Continuous measurements for artificial intelligence / machine learning

Abstract

Example embodiments of the present disclosure relate to methods, devices, apparatuses and computer readable storage medium for continuous measurements for artificial intelligence (AI) / machine learning (ML) in radio access network (RAN). The method comprises: obtaining, at a radio access network node from a data collection entity (DCE) of a radio access network, a globally unique collection identifier (GUCI) and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; selecting, based on the at least one selection criteria, one or more user devices for the data collection; and collecting measurement data from the one or more user devices.

Description

CONTINUOUS MEASUREMENTS FOR ARTIFICIAL INTELLIGENCE / MACHINE LEARNINGFIELDS

[0001] Various example embodiments of the present disclosure generally relate to the field of telecommunication and in particular, to methods, devices, apparatuses and computer readable storage medium for continuous measurements for artificial intelligence (Al) / machine learning (ML) in radio access network (RAN).BACKGROUND

[0002] Due to the great success of Al / ML technologies, the AI / ML study item, which may refer to UE-sided model and network (NW) sided model, has been discussed in 3 GPP.SUMMARY

[0003] In a first aspect of the present disclosure, there is provided an apparatus. The apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: obtain, from a data collection entity (DCE) of a radio access network, a globally unique collection identifier (GUCI) and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; select, based on the at least one selection criteria, one or more user devices for the data collection; and collect measurement data from the one or more user devices.

[0004] In a second aspect of the present disclosure, there is provided an apparatus. The apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: obtain, from an Access and Mobility management Function (AMF), at leastone GUCI label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device and / or a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements; and collect the measurement data corresponding to the received GUCI.

[0005] In a third aspect of the present disclosure, there is provided an apparatus. The apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a radio access network node, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; and receive, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification value associated with a user device selected according to the at least one selection criteria.

[0006] In a fourth aspect of the present disclosure, there is provided a method. The method comprises: obtaining, at a radio access network node from a DCE of a radio access network, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device ; selecting, based on the at least one selection criteria, one or more user devices for the data collection; and collecting measurement data from the one or more user devices.

[0007] In a fifth aspect of the present disclosure, there is provided a method. The method comprises: obtaining, at a radio access network node from an AMF, at least one GUCI label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device and / or a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements; and collecting the measurement data corresponding to the received GUCI.

[0008] In a sixth aspect of the present disclosure, there is provided a method. The method comprises: transmitting, from a DCE to a radio access network node, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device ; and receiving, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification value associated with a user device selected according to the at least one selection criteria.

[0009] In a seventh aspect of the present disclosure, there is provided an apparatus. The apparatus comprises means for obtaining, from a DCE of a radio access network, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; means for selecting, based on the at least one selection criteria, one or more user devices for the data collection; and means for collecting measurement data from the one or more user devices.

[0010] In an eighth aspect of the present disclosure, there is provided an apparatus. The apparatus comprises means for obtaining, from an AMF, at least one GUCI label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device and / or a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements; and means for collecting the measurement data corresponding to the received GUCI.

[0011] In a ninth aspect of the present disclosure, there is provided an apparatus. The apparatus comprises means for transmitting, to a radio access network node, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device ; and means for receiving, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification value associated with a user device selected according to the at least one selection criteria.

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

[0013] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS

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

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

[0016] FIG. 2 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0017] FIG. 3 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0018] FIG. 4 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0019] FIG. 5 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0020] FIG. 6 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0021] FIG. 7 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0022] FIG. 8 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0023] FIG. 9 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0024] FIG. 10 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0025] FIG. 11 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0026] FIG. 12 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0027] FIG. 13 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0028] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0029] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0030] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0031] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with anembodiment, 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.

[0032] It shall be understood that although the terms “first,” “second,” ... , etc. in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0033] 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.

[0034] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0035] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0036] As used in this application, the term “circuitry” may refer to one or more or all of the following:(a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and(b) combinations of hardware circuits and software, such as (as applicable):(i) a combination of analog and / or digital hardware circuit(s) with software / firmware and(ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and(c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0037] 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 multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0038] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long TermEvolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB- loT) 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 invarious 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.

[0039] As used herein, the term “network device” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU) at an IAB donor node. An IAB node comprises a Mobile Terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0040] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications(e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0041] 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.

[0042] In Rel-18, there has been work to introduce AI / ML in the NG-RAN in 3GPP TSG RAN WG3. For this to happen, data collection enhancements are necessary. In Rel-18, three use cases were prioritized such as AI / ML-based Network Energy Saving (NES), load balancing and mobility optimization. In Rel-19, more use cases are expected to be considered for standardization such as AI / ML Coverage and Capacity Optimization (CCO) and AI / ML slicing enhancements. In parallel, a different work is ongoing in 3GPP TSG RAN WG1 where AI / ML intelligence in the UE is considered. For this work, different use cases are considered such as AI / ML beam optimization, AI / ML positioning enhancements and AI / ML CSI prediction. So even though the use cases that were considered for NG-RAN AI / ML in 3GPP were gNB-CU centric, pertaining to the higher layers of the protocol stack, the use cases considered in 3GPP TSG RAN WG1 are gNB-DU centric, pertaining to the lower cases of the protocol stack.

[0043] Data collection is an important process for algorithm operation. Datacollection has been in discussions also in the context of AI / ML operations. Data collection is an important process that enables an AI / ML model training entity to collect the needed measurements for training. Training of an AI / ML model may be online or offline. Offline training typically assumes non real-time training e.g., in a Non-Real Time RAN Intelligent Controller (RIC), specified by the O-RAN Alliance, or Operation Administration and Maintenance (OAM), using an already collected data set. In some examples, offline training can happen at a vendor-specific Over the Top (OTT) server. In online training an AI / ML Model is (typically) trained continuously in near real-time Near-RT RIC (Near-RT RIC), specified by the 0-RAN Alliance, with the arrival of new training data samples. Online training can be performed in the gNB or in gNB-CU, gNB-CU-CP, gNB-CU-UP or gNB-DU in case of split architecture or in the UE itself.

[0044] In certain training scenarios it is important for the AI / ML Training entity to be able to collect data from the same UE across RRC state transitions. This may have the following benefits: It can facilitate the data preparation process if, for example, a measurement is taken from the “same” UE in different RRC states. This is because measurements such as Reference Singal Receiving Power (RSRP) or Reference Signal Receiving Quality (RSRQ) measurements may have a large deviation across chip vendors. To be able to compare the different values reported by different UEs data preparation will need to normalize these values per UE implementation. If Minimization of Drive Test (MDT) can correlate measurements from the same UE across RRC states then this normalization is not needed since the same UE will be giving the same error in the data measurements and data preparation becomes easier. When data is collected to train a trajectory prediction ML Model it is easier to predict trajectories by collecting (time-series) of location data from the same UE. This is because any two UEs cannot be assumed to be located at the same location so it is hard to deduce if they are part of the same (identical) trajectory or they belong to two different trajectories. This determination could create errors by erroneously merging logs from different UEs. Those errors could be avoided if trajectory information is collected per UE. Different algorithms for mobility are used in idle and connected mode. The UEwill use an algorithm for cell reselection in idle mode (with some parameters provided via network configuration), while connected mode mobility is entirely under network control but the network can also apply mobility policies differentiated per UE. This is one more reason to avoid erroneously merging logs from different UEs.

[0045] Furthermore, the importance of continuous data collection across RRC states was recognized in AI / ML for NG-RAN discussions. MDT is a promising data collection method for offline AI / ML training e.g., in the 0AM. It was agreed that the MDT framework is used as a baseline for data collection from UE. In these discussions, the concept of “continuous MDT” was defined. Continuous MDT collection is an MDT data collection that enables to collect data from the same UE across RRC states, e.g., an RRC connected state, i.e., RRC CONNECTED, or an RRC non-connected state, i.e., RRC IDLE or RRC INACTIVE.

[0046] Signaling-based MDT activation provides a continuous data collection (across RRC states) for a given UE since 0AM knows which trace sessions are activated per UE and CN (e.g., AMF) may store the signaling-based MDT configuration and configure a specific UE when it connects to the network. Since CN activates immediate MDT every time a specific UE connects to the network and since UE autonomously activates logged MDT measurements every time it transits to RRC IDLE state continuous measurements can be provided and there won’t be any interruption of the measurement series. Note that transitions between RRC INACTIVE and RRC CONNECTED have a similar behavior as the transitions between RRC IDLE and RRC CONNECTED.

[0047] However, signaling based MDT has scalability issues when selecting large number of UEs and lacks cell-level granularity. Since UE location, e.g. at cell level, is typically not known by the CN, signaling-based activation is not suitable for certain scenarios where the chosen UEs need to be located in a certain area, characterized by a cell or set of cells or by specific radio conditions (cell edge, beams , etc...).

[0048] Management-based MDT provides the advantage of being scalable when selecting large number of UEs. However, current management-based MDT mechanism cannot identify and group together MDT reports collected from the same UE across RRC states.

[0049] In addition, in management-based MDT UE selection is left to RAN implementation and it is not controllable by 0AM.

[0050] Some agreements associated with AI / ML involving the UE are listed as below:Table 1

[0051] Therefore, according to those agreements, a gNB is an entity that may configure a UE to initiate and terminate the data collection procedure. In that sense, a gNB terminating the data collection procedure may also train an AI / ML Model using the collected measurements if it has an AI / ML Training capability. Training at a gNB may be online or offline or may involve retraining of an existing AI / ML Model.However, since there is no permanent UE ID in the RAN, it is not possible for a gNB to maintain continuity in the data collection for a specific UE when UE transition to RRC IDLE state happens. Upon transition to RRC IDLE, the UE context is lost andtherefore, a gNB cannot deduce that measurements it has collected from a UE before an RRC transition to IDLE and the measurements it has collected from a UE that connects to it later in time pertain to measurements from the same UE. This problem, naturally, exists also when a UE transits to RRC IDLE state in a gNB and re-connects to a different gNB.

[0052] A similar issue exists in 0-RAN deployments where a Near-Real Time RIC may have E2 interfaces with multiple gNBs and ML training is to be performed in the Near-Real Time RIC. In this case the Near-Real Time RIC may need to initiate continuous data collection (across RRC states) for a given UE.

[0053] The present disclosure proposes a mechanism for continuous measurements for AI / ML in RAN. In this solution, a DCE of a RAN provides to a RAN node, a GUCI and at least one selection criteria for selecting a user device for a data collection. The at least one selection criteria may be related to a characteristic of the user device, a connection state of the user device, or a type of operation of the user device, or be related to training, executing or monitoring a certain AI / ML Model either at the user device or for which the user device is providing input data as part of the data collection process. The RAN node selects, based on the at least one selection criteria, one or more user devices for the data collection and collect measurement data from the one or more user devices.

[0054] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0055] FIG. 1 shows an example communication network 100 in which embodiments of the present disclosure may be implemented. As shown in FIG. 1, the communication network 100 may include user devices 130-1 and 130-2 and RAN nodes 120-1, 120-2, 120-3. Hereinafter each of the user devices 130-1 and 130-2 may also be referred to a UE, and each of RAN nodes 120-1, 120-2, 120-3 may also be referred to a gNB. The user devices 130-1 and 130-2 each may communicate with at least one of RAN nodes 120-1, 120-2, 120-3.

[0056] The communication network 100 may further include a DCE 110, which may be deployed at the RAN and communicate with RAN nodes 120-1, 120-2, 120-3. For example, the DCE 110 may be comprised in a RAN node. In case of split architecture,the DCE 110 may be a gNB-CU, a gNB-CU-CP, a gNB-CU-UP, or a gNB-DU. As another example, the DCE 110 may also operate as an individual entity. In some examples, the DCE 110 can be a RIC node or 0AM or an OTT server that may belong to a user device vendor. In some cases, for example, in an AI / ML scenario, the DCE may also be considered as Machine Learning Collection Entity (MTCE). It is also possible that the MTCE may be instantiated into a RAN node, a RIC node or in 0AM. In one alternative MTCE is inside a UE vendor server initiating data collection for a certain UE type or UE category.

[0057] The communication network 100 may further include an AMF 140, which may act as a core network node for access and mobility management. The AMF 140 may communicate with RAN nodes 120-1, 120-2, 120-3.

[0058] Hereinafter the user devices 130-1 and 130-2 may also be referred to a user device 130 collectively, and RAN nodes 120-1, 120-2, 120-3 may also be referred to a RAN node 120.

[0059] It is to be understood that the number of network nodes and user devices shown in FIG. 1 is given for the purpose of illustration without suggesting any limitations. The communication network 100 may include any suitable number of network devices and terminal devices.

[0060] Communications in the communication environment 100 may be implemented according to any proper communication protocol(s), includes, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), 5G, the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, includes but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), FDD, TDD, Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and / or any other technologies currently known or to be developed in the future.

[0061] Hereinafter, an example process of a main concept of the present disclosure will be described in detail below with reference to FIG. 2, and more example embodiments of the present disclosure will be described in detail below with reference to FIGS. 3-8.

[0062] It is to be understood that the data collection of the procedure associated with FIGS. 2-8 may refer a ML model-based data collection. The DCE of a RAN may be considered as an MTCE, which may be comprised or not be comprised in a RAN node.

[0063] The terms “GUCI label” used hereinafter may comprise at least the GUCI and a UE identifier allocated by NG-RAN node enabling the DCE to uniquely identify which GUCI and which UE the measurement report corresponds to and optionally which gNB had selected this UE.

[0064] Reference is now made to FIG. 2, which shows a signaling chart 200 for communication according to some example embodiments of the present disclosure. As shown in FIG. 2, the signaling chart 200 involves the user device 130, the DCE 110, the RAN node 120 and the AMF 140. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 200.

[0065] It is to be understood that the operation performed by the RAN node 120 may also be performed, for example, by the RAN node 120-1, the RAN node 120-2 and / or the RAN node 120-3 as shown in FIG. 1.

[0066] As shown in FIG. 2, in an initiation phase, the DCE 110 determines (202) a GUCI and at least one selection criteria for selecting a user device for a data collection and send (204) the GUCI and the at least one selection criteria for user device selection to the RAN node 120, the at least one selection criteria is related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device. That is, the at least one selection criteria may be associated with a UE characteristic, a UE capability or a UE connection, e.g., in an RRC connected state or a non-RRC connected state, such as an RRC idle or RRC inactive. The "type of operation" used herein may be refer to activity (high / low throughput, network slice(s), QoS types, serving PLMN, etc.). It is also possible that the at least one selection criteria may be related to training, executing or monitoring a certain AI / ML model either at the user device or for which the user device is providing input data as part of the datacollection process.

[0067] For example, the DCE 110 may send the GUCI and the at least one selection criteria via a data collection request for the data collection. The RAN node 120 then obtains the information from the data collection request. As another example, the DCE 110 may send this information through an internal message if DCE is inside the RAN node.

[0068] In addition to the GUCI and the at least one selection criteria, the data collection request may also comprise a pre-determined number of user devices to be selected for the data collection, a GUCI priority value associated with the data collection request, and / or information of a pre-configured set of measurements to be performed for the data collection. In some embodiments, a GUCI may be in the form of (DCE ID, Collection ID), may refer to a MeasConf ID which is a pointer to a preconfigured set of measurements.

[0069] That is, a DCE 110 may send to the RAN node 120, a collection request to collect measurements in RRC CONNECTED / RRC INACTIVE / RRC IDLE state for one or more UEs satisfying one or more criteria associated with the UE e.g. a UE characteristic, a UE capability or criteria related to UE connection. More details will be described with reference to FIGS. 3 and 4 later.

[0070] Upon receiving the information, the RAN node 120 may determine (206) which user device(s) is / are to be selected for the data collection at least based on the at least one selection criteria for user device selection. That is, the one or more user devices are selected to collect measurements in RRC CONNECTED / RRC INACTIVE / RRC IDLE state. If the pre-determined number of user devices to be selected for the data collection is indicated, the RAN node 120 may consider the number of user devices.

[0071] After one or more user devices (e.g., the user device 130) are selected for the data collection, the RAN node 120 may assign respective identification values for the one or more selected user devices. In some embodiments, identification value of a user device indicates an identifier of the user device which is a unique identification of user device in the apparatus for the GUCI and the at least one selection criteria. For example, the identification value includes an identification of the apparatus which has receivedthe data collection request.

[0072] Then the RAN node 120 may configure one or more measurements associated with the data collection and send the configuration of the one or more measurements to the selected one or more user devices. The RAN node 120 may configure the one or more user devices to collect date in RRC connected mode, RRC idle mode and / or RRC inactive mode. For example, the RAN node 120 sends (208) the configuration of the one or more measurements to the user device 130 and collect the measurement data of the one or more measurements corresponding to the requested GUCI from the user device 130.

[0073] As an example, the RAN node 120 may store the measurement data of the one or more measurements corresponding to the requested GUCI and generate a collection report based on the measurement data the one or more measurements.

[0074] Then the RAN node 120 may send (210) the collection report to the DCE 110. Whenever the RAN node 120 sends a measurement report to DCE 110 it is associated with a GUCI label. The GUCI label comprises at least the GUCI and an identifier of the user device allocated by the RAN node 120 enabling the DCE 110 to uniquely identify which GUCI and which user device the measurement report corresponds to. Optionally the GUCI label may further comprise an identifier of the RAN node 120. This enables the DCE 110 to correlate (212) measurements reports for post-processing per selection criteria (i.e. per GUCI), per user device, or even per selected RAN node.

[0075] For example, the RAN node 120 may send (210) the collection report to the DCE 110 when a period of the data collection ends. It is also possible that the RAN node 120 may send (210) the collection report to the DCE 110 upon receiving a request of the measurement report from the DCE or reaching a maximum number or volume of stored measurement data. As another example, the RAN node 120 may send (210) the collection report to the DCE 110 when an RRC state of changes.

[0076] In some embodiments, if the RAN node 120 determines that the data collection associated with the GUCI is to be stopped, the RAN node 120 derives (214) an identification of the DCE from the GUCI or the identifier or the address of the DCE contained in the GUCI and transmits (216), to the DCE, one or more collection reports including measurement data stored at the apparatus along with an associated GUCIlabel comprising a pre-determined GUCI, and / or an identification value of a user device associated with the data collection.

[0077] The RAN node 120 may also generate Data Collection (DC) context comprising one or more GUCI labels, each GUCI label identifying a GUCI corresponding to a data collection request and including at least the identification value of at least one selected user device from which measurement data was collected. Then the RAN node 120 may transmit (218) to an AMF, the generated data collection context when the RAN node determines that the user device 130 is transitioning to an RRC Idle or Inactive state. In some embodiments, the DC context mentioned herein may refer to, but not be limited to an Al context.

[0078] In a continuation phase, if the user device 130, for which the AMF 140 stores an active DC context in the AMF UE context, gets RRC connected in a RAN node 120, the AMF 140 may include the DC context (which has been transparently stored) in the NGAP Initial Context setup request message and send (220) the NG Initial context setup request including the DC context to the RAN node 120.

[0079] That is, the RAN node 120 may obtain, from an AMF 140, at least one GUCI label from a data collection context associated with a user device context or a user device connection. The GUCI label comprises at least a GUCI and / or an identification value of the user device. For example, the identification value may include an identification of a RAN node. The information received in the DC context may also contain a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements.

[0080] If the information received in the DC context does not contain a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements, then the RAN node 120 may transmit (222), to DCE 110, a GUCI fetch request at least indicating a target GUCI obtained from the at least one GUCI label. The DCE 110 may response (224) the RAN 120 with information of one or more sets of measurements to be performed associated with the target GUCI for the data collection.

[0081] Based on the information, the RAN node 120, collect (226) the measurement data corresponding to the received GUCI. In some embodiments, the RAN node 120collect measurement data of the one or more sets of measurements associated with the target GUCI from the user device and store the measurement data.

[0082] In some embodiments, the RAN node 120 may further generate (228) a collection report based on the measurement data and transmit (230), to the DCE 110, the collection report together with an associated GUCI label including at least the target GUCI and the identification value of the user device from which measurement data was collected.

[0083] Optionally, the RAN node 120 may also transmit (230), to the AMF 140, a set of GUCI labels corresponding to a user device context or user device connection. The GUCI labels are associated measurement data of one or more sets of measurements collected from the user device.

[0084] For example, the RAN node 120 may transmit a set of GUCI labels corresponding to a user device context or user device connection to the AMF 140 in response to a transition of the user device from an RRC connected state into an RRC non-connected state. As another example, the RAN node 120 may transmit a set of GUCI labels corresponding to a user device context or user device connection to the AMF 140 in response to a decision to handover the user device to another radio access node.

[0085] The procedure shown in FIG. 2 explains a main concept of the solution for continuous measurements for AI / ML in RAN. More details of different example embodiments will be further described in detail with reference to FIGS. 3-8.

[0086] Reference is now made to FIG. 3, which shows a signaling chart 300 for communication according to some example embodiments of the present disclosure. As shown in FIG. 3, the signaling chart 300 involves the user device 130-1, the user device 130-2, the DCE 110, the RAN node 120-1, the RAN node 120-2 and the AMF 140. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 300.

[0087] As shown in FIG. 3, Step 1 : DCE 110 decides (302) to train for user devices matching certain criteria and assigns a GUCI for that. As the DCE 110 may be considered as an MTCE, the GUCI may uniquely identify the MTCE equipment (MTCE ID), and uniquely identifies the collection request within this MTCE equipment(Collection ID). The GUCI is typically in the form of GUCI = (MTCE ID, Collection ID). In this option, the DCE 110 sends the same GUCI to all RAN nodes (e.g., RAN node 120-1 and RAN node 120-2) it wants to involve in the training or inference process. As an embodiment, the MTCE ID and Collection ID may be aggregated into a common URI.

[0088] The DCE 110 sends (304) the collection request to RAN node 120-1 including the GUCI, the at least one selection criteria, and optionally a maximum or desired of number of use devices to be involved for the collection and / or a GUCI priority value associated with the request. It may also indicate a reporting policy criterion (e.g. reporting at every measurement, periodic reporting, termination reporting criteria (e.g. collection duration or number of measurements reached)). The DCE may also optionally include a measurement configuration. In addition, the GUCI may also refer to a MeasConf ID which is a pointer to a pre-defined / pre-configured set of measurements. As an embodiment, the MTCE ID and Collection ID may be aggregated into a common URI.

[0089] Similarly, the DCE 110 sends (306) the collection request to RAN node 120- 2 with similar information.

[0090] The RAN node (e.g., RAN node 120-1 and RAN node 120-2) may handle the collection request selecting one or more user devices matching the received selection criteria. The RAN node may assign to a user device an identification value z (any identifier which is unique in this gNB for this GUCI e.g. z=4 if this is the fourth selected user device for this GUCI request).

[0091] If GUCI priority is received, it takes it into account to determine the priority of the request compared to other requests in case any limitation of resources apply. If a recommended or maximum number of user devices is received it takes it into account.

[0092] The RAN node 120-1 and / or RAN node 120-2 collects (308) measurements during the RRC connected / inactive / idle phase. The measurements to be collected are the ones according to measurement configuration received in the request, if received, otherwise according to measurements configured in advance by 0AM per matching GUCI or per matching Collection ID within the GUCI or otherwise RAN node 120-1 and / or RAN node 120-2 may have received in the request a MeasConf ID pointing topre-defined / pre-configured set of measurements, or alternatively RAN node 120-1 and / or RAN node 120-2 may trigger a GUCI fetch procedure towards the DCE 110 where it includes the GUCIx and receives in response from DCE 110 the corresponding measurements to be collected or an equivalent MeasConfig ID pointer. The GUCI fetch procedure may alternatively be directed to a RAN node, such as the RAN node which had selected the user device for the GUCI x.

[0093] The RAN node 120-1 may configure (310) the user device 130-1 if needed to collect the requested measurements in RRC active / inactive / idle state. Similarly, the RAN node 120-2 may configure (312) the user device 130-2 if needed to collect the requested measurements in RRC active / inactive / idle state.

[0094] As an option, if the RAN node 120-2 has been requested to report to DCE 110 at every measurement, when a measurement is received from user device 130-2 or available in RAN node 120-2, the RAN node 120-2 sends (314) it back to DCE 110 including at least a GUCI label identifying the GUCI, the ID of the RAN node 120-2 and the identification value z (an identifier, e.g., z=4) of the user device 130-2 in the RAN node 120-2. In the example of gNB2, GUCI label = (GUCI1, gNB2, UE4).

[0095] As another option, if the RAN node 120-1 has not been requested to report to DCE 110 at every measurement report available, the RAN node 120-1 may store (316) every measurement report when made available or when received from the user device 130-1, and associates to this measurement report at least a GUCI label identifying the GUCI, the ID of the RAN node 120-1 and the identification value z (an identifier, e.g., z=7) of the user device 130-1 in the RAN node 120-1. In the example of RAN node 120-1, GUCI label = (GUCI1, gNBl, UE7). This measurement report can be sent to DCE 110 later at the end of collection period or upon a DCE request.

[0096] In some embodiments, at the end of the RRC connected phase, the RAN node 120-1 sends (318) the NGAP UE context release complete message to AMF 140 including the DC Context. The DC context sent to AMF comprises the list of GUCI labels corresponding to measurement reports of measurements carried out during the RRC connected phase. In the example of FIG. 3, assuming a given UE (e.g., user device 130-1) has been selected in the RAN node 120-1 for a GUCI1 request and a GUCI8 request, the DC context= (GUCI1, gNBl, UE7, optional data to be reported, optional end of reporting information), (GUCI8, gNBl, UE7, optional data to be reported,optional end of reporting)).

[0097] A new RAN node that will handle the user device when it becomes CONNECTED again will need to know “data to be reported, end of reporting information". This information needs to be stored at AMF 140, or the new RAN node may need to fetch this information from DCE 110.

[0098] The AMF 140 may then store (320) the received DC context transparently in the AMF UE context for subsequent delivery to next RAN node at next RRC connected phase:

[0099] It is to be understood that a UE (i.e., a user device) within the CN has the SUPI / IMSI identity. When the UE is CONNECTED (has a RAN connection) there is a NGAP connection related with the UE. This NGAP connection is transient (lost / forgotten when the UE is IDLE, i.e., no more RAN connection and no more NGAP connection) and the AMF may associate this transient NGAP connection to the SUPI / IMSI context at the time this NGAP connection is created i.e., UE gets connected.

[0100] After collecting data from a UE, a RAN node may form the GUCI label as, say, (GUCI1, gNBl, UE7), i.e., RAN node assigns “7” as the UE ID for this UE. The data collection information (including gNBl, UE7) is provided to the AMF 140 over the NGAP connection at the release of the NGAP connection and then will be sent by AMF 140 to a new RAN node that will serve the UE. Because this comes over this NGAP association, the AMF 140 determines at this time of release of the NGAP association in which SUPI / IMSI context the DC context should be stored.

[0101] Reference is now made to FIG. 4, which shows a signaling chart 400 for communication according to some example embodiments of the present disclosure. As shown in FIG. 4, the signaling chart 400 involves the user device 130-1, the user device 130-2, the DCE 110, the RAN node 120-1, the RAN node 120-2 and the AMF 140. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 400.

[0102] The difference between embodiments shown in FIG. 3 and FIG. 4 is: the DCE 110 configures, in the procedure shown in FIG. 3, a same GUCI value (therefore Collection ID) to the various RAN nodes involved in a same request (with same UE selection criteria), while the DCE 110, configures, in the procedure shown in FIG. 4,different and specific GUCI values (therefore Collection IDs) to the various RAN node involved in a same request (with same UE selection criteria). Therefore, the DCE 110 is able to identify the to which RAN node a measurement belongs to from the received GUCI.

[0103] As shown in FIG. 4, The DCE 110 sends (404) the collection request to RAN node 120-1 including a first GUCI, e.g., GUCI 1 and the DCE 110 sends (406) the collection request to RAN node 120-2 including a second GUCI, e.g., GUCI 2. Other information included in the collection request may be same with the information described with reference to FIG. 3.

[0104] Corresponding to the different assigned GUCIs, the collection report generated by different RAN nodes may identify different GUCIs in the collection report. For example, the RAN node 120-2 send the collection report to the DCE 110 including a GUCI label comprises the GUCI value and the identification number z (e.g., z=4) of the UE (e.g., user device 130-2) in RAN node 120-2. Here GUCI label = (GUCI 2, UE4).

[0105] Similarly, for measurement reports stored, for example, at RAN node 120-1, the GUCI label may comprise the GUCI value and the identification value z (e.g. z=7) of the UE (e.g., user device 130-1) in RAN node 120-1. Here GUCI label = (GUCI 1, UE7).

[0106] It is to be understood that descriptions for other signaling exchanges in FIG. 4 that are same or similar with those of FIG. 3, will be omitted here.

[0107] Reference is now made to FIG. 5, which shows a signaling chart 500 for communication according to some example embodiments of the present disclosure. As shown in FIG. 5, the signaling chart 500 involves the user device 130-2 (was selected by the RAN node 120-2 for the data collection), the DCE 110, the RAN node 120-1, the RAN node 120-3 and the AMF 140. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 500.

[0108] As shown in FIG. 5, the AMF may determine (502) that a UE, for which the AMF stores an active DC context in the AMF UE context, gets RRC connected in a RAN node (e.g., the RAN node 120-3). The AMF may include the DC context (which has been transparently stored) in the NGAP Initial Context setup request message.

[0109] The RAN node 120-3 receives (504) the NG Initial context setup request including the DC context. Then the RAN node 120-3 decodes (506) the GUCI labels comprising the DC context. Depending on the collection request, each GUCI label may be encoded either as comprising at least (GUCIx, UEy) or as comprising at least (GUCIx, gNBy, UEz).

[0110] Besides, the RAN node 120-3 retrieves the measurements to be collected for this GUCI if not provided in the DC context. It can be configured with measurements to be collected associated with each GUCI value or associated with the Collection ID value within each received GUCI or it can be configured with default set of measurements to be collected or it can have received in the MeasConf ID pointing to pre-defined / pre-configured set of measurements.

[0111] Alternatively, the RAN node 120-3 may also trigger (508) a GUCI Fetch procedure towards the DCE 110 where it includes the GUCIx and receives (510) in response from DCE 110 the corresponding measurements to be collected or an equivalent MeasConfig ID pointer. The GUCI Fetch procedure may alternatively be directed to a RAN node, such as the RAN node which had selected the user device for the GUCI x.

[0112] Then the RAN node 120-3 starts (512) collecting the measurements. As part of the measurements collection, the RAN node 120-3 may configure (514) the user device 130-2 (was selected by the RAN node 120-2 for the data collection) with a subset of related measurements.

[0113] If the RAN node 120-3 has been requested to report to DEC 110 at every measurement report available, when a measurement is received from user device or available, the RAN node 120-3 sends (516) it back to DCE 110 including at least a GUCI label identifying (the GUCI, the ID of RAN node and the identification value z (e.g. z=4) of the user device in RAN node 120-2), or a GUCI label identifying (the GUCI, and the identification value z (e.g. z=4) of the user device in RAN node 120-2). In this example, GUCI label = (GUCI1, gNB2, UE4) or GUCI label = (GUCI2, UE4).

[0114] If the RAN node 120-3 has not been requested to report to DCE 110 at every measurement report available, the RAN node 120-3 stores (518) every measurement report when made available or when received from user device, and associates to thismeasurement report at least a GUCI label identifying (the GUCI, the gNB ID and the identification number z (or any identifier) of the user device in RAN node 120-2), or a GUCI label identifying (the GUCI, and the identification value z (e.g. z=4) of the user device in RAN node 120-2). In this example, GUCI label = (GUCI1, gNB2, UE4) or GUCI label =(GUCI2, UE4). This measurement report can be sent to DCE 110 later at end of collection period or upon a request of DCE 110.

[0115] At the end of the RRC connected phase, the RAN node 120-3 sends (520) the NGAP UE context release complete message to AMF 140 including the DC context. As an example, the DC context sent to AMF 140 may comprise the list of GUCI labels corresponding to measurement reports of measurements carried out during the RRC connected phase. If no change compared to DC context received in the NGAP initial Context setup, it may be omitted. AMF stores DC context in UE context.

[0116] It is to be understood that a UE (i.e., a user device) within the CN has the SUPI / IMSI identity. When the UE is CONNECTED (has a RAN connection) there is a NGAP connection related with the UE. This NGAP connection is transient (lost / forgotten when the UE is IDLE, i.e., no more RAN connection and no more NGAP connection) and the AMF may associate this transient NGAP connection to the SUPI / IMSI context at the time this NGAP connection is created i.e., UE gets connected.

[0117] After collecting data from a UE, a RAN node may form the GUCI label as, say, (GUCI1, gNBl, UE7), i.e., RAN node assigns “7” as the UE ID for this UE. The data collection information (including gNBl, UE7) is provided to the AMF 140 over the NGAP connection at the release of the NGAP connection and then will be sent by AMF 140 to a new RAN node that will serve the UE. Because this comes over this NGAP association, the AMF 140 determines at this time of release of the NGAP association in which SUPI / IMSI context the DC context should be stored.

[0118] Reference is now made to FIG. 6, which shows a signaling chart 600 for communication according to some example embodiments of the present disclosure. As shown in FIG. 6, the signaling chart 600 involves the DCE 110, the RAN node 120-1 and the AMF 140. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 600.

[0119] As shown in FIG. 6, the RAN node 120-1 decides (602) to stop data collectionfor GUCI 1 due to e.g. duration elapsed, max N number of packages stored for GUCI or for Collection ID, explicit request from DCE 110. Then the RAN node 120-1 may derive the address of DCE 110 from the GUCI or the DCE ID (e.g., MTCE ID (node ID) contained in the GUCI.

[0120] The RAN node 120-1 sends (604) the N stored measurement collection packages corresponding to GUCI 1 to the DCE 110 associated with the corresponding GUCI label. GUCI label = (GUCI1, gNBl, UE7) or (GUCI1, UE7).

[0121] In some embodiments, at the end of an RRC connected phase, the RAN node 120-1 sends (606) the NG UE context release complete message to the AMF 140 where it includes the updated DC context. The updated DC context no longer includes GUCI 1 due to its termination. The DC context stores and replaces the existing one in the AMF UE context.

[0122] Similar with the procedure associated with signaling exchanges 602-606, in the case where the measurement request for GUCI 1 which terminates was the last one, the NGAP UE context release request may contain either no DC context or an empty DC context. AMF stores the DC context in UE context.

[0123] It is to be understood that a UE (i.e., a user device) within the CN has the SUPI / IMSI identity. When the UE is CONNECTED (has a RAN connection) there is a NGAP connection related with the UE. This NGAP connection is transient (lost / forgotten when the UE is IDLE, i.e., no more RAN connection and no more NGAP connection) and the AMF may associate this transient NGAP connection to the SUPI / IMSI context at the time this NGAP connection is created i.e., UE gets connected.

[0124] After collecting data from a UE, a RAN node may form the GUCI label as, say, (GUCI1, gNBl, UE7), i.e., RAN node assigns “7” as the UE ID for this UE. The data collection information (including gNBl, UE7) is provided to the AMF 140 over the NGAP connection at the release of the NGAP connection and then will be sent by AMF 140 to a new RAN node that will serve the UE. Because this comes over this NGAP association, the AMF 140 determines at this time of release of the NGAP association in which SUPI / IMSI context the DC context should be stored.

[0125] In some embodiments, an Xn handover or an NG handover during the connected phase from a source RAN node to a target RAN node, the correspondingprocedure will be described with reference to FIG. 7 and FIG. 8.

[0126] Reference is now made to FIG. 7, which shows a signaling chart 700 for communication according to some example embodiments of the present disclosure. As shown in FIG. 7, the signaling chart 700 involves the DCE 110, the RAN node 120-1, the RAN node 120-2 and the AMF 140. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 700.

[0127] The source RAN node (hereinafter may be referred to the RAN node 120-1) has current DC context = (GUCI label 1, GUCI label2) at time of triggering an Xn handover.

[0128] As an option, the RAN node 120-1 includes the DC context in the Xn handover request message and sends (702) it to a target RAN node (hereinafter may be referred to the RAN node 120-2).

[0129] As another option, the RAN node 120-1 sends (704) a UE context notification indication to AMF 140 containing the DC context before triggering the Xn handover to the RAN node 120-2. The RAN node 120-1 sends (706) an Xn handover request.

[0130] After handover execution (708), the RAN node 120-2 sends (710) a path switch request message to AMF 140. The AMF includes the DC context earlier received and sends (712) it in the NG Path Switch Request Acknowledge message to the RAN node 120-2.

[0131] Alternatively, instead of including the DC context in the NG Path Switch Request Acknowledge message, the AMF 140 may include the DC context in an NG UE context modification request message and sent it to the RAN node 120-2 after the NG path switch request acknowledge message.

[0132] Then for both options as described above, after receiving the DC context, the RAN node 120-2 may trigger the new GUCI fetch procedure to retrieve the necessary measurement configuration(s) corresponding to GUCI labels, otherwise may be preconfigured by 0AM.

[0133] Reference is now made to FIG. 8, which shows a signaling chart 800 for communication according to some example embodiments of the present disclosure. As shown in FIG. 8, the signaling chart 800 involves the DCE 110, the RAN node 120-1,the RAN node 120-2 and the AMF 140. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 800.

[0134] The source RAN node (hereinafter may be referred to the RAN node 120-1) has current DC context = (GUCI label 1, GUCI label2) at time of triggering an NG handover.

[0135] As shown in FIG. 8, as an option, the RAN node 120-1 includes the DC context in the source to target container which is transparently relayed by AMF 140 inside the NG Handover Required message and the NG Handover Request message. The RAN node 120-1 sends (802) the NG Handover Required message to the AMF 140. The AMF 140 sends (804) the NG Handover Request message to the target RAN node (hereinafter may be referred to the RAN node 120-2).

[0136] As another option, the RAN node 120-1 sends (806) the DC context to AMF 140 within the NG handover required message.

[0137] Then the AMF 140 sends (808) the DC context to the RAN node 120-2 within the NG handover request message.

[0138] Alternatively, the AMF 140 may sends (812) the DC context to the RAN node 120-2 within an NG UE context modification request message sent after the handover execution (810).

[0139] Then for both options as described above, after receiving the DC context, the RAN node 120-2 may trigger the new GUCI fetch procedure to retrieve the necessary measurement configuration(s) corresponding to GUCI labels, otherwise may be preconfigured by 0AM.

[0140] In this way, the solution proposed in the present disclosure enables to make model training or interference using multiple UEs corresponding to a certain criterion, and across RRC connected / inactive / idle phases. It extends continuity in tracing mechanisms and addresses more general scenarios of data collection.

[0141] Furthermore, it may also enable to train at different granularity: per GUCI, per GUCI / gNB or per GUCI / gNB / UE, per list of GUCI / selected UEs or per list of GUCI / gNB / selected UEs.

[0142] FIG. 9 shows a flowchart of an example method 900 implemented at anapparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 900 will be described from the perspective of the RAN node 120 in FIG. 1.

[0143] At block 910, the RAN node 120 obtains, from a DCE of a radio access network, a GUCI and at least one selection criteria for selecting a user device for a data collection. The at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device.

[0144] At block 920, the RAN node 120 selects, based on the at least one selection criteria, one or more user devices for the data collection.

[0145] At block 930, the RAN node 120 collects measurement data from the one or more user devices.

[0146] In some example embodiments, the method 900 further comprises: receiving a data collection request for the data collection from the DCE; and obtaining the GUCI and the at least one selection criteria from the data collection request.

[0147] In some example embodiments, the data collection request further comprises at least one of the following: a pre-determined number of user devices to be selected for the data collection, or a GUCI priority value associated with the data collection request, or information of a pre-configured set of measurements to be performed for the data collection.

[0148] In some example embodiments, the method 900 further comprises: assigning respective identification values for the one or more selected user devices, wherein an identification value of a user device indicates an identifier of the user device which is a unique identification of user device in the apparatus for the GUCI and the at least one selection criteria.

[0149] In some example embodiments, the identification value includes an identification of the apparatus which has received the data collection request.

[0150] In some example embodiments, the method 900 further comprises: in accordance with a request that collected data is to be reported for one or more measurements, generating a collection report at least including a GUCI label comprising at least the GUCI, and the identification value of the user device from whichmeasurement data was collected corresponding to the data collection request; and transmitting the collection report to the DCE.

[0151] In some example embodiments, the method 900 further comprises: storing measurement data of a set of measurements performed by at least one of the at least one selected user devices corresponding to the data collection request; generating a collection report based on the measurement data of the set of measurements; and transmitting, to the DCE, the collection report together with a GUCI label identifying the GUCI, and including at least the identification value of the at least one selected user device from which measurement data was collected.

[0152] In some example embodiments, the method 900 further comprises: transmitting the collection report to the DCE in response to at least one of: the end of a period of the data collection, or receiving a request of the measurement report from the DCE, or reaching a maximum number or volume of stored measurement data, or a change of an RRC state of a selected user device.

[0153] In some example embodiments, the method 900 further comprises: in accordance with a determination that the data collection associated with the GUCI is to be stopped, deriving an identification of the DCE from the GUCI or the identifier or the address of the DCE contained in the GUCI; and transmitting, to the DCE, one or more collection reports including measurement data stored at the apparatus along with an associated GUCI label comprising at least one of the following: a pre-determined GUCI, an identification value of at least one user device associated with the data collection.

[0154] In some example embodiments, the method 900 further comprises: generating a Data Collection, DC, context comprising one or more GUCI labels, each GUCI label identifying a GUCI corresponding to a data collection request and including at least one of the identification value of the at least one selected user device from which measurement data was collected and information of a pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements.

[0155] In some example embodiments, the method 900 further comprises: determining that a user device is transitioning to an RRC Idle state, and transmitting,to an AMF, the generated data collection context.

[0156] In some example embodiments, the method 900 further comprises: in accordance with an Xn handover during the RRC connected state of a user device from the apparatus to a further network node, transmitting, to the further network node, an Xn handover request for the user device including the DC context associated with the GUCI.

[0157] In some example embodiments, the method 900 further comprises: in accordance with an Xn handover during the RRC connected state of a user device from the apparatus to a further network node, transmitting, to an AMF, a UE context notification indication including the DC context associated with the GUCI.

[0158] In some example embodiments, the method 900 further comprises: in accordance with an NG handover during the RRC connected state of a user device, transmitting, to an AMF, an NG Handover Required message including the DC context associated with the GUCI.

[0159] In some example embodiments, the data collection relates to a machine learning model-based data collection.

[0160] In some example embodiments, the apparatus comprises a radio access network node.

[0161] In some example embodiments, the DCE comprises a model training collection entity.

[0162] In some example embodiments, the DCE is comprised in a radio access network node.

[0163] FIG. 10 shows a flowchart of an example method 1000 implemented at an apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1000 will be described from the perspective of the RAN node 120 in FIG. 1.

[0164] At block 1010, the RAN node 120 obtains, from an AMF, at least one globally unique collection identifier, GUCI, label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device and / or information of apre-configured set of measurements to be performed for the data collection or a set of measurements requirements.

[0165] At block 1020, the RAN node 120 collects the measurement data corresponding to the received GUCI.

[0166] In some example embodiments, the identification value includes an identification of a radio access node.

[0167] In some example embodiments, the method 1000 further comprises: transmitting, to a data collection entity, DCE, of a radio access network, a GUCI fetch request at least indicating a target GUCI obtained from the at least one GUCI label; and obtaining, from the DCE, information of one or more sets of measurements to be performed associated with the target GUCI for the data collection.

[0168] In some example embodiments, the method 1000 further comprises: collecting measurement data of the one or more sets of measurements associated with the target GUCI from the user device in a radio resource control, RRC, connected state and / or non-connected state; and storing the measurement data.

[0169] In some example embodiments, the method 1000 further comprises: generating a collection report based on the measurement data; and transmitting the collection report to a DCE together with an associated GUCI label including at least the target GUCI and the identification value of the user device from which measurement data was collected.

[0170] In some example embodiments, the method 1000 further comprises: transmitting, to the AMF, a set of GUCI labels corresponding to a user device context or user device connection, wherein the GUCI labels are associated measurement data of one or more sets of measurements collected from the user device.

[0171] In some example embodiments, the method 1000 further comprises: transmitting, to the AMF, the set of GUCI labels in response to at least one of the following: a transition of the user device from an RRC connected state into an RRC non-connected state, or a decision to handover the user device to another radio access node.

[0172] In some example embodiments, the method 1000 further comprises: receiving,from a user device, a set of measurement data collected by the user device in RRC idle or RRC inactive state and an associated Data Collection, DC, context comprising at least one GUCI or one GUCI label; and performing at least one of: storing the received measurement data together with the GUCI or GUCI label; sending to the DCE the received measurement data as a collection report together with the corresponding received GUCI or GUCI label; retrieving a collection data request corresponding to the received GUCI or GUCI label and triggering additional collection data; or including the received GUCI or GUCI label in a DC context and sending the DC context to an AMF.

[0173] In some example embodiments, the data collection relates to a machine learning model-based data collection.

[0174] In some example embodiments, the apparatus comprises a radio access network node.

[0175] In some example embodiments, the DCE comprises a model training collection entity.

[0176] In some example embodiments, the DCE is comprised in a radio access network node.

[0177] FIG. 11 shows a flowchart of an example method 1100 implemented at an apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1100 will be described from the perspective of the DCE 110 in FIG. 1.

[0178] At block 1110, the DCE 110 transmits, to a radio access network node, a globally unique collection identifier, GUCI, and at least one selection criteria for selecting a user device for a data collection. The at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device. The at least one selection criteria may also be AI / ML specific and user devices may be user devices in need of training, executing or monitoring of a certain AI / ML Model or for which the user device is providing input data as part of the data collection process.

[0179] At block 1120, the DCE 110 receives, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification valueassociated with a user device selected according to the at least one selection criteria.

[0180] In some example embodiments, the method 1100 further comprises: transmitting, to the radio access network node, the GUCI and the at least one selection criteria via a data collection request for the data collection.

[0181] In some example embodiments, the data collection request further comprises at least one of the following: a pre-determined number of user devices to be selected for the data collection, or a GUCI priority value associated with the data collection request, or information of a pre-configured set of measurements to be performed for the data collection.

[0182] In some example embodiments, the identification value of the user device indicates an identifier of the user device which is a unique identification of user device in the radio access network node which has selected the user device for the GUCI and the at least one selection criteria.

[0183] In some example embodiments, the identification value includes an identification of the radio access network node which has received the data collection request.

[0184] In some example embodiments, the method 1100 further comprises: receiving a GUCI fetch request including at least a GUCI; and transmitting in response to the GUCI fetch request information of one or more sets of measurements to be performed associated with the target GUCI.

[0185] In some example embodiments, the method 1100 further comprises: receiving one or more collection reports, each including or associated with a GUCI label comprising at least an identification value of a user device; and correlating the measurement reports which have the same identification value to pertain to the same user device.

[0186] In some example embodiments, the method 1100 further comprises: receiving one or more collection reports, each including or associated with a GUCI label comprising at least an identification value of a user device which includes a radio access node identity; and correlating the measurement reports which identification value contains the same radio access node identity.

[0187] In some example embodiments, the method 1100 further comprises: receiving one or more collection reports, each including or associated with a GUCI label comprising at least a GUCI and an identification value of a user device; and correlating the measurement reports which have the same GUCI value.

[0188] In some example embodiments, the data collection relates to a machine learning model-based data collection.

[0189] In some example embodiments, the apparatus comprises a radio access network node.

[0190] In some example embodiments, the DCE comprises a model training collection entity.

[0191] In some example embodiments, the DCE is comprised in a radio access network node.

[0192] In some example embodiments, an apparatus capable of performing any of the method 900 (for example, the RAN node 120 in FIG. 1) may comprise means for performing the respective operations of the method 900. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The apparatus may be implemented as or included in the RAN node 120 in FIG. 1.

[0193] In some example embodiments, the apparatus comprises means for obtaining, from a DCE of a radio access network, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device ; means for selecting, based on the at least one selection criteria, one or more user devices for the data collection; and means for collecting measurement data from the one or more user devices.

[0194] In some example embodiments, the apparatus comprises means for receiving a data collection request for the data collection from the DCE; and means for obtaining the GUCI and the at least one selection criteria from the data collection request.

[0195] In some example embodiments, the data collection request further comprises at least one of the following: a pre-determined number of user devices to be selectedfor the data collection, or a GUCI priority value associated with the data collection request, or information of a pre-configured set of measurements to be performed for the data collection.

[0196] In some example embodiments, the apparatus comprises means for assigning respective identification values for the one or more selected user devices, wherein an identification value of a user device indicates an identifier of the user device which is a unique identification of user device in the apparatus for the GUCI and the at least one selection criteria.

[0197] In some example embodiments, the identification value includes an identification of the apparatus which has received the data collection request.

[0198] In some example embodiments, the apparatus comprises means for, in accordance with a request that collected data is to be reported for one or more measurements, generating a collection report at least including a GUCI label comprising at least the GUCI, and the identification value of the user device from which measurement data was collected corresponding to the data collection request; and means for transmitting the collection report to the DCE.

[0199] In some example embodiments, the apparatus comprises means for storing measurement data of a set of measurements performed by at least one of the at least one selected user devices corresponding to the data collection request; means for generating a collection report based on the measurement data of the set of measurements; and means for transmitting, to the DCE, the collection report together with a GUCI label identifying the GUCI, and including at least the identification value of the at least one selected user device from which measurement data was collected.

[0200] In some example embodiments, the method 900 further comprises: transmitting the collection report to the DCE in response to at least one of the end of a period of the data collection, or receiving a request of the measurement report from the DCE, or reaching a maximum number or volume of stored measurement data, or a change of an RRC state of the at least one selected user device.

[0201] In some example embodiments, the apparatus comprises means for, in accordance with a determination that the data collection associated with the GUCI is to be stopped, deriving an identification of the DCE from the GUCI or the identifier orthe address of the DCE contained in the GUCI; and means for transmitting, to the DCE, one or more collection reports including measurement data stored at the apparatus along with an associated GUCI label comprising at least one of the following: a predetermined GUCI, an identification value of a user device associated with the data collection.

[0202] In some example embodiments, the apparatus comprises means for generating a Data Collection, DC, context comprising one or more GUCI labels, each GUCI label identifying a GUCI corresponding to a data collection request and including at least one of the identification value of the at least one selected user device from which measurement data was collected and information of a pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements.

[0203] In some example embodiments, the apparatus comprises means for determining that a user device is transitioning to an RRC Idle state, and means for transmitting, to an AMF, the generated data collection context.

[0204] In some example embodiments, the apparatus comprises means for, in accordance with an Xn handover during the RRC connected state of a user device from the apparatus to a further network node, transmitting, to the further network node, an Xn handover request for the user device including the DC context associated with the GUCI.

[0205] In some example embodiments, the apparatus comprises means for, in accordance with an Xn handover during the RRC connected state of a user device from the apparatus to a further network node, transmitting, to an AMF, a UE context notification indication including the DC context associated with the GUCI.

[0206] In some example embodiments, the apparatus comprises means for, in accordance with an NG handover during the RRC connected state of a user device, transmitting, to an AMF, an NG Handover Required message including the DC context associated with the GUCI.

[0207] In some example embodiments, the data collection relates to a machine learning model-based data collection.

[0208] In some example embodiments, the apparatus comprises a radio accessnetwork node.

[0209] In some example embodiments, the DCE comprises a model training collection entity.

[0210] In some example embodiments, the DCE is comprised in a radio access network node.

[0211] In some example embodiments, the apparatus further comprises means for performing other operations in some example embodiments of the method 900 or the RAN node 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 apparatus.

[0212] In some example embodiments, an apparatus capable of performing any of the method 1000 (for example, the RAN node 120 in FIG. 1) may comprise means for performing the respective operations of the method 1000. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The apparatus may be implemented as or included in the RAN node 120 in FIG. 1.

[0213] In some example embodiments, the apparatus comprises means for obtaining, from an AMF, at least one GUCI label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device and / or information of a pre-configured set of measurements to be performed for the data collection or a set of measurements requirements; and means for collecting the measurement data corresponding to the received GUCI.

[0214] In some example embodiments, the identification value includes an identification of a radio access node.

[0215] In some example embodiments, the apparatus further comprises: means for transmitting, to a data collection entity, DCE, of a radio access network, a GUCI fetch request at least indicating a target GUCI obtained from the at least one GUCI label; and means for obtaining, from the DCE, information of one or more sets of measurements to be performed associated with the target GUCI for the data collection.

[0216] In some example embodiments, the apparatus further comprises: means for collecting measurement data of the one or more sets of measurements associated with the target GUCI from the user device in a radio resource control, RRC, connected state and / or non-connected state; and means for storing the measurement data.

[0217] In some example embodiments, the apparatus further comprises: means for generating a collection report based on the measurement data; and means for transmitting the collection report to a DCE together with an associated GUCI label including at least the target GUCI and the identification value of the user device from which measurement data was collected.

[0218] In some example embodiments, the apparatus further comprises: means for transmitting, to the AMF, a set of GUCI labels corresponding to a user device context or user device connection, wherein the GUCI labels are associated measurement data of one or more sets of measurements collected from the user device.

[0219] In some example embodiments, the apparatus further comprises: means for transmitting, to the AMF, the set of GUCI labels in response to at least one of the following: a transition of the user device from an RRC connected state into an RRC non-connected state, or a decision to handover the user device to another radio access node.

[0220] In some example embodiments, the apparatus further comprises: means for receiving, from a user device, a set of measurement data collected by the user device in RRC idle or RRC inactive state and an associated Data Collection, DC, context comprising at least one GUCI or one GUCI label; and means for performing at least one of: storing the received measurement data together with the GUCI or GUCI label; sending to the DCE the received measurement data as a collection report together with the corresponding received GUCI or GUCI label; retrieving a collection data request corresponding to the received GUCI or GUCI label and triggering additional collection data; or including the received GUCI or GUCI label in a DC context and sending the DC context to an AMF.

[0221] In some example embodiments, the data collection relates to a machine learning model-based data collection.

[0222] In some example embodiments, the apparatus comprises a radio accessnetwork node.

[0223] In some example embodiments, the DCE comprises a model training collection entity.

[0224] In some example embodiments, the DCE is comprised in a radio access network node.

[0225] In some example embodiments, the apparatus further comprises means for performing other operations in some example embodiments of the method 1000 or the RAN node 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 apparatus.

[0226] In some example embodiments, an apparatus capable of performing any of the method 1100 (for example, the DCE 110 in FIG. 1) may comprise means for performing the respective operations of the method 1100. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The apparatus may be implemented as or included in the DCE 110 in FIG. 1.

[0227] In some example embodiments, the apparatus comprises means for transmitting, to a radio access network node, a GUCI, and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; and means for receiving, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification value associated with a user device selected according to the at least one selection criteria.

[0228] In some example embodiments, the apparatus further comprises: means for transmitting, to the radio access network node, the GUCI and the at least one selection criteria via a data collection request for the data collection.

[0229] In some example embodiments, the data collection request further comprises at least one of the following: a pre-determined number of user devices to be selected for the data collection, or a GUCI priority value associated with the data collection request, or information of a pre-configured set of measurements to be performed forthe data collection.

[0230] In some example embodiments, the identification value of the user device indicates an identifier of the user device which is a unique identification of user device in the radio access network node which has selected the user device for the GUCI and the at least one selection criteria.

[0231] In some example embodiments, the identification value includes an identification of the radio access network node which has received the data collection request.

[0232] In some example embodiments, the apparatus further comprises: means for receiving a GUCI fetch request including at least a GUCI; and means for transmitting in response to the GUCI fetch request information of one or more sets of measurements to be performed associated with the target GUCI.

[0233] In some example embodiments, the apparatus further comprises: means for receiving one or more collection reports, each including or associated with a GUCI label comprising at least an identification value of a user device; and means for correlating the measurement reports which have the same identification value to pertain to the same user device.

[0234] In some example embodiments, the apparatus further comprises: means for receiving one or more collection reports, each including or associated with a GUCI label comprising at least an identification value of a user device which includes a radio access node identity; and means for correlating the measurement reports which identification value contains the same radio access node identity.

[0235] In some example embodiments, the apparatus further comprises: means for receiving one or more collection reports, each including or associated with a GUCI label comprising at least a GUCI and an identification value of a user device; and means for correlating the measurement reports which have the same GUCI value.

[0236] In some example embodiments, the data collection relates to a machine learning model-based data collection.

[0237] In some example embodiments, the apparatus comprises a radio access network node.

[0238] In some example embodiments, the DCE comprises a model training collection entity.

[0239] In some example embodiments, the DCE is comprised in a radio access network node.

[0240] In some example embodiments, the apparatus further comprises means for performing other operations in some example embodiments of the method 1100 or the DCE 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 apparatus.

[0241] FIG. 12 is a simplified block diagram of a device 1200 that is suitable for implementing example embodiments of the present disclosure. The device 1200 may be provided to implement a communication device, for example, the DCE 110 or the RAN node 120 as shown in FIG. 1. As shown, the device 1200 includes one or more processors 1210, one or more memories 1220 coupled to the processor 1210, and one or more communication modules 1240 coupled to the processor 1210.

[0242] The communication module 1240 is for bidirectional communications. The communication module 1240 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 1240 may include at least one antenna.

[0243] The processor 1210 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 1200 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.

[0244] The memory 1220 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 1224, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital videodisk (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) 1222 and other volatile memories that will not last in the powerdown duration.

[0245] A computer program 1230 includes computer executable instructions that are executed by the associated processor 1210. The instructions of the program 1230 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 1230 may be stored in the memory, e.g., the ROM 1224. The processor 1210 may perform any suitable actions and processing by loading the program 1230 into the RAM 1222.

[0246] The example embodiments of the present disclosure may be implemented by means of the program 1230 so that the device 1200 may perform any process of the disclosure as discussed with reference to FIG. 2 to FIG. 11. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0247] In some example embodiments, the program 1230 may be tangibly contained in a computer readable medium which may be included in the device 1200 (such as in the memory 1220) or other storage devices that are accessible by the device 1200. The device 1200 may load the program 1230 from the computer readable medium to the RAM 1222 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).

[0248] FIG. 13 shows an example of the computer readable medium 1300 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 1300 has the program 1230 stored thereon.

[0249] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller,microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0250] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer readable medium, such as a non-transitory computer readable medium. The computer program product includes 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.

[0251] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0252] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0253] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0254] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable subcombination.

[0255] Although the present disclosure has been described in languages specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

WHAT IS CLAIMED IS:

1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: obtain, from a data collection entity, DCE, of a radio access network, a globally unique collection identifier, GUCI, and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; select, based on the at least one selection criteria, one or more user devices for the data collection; and collect measurement data from the one or more user devices.

2. The apparatus of claim 1, wherein the apparatus is caused to: receive a data collection request for the data collection from the DCE; and obtain the GUCI and the at least one selection criteria from the data collection request.

3. The apparatus of claim 2, wherein the data collection request further comprises at least one of the following: a pre-determined number of user devices to be selected for the data collection, or a GUCI priority value associated with the data collection request, or information of pre-configured set of measurements to be performed for the data collection.

4. The apparatus of any claims 2 to 3, wherein the apparatus is caused to: assign respective identification values for the one or more selected user devices, wherein an identification value of a user device indicates an identifier of the user device which is a unique identification of user device in the apparatus for the GUCI and the at least one selection criteria.

5. The apparatus of claim 4 wherein the identification value includes an identification of the apparatus which has received the data collection request.

6. The apparatus of any of claims 2-5, wherein the apparatus is caused to: in accordance with a request that collected data is to be reported for one or more measurements, generate a collection report at least including a GUCI label comprising at least the GUCI, and the identification value of the user device from which measurement data was collected corresponding to the data collection request; and transmit the collection report to the DCE.

7. The apparatus of any of claims 2-5, wherein the apparatus is caused to: store measurement data of a set of measurements performed by at least one of the selected user devices corresponding to the data collection request; generate a collection report based on the measurement data of the set of measurements; and transmit, to the DCE, the collection report together with a GUCI label identifying the GUCI and including at least the identification value of the at least one selected user device from which measurement data was collected.

8. The apparatus of claim 7 wherein apparatus is caused to: transmit the collection report to the DCE in response to at least one of: the end of a period of the data collection, orreceiving a request of the measurement report from the DCE, or reaching a maximum number or volume of stored measurement data, or a change of an RRC state of a selected user device.

9. The apparatus of any of claims 1-8, wherein apparatus is caused to: in accordance with a determination that the data collection associated with the GUCI is to be stopped, derive an identification of the DCE from the GUCI or the identifier or the address of the DCE contained in the GUCI; and transmit, to the DCE, one or more collection reports including measurement data stored at the apparatus along with an associated GUCI label comprising at least one of the following: a pre-determined GUCI, an identification value of at least one user device associated with the data collection.

10. The apparatus of any of claims 1 to 9, wherein the apparatus is caused to: generate a Data Collection, DC, context comprising one or more GUCI labels, each GUCI label identifying a GUCI corresponding to a data collection request and including at least one of the identification values of the at least one selected user device from which measurement data was collected and a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements; and store the DC context at the apparatus.

11. The apparatus of claim 10, wherein the apparatus is caused to: determine that a user device is transitioning to an RRC Idle state, and transmit, to an AMF, the generated data collection context.

12. The apparatus of any of claims 1-11, wherein the apparatus is caused to: in accordance with an Xn handover during the RRC connected state of a user device from the apparatus to a further network node, transmit, to the further network node, an Xn handover request for the user device including the DC context associated with the GUCI.

13. The apparatus of any of claims 1-11, wherein apparatus is caused to: in accordance with an Xn handover during the RRC connected state of a user device from the apparatus to a further network node, transmit, to an AMF, a UE context notification indication including the DC context associated with the GUCI.

14. The apparatus of any of claims 1-11, wherein apparatus is caused to: in accordance with an NG handover during the RRC connected state of a user device, transmit, to an AMF, an NG Handover Required message including the DC context associated with the GUCI.

15. The apparatus of any of claims 1-14, wherein the data collection relates to a machine learning model-based data collection.

16. The apparatus of any of claims 1-15, wherein the apparatus comprises a radio access network node.

17. The apparatus of any of claims 1-16, wherein the DCE comprises a model training collection entity.

18. The apparatus of any of claims 1-17, wherein the DCE is comprised in a radio access network node.

19. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: obtain, from an AMF, at least one globally unique collection identifier, GUCI, label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device; and / or a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements; and collect the measurement data corresponding to the received GUCI.

20. The apparatus of claim 19, wherein the identification value includes an identification of a radio access node.

21. The apparatus of claim 19 or 20, wherein the apparatus is caused to: transmit, to a data collection entity, DCE, of a radio access network, a GUCI fetch request at least indicating a target GUCI obtained from the at least one GUCI label; and obtain, from the DCE, information of one or more sets of measurements to be performed associated with the target GUCI for the data collection.

22. The apparatus of claim 19, wherein the apparatus is caused to: collect measurement data of the one or more sets of measurements associated with the target GUCI from the user device in a radio resource control, RRC, connected state and / or non-connected state; and store the measurement data.

23. The apparatus of claim 22, wherein the apparatus is caused to: generate a collection report based on the measurement data; and transmit the collection report to a DCE together with an associated GUCI label including at least the target GUCI and the identification value of the user device from which measurement data was collected.

24. The apparatus of claim any of claims 19-23, wherein the apparatus is caused to: transmit, to the AMF, a set of GUCI labels corresponding to a user device context or user device connection, wherein the GUCI labels are associated measurement data of one or more sets of measurements collected from the user device.

25. The apparatus of claim 24, wherein the apparatus is caused to: transmit, to the AMF, the set of GUCI labels in response to at least one of the following: a transition of the user device from an RRC connected state into an RRC non-connected state, or a decision to handover the user device to another radio access node.

26. The apparatus of any of claims 19-25, wherein the apparatus is caused to: receive, from a user device, a set of measurement data collected by the user device in RRC idle or RRC inactive state and an associated Data Collection, DC, context comprising at least one GUCI or one GUCI label; and perform at least one of: storing the received measurement data together with the GUCI or GUCI label; sending to the DCE the received measurement data as a collection report together with the corresponding received GUCI or GUCI label; retrieving a collection data request corresponding to the received GUCI orGUCI label and triggering additional collection data; or including the received GUCI or GUCI label in a DC context and sending the DC context to an AMF.

27. The apparatus of any of claims 19-26, wherein the data collection relates to a machine learning model-based data collection.

28. The apparatus of any of claims 19-27, wherein the apparatus comprises a radio access network node.

29. The apparatus of any of claims 19-28, wherein the DCE comprises a model training collection entity.

30. The apparatus of any of claims 19-29, wherein the DCE entity is comprised in a radio access network node.

31. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a radio access network node, a globally unique collection identifier, GUCI, and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; and receive, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification value associated with a user device selected according to the at least one selection criteria.

32. The apparatus of claim 31, wherein the apparatus is caused to: transmit, to the radio access network node, the GUCI and the at least one selection criteria via a data collection request for the data collection.

33. The apparatus of claim 32, wherein the data collection request further comprises at least one of the following: a pre-determined number of user devices to be selected for the data collection, or a GUCI priority value associated with the data collection request, or information of a pre-configured set of measurements to be performed for the data collection.

34. The apparatus of any of claims 31-33, wherein the identification value of the user device indicates an identifier of the user device which is a unique identification of user device in the radio access network node which has selected the user device for the GUCI and the at least one selection criteria.

35. The apparatus of any of claims 31-33, wherein the identification value includes an identification of the radio access network node which has received the data collection request.

36. The apparatus of any of claims 31-33, wherein the apparatus is caused to: receive a GUCI fetch request including at least a GUCI; and transmit in response to the GUCI fetch request information of one or more sets of measurements to be performed associated with the target GUCI.

37. The apparatus of any of claims 31-36, wherein the apparatus is caused to: receive one or more collection reports, each including or associated with a GUCI label comprising at least an identification value of a user device; and correlate the measurement reports which have the same identification value to pertain to the same user device.

38. The apparatus of any of claims 31-36, wherein the apparatus is caused to: receive one or more collection reports, each including or associated with a GUCI label comprising at least an identification value of a user device which includes a radio access node identity; and correlate the measurement reports which identification value contains the same radio access node identity.

39. The apparatus of any of claims 31-36, wherein the apparatus is caused to: receive one or more collection reports, each including or associated with a GUCI label comprising at least a GUCI and an identification value of a user device; and correlate the measurement reports which have the same GUCI value.

40. The apparatus of any of claims 31-39, wherein the data collection relates to a machine learning model-based data collection.

41. The apparatus of any of claims 31-40, wherein the apparatus comprises a Data Collection Entity, DCE, or a model training collection entity.

42. The apparatus of any of claims 31-41, wherein the apparatus is comprised in the radio access network node.

43. A method comprising: obtaining, at a radio access network node from a DCE of a radio access network, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; selecting, based on the at least one selection criteria, one or more user devices for the data collection; and collecting measurement data from the one or more user devices.

44. A method comprising: obtaining, at a radio access network node from an AMF, at least one GUCI label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device and / or and a measurement identifier associated with preconfigured set of measurements to be performed for the data collection or of a set of measurements requirements; and collecting the measurement data corresponding to the received GUCI.

45. A method comprising: transmitting, from a DCE to a radio access network node, a GUCI, and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; and receiving, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification value associated with a user device selected according to the at least one selection criteria.

46. An apparatus comprising: means for obtaining, from a DCE of a radio access network, a GUCI and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; means for selecting, based on the at least one selection criteria, one or more user devices for the data collection; and means for collecting measurement data from the one or more user devices.

47. An apparatus comprising: means for obtaining, from an AMF, at least one GUCI label from a data collection context associated with a user device context or a user device connection, wherein a GUCI label comprises at least a GUCI and / or an identification value of the user device and / or and a measurement identifier associated with pre-configured set of measurements to be performed for the data collection or of a set of measurements requirements; and means for collecting the measurement data corresponding to the received GUCI.

48. An apparatus comprising: means for transmitting, to a radio access network node, a GUCI, and at least one selection criteria for selecting a user device for a data collection, the at least one selection criteria being related to a characteristic of the user device, a connection state of the user device or a type of operation of the user device; and means for receiving, from the radio access node, one or more data collection reports each comprising at least the GUCI and an identification value associated with a user device selected according to the at least one selection criteria.

49. A computer readable medium comprising instructions stored thereon for causing an apparatus at least to perform the method of claim 43 or the method of claim44 or the method of claim 45.

Images