Providing ground truth labels

Abstract

Example embodiments of the present disclosure relate to methods, devices, apparatuses and computer readable storage medium for providing ground truth (GT) labels. The method comprises: at a first apparatus, receiving, from a second apparatus, a first message used for indicating the first apparatus to obtain and store at least one set of positioning-related estimations; in response to the first message, determining the at least one set of positioning-related estimations; and transmitting, to the second apparatus, a second message comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

Description

PROVIDING GROUND TRUTH LABELS CROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority to, and the benefit of, Finland Application No.20245168, filed February 15, 2024, the contents of which are hereby incorporated by reference in their entirety. FIELDS

[0002] Various example embodiments of the present disclosure generally relate to the fieldof telecommunication and in particular, to methods, devices, apparatuses and computerreadable storage medium for providing ground truth (GT) labels.BACKGROUND

[0003] Location-awareness enables various location-based services in differentapplications and thus is a fundamental aspect of wireless communication and positioning networks. The integration and utilization of location information in day-to-day applications are growing significantly as the technology evolves.

[0004] Now the positioning technology may depend on artificial intelligence (AI)algorithms / techniques, which is intrinsically superior in terms of accuracy and efficiency for apositioning inference. In this aspect, how to provide GT labels to validate and improve theperformance monitoring which is curial part of life cycle management (LCM) of an AIMLtechnique is desirable to be further discussed.SUMMARY

[0005] In a first aspect of the present disclosure, there is provided a first apparatus. Thefirst 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 at least to: receive, from a second apparatus, a first message used for indicating the first apparatus to obtain and store at least one set of positioning-related estimations; in response to the first message, determine the at least one set of positioning-related estimations; and transmit, to the second apparatus, a second message comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-relatedestimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0006] 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 at least to: transmit, to a first apparatus, a first message used for indicating the first apparatus to obtain at least one set of positioning-related estimations; and receive, from the first apparatus, a second message comprising at least one of the following: at least one set of positioning- related estimations obtained by the first apparatus in response to the first message, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0007] In a third aspect of the present disclosure, there is provided a method. The methodcomprises: receiving, from a second apparatus, a first message used for indicating the first apparatus to obtain and store at least one set of positioning-related estimations; in response to the first message, determining the at least one set of positioning-related estimations; and transmitting, to the second apparatus, a second message comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0008] In a fourth aspect of the present disclosure, there is provided a method. The methodcomprises: transmitting, to a first apparatus, a first message used for indicating the first apparatus to obtain at least one set of positioning-related estimations; and receiving, from the first apparatus, a second message comprising at least one of the following: at least one set of positioning-related estimations obtained by the first apparatus in response to the first message, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0009] In a fifth aspect of the present disclosure, there is provided a first apparatus. Thefirst apparatus comprises means for receiving, from a second apparatus, a first message used for indicating the first apparatus to obtain and store at least one set of positioning-related estimations; means for in response to the first message, determining the at least one set of positioning-related estimations; and means for transmitting, to the second apparatus, a second message comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-related estimations, wherein thefirst set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0010] In a sixth aspect of the present disclosure, there is provided a second apparatus. Thesecond apparatus comprises means for transmitting, to a first apparatus, a first message used for indicating the first apparatus to obtain at least one set of positioning-related estimations; and means for receiving, from the first apparatus, a second message comprising at least one of the following: at least one set of positioning-related estimations obtained by the first apparatus in response to the first message, or a first set of the at least one set of positioning- related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0011] In a seventh aspect of the present disclosure, there is provided a computer readablemedium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the third aspect.

[0012] In an eighth aspect of the present disclosure, there is provided a computer readablemedium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the fourth aspect.

[0013] It is to be understood that the Summary section is not intended to identify key oressential 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

[0014] Some example embodiments will now be described with reference to theaccompanying drawings, where:

[0015] FIG. 1 illustrates an example communication environment in which exampleembodiments of the present disclosure can be implemented;

[0016] FIG. 2 illustrates a signaling chart for communication according to some exampleembodiments of the present disclosure;

[0017] FIG. 3A and FIG. 3B illustrate further signaling charts for communicationaccording to some example embodiments of the present disclosure;

[0018] FIG. 4A and 4B illustrate signaling charts for communication according to someexample embodiments of the present disclosure;

[0019] FIG. 5 illustrates a flowchart of a method implemented at a first device according tosome example embodiments of the present disclosure;

[0020] FIG. 6 illustrates a flowchart of a method implemented at a second device accordingto some example embodiments of the present disclosure;

[0021] FIG. 7 illustrates a simplified block diagram of a device that is suitable forimplementing example embodiments of the present disclosure; and

[0022] Throughout the drawings, the same or similar reference numerals represent thesame or similar element. DETAILED DESCRIPTION

[0023] Principle of the present disclosure will now be described with reference to someexample 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.

[0024] In the following description and claims, unless defined otherwise, all technical andscientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0025] References in the present disclosure to “one embodiment,” “an embodiment,” “anexample 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.

[0026] It shall be understood that although the terms “first,” “second,”…, etc. in front ofnoun(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.

[0027] 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.

[0028] As used herein, unless stated explicitly, performing a step “in response to A” doesnot indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0029] The terminology used herein is for the purpose of describing particularembodiments 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.

[0030] As used in this application, the term “circuitry” may refer to one or more or all ofthe 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.

[0031] This definition of circuitry applies to all uses of this term in this application,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 multipleprocessors) 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 integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0032] As used herein, the term “communication network” refers to a network followingany suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), 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.

[0033] As used herein, the term “network device” refers to a node in a communicationnetwork 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 head (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.

[0034] The term “terminal device” refers to any end device that may be capable of wirelesscommunication. 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), an unmanned aerial vehicle (UAV) 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 (IoT) 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.

[0035] 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.

[0036] In Release-17, 3rd generation partnership project (3GPP) started New Radio (NR)positioning enhancement work, focusing on increasing accuracy, reducing latency, and increasing efficiency (low complexity; low power consumption; low overhead) based on Rel- 16 solutions.

[0037] In Release 18, a new study item has been approved to explore the benefits ofaugmenting the air-interface with Artificial Intelligence / Machine Learning (AI / ML). One of the use cases is the positioning accuracy enhancements considered AI / ML methodology.

[0038] For instance, AI / ML based methodology could be used to derive line of sight(LOS) / non-line of sight (NLOS) classifications in order to achieve higher positioning accuracy. The scope of the study item is not limited to only the LOS / NLOS classification for positioning accuracy and can include any validation / inference / training / management / monitoring / other ML stageof ML model for any positioning measurements. Furthermore, the study item may assess potential specification impact to support AI-ML with different level of collaborations between UE and network. Initial sets of use cases and potential standard impacts are as follow:

[0039] Use cases to focus on:- Initial set of use cases including:o A channel status information (CSI) feedback enhancement, e.g., overheadreduction, improved accuracy, prediction [radio access network (RAN)1]; oBeam management, e.g., beam prediction in time, and / or spatial domain foroverhead and latency reduction, beam selection accuracy improvement [RAN1]; oPositioning accuracy enhancements for different scenarios including, e.g.,those with heavy NLOS conditions [RAN1]; -Finalize representative sub use cases for each use case for characterization andbaseline performance evaluations: oThe AI / ML approaches for the selected sub use cases need to be diverseenough to support various requirements on the next Generation Node B (gNB)- UE collaboration levels.

[0040] AI / ML model, terminology and description to identify common and specificcharacteristics for framework investigations: -Characterize the defining stages of AI / ML related algorithms and associatedcomplexity: oModel generation, e.g., model training (including input / output, pre- / post-process, online / offline as applicable), model validation, model testing, as applicable; oInference operation, e.g., input / output, pre- / post-process, as applicable;o Identify various levels of collaboration between UE and gNB pertinent to theselected use cases, e.g., oNo collaboration: implementation-based only AI / ML algorithms withoutinformation exchange [for comparison purposes]; oVarious levels of UE / gNB collaboration targeting at separate or joint MLoperation; -Characterize lifecycle management of AI / ML model: e.g., model training, modeldeployment, model inference, model monitoring, model updating; -Dataset(s) for training, validation, testing, and inference;- Identify common notation and terminology for AI / ML related functions, proceduresand interfaces.

[0041] A pre-requirement in AI / ML supervised learning is that testing, and validation dataneed to be labelled beforehand, which sounds obvious. Data labelling is not for free, as it typically requires external devices to support an in-field measurement. The positioning reference unit (PRU) may be intrinsically suitable to accommodate real-world measurement and labelling for AIML based learning.

[0042] Regarding ground truth label generation for AI / ML based positioning, the followingoptions of entity to generate ground truth label are identified when beneficial and necessary (e.g., limited PRU availability):^ UE with estimated / known location generates ground truth label and correspondinglabel quality indicator; obased on non-NR and / or NR RAT-dependent and / or NR RAT-independentpositioning methods; oAt least for UE-based positioning with UE-side model (Case 1) and UE-assistedpositioning with UE-side model (Case 2a);^ Network entity generates ground truth label and corresponding label quality indicator;o based on non-NR and / or NR RAT-dependent and / or NR RAT-independentpositioning methods; oAt least for UE-assisted / LMF-based positioning with LMF-side model (Case 2b),NG-RAN node assisted positioning with gNB-side model (Case 3a) and NG- RAN node assisted positioning with LMF-side model (Case 3b).

[0043] Regarding monitoring for AI / ML based positioning, at least the following aspectsare identified for further study on benefit(s), feasibility, necessity and potential specification impact for each case (Case 1 to 3b)^ Assistance signalling from LMF to UE / PRU / gNB for UE / gNB-side model monitoring;^ Assistance signalling from UE / PRU for network-side model monitoring;^ Model monitoring based on provided ground truth label (or its approximation);o Monitoring metric: statistics of the difference between model output andprovided ground truth label; oProvisioning of ground truth label and associated label quality;^ Model monitoring using at least statistics of measurement(s) without ground truthlabel; oMonitoring metric: e.g., statistics of measurement(s) compared to the statisticsassociated with the training data; oNote1: the measurement(s) may or may not be the same as model input.

[0044] Note2: other monitoring methods (e.g., based on statistics of model output withoutground truth label, based UE motion sensor and / or jointly based on multiple monitoring metrics) are not precluded.

[0045] According to the recently approved WI on “New WID on Artificial Intelligence(AI) / Machine Learning (ML) for NR Air Interface”^ Positioning accuracy enhancements, encompassing [RAN1 / RAN2 / RAN3]:oDirect AI / ML positioning: ^(1st priority) Case 1: UE-based positioning with UE-side model, direct AI / MLpositioning; ^(2nd priority) Case 2b: UE-assisted / LMF-based positioning with LMF-sidemodel, direct AI / ML positioning; ^(1st priority) Case 3b: NG-RAN node assisted positioning with LMF-sidemodel, direct AI / ML positioning; oAI / 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; oSpecify necessary measurements, signaling / mechanism(s) to facilitate life cycle management (LCM) operations specific to the Positioning accuracy enhancements use cases, if any; oInvestigate and specify the necessary signaling of necessary measurementenhancements (if any); oEnabling 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.

[0046] Based on discussions, provide options to generate the ground-truth label andcorresponding label quality indicator using non-NR and / or NR RAT-dependent and / or NR- RAT-independent positioning method. Although, the use of PRU is discussed for the groundtruth label acquisition but given that the UE and PRU may be deployed geographically ondifferent location leads to ambiguity for the ground truth. However, the prior art is unable to address how the ground truth label can be tested / validated and can be utilized for performance monitoring or training propose, related signaling and procedure have not been disclosed yet.

[0047] Merely for a better understanding, some related terminologies are listed as below.Terminology DescriptionAI / ML model A process to train an AI / ML Model [by learning the training input / output relationship] in a data driven manner and obtain the trained AI / ML Model for inference AI / ML model A process of using a trained AI / ML model to produce a set Inference of outputs based on a set of inputs AI / ML model A subprocess of training, to evaluate the quality of an validation AI / ML model using a dataset different from one used for model training, that helps selecting model parameters thatUE-side (AI / ML) An AI / ML Model whose inference is performed entirely at model the UE Network-side An AI / ML Model whose inference is performed entirely at (AI / ML) model the network One-sided (AI / ML) A UE-side (AI / ML) model or a Network-side (AI / ML) model model Model monitoring A procedure that monitors the inference performance of theAI / ML model Supervised learning A process of training a model from input and itscorresponding labels. Model activation enable an AI / ML model for a specific functionModel deactivation disable an AI / ML model for a specific functionModel switching Deactivating a currently active AI / ML model and activatinga different AI / ML model for a specific function

[0048] The following procedure may be considered for defining core requirements:^ Performance monitoring procedure, including performance evaluation and decision-making procedure for AI / ML functionalities / models;^ Functionality / Model management procedure, including functionality / modelselection / activation / deactivation, and functionality / modelswitching / fallback / transfer / delivery / update;^ Latency / interruption requirement for the above procedures.Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Example Environment

[0049] FIG. 1 illustrates an example communication environment 100 in which exampleembodiments of the present disclosure can be implemented. In the communication environment 100, there are a plurality of communication devices, for example, a first apparatus 110 and a second apparatus 120. The second apparatus 120 can communicate with the first apparatus 110.

[0050] In the following embodiments, the first apparatus 110 may comprise one of thefollowing: a terminal device, a network device or an unmanned aerial vehicle (UAV) device, while the second apparatus 120 may comprise a location management function (LMF) or a terminal device.

[0051] As one example scenario, the first apparatus 110 is a terminal device / UAU / gNBand the second apparatus 120 is an LMF. As another example scenario, the first apparatus 110 is a terminal device, and the second apparatus 120 is another terminal device.

[0052] Both the direct AI / ML positioning and AI / ML assisted positioning are supported.As for the direct AI / ML positioning, the AI / ML model output is a UE location, e.g.,fingerprinting based on channel observation as the input of AI / ML model. As for AI / ML assisted positioning, the AI / ML model output is a new measurement and / or enhancement of existing measurement, e.g., LOS / NLOS identification, timing and / or angle of measurement, likelihood of measurement.

[0053] There are 5 use-cases which may supported in communication environment 100,namely:^ Case 1: UE-based positioning with UE-side model, direct AI / ML or AI / ML assistedpositioning;^ Case 2a: UE-assisted / LMF-based positioning with UE-side model, AI / ML assistedpositioning;^ Case 2b: UE-assisted / LMF-based positioning with LMF-side model, direct AI / MLpositioning;^ Case 3a: NG-RAN node assisted positioning with gNB-side model, AI / ML assistedpositioning;^ Case 3b: NG-RAN node assisted positioning with LMF-side model, direct AI / MLpositioning.

[0054] Generally speaking, ground truth labels that are associated with model inferenceoutput are required in order to train and monitor the performance of any (supervised) AIML model.

[0055] Performance of a model is highly correlated with the quality of the ground truthlabels. Furthermore, as part of functionality-based life-cycle management (LCM), monitoring, thus reliability of ground truth information, is significantly important in order to trigger model selection / deactivation / switching / fallback.

[0056] Furthermore, the UE might encounter a new environment that has significantlydifferent characteristics from the environment where the AI / ML model is trained. In suchsituation, the network vendor would like to monitor the performance of its AI / ML model before employing it for real-time inference. For this, the required “ground truth” data needs to be available at the network side.

[0057] It is expected that the UE / chipset vendors would not disclose / expose the details oftheir AIML model for positioning purposes deployed at the UE, which could be a part of their proprietary algorithm (e.g., black box). Thus, the network would not have any knowledge about the UE-side AI / ML model, including its accuracy or performance in terms of positioning. However, network would want to monitor the performance of the AI / ML model, to determine how reliable the UE-based positioning estimates are, e.g., so as to respond to a positioning service request.

[0058] However, currently there are no mechanisms proposed or specified for the UE ornetwork (NW) to evaluate if acquired positioning-related estimations can be used as ground truth (or its approximation) for the propose of model monitoring or training. This is the gap our invention addresses.

[0059] In this invention, a mechanism to evaluate if a positioning-related estimation (i.e.,UE position or positioning-related intermediate feature, e.g., Angle of Arrival (AoA), Time of Arrival (ToA), Time Difference of Arrival (TDOA), Reference Signal Time Difference(RSTD), Reference Signal Received Path Power (RSRPP), Reference signal carrier phasedifference (RSCPD), Reference Signal Carrier Phase (RSCP), LOS / NLOS indicator, PathPhase, soft information / high resolution of RSTD) using a (non-ML) and / or ML-based methodor any combination of those, may be used as a ground truth for ML positioning is proposed.

[0060] The present disclosure mainly focuses on evaluating the collected estimations suchas by using on-device inertial measurement unit (IMU) data (e.g., accelerometer,magnetometer, and gyroscope, and the likes) as well as the positioning-related estimationsbased on the existing RAT-dependent measurements (time, angle, phase), and determining which one(s) to use as ground truth according to network preferences including confidence value and relative errors between the estimations. Work Principle and Example Signaling for Communication

[0061] Reference is now made to FIG. 2, which illustrates a signalling flow 200 ofcommunication in accordance with some embodiments of the present disclosure. For thepurposes of discussion, the signalling flow 200 will be discussed with reference to FIG.1, for example, by using the first apparatus 110 and the second apparatus 120.

[0062] It is to be understood that the operations at the first apparatus 110 and the secondapparatus 120 should be coordinated. In other words, the second apparatus 120 and the first apparatus 110 should have common understanding about configurations, parameters and so on. Such common understanding may be implemented by any suitable interactions between the second apparatus 120 and the first apparatus or both the second apparatus 120 and the first apparatus 110-1 applying the same rule / policy.

[0063] In the following, although some operations are described from a perspective of thefirst apparatus, 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. Merely for brevity, some of the same or similar contents are omitted here.

[0064] In the following embodiments, the first apparatus 110 may comprise one of thefollowing: a terminal device, a network device or an unmanned aerial vehicle (UAV) device, while the second apparatus 120 may comprise a location management function or a terminal device.

[0065] As one example scenario, the first apparatus 110 is a terminal device / UAU / gNBand the second apparatus 120 is an LMF. As another example scenario, the first apparatus 110 is a terminal device, and the second apparatus 120 is another terminal device.

[0066] In operation, the first apparatus 110 receives 220 a first message from a secondapparatus 120, where the first message is used for indicating the first apparatus 110 to obtain and store at least one set of positioning-related estimations. In response to the first message, the first apparatus 110 determines 230 the at least one set of positioning-related estimations. Then, the first apparatus 110 transmits 240 a second message to the second apparatus 120.

[0067] In some embodiments, the second message comprises the at least one set ofpositioning-related estimations. This option is especially suitable for the scenario where the second apparatus 120 is responsible for determining the ground truth labels.

[0068] Alternatively, in some embodiments, the second message comprises a first set of theat least one set of positioning-related estimations, where the first set of positioning-relatedestimations is selected by the first apparatus 110 as ground truth labels. This option isespecially suitable for the scenario where the first apparatus 110 is responsible for determining the ground truth labels.

[0069] Details about the first message is discussed first. In some embodiment, the firstmessage may indicate at least one of the following:^ measurement window information used for obtaining or storing the at least one set ofpositioning-related estimations,^ periodicity-related information used for obtaining the at least one set of positioning-related estimations,^ a first indication used for indicating the first apparatus 110 to report the positioning-related estimations,^ a second indication used for indicating the first apparatus 110 to report the ground truthlabels,^ a third indication indicating a reporting type of the second message, the reporting typebeing one of the following: periodic, semi-persistent, or event-triggered.

[0070] According to some embodiments of the present disclosure, prior to transmitting thefirst message, the second apparatus 120 may optionally transmit assistance data to the first apparatus 110. As illustrated in FIG.2. the second apparatus 120 may transmit 210 assistance data to the first apparatus 110. In particular, the assistance data may indicate at least one of the following:^ at least one method, each method is used for obtaining a set of positioning-relatedestimations,^ a preference order of the at least one method,^ a confidence level requirement used by the first apparatus 110 to select the ground truthlabels, or^ a threshold indicating an absolute value of a maximum difference between twopositioning-related estimations obtained according to two different methods.

[0071] The above assistance data may be used by the first apparatus 110 to obtain thepositioning-related estimations and / or the ground truth labels. It should be noted that any of the above the assistance data may be pre-defined, or may be stipulated to be a default value. In summary, the assistance data may be predefined or dynamically configured by the secondapparatus 120. The present discourse is not limited in this regard.

[0072] In some embodiment, the transmission of the assistance data is conditionally.Specifically, the first apparatus 110 may transmit a first request for the assistance data to thesecond apparatus 120. The second apparatus 120 may transmit the assistance data in response to the first request.

[0073] Further, in the present disclosure, the positioning-related estimations may beobtained by nay existing method or any newly-introduced method, including but not limitedto^ a non-new radio (non-NR) positioning method,^ a new radio (NR) radio access technology (RAT)-dependent positioning method,^ an NR RAT-independent positioning method,^ a machine leaning (ML)-based method, or^ a non-ML method.

[0074] In particular, in order to further improve the accuracy of ground truth labels, insome embodiments, the positioning-related estimations may be obtained by non-ML method.

[0075] As discussed above, the second message may comprise either the at least one set ofpositioning-related estimations or the selected ground truth labels (i.e., a first set of the at leastone set of positioning-related estimations). In the following, these two different options willbe discussed separately。

[0076] Embodiments where the second message comprises the selected ground truth labels(i.e., a first set of the at least one set of positioning-related estimations) will be discussed byreferring to FIG. 3A, which illustrates a further signaling charts 300A for communicationaccording to some example embodiments of the present disclosure.

[0077] Actions of 210, 220 and 230 in FIG. 3A are the same as the actions 210, 220 and230 in FIG.2. Merely for brevity, the same or similar contents are omitted here.

[0078] In the example of FIG. 3A, the at least one set of positioning-related estimationscomprises:^ the first set of positioning-related estimations obtained based on a first method, and^ a second set of positioning-related estimations obtained based on a second method.

[0079] As illustrated in FIG. 3A, the first apparatus 110 may determine 310 the first set ofpositioning-related estimations (as the ground truth labels) from the at least one set ofpositioning-related estimations based on at least one of the following:^ a fourth indication from the second apparatus 120, wherein the fourth indicationindicates the first method;^ a first preference order of the first method being higher than a second preference orderof the second method, or^ a first confidence value of the first method being higher than a second confidence valueof the second method.

[0080] Alternatively, in some embodiment, the first apparatus 110 may select two methods,where an absolute value of a difference of estimations of the two methods is smaller than athreshold (such as, a default value, or configured by the assistant data). Then, one of the estimations may be selected as ground truth label.

[0081] Specifically, in some embodiment, if the first apparatus 110 determines that anabsolute value of a difference between an estimation in the first set and an estimation in thesecond first set is smaller than a threshold, the first apparatus 110 may determine theestimation in the first set of positioning-related estimations as the ground truth label based on at least one of the following:^ a random selection;^ a first preference order of the first method being higher than a second preference orderof the second method, or^ a first confidence value of the first method being higher than a second confidence valueof the second method.

[0082] Then, as illustrated in FIG. 3A, the first apparatus 110 may transmit 320-1 thesecond message comprises the selected ground truth labels to the second apparatus 120. Insome embodiment, together with the first set of positioning-related estimations, the secondmessage may further comprise:^ a fifth indication indicating a first method used for obtaining the first set of positioning-related estimations, or^ a sixth indication indicating a label quality indicator.

[0083] In some embodiment, in response to failing to determine the ground truth labels, thefirst apparatus 110 may transmit 320-2 a second request for a third message indicatingconfiguration information for obtaining at least one another set of positioning-relatedestimations. Accordingly, the second apparatus 120 may transmit 330 a third message to the first apparatus 110, such as, re-configuring measurement and reporting resources forobtaining at least one another set of positioning-related estimations.

[0084] Embodiments where the second message comprises the at least one set ofpositioning-related estimations will be discussed by referring to FIG. 3B, which illustrates afurther signaling charts 300B for communication according to some example embodiments ofthe present disclosure.

[0085] Actions of 210, 220 and 230 in FIG. 3B are the same as the actions 210, 220 and230 in FIG.2. Merely for brevity, the same or similar contents are omitted here.

[0086] As illustrated in FIG. 3B, the first apparatus 110 transmit 350 the second messagecomprising at least one set of positioning-related estimations to the second apparatus 120, where at least one set of positioning-related estimations may comprise:^ the first set of positioning-related estimations obtained based on a first method, and^ a second set of positioning-related estimations obtained based on a second method.

[0087] As for the second apparatus 120, as illustrated in FIG. 3B, after receiving thesecond message comprising the at least one set of positioning-related estimations, the second apparatus 120 may determine 360 a first set of the positioning-related estimations as groundtruth labels and transmit 370-1 a fourth message indicating the first set of positioning-relatedestimations to the first apparatus 110.

[0088] In some embodiment, in addition to the selected ground truth labels, the fourthmessage may further comprise:^ a seventh indication indicating a first method used for obtaining the first set ofpositioning-related estimations, or^ an eighth indication indicating a label quality indicator.

[0089] The procedure used by the second apparatus 120 for selecting the ground truthlabels are similar with that used by the first apparatus 110 for selecting the ground truth labels, as discussed below.

[0090] In some embodiment, the second apparatus 120 may determine 360 the first set ofpositioning-related estimations (as the ground truth labels) from the at least one set ofpositioning-related estimations based on at least one of the following:^ a first preference order of the first method being higher than a second preference orderof the second method, or^ a first confidence value of the first method being higher than a second confidence valueof the second method.

[0091] Alternatively, in some embodiment, the second apparatus 120 may select twomethods, where an absolute value of a difference of estimations of the two methods is smallerthan a threshold (such as, a default value, or configured by the assistant data). Then, one of the estimations may be selected as ground truth label.

[0092] Specifically, in some embodiment, if the second apparatus 120 determines that anabsolute value of a difference between an estimation in the first set and an estimation in thesecond first set is smaller than a threshold, second apparatus 120 may determine theestimation in the first set of positioning-related estimations as the ground truth label based on at least one of the following:^ a random selection;^ a first preference order of the first method being higher than a second preference orderof the second method, or^ a first confidence value of the first method being higher than a second confidence valueof the second method.

[0093] Further, if the second apparatus 120 fails to determine the ground truth labels, thesecond apparatus may trigger the first apparatus 110 to report at least one another set ofpositioning-related estimations. As illustrated in FIG.3B, if the second apparatus 120 fails to determine the ground truth labels, the second apparatus 120 may transmit 330 a third message to the first apparatus 110, such as, re-configuring measurement and reporting resources forobtaining at least one another set of positioning-related estimations.Embodiments

[0094] For a better understanding, further example embodiments will be discussed withreference to FIG. 4A and FIG. 4B, which illustrate signaling charts 400A and 400B forcommunication according to some example embodiments of the present disclosure.

[0095] In the example of FIG. 4A, at Step 1, Node 2 (e.g., Location Management Function(LMF)) may provide assistance data for ground truth (GT-AD) evaluation to Node 1 (e.g., UE, gNB), which may consist of at least one or more of the following:^ preference of using a specific non-ML method such as a specific RAT-based method,e.g., downlink (DL) TDOA, or non-RAT method, e.g., LIDAR, to generate positioning- related estimation to be used as GT. In an embodiment, it could be a list of n methods ordered with respect to preference (e.g., first method on the list corresponds to the most preferred one);^ confidence level associated with collected estimation to be used to evaluate whether theestimation can be used as GT;^ threshold value or confidence level associated with a difference between estimationsdone by two methods (e.g., indicated for all (n choose 2) of above n methods, or for a subset of them), or^ number of estimations N or time interval T, after which Node 1 should discard theestimations using as GT if they do not obey required confidence level or threshold value.

[0096] It should be noted that the non-ML method discussed herein may be either an RAT-based method or non-RAT method, either of them may be a time-based positioningestimation, an angle and / or phase based positioning estimation. Examples of an RAT-basedmethod include but are not limited to, a multi-round-trip-time (RTT) positioning, enhancedcell-ID (E-CID) positioning, TDOA positioning, an observed time difference of arrival(OTDOA), AoA positioning, AoD positioning, assisted global navigation satellite system (A- GNSS) and son on. Examples of a non-RAT method include but are not limited to, LIDAR, sensor, WLAN, Bluetooth and so on. It should be understood that the above example methods are only for the purpose of illustration without suggesting any limitations. Thepresent discourse is not limited with regard to the specific type of positioning method.

[0097] Additionally, in some embodiments, Node 1 may request Node 2 to provide GT-AD

[0098] At Step 2, Node 2 (e.g., LMF) may request Node 1 to generate positioning relatedestimations (e.g., UE position or intermediate feature) using one or more RAT and non-RAT (e.g., local sensor data) based techniques indicated in GT-AD, in parallel to ML-based estimations.

[0099] In an embodiment, Node 2 may configure a time window, frequency / periodicity togenerate and save the positioning-related estimations (as well as associated measurements).

[0100] In an embodiment, Node 2 may configure Node 1 to report the generated and savedestimations (and associated measurements) to Node 2 for the case where Node 2 evaluates which estimation(s) to be used as GT.

[0101] In an embodiment, Node 2 may configure Node 1 to report the GT it determines.

[0102] In the embodiments, the report could be configured as periodical / triggered / semi-persistent. E.g., the frequency of reporting may be configured on mobility or channel conditions of Node 1 (if UE), or between Node 1 (if gNB) and another node (target UE).

[0103] Additionally, in some embodiments, in Case 3b (LMF-side model), LMF may act asNode 2 and UE acts as Node 1. The LMF sends the GT-AD and the request to the UE over the LTE Positioning Protocol (LPP) protocol.

[0104] At Step 3, on the reception of the indication from Node 2 (e.g., LMF), Node 1 (e.g.,UE) may generate positioning-related estimations via indicated RAT-dependent or non-RAT dependent method(s) to be evaluated for using them as GT, together with ML-based positioning estimations, and stores them according to the configuration provided in Step 2 by Node 2.

[0105] For example, in Case 1 (UE-side model, direct AIML positioning), UE stores thesensor data measurements (e.g., IMU measurements) and inference output (i.e., position estimation) based on the inputs following RAT-dependent measurements such as channelimpulse response (CIR), power delay profile (PDP), DP, etc.

[0106] In another example, in Case 3b (LMF-side model), the UE only stores the sensordata measurements.

[0107] Embodiments where Node 1 evaluates the estimation to be used as GT will bediscussed first.

[0108] As illustrated in alternative 1 in FIG. 4A, in some embodiments, Node 1 mayperform one or more of the following to determine whether to utilize the performed estimations as GT. For example, select one of the methods indicated by Node 2 in GT-AD and directly use the estimation performed by the selected method as GT. Alternatively, Node1 may compare the confidence value of the estimation to the value provided in GT-AD, anduse the estimation as GT if confidence value is better.

[0109] Alternatively, in some embodiments, Node 1 may Select two of the methodsindicated by Node 2 in GT-AD and compute the “delta” that indicates the difference between the estimations done by the two methods. Compare the computed “delta” with the indicated threshold in GT-AD, then select one of two methods as stated in Step 1 to use its estimation as GT if delta is smaller than (or equal to) the threshold:^ in an embodiment, it is left up to implementation of Node 1, which one of the twomethods to select;^ in another embodiment, Node 1 selects the method with the highest preference valueindicated in GT-AD;^ in another embodiment, Node 1 selects the method that has the highest confidence value(as evaluated above); or^ in an embodiment, Node 1 selects one of the two methods randomly, e.g., as perconfiguration.

[0110] Then, Node 1 may provide the selected estimation to be used as GT to Node 2together with the associated information, e.g., which method Node 1 has utilized to determine the GT.

[0111] In some embodiments, if Node 1 cannot determine GT (e.g., after evaluating Ndifferent estimations or the estimations collected within time interval T), it may request new measurements from network (e.g., LMF / Node 2) to make new estimations. In turn, the network may re-configure the network resources (time, a positioning reference signal (PRS) / sounding reference signal (SRS) bandwidth, no. of transmission reception point (TRP)s) for the new estimations.

[0112] In an embodiment, Node 1 also derives and indicates quality indicator associatedwith the GT to Node 2.

[0113] In the following, embodiments where Node 2 evaluates the estimation to be used asGT will be discussed.

[0114] As illustrated in alternative 2 in FIG. 4A, in some embodiments, if configured forreporting, Node 1 reports the estimations collected via RAT and non-RAT methods to Node 2, according to configuration provided in Step 1.

[0115] For example, in case of case 3b (LMF-side model) the Node 1 (UE) reports theRAT and non-RAT measurements corresponding to the GT-AD configuration shared by the Node 2 (LMF).

[0116] Then, in some embodiments, Node 2 evaluates the reported estimations to be usedas GT. It may use one of the methods listed for Node 1 in Step 4 above. It may provide the determined GT to Node 1 (e.g., so that Node 1 uses it for monitoring or (re)training).

[0117] Reference is now made to FIG. 4B, which is illustrated as one possible non-limitingexample embodiment.

[0118] In the example of FIG. 4B, Node 1 receives GT-AD from Node 2, indicating storingRAT ^^^^^and non-RAT ^^^^^measurements, and confidence level Δ^^.

[0119] Additionally, in some embodiments, in the case of “Case 1 (UE-side model)”, Node1 may calculate the deviation of the position estimates done by using the RAT and non-RATmeasurements for a given time instance ^, e.g., ^[^] = |^^^^^ − ^^^^^|, and compare it withΔ^^.

[0120] Alternatively, in some embodiments, in the case of “Case 3b (LMF-side model)”,Node 1 simply reports the stored measurements, and Node 2 calculates the deviation of the position estimates between the RAT and non-RAT estimations for a given time instance ^,e.g., ^[^] = |^^^^^ − ^^^^^|, and compare it with the confidence level Δ^^;

[0121] In some embodiments, if the deviation is smaller or equal than the confidence level,the estimated data is considered to be used as GT, which could be used for the purpose of model monitoring.

[0122] In one specific implementation case, the RAT ^^^^^ is considered to be used asGT. In another specific implementation case, non-RAT ^^^^^is considered to be used as GT. Alternatively, instead of relying one value, the node can be configured to evaluate any other possible mathematical operation and / or combination of mathematical operations between the RAT ^^^^^and non-RAT ^^^^^, which is specific to network implementations and accuracyrequirements.

[0123] Additionally, in the case of “Case 1 (UE-side model)”, Node 1 may report thedetermined GT and corresponding “quality indicator” to Node 2;

[0124] In some embodiments, if the deviation is larger than the confidence level, theestimation is evaluated as not usable as GT for given time instance ^. In this case, to avoid impulsive decision (i.e., false negative), additional RAT and non-RAT measurements can be conducted in the subsequent time instances and compare their deviation with the confidence;

[0125] In some embodiments, if the estimations are found not to be suitable for GT for N(configurable) subsequent time instances or time interval T: {^, ^ + 1} (configurable), Node 1(or Node 2) declares the estimation cannot be used as GT, which could be, e.g., due to either defective on-device sensor or inadequate radio measurements. In such cases, the node discards the estimations and requests new measurements to generate new estimations;

[0126] It should be noted that to simplify the exposition, in the previous section, we focuson the standard UE – LMF scenarios. However, all the described mechanisms can easily beextended to, e.g., device-to-device (D2D) and sidelink (SL) positioning scenarios by a person skilled in the related art. As an example, the sidelink anchor- / supporting -UE (S-UE) receives indication from sidelink target UE (T-UE) to enable the assistance data for the propose of ground truth validation. The GT-AD includes, e.g., SL measurements over the PC5 interface and non-SL measurements (e.g., may include both RAT and non-RAT sensor measurements). Similar to above, the evaluation for GT can be performed either at T-UE or at S-UE, as illustrated in Figure 2. Such implementation might be, in particular, relevant to the SL positioning of a T-UE with the help of other UEs serving as anchors by transmitting or receiving SL positioning reference signals (SL PRS) to evaluate positioning-related estimations as ground truth for the propose of model monitoring. Example Methods

[0127] FIG. 5 shows a flowchart of an example method 500 implemented at a first devicein accordance with some example embodiments of the present disclosure. For the purpose ofdiscussion, the method 500 will be described from the perspective of the first apparatus 110 inFIG.1.

[0128] At block 510, the first apparatus receives, from a second apparatus, a first messageused for indicating the first apparatus to obtain and store at least one set of positioning-related estimations.

[0129] At block 520, in response to the first message, the first apparatus determines the atleast one set of positioning-related estimations.

[0130] At block 530, the first apparatus transmits, to the second apparatus, a secondmessage comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0131] In some example embodiments, the first message indicates at least one of thefollowing: measurement window information used for obtaining or storing the at least one setof positioning-related estimations, periodicity-related information used for obtaining the atleast one set of positioning-related estimations, a first indication used for indicating the first apparatus to report the positioning-related estimations, a second indication used for indicating the first apparatus to report the ground truth labels, a third indication indicating a reporting type of the second message, the reporting type being one of the following: periodic, semi- persistent, or event-triggered.

[0132] In some example embodiments, the first apparatus may receive, from the secondapparatus, assistance data indicating at least one of the following: at least one method, each method is used for obtaining a set of positioning-related estimations, a preference order of the at least one method, a confidence level requirement used by the first apparatus to select the ground truth labels, or a threshold indicating an absolute value of a maximum difference between two positioning-related estimations obtained according to two different methods.

[0133] In some example embodiments, the first apparatus may transmit, to the secondapparatus, a first request for the assistance data.

[0134] In some example embodiments, the at least one set of positioning-relatedestimations comprises: the first set of positioning-related estimations obtained based on a first method, and a second set of positioning-related estimations obtained based on a second method, and wherein the first apparatus is caused to: determine, from the at least one set of positioning-related estimations, the first set of positioning-related estimations as the ground truth labels based on at least one of the following: a fourth indication from the second apparatus, wherein the fourth indication indicates the first method; a first preference order of the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

[0135] In some example embodiments, the at least one set of positioning-relatedestimations comprises: the first set of positioning-related estimations obtained based on a first method, and a second set of positioning-related estimations obtained based on a second method, and wherein the first apparatus is caused to: in accordance with a determination that an absolute value of a difference between an estimation in the first set and an estimation in the second first set is smaller than a threshold, determining the estimation in the first set of positioning-related estimations as the ground truth label based on at least one of thefollowing: a random selection; a first preference order of the first method being higher than asecond preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

[0136] In some example embodiments, together with the first set of positioning-relatedestimations, the second message further comprises: a fifth indication indicating a first method used for obtaining the first set of positioning-related estimations, or a sixth indication indicating a label quality indicator.

[0137] In some example embodiments, in response to failing to determine the ground truthlabels, the first apparatus may transmit a second request for a third message indicatingconfiguration information for obtaining at least one another set of positioning-related estimations.

[0138] In some example embodiments, after transmitting the second message comprisingthe at least one set of positioning-related estimations, the first apparatus may receive a fourthmessage from the second apparatus, the fourth message indicating the first set of positioning- related estimations is selected by the second apparatus as ground truth labels.

[0139] In some example embodiments, the fourth message further comprises: a seventhindication indicating a first method used for obtaining the first set of positioning-relatedestimations, or an eighth indication indicating a label quality indicator.

[0140] In some example embodiments, the at least one method comprises at least one ofthe following: a non-new radio (non-NR) positioning method, a new radio (NR) radio access technology (RAT)-dependent positioning method, an NR RAT-independent positioning method, or a machine leaning (ML)-based method.

[0141] In some example embodiments, the first apparatus comprises one of the following:a terminal device, a network device or an unmanned aerial vehicle (UAV) device, and the second apparatus comprises a location management function or a terminal device.

[0142] FIG. 6 shows a flowchart of an example method 600 implemented at a seconddevice 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 secondapparatus 120 in FIG. 1.

[0143] At block 610, the second apparatus transmits, to a first apparatus, a first messageused for indicating the first apparatus to obtain at least one set of positioning-related estimations.

[0144] At block 620, the second apparatus receives, from the first apparatus, a secondmessage comprising at least one of the following: at least one set of positioning-related estimations obtained by the first apparatus in response to the first message, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0145] In some example embodiments, the first message indicates at least one of thefollowing: measurement window information used for obtaining or storing the at least one setof positioning-related estimations, periodicity-related information used for obtaining the at least one set of positioning-related estimations, a first indication used for indicating the first apparatus to report the positioning-related estimations, a second indication used for indicating the first apparatus to report the ground truth labels, a third indication indicating a reporting type of the second message, the reporting type being one of the following: periodic, semi- persistent, or event-triggered.

[0146] In some example embodiments, the second apparatus may transmit, to the firstapparatus, assistance data indicating at least one of the following: at least one method, each method is used for obtaining a set of positioning-related estimations, a preference order of the at least one method, a confidence level requirement used by the first apparatus to select the ground truth labels, or a threshold indicating an absolute value of a maximum difference between two positioning-related estimations obtained according to two different methods.

[0147] In some example embodiments, the second apparatus may receive, form the firstapparatus, a first request for the assistance data.

[0148] In some example embodiments, after receiving the second message comprising theat least one set of positioning-related estimations, the second apparatus may determine a firstset of the positioning-related estimations as ground truth labels; and transmitting, to the first apparatus, a fourth message indicating the first set of positioning-related estimations.

[0149] In some example embodiments, the fourth message further comprises: a seventhindication indicating a first method used for obtaining the first set of positioning-relatedestimations, or an eighth indication indicating a label quality indicator.

[0150] In some example embodiments, the at least one set of positioning-relatedestimations comprises: the first set of positioning-related estimations obtained based on a first method, and a second set of positioning-related estimations obtained based on a second method, and wherein the second apparatus is caused to: determine, from the at least one set of positioning-related estimations, the first set of positioning-related estimations as the ground truth labels based on at least one of the following: a first preference order of the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

[0151] In some example embodiments, the at least one set of positioning-relatedestimations comprises: and wherein the second apparatus is caused to: in accordance with a determination that an absolute value of a difference between an estimation in the first set and an estimation in the second first set is smaller than a threshold, determining the estimation in the first set of positioning-related estimations as the ground truth label based on at least one of the following: a random selection; a first preference order of the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

[0152] In some example embodiments, together with the first set of positioning-relatedestimations, the second message further comprises: a fifth indication indicating a first method used for obtaining the first set of positioning-related estimations, or a sixth indication indicating a label quality indicator.

[0153] In some example embodiments, the second apparatus may receive, from the firstapparatus, a second request for a third message indicating configuration information for obtaining at least one another of positioning-related estimations.

[0154] In some example embodiments, the at least one method comprises at least one ofthe following: a non-new radio (non-NR) positioning method, a new radio (NR) radio access technology (RAT)-dependent positioning method, an NR RAT-independent positioning method, or a machine leaning (ML)-based method.

[0155] In some example embodiments, the first apparatus comprises one of the following:a terminal device, a network device or an unmanned aerial vehicle (UAV) device, and the second apparatus comprises a location management function or a terminal device.Example Apparatus, Device and Medium

[0156] In some example embodiments, a first apparatus capable of performing any of themethod 500 (for example, the first apparatus 110 in FIG. 1) may comprise means forperforming 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 first apparatus may be implemented as or included in the first apparatus 110 inFIG. 1.

[0157] In some example embodiments, the first apparatus comprises means for receiving,from a second apparatus, a first message used for indicating the first apparatus to obtain and store at least one set of positioning-related estimations; means for in response to the first message, determining the at least one set of positioning-related estimations; and means for transmitting, to the second apparatus, a second message comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0158] In some example embodiments, the first message indicates at least one of thefollowing: means for measurement window information used for obtaining or storing the at least one set of positioning-related estimations, means for periodicity-related information used for obtaining the at least one set of positioning-related estimations, a first indication used for indicating the first apparatus to report the positioning-related estimations, a second indication used for indicating the first apparatus to report the ground truth labels, means for a third indication indicating a reporting type of the second message, the reporting type being one of the following: periodic, semi-persistent, or event-triggered.

[0159] In some example embodiments, the first apparatus further comprises: means forreceiving, from the second apparatus, assistance data indicating at least one of the following: at least one method, each method is used for obtaining a set of positioning-related estimations, a preference order of the at least one method, a confidence level requirement used by the first apparatus to select the ground truth labels, or a threshold indicating an absolute value of a maximum difference between two positioning-related estimations obtained according to two different methods.

[0160] In some example embodiments, the first apparatus further comprises: means fortransmitting, to the second apparatus, a first request for the assistance data.

[0161] In some example embodiments, the at least one set of positioning-relatedestimations comprises: the first set of positioning-related estimations obtained based on a first method, and a second set of positioning-related estimations obtained based on a second method, and wherein the first apparatus is caused to: determine, from the at least one set of positioning-related estimations, the first set of positioning-related estimations as the ground truth labels based on at least one of the following: a fourth indication from the second apparatus, wherein the fourth indication indicates the first method; a first preference order of the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

[0162] In some example embodiments, the at least one set of positioning-relatedestimations comprises: the first set of positioning-related estimations obtained based on a first method, and a second set of positioning-related estimations obtained based on a second method, means for and wherein the first apparatus is caused to: in accordance with a determination that an absolute value of a difference between an estimation in the first set and an estimation in the second first set is smaller than a threshold, determining the estimation in the first set of positioning-related estimations as the ground truth label based on at least one of the following: a random selection; a first preference order of the first method being higherthan a second preference order of the second method, or a first confidence value of the firstmethod being higher than a second confidence value of the second method.

[0163] In some example embodiments, together with the first set of positioning-relatedestimations, the second message further comprises: a fifth indication indicating a first method used for obtaining the first set of positioning-related estimations, or a sixth indication indicating a label quality indicator.

[0164] In some example embodiments, the first apparatus further comprises: means for inresponse to failing to determine the ground truth labels, transmitting a second request for a third message indicating configuration information for obtaining at least one another set of positioning-related estimations.

[0165] In some example embodiments, the first apparatus further comprises: means forafter transmitting the second message comprising the at least one set of positioning-related estimations, receiving a fourth message from the second apparatus, the fourth message indicating the first set of positioning-related estimations is selected by the second apparatus as ground truth labels.

[0166] In some example embodiments, the fourth message further comprises: a seventhindication indicating a first method used for obtaining the first set of positioning-relatedestimations, or an eighth indication indicating a label quality indicator.

[0167] In some example embodiments, the at least one method comprises at least one ofthe following: a non-new radio (non-NR) positioning method, a new radio (NR) radio access technology (RAT)-dependent positioning method, an NR RAT-independent positioning method, or a machine leaning (ML)-based method.

[0168] In some example embodiments, the first apparatus comprises one of the following:a terminal device, a network device or an unmanned aerial vehicle (UAV) device, and the second apparatus comprises a location management function or a terminal device.

[0169] In some example embodiments, the first apparatus further comprises means forperforming other operations in some example embodiments of the method 500 or the first apparatus 110. In some example embodiments, the means comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the first apparatus.

[0170] In some example embodiments, a second apparatus capable of performing any ofthe method 600 (for example, the second apparatus 120 in FIG.1) 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 second apparatus may be implemented as or included in the second apparatus 120 in FIG.1.

[0171] In some example embodiments, the second apparatus comprises means fortransmitting, to a first apparatus, a first message used for indicating the first apparatus to obtain at least one set of positioning-related estimations; and means for receiving, from the first apparatus, a second message comprising at least one of the following: at least one set of positioning-related estimations obtained by the first apparatus in response to the first message, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

[0172] In some example embodiments, the first message indicates at least one of thefollowing: means for measurement window information used for obtaining or storing the at least one set of positioning-related estimations, means for periodicity-related information used for obtaining the at least one set of positioning-related estimations, a first indication used for indicating the first apparatus to report the positioning-related estimations, a second indication used for indicating the first apparatus to report the ground truth labels, means for a thirdindication indicating a reporting type of the second message, the reporting type being one of the following: periodic, semi-persistent, or event-triggered.

[0173] In some example embodiments, the second apparatus further comprises: means fortransmitting, to the first apparatus, assistance data indicating at least one of the following: at least one method, each method is used for obtaining a set of positioning-related estimations, a preference order of the at least one method, a confidence level requirement used by the first apparatus to select the ground truth labels, or a threshold indicating an absolute value of a maximum difference between two positioning-related estimations obtained according to two different methods.

[0174] In some example embodiments, the second apparatus further comprises: means forreceiving, form the first apparatus, a first request for the assistance data.

[0175] In some example embodiments, the second apparatus further comprises: means forafter receiving the second message comprising the at least one set of positioning-related estimations, determining a first set of the positioning-related estimations as ground truth labels; and means for transmitting, to the first apparatus, a fourth message indicating the first set of positioning-related estimations.

[0176] In some example embodiments, the fourth message further comprises: a seventhindication indicating a first method used for obtaining the first set of positioning-relatedestimations, or an eighth indication indicating a label quality indicator.

[0177] In some example embodiments, the at least one set of positioning-relatedestimations comprises: the first set of positioning-related estimations obtained based on a first method, and a second set of positioning-related estimations obtained based on a second method, and wherein the second apparatus is caused to: determine, from the at least one set of positioning-related estimations, the first set of positioning-related estimations as the ground truth labels based on at least one of the following: a first preference order of the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

[0178] In some example embodiments, the at least one set of positioning-relatedestimations comprises: means for and wherein the second apparatus is caused to: in accordance with a determination that an absolute value of a difference between an estimation in the first set and an estimation in the second first set is smaller than a threshold, determining the estimation in the first set of positioning-related estimations as the ground truth label based on at least one of the following: a random selection; a first preference orderof the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

[0179] In some example embodiments, together with the first set of positioning-relatedestimations, the second message further comprises: a fifth indication indicating a first method used for obtaining the first set of positioning-related estimations, or a sixth indication indicating a label quality indicator.

[0180] In some example embodiments, the second apparatus further comprises: means forreceiving, from the first apparatus, a second request for a third message indicating configuration information for obtaining at least one another of positioning-related estimations.

[0181] In some example embodiments, the at least one method comprises at least one ofthe following: a non-new radio (non-NR) positioning method, a new radio (NR) radio access technology (RAT)-dependent positioning method, an NR RAT-independent positioning method, or a machine leaning (ML)-based method.

[0182] In some example embodiments, the first apparatus comprises one of the following:a terminal device, a network device or an unmanned aerial vehicle (UAV) device, and the second apparatus comprises a location management function or a terminal device.

[0183] In some example embodiments, the second apparatus further comprises means forperforming other operations in some example embodiments of the method 600 or the second apparatus 120. In some example embodiments, the means comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the second apparatus.

[0184] FIG. 7 is a simplified block diagram of a device 700 that is suitable forimplementing example embodiments of the present disclosure. The device 700 may be provided to implement a communication device, for example, the first apparatus 110 or the second apparatus 120 as shown in FIG.1. As shown, the device 700 includes one or more processors 710, one or more memories 720 coupled to the processor 710, and one or more communication modules 740 coupled to the processor 710.

[0185] The communication module 740 is for bidirectional communications. Thecommunication module 740 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 740 may include at least one antenna.

[0186] The processor 710 may be of any type suitable to the local technical network andmay 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 700 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.

[0187] The memory 720 may include one or more non-volatile memories and one or morevolatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 724, 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) 722 and other volatile memories that will not last in the power-down duration.

[0188] A computer program 730 includes computer executable instructions that areexecuted by the associated processor 710. The instructions of the program 730 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 730 may be stored in the memory, e.g., the ROM 724. The processor 710 may perform any suitable actions and processing by loading the program 730 into the RAM 722.

[0189] The example embodiments of the present disclosure may be implemented by meansof the program 730 so that the device 700 may perform any process of the disclosure as discussed with reference to FIG.2 to FIG.6. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0190] In some example embodiments, the program 730 may be tangibly contained in acomputer readable medium which may be included in the device 700 (such as in the memory 720) or other storage devices that are accessible by the device 700. The device 700 may load the program 730 from the computer readable medium to the RAM 722 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).

[0191] Generally, various embodiments of the present disclosure may be implemented inhardware 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.

[0192] Some example embodiments of the present disclosure also provide at least onecomputer program product tangibly stored on a computer readable medium, such as a non- transitory computer readable medium. The computer program product includes computer- executable 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.

[0193] Program code for carrying out methods of the present disclosure may be written inany 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 theprocessor or controller, cause the functions / operations specified in the flowcharts and / or blockdiagrams 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.

[0194] In the context of the present disclosure, the computer program code or related datamay be carried by any suitable carrier to enable the device, apparatus or processor to performvarious processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0195] The computer readable medium may be a computer readable signal medium or acomputer 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.

[0196] Further, although operations are depicted in a particular order, this should not beunderstood 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.

[0197] Although the present disclosure has been described in languages specific tostructural 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

CLAIMS 1. A first apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from a second apparatus, a first message used for indicating the first apparatus to obtain and store at least one set of positioning-related estimations; in response to the first message, determine the at least one set of positioning-related estimations; and transmit, to the second apparatus, a second message comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-related estimations, wherein thefirst set of positioning-related estimations is selected by the first apparatus as ground truthlabels.

2. The first apparatus of claim 1, wherein the first message indicates at least one ofthe following: measurement window information used for obtaining or storing the at least one set of positioning-related estimations, periodicity-related information used for obtaining the at least one set of positioning- related estimations, afirst indication used for indicating the first apparatus to report the positioning-related estimations, asecond indication used for indicating the first apparatus to report the ground truthlabels, a third indication indicating a reporting type of the second message, the reporting type being one of the following: periodic, semi-persistent, or event-triggered.

3. The first apparatus of claim 1, wherein the first apparatus is caused to: receive, from the second apparatus, assistance data indicating at least one of thefollowing: at least one method, each method is used for obtaining a set of positioning-related estimations, apreference order of the at least one method,a confidence level requirement used by the first apparatus to select the ground truthlabels, or athreshold indicating an absolute value of a maximum difference between twopositioning-related estimations obtained according to two different methods.

4. The first apparatus of claim 3, wherein the first apparatus is caused to: transmit, to the second apparatus, a first request for the assistance data.

5. The first apparatus of claim 1, wherein the at least one set of positioning-relatedestimations comprises: the first set of positioning-related estimations obtained based on a first method, and asecond set of positioning-related estimations obtained based on a second method,and wherein the first apparatus is caused to: determine, from the at least one set of positioning-related estimations, the first set of positioning-related estimations as the ground truth labels based on at least one of the following: afourth indication from the second apparatus, wherein the fourth indicationindicates the first method; a first preference order of the first method being higher than a second preference order of the second method, or afirst confidence value of the first method being higher than a second confidencevalue of the second method.

6. The first apparatus of claim 1, wherein the at least one set of positioning-related estimations comprises: the first set of positioning-related estimations obtained based on a first method, and asecond set of positioning-related estimations obtained based on a second method,and wherein the first apparatus is caused to: in accordance with a determination thatan absolute value of a difference between an estimation in the first set and an estimationin the second first set is smaller than a threshold, determine the estimation in the first setof positioning-related estimations as the ground truth label based on at least one of the following: a random selection; a first preference order of the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

7. The first apparatus of claim 1, wherein, together with the first set of positioning-related estimations, the second message further comprises:a fifth indication indicating a first method used for obtaining the first set ofpositioning-related estimations, or asixth indication indicating a label quality indicator.

8. The first apparatus of claim 1, wherein the first apparatus is caused to:in response to failing to determine the ground truth labels, transmit a second request for a third message indicating configuration information for obtaining at least one another set of positioning-related estimations.

9. The first apparatus of claim 1, wherein the first apparatus is caused to: after transmitting the second message comprising the at least one set of positioning- related estimations, receive a fourth message from the second apparatus, the fourth message indicating the first set of positioning-related estimations is selected by the second apparatus as ground truth labels.

10. The first apparatus of claim 9, wherein the fourth message further comprises:a seventh indication indicating a first method used for obtaining the first set ofpositioning-related estimations, or an eighth indication indicating a label quality indicator.

11. The first apparatus of claim 1, wherein the at least one method comprises at least one of the following: anon-new radio (non-NR) positioning method,a new radio (NR) radio access technology (RAT)-dependent positioning method,an NR RAT-independent positioning method, or a machine leaning (ML)-based method.

12. The first apparatus of any of claims 1-11, wherein, the first apparatus comprises one of the following: a terminal device, a network device or an unmanned aerial vehicle (UAV) device, and the second apparatus comprises a location management function or a terminal device.

13. A second apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to: transmit, to a first apparatus, a first message used for indicating the first apparatus to obtain at least one set of positioning-related estimations; and receive, from the first apparatus, a second message comprising at least one of the following: at least one set of positioning-related estimations obtained by the first apparatus in response to the first message, or a first set of the at least one set of positioning-related estimations, wherein the firstset of positioning-related estimations is selected by the first apparatus as ground truthlabels.

14. The second apparatus of claim 13, wherein the first message indicates at least one of the following: measurement window information used for obtaining or storing the at least one set of positioning-related estimations, periodicity-related information used for obtaining the at least one set of positioning- related estimations, afirst indication used for indicating the first apparatus to report the positioning-related estimations, asecond indication used for indicating the first apparatus to report the ground truthlabels,a third indication indicating a reporting type of the second message, the reporting type being one of the following: periodic, semi-persistent, or event-triggered.

15. The second apparatus of claim 13, wherein the second apparatus is caused to: transmit, to the first apparatus, assistance data indicating at least one of the following: at least one method, each method is used for obtaining a set of positioning-related estimations, apreference order of the at least one method,a confidence level requirement used by the first apparatus to select the ground truthlabels, or athreshold indicating an absolute value of a maximum difference between twopositioning-related estimations obtained according to two different methods.

16. The second apparatus of claim 15, wherein the second apparatus is caused to: receive, form the first apparatus, a first request for the assistance data.

17. The second apparatus of claim 13, wherein the second apparatus is caused to: after receiving the second message comprising the at least one set of positioning- related estimations, determine a first set of the positioning-related estimations as ground truth labels; and transmit, to the first apparatus, a fourth message indicating the first set of positioning-related estimations.

18. The second apparatus of claim 17, wherein the fourth message further comprises:a seventh indication indicating a first method used for obtaining the first set ofpositioning-related estimations, or an eighth indication indicating a label quality indicator.

19. The second apparatus of claim 13, wherein the at least one set of positioning-related estimations comprises: the first set of positioning-related estimations obtained based on a first method, and asecond set of positioning-related estimations obtained based on a second method,and wherein the second apparatus is caused to: determine, from the at least one setof positioning-related estimations, the first set of positioning-related estimations as the ground truth labels based on at least one of the following: a first preference order of the first method being higher than a second preference order of the second method, or afirst confidence value of the first method being higher than a second confidencevalue of the second method.

20. The second apparatus of claim 13, wherein the at least one set of positioning- related estimations comprises: the first set of positioning-related estimations obtained based on a first method, and asecond set of positioning-related estimations obtained based on a second method,and wherein the second apparatus is caused to: and wherein the second apparatus is caused to: in accordance with a determinationthat an absolute value of a difference between an estimation in the first set and anestimation in the second first set is smaller than a threshold, determine the estimation in the first set of positioning-related estimations as the ground truth label based on at least one of the following: a random selection; a first preference order of the first method being higher than a second preference order of the second method, or a first confidence value of the first method being higher than a second confidence value of the second method.

21. The second apparatus of claim 13, wherein, together with the first set ofpositioning-related estimations, the second message further comprises:a fifth indication indicating a first method used for obtaining the first set ofpositioning-related estimations, or asixth indication indicating a label quality indicator.

22. The second apparatus of claim 13, wherein the second apparatus is caused to:receive, from the first apparatus, a second request for a third message indicating configuration information for obtaining at least one another of positioning-related estimations.

23. The second apparatus of claim 13, wherein the at least one method comprises at least one of the following: anon-new radio (non-NR) positioning method,a new radio (NR) radio access technology (RAT)-dependent positioning method,an NR RAT-independent positioning method, or a machine leaning (ML)-based method.

24. The second apparatus of any of claims 13-23, wherein, the first apparatus comprises one of the following: a terminal device, a network device or an unmanned aerial vehicle (UAV) device, and the second apparatus comprises a location management function or a terminal device.

25. A method comprising: receiving, from a second apparatus, a first message used for indicating the first apparatus to obtain and store at least one set of positioning-related estimations; in response to the first message, determining the at least one set of positioning- related estimations; and transmitting, to the second apparatus, a second message comprising at least one of the following: the at least one set of positioning-related estimations, or a first set of the at least one set of positioning-related estimations, wherein the first set of positioning-related estimations is selected by the first apparatus as ground truth labels.

26. A method comprising: transmitting, to a first apparatus, a first message used for indicating the first apparatus to obtain at least one set of positioning-related estimations; and receiving, from the first apparatus, a second message comprising at least one of the following: at least one set of positioning-related estimations obtained by the first apparatus in response to the first message, or a first set of the at least one set of positioning-related estimations, wherein the firstset of positioning-related estimations is selected by the first apparatus as ground truth labels.

27. A computer readable medium comprising instructions stored thereon for causingan apparatus at least to perform the method of claim 25 or claim 26.

Images