined / assigned for each AI / ML model” in D is not needed, ■ Alt.4: Model ID is determined by pre-defined rule(s) in the specification, o Note: D is to facilitate AI / ML model inference • Note: Step A / B / C and additional interaction of associated IDs between UE and NW can be considered as a different solution for resolving the consistency without model identification.

[0044] As used herein, a machine learning (ML) entity may be an ML model or may contain an ML model and ML model related metadata. The ML entity may be managed as a single composite entity. In some example embodiments, the ML entity may be implemented as an ML application.

[0045] To facilitate understanding of the terminologies, RANI agreements on the list of terminologies used for AI / ML are provided below.

[0046] AI / ML Model: A data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs.

[0047] AI / ML model delivery: A generic term referring to delivery of an AI / ML model from one entity to another entity in any manner. Note: An entity could mean a network node / function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.

[0048] AI / ML model Inference: A process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0049] AI / ML model testing: A subprocess of training, to evaluate the performance of a final AI / ML model using a 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.

[0050] AI / ML model training: A process to train an AI / ML Model [by learning the input / output relationship] in a data driven manner and obtain the trained AI / ML Model for inference.

[0051] AI / ML model transfer: Delivery of an AI / ML model over the air interface in a manner that is not transparent to 3GPP signalling, either parameters of a model structure known at the receiving end or a new model with parameters. Delivery may contain a full model or a partial model.

[0052] AI / ML model validation: A subprocess of training, to evaluate the quality of an AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

[0053] Data collection: 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.

[0054] Federated learning / federated training: 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.

[0055] Functionality identification: A process / method of identifying an AI / ML functionality for the common understanding between the NW and the UE. Note: 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.

[0056] Model activation: enable an AI / ML model for a specific function.

[0057] Model deactivation: disable an AI / ML model for a specific function.

[0058] Model download: Model transfer from the network to UE.

[0059] Model identification: A process / method of identifying an AI / ML model for the common understanding between the NW and the UE. Note: The process / method of model identification may or may not be applicable. Note: Information regarding the AI / ML model may be shared during model identification.

[0060] Model monitoring: A procedure that monitors the inference performance of the AI / ML model.

[0061] Model parameter update: Process of updating the model parameters of a model.

[0062] Model selection: The process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature. Note: Model selection may or may not be carried out simultaneously with model activation.

[0063] Model switching: Deactivating a currently active AI / ML model and activating a different AI / ML model for a specific function.

[0064] Model update: Process of updating the model parameters and / or model structure of a model.

[0065] Model upload: Model transfer from UE to the network.

[0066] Network-side (AI / ML) model: An AI / ML Model whose inference is performed entirely at the network.

[0067] Offline field data: The data collected from field and used for offline training of the AI / ML model.

[0068] Offline training: 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: This definition only serves as a 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.

[0069] Online field data: The data collected from field and used for online training of the AI / ML model.

[0070] Online training: 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: the notion of (near) real-time vs. non real-time is context-dependent and is relative to the inference time-scale. Note: This definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Note: Fine-tuning / re-training may be done via online or offline training.

[0071] Reinforcement Learning (RL): A process of training an AI / ML model from input (a.k.a. state) and a feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with.

[0072] Semi-supervised learning: A process of training a model with a mix of labelled data and unlabelled data.

[0073] Supervised learning: A process of training a model from input and its corresponding labels.

[0074] Two-sided (AI / ML) model: A paired AI / ML Model(s) over which j oint 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.

[0075] UE-side (AI / ML) model: An AI / ML Model whose inference is performed entirely at the UE.

[0076] Unsupervised learning: A process of training a model without labelled data.

[0077] Proprietary-format models: ML models of vendor- / device-specific proprietary format, from 3GPP perspective. They are not mutually recognizable across vendors and hide model design information from other vendors when shared. Note: An example is a device-specific binary executable format.

[0078] Open-format models: 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.

[0079] In the context of the present disclosure, for an AI / ML-enabled feature / feature group (FG), additional conditions refer to any aspects that are assumed for the training of the model but are not a part of UE capability for the AI / ML-enabled feature / FG. It does not imply that additional conditions are necessarily specified. Additional conditions can be divided into two categories: NW-side additional conditions and UE-side additional conditions. One interpretation for NW-side additional conditions is that they represent a set of settings or parameters defined by the NW entity, which has direct impact on the measurements realized in the UE entity.

[0080] In addition, a working assumption regarding “Associated identity, ID” has been agreed. Specifically, regarding the associated ID for release 19, the UE may assume that NW-side additional conditions with the same associated ID are consistent at least within a cell. Further, this UE assumption may be (or may be not) applicable for multiple cells.

[0081] For the purpose of illustrations, example embodiments are described with reference to positioning scenario. It is noted that example embodiments of the present disclosure can also be implemented in other scenarios. The present disclosure is not limited in this regard.

[0082] In the following, a data collection / training phase is used as an example of the first ML phase and an inference phase is used as an example of the second ML phase for describing some specific example embodiments of the present disclosure. However, the first ML phase and the second ML phase may be any suitable ML phase. The present disclosure is not limited in this regard.

[0083] Further, a location management function (LMF) is used as an example of a core network entity for describing some specific example embodiments of the present disclosure. It is noted that example embodiments described with regard to the LMF are equally applicable to other core network entity, including but not limited to, access and mobility management function (AMF) and so on.

[0084] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Example Environment

[0085] FIG. 1A illustrates an example communication environment 100A in which example embodiments of the present disclosure can be implemented. In the communication environment 100 A, a plurality of communication devices, including a first apparatus 110 and a second apparatus 120, may communicate with each other. In the example of FIG. 1A, the first apparatus 110 may be a UE and the second apparatus 120 may be a network device (especially a core network device, such as, LMF).

[0086] Further, the first apparatus 110 may receive signals (such as, positioning reference signals) from more than one third apparatus 130. In the example of FIG. 1A, the first apparatus 110 may receive signals from the third apparatuses 130-1 to 130-N. For ease of discussion, the third apparatuses 130-1 to 130-N may be collectively referred to as the third apparatus 130.

[0087] In some example embodiments, the third apparatuses 130 may be gNB / transmission reception point (TRP).

[0088] FIG. IB illustrates another example communication environment in which example embodiments of the present disclosure can be implemented. In the example of FIG. IB, the first apparatus 110 (i.e., the target UE) may be receive reference signals from different gNBs / TRPs to enable fingerprinting training / inference. In the example of FIG. IB, each gNB / TRP may be associated with a specific associated ID.

[0089] It is to be understood that the number of devices and their connections shown in FIG. 1A and FIG. IB are only for the purpose of illustration without suggesting any limitation. The communication environments 100A and 100B may include any suitable number of devices configured to implementing example embodiments of the present disclosure. Although not shown, it would be appreciated that one or more additional devices may be deployed in the communication environments 100A and 100B. It is noted that although illustrated as a network device, the second apparatus 120 may be another device than a network device (especially a core network device, such as, LMF). Although illustrated as a terminal device, the first apparatus 110 may be another device than a terminal device.

[0090] In the following, for the purpose of illustration, some example embodiments are described with the first apparatus 110 operating as a UE and the second apparatus 120 operating as a network device. However, in some example embodiments, operations described in connection with a terminal device may be implemented at a network device or other device, and operations described in connection with a network device may be implemented at a terminal device or other device.

[0091] In some example embodiments, a link from the third apparatus 130 to the first apparatus 110 is referred to as a downlink (DL), while a link from the first apparatus 110 to the third apparatus 130 is referred to as an uplink (UL). In DL, the third apparatus 130 is a transmitting (TX) device (or a transmitter) and the first apparatus 110 is a receiving (RX) device (or a receiver). In UL, the first apparatus 110 is a TX device (or a transmitter) and the third apparatus 130 is a RX device (or a receiver).

[0092] Communications in the communication environments 100A and 100B may be implemented according to any proper communication protocol(s), comprising, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), the fifth generation (5G), 5.5G, the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and / or any other technologies currently known or to be developed in the future. Work Principle and Example Signalins for Communication

[0093] Generally speaking, the direct application of associated ID(s) is straightforward when the AI / ML use case is always between one specific UE and one serving gNB / TRP. However, for AI / ML positioning, the system may include several gNBs / TRPs because the fingerprint inference. For instance, for such as Case 1 (i.e., UE-based positioning with UE-side model, direct AI / ML positioning), the target UE receives reference signals from different gNBs / TRPs to enable fingerprinting training / inference.

[0094] There is a necessity of a new signalization to enable the utilization of associated ID(s) when network-side additional conditions and configuration are involved to ensure consistency between such as training / data collection and inference / monitoring.

[0095] According to some example embodiments of the present disclosure, there is provided a solution related to NW-side additional conditions for such as AI / ML positioning. With the example embodiments discussed herein, consistency among different ML phases may be ensured.

[0096] To enable the usage of associated ID(s) in AI / ML positioning, specifically for UE-side cases (such as, Case 1 UE-based positioning with UE-side model and direct AI / ML positioning, and Case 2a UE-assisted / LMF-based positioning with UE-side model and AI / ML assisted positioning), the present disclosure proposes a set of parameters that require signalization to enable the usability of associated ID(s) for ensuring consistency between different phases.

[0097] In operation, for the first ML phase (such as, a data collection / training), a second apparatus / NW (such as, an LMF) assists UE configuration providing a parameter (such as, a quality indicator, a key performance indicator (KPI) or a radio measurement sensitivity), which may be referred to as radioIndicator. The radioIndicator may be used as a reference to indicate whether one specific target UE is in the range of the coverage of one specific TRP / gNB. Thus, it is expected a set of TRPs / gNBs to be mapped for one specific UE doing data collection for UE-side cases. Using the radioIndicator will enable to identify a list of set of associated ID(s). From this list, the UE may down select in top of another parameter represented as numAssocIDs (the number of associated ID(s)), which represents the maximum / minimum number of associated ID(s) involved in data collection. When the data collection is completed, the LMF may define a data-coHeciion-Associated ID which is shared with the UE to map the already data collected.

[0098] For the second ML phase (such as, inference), UE uses the data-collection-Associated ID (received from the second apparatus / NW, such as, LMF) to identify the radioIndicator and / or match the most suitable model for that specific location.

[0099] Reference is made to FIG. 2, which illustrates a signaling flow 200 of communication in accordance with some embodiments of the present disclosure. For the purposes of discussion, signaling flow 200 will be discussed with reference to FIG. 1A and FIG. IB, for example, by using the first apparatus 110 and the second apparatus 120.

[0100] It is to be understood that the operations at the first apparatus 110 and the second apparatus 120 should be coordinated. In other words, the first apparatus 110, the second apparatus 120 should have common understanding about configurations, parameters and so on. Such common understanding may be implemented by any suitable interactions or applying the same rule / policy.

[0101] In the following, although some operations are described from a perspective of the first apparatus 110, it is to be understood that the corresponding operations should be performed by the second apparatus 120. Similarly, although some operations are described from a perspective of the second apparatus 120, it is to be understood that the corresponding operations should be performed by the first apparatus 110. Merely for brevity, some of the same or similar contents are omitted here.

[0102] Merely for a better understanding, in the following example embodiments, the first apparatus 110 may function as a terminal apparatus, the second apparatus 120 may function as a core network device (such as, an LMF). In this event, the second apparatus 120 may communicate with the terminal device via LPP messages.

[0103] In operation, as illustrated in FIG. 2, the first apparatus 110 transmits (206-1) a first message to the second apparatus 120, and the second apparatus receives (206-2) the first message accordingly. In particular, the first message indicates at least one associated identity (ID) (also may be call as a list of associated identities) used by the first apparatus 110 during a first ML phase, where each associated identity corresponds to an additional condition of network. Refer to the example of FIG. IB, the at least one associated identity may be the associated identities #1 to #3.

[0104] Based on the first message, the second apparatus 120 associates (208) an association indicator (which may be represented as data-collection-Associated ID) with a second configuration, where the second configuration at least comprises information about the at least one associated identity, such as, the second configuration is a log maintained by the second apparatus 120 locally, which may be represented as Log nw.

[0105] Then, the second apparatus 120 transmits (210-1) a second message indicating the association indicator and the first apparatus 110 receives (210-2) the second message accordingly.

[0106] Based on the second message, the first apparatus 110 associates (212) the same association indicator with a first configuration, where the first configuration also at least comprises information about the at least one associated identity, such as, the first configuration is a log maintained by the first apparatus 110 locally, which may be represented as Log ue.

[0107] In summary, by using the same association indicator, a specific first phase which is associated with a specific network additional condition may be uniquely identified at both the first apparatus 110 and the second apparatus 120.

[0108] In the following, more details about the first configuration maintained at the first apparatus 110 will be discussed.

[0109] In some example embodiments, except for the at least one associated identity, the first configuration may further comprise at least one of the following: • a first indication (which may be represented as radioIndicator) to be used by the first apparatus 110 to determine a set of associated identities, or • a second indication (which may be represented as numAssocIDs) of the maximum or minimum number of associated identities to be used during the first ML phase.

[0110] According to some example embodiments of the present discourse, the first and / or the second indication may be configured by the second apparatus 120. As illustrated in FIG. 2, the second apparatus 120 may transmit (204-1) configuration information to the first apparatus 110, and the first apparatus 110 may receive (204-2) the configuration information accordingly. In particular, the configuration information may indicate the first and / or the second indication.

[0111] In some cases, the configuration information may be a setting for the first ML phase. In this event, the first apparatus 110 may perform the first ML phase based at least in part on the configuration information.

[0112] Specifically, in some example embodiments, the first apparatus 110 may determine, based on the configuration information, the at least one associated identity to be used during the first ML phase.

[0113] Additionally, in some example embodiments, the first indication may be one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity. In this event, the first apparatus 110 may determine, from a plurality of associated identities and based on the first indication, a set of associated identities and then may determine, based on the second indication of the maximum or minimum number, the at least one associated identity from the set of associated identities. As one specific example of FIG. IB, the first apparatus 110 may determine associated identities #1 to #4 based on the first indication, and may select associated identities #1 to #3 based on the second indication. That is, the first apparatus 110 may use associated identities #1 to #3 (which may correspond to TRP / gNB #1 to #3) for data collection.

[0114] Next, the first apparatus 110 may perform the first ML phase based on the at least one associated identity to obtain a dataset. When the first ML phase has been completed, the first apparatus 110 may associate the dataset with first configuration.

[0115] Finally, the first apparatus 110 may deploy an ML model accordingly. Moreover, the ML model may be identified with a specific association indicator, and the specific association indicator has been linked to a specific first ML phase.

[0116] In summary, at the first apparatus 110, the model / a specific first ML phase may be uniquely identified by the association indicator, by maintaining a first configuration. As a corresponding operation, the second apparatus 120 also needs to maintain a second configuration. In the following, more details about the second configuration will be discussed.

[0117] Similar with the first configuration, except for the at least one associated identity and the association indicator, the second configuration may further comprise at least one of the following: the first indication, the second indication, or an identity of a serving cell of the first apparatus 110.

[0118] As discussed above, the configuration information may be a setting for the first ML phase determined by the second apparatus 120. In order to enable the configuration information more proper, the first apparatus 110 may provide its capability to the second apparatus 120. As illustrated in FIG. 2, the first apparatus 110 may transmit (202-1) capability-related information to the second apparatus 120, and the second apparatus 120 may receive (202-2) the capability-related information accordingly. In some example embodiments, the capability-related information may comprise at least one of the following: • an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, • a set of maximum numbers of associated identities supported by the first apparatus, or • a set of minimum numbers of associated identities supported by the first apparatus.

[0119] Based on the capability-related information, the second apparatus 120 may determine the configuration information more properly, and also may assign an association indicator to the first apparatus 110 as discussed above.

[0120] To better understand the above example processes of the first ML phase, some example processes are discussed with reference to FIG. 3 A, which illustrates a signaling flow 300A of the first ML phase according to some example embodiments of the present disclosure.

[0121] In the example of FIG. 3A, associated IDs are used for data collection in AI / ML positioning for consistency purposes, UE is used as an example of the first apparatus 110, the NW (LMF) is used as an example of the second apparatus 120.

[0122] In operation, at Step 1, UE may optionally report conditions (such as, capability-related information as discussed above) to NW (LMF). At Step 2, NW (LMF) may set the respective functionality to enable the data collection based on the conditions received in Step 1. Further, in some embodiments, below parameters may be determined: • the radioIndicator, this radioIndicator may be referred to quality indicator or KPI or radio measurement; • the numAssocIDs (number of associated ID(s)) that may be involved in the data collection.

[0123] At Step 3, NW (LMF) may deliver the functionality setting (i e , configuration information as discussed above), the radioIndicator, and numAssocIDs parameters to the UE.

[0124] At Step 4, by using the radioIndicator parameter, the UE is capable to identify a set of associated IDs. At Step 5, on top of the list of associated ID(s), the UE may select a list of associated IDs to be included in the data collection process. For example, the numAssocIDs refers to the maximum number of associated IDs to be included in the data collection process, such as, 3. In this specific example, UE may down select 3 associated IDs on top of the set of associated IDs determined based on the radioIndicator parameter.

[0125] At Step 6, Data collection at UE is performed. At Step 7, when data collection is done, in addition to the data, the following additional information is included in a local Logue: • The list of associated IDs, where every associated ID is related to: one specific reference signal configuration; and / or the NW-side additional conditions related to one specific cell. • radioIndicator parameter, and • the numAssocIDs parameter.

[0126] It is noted that if the radioIndicator is unique for all UEs doing data collection, it does not need to be included in the dataset but included in the Log ue. Alternatively, if the radioIndicator is specific for each UE, thus, it should be part of the data collection done per UE.

[0127] At Step 8, UE reports to the NW (LMF) the list of associated identities considered in the data collection, i.e., the first message.

[0128] At Step 9. NW (LMF) includes the list of associated IDs, radio Indicator, numAssocIDs parameters, and the serving cell information to generate a local Log m in the NW.

[0129] At Step 10, The NW incorporate a data-coHection-Associated ID (i.e., an association indicator) to the log nw. At Step 11, the NW assists UE providing the data-col I ection-Associated ID, i.e., transmit the second message to the UE. At Step 12, the UE incorporate the data-collection-Associated ID to the local Log ue.

[0130] At Step 13, UE-side model may be developed (Model training may be performed accordingly).

[0131] The aforementioned process may be repeatedly executed, and thus one or more models may be deployed at the first apparatus 110 and one or more respective association indicators corresponding to the one or more models may be determined.

[0132] In particular, a set of first configurations may be maintained at the first apparatus 110, where the set of first configurations are associated with a set of respective association indicators and each first configuration may comprise at least one of • a respective association indicator of the first configuration. • a dataset obtained by the first apparatus 110 based on the first configuration during a first ML phase different from the second ML phase, • a first indication used by the first apparatus 110 to determine a set of associated identities during the first ML phase, or • a second indication of the maximum or minimum number of associated identities used by the first apparatus 110 during the first ML phase • at least one associated identity used by the first apparatus 110 during a first ML phase, each associated identity corresponding to an additional condition of network.

[0133] Accordingly, a set of second configurations may be maintained at the second apparatus 120, where the set of second configurations are associated with a set of respective association indicators and each second configuration may comprise at least one of: • a respective association indicator of the second configuration, • an identity of a serving cell of the first apparatus 110, • a first indication used by the first apparatus 110 to determine a set of associated identities during the first ML phase, or • a second indication of the maximum or minimum number of associated identities used by the first apparatus 110 during the first ML phase • at least one associated identity used by the first apparatus 110 during a first ML phase, each associated identity corresponding to an additional condition of network.

[0134] Then, by using the association indicator(s), the ML model may be determined proper in the second ML phase. Such example processes will be further discussed with reference to FIG. 2.

[0135] In operation, the second apparatus 120 determine (252) at least one second configuration from the set of second configurations, and transmits (254) configuration information to the first apparatus 110. In particular, the configuration information comprises at least one association indicator.

[0136] Details about how to determine the at least one second configuration will be discussed first.

[0137] In some example embodiments, the second apparatus 120 may determine the at least one second configuration from the set of second configurations based at least in part on an identity of a serving cell of the first apparatus 110.

[0138] Further, the at least one second configuration may be determined based on the capability of the first apparatus 110. As illustrated in FIG. 2, the first apparatus 110 may transmit (250) capability-related information to the second apparatus 120, and the second apparatus 120 may receive (250-2) the capability-related information from the first apparatus 110 accordingly. In particular, the capability-related information may comprise at least one of the following: • an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, • a set of maximum numbers of associated identities supported by the first apparatus 110, or • a set of minimum numbers of associated identities supported by the first apparatus 110.

[0139] Based on the capability-related information, the second apparatus 120 may determine the configuration information more properly.

[0140] Accordingly, the first apparatus 110 receives (254) the configuration information from the second apparatus 120. Then, the first apparatus 110 determines (256), based on the at least one association indicator, a first configuration from a set of first configurations.

[0141] Next, the first apparatus 110 may perform the second ML phase (such as, an inference phase or a monitoring phase) based on the first configuration.

[0142] As illustrated in FIG. 2, the first apparatus 110 may determine (258) an ML model corresponding to the first configuration, and then may perform (260) such as a positioning procedure by using the ML model.

[0143] To better understand the above example processes of inference, some example processes are discussed with reference to FIG. 3B, which illustrates a signaling flow 300B of a second ML phase according to some example embodiments of the present disclosure.

[0144] In the example of FIG. 3B, the inference is used as an example of the second ML phase, UE is used as an example of the first apparatus 110, the NW (LMF) is used as an example of the second apparatus 120.

[0145] In operation, at Step 1, UE reports conditions to NW (LMF). At Step 2, NW (LMF) sets the respective Functionality for inference and the data-collection-Associated ID(s) matched to that certain serving cell are identified.

[0146] At Step 3, NW (LMF) delivers the respective functionality setting, including the available data-collection-AssociatedID(s) matching the specific serving cell.

[0147] At Step 4, the UE identifies the best match of data-collection-Associated ID(s) received from the NW with the available collection-Associated ID(s) used for training the available models in UE-side. At Step 5, the model selection is done, and the Functionality is ready for inference. Example Method

[0148] FIG. 4 shows a flowchart of an example method 400 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 400 will be described from the perspective of the first apparatus 110 in FIG. 1 A.

[0149] At block 410, the first apparatus transmits, to a second apparatus, a first message indicating at least one associated identity used by the first apparatus during a first machine learning (ML) phase, each associated identity corresponding to an additional condition of network.

[0150] At block 420, the first apparatus receives, from the second apparatus, a second message indicating an association indicator.

[0151] At block 430, the first apparatus associates the association indicator with a first configuration at least comprising information about the at least one associated identity.

[0152] In some example embodiments, the first configuration further comprises at least one of the following: a first indication to be used by the first apparatus to determine a set of associated identities, or a second indication of the maximum or minimum number of associated identities to be used during the first ML phase.

[0153] In some example embodiments, the first apparatus may receive, from the second apparatus, configuration information associated with the first ML phase and indicating at least one of the following: thing first indication to be used by the first apparatus to determine the set of associated identities, or thing second indication of the maximum or minimum number of associated identities to be used during the first ML phase.

[0154] In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0155] In some example embodiments, the first apparatus may determine, from a plurality of associated identities and based on the first indication, the set of associated identities; and determining, based on the second indication of the maximum or minimum number, the at least one associated identity from the set of associated identities.

[0156] In some example embodiments, the first apparatus may determine, based on the configuration information, the at least one associated identity to be used during the first ML phase; performing the first ML phase based on the at least one associated identity to obtain a dataset; and associating the dataset with first configuration.

[0157] In some example embodiments, the first apparatus may transmit, to the second apparatus, capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus.

[0158] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0159] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

[0160] FIG. 5 shows a flowchart of an example method 500 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 500 will be described from the perspective of the second apparatus 120 in FIG. 1 A.

[0161] At block 510, the second apparatus receives, from a first apparatus, a first message indicating at least one associated identity used by the first apparatus during a first machine learning (ML) phase, each associated identity corresponding to an additional condition of network.

[0162] At block 520, the second apparatus associates an association indicator with a second configuration at least comprising information about the at least one associated identity.

[0163] At block 530, the second apparatus transmit, to the first apparatus, a second message indicating the association indicator.

[0164] In some example embodiments, the second configuration further comprises at least one of the following: a first indication to be used by the first apparatus to determine a set of associated identities, a second indication of the maximum or minimum number of associated identities to be used during the first ML phase, or an identity of a serving cell of the first apparatus.

[0165] In some example embodiments, the second apparatus may transmit, to the first apparatus, configuration information associated with the first ML phase and indicating at least one of the following: thing first indication to be used by the first apparatus to determine the set of associated identities, or thing second indication of the maximum or minimum number of associated identities to be used during the first ML phase.

[0166] In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0167] In some example embodiments, the second apparatus may receive capability-related information from the first apparatus, the capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus; and determine the configuration information based on at least in part on the capability-related information.

[0168] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0169] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

[0170] FIG. 6 shows a flowchart of an example method 600 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 600 will be described from the perspective of the first apparatus 110 in FIG. 1 A.

[0171] At block 610, the first apparatus receives, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator.

[0172] At block 620, the first apparatus determines, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

[0173] In some example embodiments, each first configuration further comprises at least one of the following: a respective association indicator of the first configuration, a dataset obtained by the first apparatus based on the first configuration during a first ML phase different from the second ML phase, a first indication used by the first apparatus to determine a set of associated identities during the first ML phase, or a second indication of the maximum or minimum number of associated identities used by the first apparatus during the first ML phase.

[0174] In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0175] In some example embodiments, the first apparatus may perform, based on at least part of the first configuration, a first ML phase by using the at least one associated identity; transmit, to the second apparatus, a first message indicating the at least one associated identity; receive, from the second apparatus, a second message indicating the respective association indicator; and associate the respective association indicator with the first configuration at least comprising information about the at least one associated identity.

[0176] In some example embodiments, the first apparatus may determine an ML model corresponding to the first configuration; and performing a positioning procedure by using the ML model.

[0177] In some example embodiments, the first apparatus may transmit, to the second apparatus, capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and the second ML phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus.

[0178] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0179] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

[0180] FIG. 7 shows a flowchart of an example method 700 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 700 will be described from the perspective of the second apparatus 120 in FIG. 1A.

[0181] At block 710, the second apparatus determines, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

[0182] At block 720, the second apparatus transmits, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

[0183] In some example embodiments, each second configuration further comprises at least one of the following: a respective association indicator of the second configuration, a first indication to be used by the first apparatus to determine a set of associated identities, a second indication of the maximum or minimum number of associated identities to be used during the first ML phase, or an identity of a serving cell of the first apparatus.

[0184] In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0185] In some example embodiments, the second apparatus may receive, from a first apparatus, a first message indicating at least one associated identity used by the first apparatus during the first ML phase; associating the respective association indicator with the second configuration at least comprising information about the at least one associated identity; and transmit, to the first apparatus, a second message indicating the respective association indicator.

[0186] In some example embodiments, the second apparatus may determine the at least one second configuration from the set of second configurations based at least in part on an identity of a serving cell of the first apparatus.

[0187] In some example embodiments, the second apparatus may receive capability-related information from the first apparatus, the capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus; and determine the configuration information based on at least in part on the capability-related information.

[0188] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0189] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device. Example Apparatus, Device and Medium

[0190] In some example embodiments, a first apparatus capable of performing any of the method 400 (for example, the first apparatus 110 in FIG. 1A) may comprise means for performing the respective operations of the method 400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1 A. [019l]In some example embodiments, the first apparatus comprises means for transmitting, to a second apparatus, a first message indicating at least one associated identity used by the first apparatus during a first machine learning (ML) phase, each associated identity corresponding to an additional condition of network; and means for receiving, from the second apparatus, a second message indicating an association indicator; and means for associating the association indicator with a first configuration at least comprising information about the at least one associated identity.

[0192] In some example embodiments, the first configuration further comprises at least one of the following: a first indication to be used by the first apparatus to determine a set of associated identities, or a second indication of the maximum or minimum number of associated identities to be used during the first ML phase.

[0193] In some example embodiments, the first apparatus further comprises: means for receiving, from the second apparatus, configuration information associated with the first ML phase and indicating at least one of the following: a first indication to be used by the first apparatus to determine the set of associated identities, or a second indication of the maximum or minimum number of associated identities to be used during the first ML phase.

[0194] In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0195] In some example embodiments, the first apparatus further comprises: means for determining, from a plurality of associated identities and based on the first indication, the set of associated identities; and means for determining, based on the second indication of the maximum or minimum number, the at least one associated identity from the set of associated identities.

[0196] In some example embodiments, the first apparatus further comprises: means for determining, based on the configuration information, the at least one associated identity to be used during the first ML phase; means for performing the first ML phase based on the at least one associated identity to obtain a dataset; and means for associating the dataset with first configuration.

[0197] In some example embodiments, the first apparatus further comprises: means for transmitting, to the second apparatus, capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus.

[0198] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0199] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

[0200] In some example embodiments, a second apparatus capable of performing any of the method 500 (for example, the second apparatus 120 in FIG. 1A) may comprise means for performing the respective operations of the method 500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1A.

[0201] In some example embodiments, the second apparatus comprises means for receiving, from a first apparatus, a first message indicating at least one associated identity used by the first apparatus during a first machine learning (ML) phase, each associated identity corresponding to an additional condition of network; means for associating an association indicator with a second configuration at least comprising information about the at least one associated identity; and means for transmitting, to the first apparatus, a second message indicating the association indicator.

[0202] In some example embodiments, the second configuration further comprises at least one of the following: a first indication to be used by the first apparatus to determine a set of associated identities, a second indication of the maximum or minimum number of associated identities to be used during the first ML phase, or an identity of a serving cell of the first apparatus.

[0203] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, configuration information associated with the first ML phase and indicating at least one of the following: a first indication to be used by the first apparatus to determine the set of associated identities, or a second indication of the maximum or minimum number of associated identities to be used during the first ML phase. [ 02041 In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0205] In some example embodiments, the second apparatus further comprises: means for receiving capability-related information from the first apparatus, the capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus; and means for determining the configuration information based on at least in part on the capability-related information.

[0206] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0207] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

[0208] In some example embodiments, a first apparatus capable of performing any of the method 600 (for example, the first apparatus 110 in FIG. 1 A) may comprise means for performing the respective operations of the method 600. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1 A.

[0209] In some example embodiments, the first apparatus comprises means for receiving, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator; and means for determining, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

[0210] In some example embodiments, each first configuration further comprises at least one of the following: a respective association indicator of the first configuration, a dataset obtained by the first apparatus based on the first configuration during a first ML phase different from the second ML phase, a first indication used by the first apparatus to determine a set of associated identities during the first ML phase, or a second indication of the maximum or minimum number of associated identities used by the first apparatus during the first ML phase. [021 l]In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0212] In some example embodiments, the first apparatus further comprises: means for performing, based on at least part of the first configuration, a first ML phase by using the at least one associated identity; means for transmitting, to the second apparatus, a first message indicating the at least one associated identity; means for receiving, from the second apparatus, a second message indicating the respective association indicator; and means for associating the respective association indicator with the first configuration at least comprising information about the at least one associated identity.

[0213] In some example embodiments, the first apparatus further comprises: means for determining an ML model corresponding to the first configuration; and means for performing a positioning procedure by using the ML model. [0214|In some example embodiments, the first apparatus further comprises: means for transmitting, to the second apparatus, capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and the second ML phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus.

[0215] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0216] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

[0217] In some example embodiments, a second apparatus capable of performing any of the method 700 (for example, the second apparatus 120 in FIG. 1A may comprise means for performing the respective operations of the method 700. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1A.

[0218] In some example embodiments, the second apparatus comprises means for determining, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network; and means for transmitting, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

[0219] In some example embodiments, each second configuration further comprises at least one of the following: a respective association indicator of the second configuration, a first indication to be used by the first apparatus to determine a set of associated identities, a second indication of the maximum or minimum number of associated identities to be used during the first ML phase, or an identity of a serving cell of the first apparatus.

[0220] In some example embodiments, the first indication is one of the following: a quality indicator, a key performance indicator (KPI), or a radio measurement sensitivity.

[0221] In some example embodiments, the second apparatus further comprises: means for receiving, from a first apparatus, a first message indicating at least one associated identity used by the first apparatus during the first ML phase; means for associating the respective association indicator with the second configuration at least comprising information about the at least one associated identity; and means for transmitting, to the first apparatus, a second message indicating the respective association indicator.

[0222] In some example embodiments, the second apparatus further comprises: means for determining the at least one second configuration from the set of second configurations based at least in part on an identity of a serving cell of the first apparatus. [02231In some example embodiments, the second apparatus further comprises: means for receiving capability-related information from the first apparatus, the capability-related information comprising at least one of the following: an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase, a set of maximum numbers of associated identities supported by the first apparatus, or a set of minimum numbers of associated identities supported by the first apparatus; and means for determining the configuration information based on at least in part on the capability-related information.

[0224] In some example embodiments, the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

[0225] In some example embodiments, the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

[0226] FIG. 8 is a simplified block diagram of a device 800 that is suitable for implementing example embodiments of the present disclosure. The device 800 may be provided to implement a communication device, for example, the first apparatus 110 or the second apparatus 120 as shown in FIG. 1A. As shown, the device 800 includes one or more processors 810, one or more memories 820 coupled to the processor 810, and one or more communication modules 840 coupled to the processor 810.

[0227] The communication module 840 is for bidirectional communications. The communication module 840 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 840 may include at least one antenna.

[0228] The processor 810 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 800 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[0229] The memory 820 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 824, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random-access memory (RAM) 822 and other volatile memories that will not last in the power-down duration.

[0230] A computer program 830 includes computer executable instructions that are executed by the associated processor 810. The instructions of the program 830 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 830 may be stored in the memory, e.g., the ROM 824. The processor 810 may perform any suitable actions and processing by loading the program 830 into the RAM 822.

[0231] The example embodiments of the present disclosure may be implemented by means of the program 830 so that the device 800 may perform any process of the disclosure as discussed with reference to FIG. 2 to FIG. 7. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0232] In some example embodiments, the program 830 may be tangibly contained in a computer readable medium which may be included in the device 800 (such as in the memory 820) or other storage devices that are accessible by the device 800. The device 800 may load the program 830 from the computer readable medium to the RAM 822 for execution. In some example embodiments, the computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0233] FIG. 9 shows an example of the computer readable medium 900 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 900 has the program 830 stored thereon.

[0234] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0235] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer readable medium, such as a non-transitory computer readable medium. The computer program product includes computerexecutable instructions, such as those included in program modules, being executed in a device on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0236] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0237] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0238] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include 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), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0239] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable sub-combination.

[0240] Although the present disclosure has been described in languages specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A first apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to:receive, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator; anddetermine, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

2. The first apparatus of claim 1, wherein each first configuration further comprises at least one of the following:a respective association indicator of the first configuration,a dataset obtained by the first apparatus based on the first configuration during a first ML phase different from the second ML phase,a first indication used by the first apparatus to determine a set of associated identities during the first ML phase, ora second indication of the maximum or minimum number of associated identities used by the first apparatus during the first ML phase.

3. The first apparatus of claim 2, wherein the first indication is one of the following: a quality indicator,a key performance indicator (KPI), ora radio measurement sensitivity.

4. The first apparatus of claim 1, wherein the first apparatus is caused to:perform, based on at least part of the first configuration, a first ML phase by using the at least one associated identity;transmit, to the second apparatus, a first message indicating the at least one associated identity;receive, from the second apparatus, a second message indicating the respective association indicator; andassociate the respective association indicator with the first configuration at least comprising information about the at least one associated identity.

5. The first apparatus of claim 1, wherein the first apparatus is caused to: determine an ML model corresponding to the first configuration; and perform a positioning procedure by using the ML model.

6. The first apparatus of claim 1, wherein the first apparatus is caused to: transmit, to the second apparatus, capability-related information comprising at least one of the following:an indication of a support of a consistency between the first ML phase and the second ML phase,a set of maximum numbers of associated identities supported by the first apparatus, ora set of minimum numbers of associated identities supported by the first apparatus.

7. The first apparatus of claim 1, wherein the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

8. The first apparatus of any of claims 1-7, wherein the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

9. A second apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus to:determine, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity usedby the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network; andtransmit, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

10. The second apparatus of claim 9, wherein each second configuration further comprises at least one of the following:a respective association indicator of the second configuration,a first indication to be used by the first apparatus to determine a set of associated identities,a second indication of the maximum or minimum number of associated identities to be used during the first ML phase, oran identity of a serving cell of the first apparatus.

11. The second apparatus of claim 10, wherein the first indication is one of the following:a quality indicator,a key performance indicator (KPI), ora radio measurement sensitivity.

12. The second apparatus of claim 9, wherein the second apparatus is caused to:receive, from a first apparatus, a first message indicating at least one associated identity used by the first apparatus during the first ML phase;associate the respective association indicator with the second configuration at least comprising information about the at least one associated identity; andtransmit, to the first apparatus, a second message indicating the respective association indicator.

13. The second apparatus of claim 9, wherein the second apparatus is caused to:determine the at least one second configuration from the set of second configurations based at least in part on an identity of a serving cell of the first apparatus.

14. The second apparatus of claim 9, wherein the second apparatus is caused to:receive capability-related information from the first apparatus, the capability-related information comprising at least one of the following:an indication of a support of a consistency between the first ML phase and a second ML phase different from the first phase,a set of maximum numbers of associated identities supported by the first apparatus, ora set of minimum numbers of associated identities supported by the first apparatus; anddetermine the configuration information based on at least in part on the capability-related information.

15. The second apparatus of claim 14, wherein the first ML phase comprises at least one of the following: a data collection phase or training phase and the second ML phase comprises at least one of the following: an inference phase or a monitoring phase.

16. The second apparatus of any of claims 9-15, wherein the first apparatus is a terminal device, and the second apparatus is a core network entity and / or network device.

17. A method comprising:receiving, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator; anddetermining, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

18. A method comprising:determining, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding toan additional condition of network; andtransmitting, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

19. A first apparatus comprising:means for receiving, from the second apparatus, configuration information associated with a second machine learning (ML) phase, wherein the configuration information comprising at least one association indicator; andmeans for determining, based on the at least one association indicator, a first configuration from a set of first configurations, each of the set of first configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network.

20. A second apparatus comprising:means for determining, from a set of second configurations, at least one second configuration to be used by the first apparatus, each of the set of second configurations being associated with a respective association indicator and comprising at least one associated identity used by the first apparatus during a first ML phase, each associated identity corresponding to an additional condition of network; andmeans for transmitting, to the first apparatus, configuration information associated with a second machine learning (ML) phase, the configuration information comprising at least one association indicator.

21. A computer readable medium comprising instructions stored thereon for causing an apparatus at least to perform the method of claim 17 or 18.

Images