Methods, apparatus and computer programs

Abstract

A user equipment (UE) collects training data for sending to a location management function (LMF) for use in training a machine learning or artificial intelligence system. The UE sends to the LMF infor

Description

TECHNICAL FIELD Various example embodiments relate generally to methods, apparatus, system and computer programs and in particular, but not exclusively, methods, apparatus, system and computer programs relating to reporting of collected training data. BACKGROUND A communication network can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network. A mobile or wireless communication network is one example of a communication network. Such communication networks operate in according with standards such as those provided by 3GPP (Third Generation Partnership Project) or ETSI (European Telecommunications Standards Institute). Examples of standards are the so-called 5G (5th Generation) standards provided by 3GPP and future standards such as 6G and beyond. BRIEF DESCRIPTION Some example embodiments of this disclosure will be described with respect to certain aspects. These aspects are not intended to indicate key or essential features of the embodiments of this disclosure, nor are they intended to be used to limit the scope thereof. Other features, aspects, and elements will be readily apparent to a person skilled in the art in view of this disclosure. According to a first aspect, there is provided a user equipment comprising: means for sending to a location management function, information about a capability of the user equipment to store collected training data relating to location or positioning measurements; means for receiving from a location management function , information about at least one latency for reporting collected training data to the location management function; and means for collecting training data relating to location or positioning measurements and reporting the collected training data to the location management function, within a time window based on the information about the at least one latency for reporting collected training data. Other optional features of the first aspect may be seen from the dependent claims which are dependent on claim 1. According to a second aspect, there is provided a method comprising: sending to a location management function, information about a capability of a user equipment to store collected training data relating to location or positioning measurements; receiving from a location management function, information about at least one latency for reporting collected training data to the location management function; and collecting training data relating to location or positioning measurements and reporting the collected training data to the location management function, within a time window based on the information about the at least one latency for reporting collected training data. The method may comprise receiving from a base station, information about a measurement configuration to be used to collect the training data. The information about the measurement configuration may comprise information about one or more of: reference signals to be used for the collecting of the training data; and transmission times of the reference signals to be used for the collecting of the training data. The information about the transmission times of the reference signals to be used for the collecting of the training data may indicate that the reference signals are transmitted periodically, aperiodically, semi-statically, or on an event basis. The information about the measurement configuration to be used to collect the training data may be received in a radio resource control message. The information about the capability of the user equipment to store collected training data relating to location or positioning measurements may be provided in a LTE positioning protocol message, The information about at least one latency for reporting collected training data to the location management function may be provided in an LTE positioning protocol message. The information about at least one latency for reporting collected training data to the location management function may be provided in a request for location information message. The at least one latency for reporting collected training data may be dependent on one or more of: transmission times associated with reference signals used for the collecting of training data; the capability of the user equipment to store collected training data; an availability of one or more timers associated with the collecting of the training data; a mobility profile of the user equipment; the amount of collected training data from a user equipment or a group of user equipment; a storage capacity of the location management function; availability of radio resources; availability of control plane radio resources; or a measurement configuration of the user equipment for the collecting of the training data. The information about the capability of the user equipment to store collected training data may comprise information about one or more of: a maximum storage capacity of the user equipment; a maximum storage capacity of the user equipment for training data collection; a currently available storage capacity of the user equipment for training data collection; or a change in the available storage capacity of the user equipment for training data collection. The method may comprise starting a timer when the collection of training data is started, said timer being based on one of said at least one latency. The method may comprise determining that the timer is within a threshold amount of time before expiry of the timer and, in response to determining that the timer is within a threshold amount of time before expiry of the time, causing one or more indicators that the collected training data is ready to be reported to be sent to the location management function. The method may comprise determining that the user equipment is not in a connected state and the timer is within a threshold amount of time before expiry of the timer and, in response to determining that the equipment is not in a connected state and the timer is within a threshold amount of time before expiry of the time, causing the user equipment to enter the connected state. The method may comprise, when user equipment enters the connected state, causing one or more indicators that the collected training data is ready to be reported to be sent to the location management function. The method may comprise determining that the user equipment is about to enter an idle or inactive state, and before the user equipment enters the idle or inactive state, reporting the collected data before the user equipment enters the idle or inactive state. The method may comprise determining that the user equipment is about to enter an idle or inactive state, and saving, before the user equipment enters the idle or inactive state, the collected data before the user equipment enters the idle or inactive state. The timer may be ended if all the collected training data has been reported or if the timer expires. The method may comprise reporting to the location management function, an expiry of the timer. The method may be performed by an apparatus. The apparatus may be or be in a user equipment. The apparatus may comprise 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 provide one or more of the methods of the second aspect. According to the third aspect, there is provided an apparatus providing a location management function, the apparatus comprising means for: receiving, information about a capability of a user equipment to store collected training data relating to location or positioning measurements; providing to the user equipment, information about at least one latency for reporting collected training data to the location management function; and receiving training data relating to location or positioning measurements within a time window based on the information about the at least one latency for reporting collected training data. The means may be for providing the information about at least one latency for reporting collected training data to the location management function in a LTE positioning protocol message. The means may be for receiving the information about the capability of the user equipment to store collected training data relating to location or positioning measurements in an LTE positioning protocol message. The means may be for sending measurement configuration information relating to the location or positioning measurements to a base station. The means may be for providing, information about a measurement configuration to be used to collect the training data. The information about the measurement configuration may comprise information about one or more of: reference signals to be used for the collecting of the training data; and transmission times of the reference signals to be used for the collecting of the training data. The information about the transmission times of the reference signals to be used for the collecting of the training data may indicate that the reference signals are transmitted periodically, aperiodically, semi-statically, or on an event basis. The information about at least one latency for reporting collected training data to the location management function may be provided in a request for location information message. The at least one latency for reporting collected training data may be dependent on one or more of: transmission times associated with reference signals used for the collecting of training data; the capability of the user equipment to store collected training data; an availability of one or more timers associated with the collecting of the training data; a mobility profile of the user equipment; the amount of collected training data from a user equipment or a group of user equipment; a storage capacity of the location management function; availability of radio resources; availability of control plane radio resources; or a measurement configuration of the user equipment for the collecting of the training data. The information about the capability of the user equipment to store collected training data may comprise information about one or more of: a maximum storage capacity of the user equipment; a maximum storage capacity of the user equipment for training data collection; a currently available storage capacity of the user equipment for training data collection; or a change in the available storage capacity of the user equipment for training data collection. The apparatus may be a or provided in a network node. The network node may be a data collector. The network node may provide a location management function. According to a fourth aspect, there is provided a method comprising: receiving, information about a capability of a user equipment to store collected training data relating to location or positioning measurements; providing to the user equipment, information about at least one latency for reporting collected training data to the location management function; and receiving training data relating to location or positioning measurements within a time window based on the information about the at least one latency for reporting collected training data. The method may comprise providing the information about at least one latency for reporting collected training data to the location management function in a LTE positioning protocol message. The method may comprise receiving the information about the capability of the user equipment to store collected training data relating to location or positioning measurements in an LTE positioning protocol message. The method may comprise sending measurement configuration information relating to the location or positioning measurements to a base station. The method may comprise providing, information about a measurement configuration to be used to collect the training data. The information about the measurement configuration may comprise information about one or more of: reference signals to be used for the collecting of the training data; and transmission times of the reference signals to be used for the collecting of the training data. The information about the transmission times of the reference signals to be used for the collecting of the training data may indicate that the reference signals are transmitted periodically, aperiodically, semi-statically, or on an event basis. The information about at least one latency for reporting collected training data to the location management function may be provided in a request for location information message. The at least one latency for reporting collected training data may be dependent on one or more of: transmission times associated with reference signals used for the collecting of training data; the capability of the user equipment to store collected training data; an availability of one or more timers associated with the collecting of the training data; a mobility profile of the user equipment; the amount of collected training data from a user equipment or a group of user equipment; a storage capacity of the location management function; availability of radio resources; availability of control plane radio resources; or a measurement configuration of the user equipment for the collecting of the training data. The information about the capability of the user equipment to store collected training data may comprise information about one or more of: a maximum storage capacity of the user equipment; a maximum storage capacity of the user equipment for training data collection; a currently available storage capacity of the user equipment for training data collection; or a change in the available storage capacity of the user equipment for training data collection. The method may be provided by an apparatus. The apparatus may be a or provided in a network node. The network node may be a data collector. The network node may provide a location management function. The apparatus may comprise 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 provide one or more of the methods of the fourth aspect. According to another aspect, there is provided a computer readable medium comprising program instructions stored thereon for performing at least one of the above methods. According to an aspect, there is provided a non-transitory computer readable medium comprising program instructions stored thereon for performing at least one of the above methods. According to an aspect, there is provided a non-volatile tangible memory medium comprising program instructions stored thereon for performing at least one of the above methods. In the above, many different aspects have been described. It should be appreciated that further aspects may be provided by the combination of any two or more of the aspects described above. Various other aspects are also described in the following detailed description and in the attached claims. LIST OF THE DRAWINGS In the following, the invention will be described in greater detail with reference to the embodiments and the accompanying drawings, in which: Fig. 1 shows an example of a communication network to which examples disclosed herein may be applied; Fig. 2 schematically illustrates latency in reporting of collected training data; Fig. 3 shows an example of a first procedure; Figs. 4A and B shows an example of a second procedure; Figs. 5A and B show an example of a third procedure; Figs. 6A and B show an example of a fourth procedure; Figs. 7 to 12 show first to eight methods of some embodiments; and Fig. 13 shows an example of an apparatus. DESCRIPTION OF EMBODIMENTS The following embodiments are exemplary. Although the specification may refer to “an”, “one", or "some” embodiment(s) in several locations of the text, this does not necessarily mean that each reference is made to the same embodiments], or that a particular feature only applies to a single embodiment. Single features of different embodiments may also be combined to provide other embodiments. Further, when a particular feature, structure, or characteristic is described in connection of an embodiment, it is within the knowledge of one skilled in the art to apply such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described. It shall be understood that although the terms “first,” “second” 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. For the purposes of the present disclosure, the phrases "at least one of A or B", "at least one of A and B”, and “A and / or B” means (A), (B), or (A and B). For the purposes of the present disclosure, the phrase "A, B, and / or C" means [A], (B), (C), (A and B), (A and C), (B and C), or (A, B, and C). Embodiments described may be implemented in a communication network, such as any of the following radio access technologies (RATs]: Worldwide Interoperability for Micro-wave Access [WiMAX], Global System for Mobile communications (GSM, 2G], GSM EDGE radio access Network [GERAN], General Packet Radio Service [GRPS], Universal Mobile Telecommunication System (UMTS, 3G] based on basic wideband-code division multiple access (W-CDMA], high-speed packet access (HSPA], Long Term Evolution (LTE], LTE-Advanced, and enhanced LTE (eLTE], 5G (also called NR], or any future RAT such as 6G. Moreover, communication within the communication network may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA], Frequency Division Multiple Access (FDMA], Time Division Multiple Access (TDMA], Frequency Division Duplex (FDD], Time Division Duplex (TDD], Multiple-Input Multiple-Output (MIMO], Orthogonal Frequency Division Multiple (OFDM], and / or Discrete Fourier Transform spread OFDM (DFT-s-OFDM]. As used herein, the term "network device” or “network node” refers to a node in a communication network via which user equipment may access the network and / or which is capable of controlling radio communication and managing radio resources within a cell. The network node or network device may be referred to as a base station (BS], an access point (AP] or an access node. The network device may be, depending on the applied technology, for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio head (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node, 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, or an aircraft network device. Moreover, in connection with a split radio access network (RAN), the network device may refer to a centralised unit (CU) of a base station and / or a distributed unit (DU) of a base station. There may also be radio units (RU). A RU may be provide as part of a DU. An interface between CU and DU (CP) may be referred to as an Fl interface in NR. An interface between CU -UP and CU- CP may be referred to as an El interface in NR. In the split RAN architecture, node operations may be carried out, at least partly, in the central / centralized unit, CU, (e.g. server, host or node) operationally coupled to the DU, (e.g. a radio head / node). One CU may control one or more DUs, acting at least as transmit / receive (Tx / Rx) nodes. In some embodiments, the DUs may comprise e.g. a radio link control (RLC) layer, medium access control (MAC) layer and a physical (PHY) layer, whereas the CU may comprise the layers above RLC layer, such as a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) and an internet protocol (IP) layers. Other functional splits are possible too. In practice, any processing task may be performed in either the CU or the DU and the boundary where the responsibility is shifted between the CU and the DU may depend on the applied implementation. The term “terminal device" refers to any end device that may be capable of wireless communication. By way of example, a terminal device may be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), or a Mobile Station (MS). The terminal device may include 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, USB dongles, an Internet of Things (JoT) 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. A term "resource”, as used herein, may refer to radio resources in time domain, in frequency domain, in space domain, and / or in code domain. Some examples of resources include e.g. a physical resource block (PRE), a radio frame, a subframe, a time slot, a sub band, a frequency region, a sub-carrier, a beam, etc. The term "transmission” and / or “reception” may refer to wirelessly transmitting and / or receiving via a wireless propagation channel on radio resources. Fig. 1 illustrates an example of a communication network to which examples disclosed herein may be applied. The communication network or a cellular communication network may comprise a network node 110 providing one or more cells, such as cell 100, and a network node 112 providing one or more other cells, such as cell 102. Each cell may be, e.g., a macro cell, a micro cell, femto, or a pico cell, for example. The cell may define a coverage area or a service area of the corresponding access node. The network node 110 may provide a user equipment (UE) 120 (one or more UEs) with wireless access to the communication network. The wireless access may comprise downlink (DL) communication from the network node to the UE 120 and uplink (UL) communication from the UE 120 to the network node. Examples of uplink channels comprise physical uplink control channel (PUCCH) for transmitting control information and physical uplink shared channel (PUSCH) for transmitting data towards the network. Examples of downlink channels comprise physical downlink control channel (PDCCH) for transmitting control information and physical downlink shared channel (PDSCH) for transmitting data towards the user equipment. There may be a plurality of UEs 120, 122 in the system. Each of them may be served by the same or by different network nodes 110,112. UE may be configured with dual connectivity (DC), wherein the UE, e.g. UE 120, may be connected to multiple network nodes 110, 112. The UEs 120, 122 may communicate with each other, in case device-to-device (D2D) communication interface is established between them via a so-called sidelink (SL). Such D2D communications may be referred to as machine-to-machine, peer-to-peer (P2P) communications, or vehicle-to-vehicle (V2V), for example. In the case of multiple network nodes in the communication network, the network nodes may be connected to each other via an interface. LTE specifications call such an interface as X2 interface. An interface between an LTE node and a 5G node, or between two 5G nodes may be called Xn interface. The network nodes 110 and 112 may be further connected via another interface to a core network 116 of the communication network. The LTE specifications specify the core network as an evolved packet core (EPC), and the core network may comprise e.g. a mobility management entity (MME) and a gateway node. The MME may handle mobility of terminal devices in a tracking area encompassing a plurality of cells and handle signalling connections between the terminal devices and the core network. The gateway node may handle data routing in the core network and to / from the terminal devices. The 5G specifications specify the core network as a 5G core (5GC). The 5G core may comprise e.g. an access and mobility management function (AMF) and a user plane function / gateway (UPF) and other functions. The AMF may handle termination of non-access stratum (NAS) signalling, NAS ciphering &integrity protection, registration management, connection management, mobility management, access authentication and authorization, security context management. The UPF node may support packet routing and forwarding, packet inspection and quality of service (QoS) handling, for example. Artificial intelligence (AI) can be broadly defined as getting computers to perform tasks mimicking human brain. Machine learning (ML) is one category of AI techniques: computer algorithms able to automatically improve their performance without explicit programming. AI / ML can help adjust and optimize radio access network (RAN) parameters and settings using (real-time) monitoring and prediction of network performance, quality, and demand. Additionally, AI / ML can identify and diagnose degradation in network performance, as well as provide protection from cyberattacks. AI / ML is usable in energy saving, load balancing, mobility optimization, link adaptation and security just to mention but a few. It is envisioned that AI / ML will enable real-time analysis as well as automated operation and control in 5G and beyond RAN. This requires the availability of data streamed from wireless devices in a timely manner, especially in extremely time-critical applications such as real-time video monitoring and extended reality (XR). This may be reflected in network architecture, such as by placing and moving ML agents to the required locations in the network, for example for data collection. User devices (mobile devices) may assist network in decision-making in resource management, thus a user device may act as an infrastructure resource. As the network evolves to programmable and flexible cloud native implementation, AI / ML-based network automation will be used to simplify network management and optimization. It is expected that parts of the air interface, in particular signal processing algorithms, are supported and eventually even replaced with machine learning models. Thus, a 6G wireless communication standard will natively support an Al-based air interface. Machine learning algorithms are usually classified into four different types: supervised learning, unsupervised learning, semi-supervised learning and reinforcement learning. In supervised learning the algorithm learns from labelled data. For training, the algorithm receives input data and corresponding correct output labels. The algorithm is trained to predict accurate labels for new data. In unsupervised learning the algorithm analyses unlabelled data. The aim is to discover patterns, relationships, or structures within the data, for example, unsupervised learning algorithms make groups of similar data points. Semi-supervised learning is a hybrid machine learning approach that combines labelled and unlabelled data for training. A limited amount of labelled data and a larger set of unlabelled data is used to improve training. This approach is useful when acquiring labelled data is expensive or time-consuming as is the case in many real-world applications. Semi-supervised learning techniques can be applied to various tasks, such as classification, regression, and anomaly detection, allowing models to make more accurate predictions and generalize better in real-world scenarios. Reinforcement learning is a machine learning algorithm which learns from trial and error. An ML agent interacts with environment and learns from experience aiming to maximize cumulative rewards. The ML agent receives feedback through rewards or penalties based on its actions. The agent learns to take actions that lead to the most favourable outcomes over time. The algorithm adapts to changing environments, and achieve long-term goals through a sequence of actions. An example of an ML algorithm found applicable to adjust and optimize the radio access network (RAN) parameters and settings is deep learning. Deep learning is a subset of machine learning algorithms using a neural network. Neural networks are also known as artificial neural networks (ANNs) or simulated neural networks (SNNs). Deep learning can be based on supervised, semi-supervised or unsupervised learning. Artificial neural networks (ANNs) are comprised of an input layer, one or more hidden layers, and an output layer. Each node of a layer, or an artificial neuron, connects to another one and has an associated weight as well as a threshold value. If the output of an individual node is above the threshold value specified to this node, the node is activated and sending or passing data to the next layer of the neural network. In the case the supervised learning is applied in the training of a neural network, the training is carried out by using examples, each of which contains a known "input" and "result", forming probability-weighted associations between them. The training comprises determining the difference between the output of the neural network (a prediction) for an input and a target output for the same input. The difference is called an error value. The neural network then adjusts its weighted associations according to a learning rule and using this error value. Successive adjustments makes the neural network produce output that is approaching the target output. After a sufficient number of these adjustments, the training can be terminated based on a certain criteria. Some embodiments relate to the collection of training data. The training data (TD) may be Al / ML data. Some embodiments may relate to the collecting of UE measurements for offline training of UE-sided, NW-sided and 2-sided AI / ML models for different use cases, e.g., beam management and positioning. Latency may refer to the time difference from when a UE measurement is ready for transmission by the UE to when the report reaches the data collector... The data collector may be the first entity outside of the UE that receives the UE measurement / data report in a non-transparent way, i.e., data is visible and can be comprehended by that node. Reference is made to Figure 2 which shows the sampling interval duration 200 of first and second reports (Report# 1 and Report#2) and the transmission of the reports by the UE to the gNB. In this document, the terms reporting, report transmission and transmission of the reports may be used interchangeably. When the data collector is a radio access node, e.g., gNB, the latency 202 is the latency of the air interface between the UE and the radio access node. When the data collector is a core network entity such as a LMF (location management function), the latency refers to the time consumed to transfer data from the UE to LMF. Sampling interval duration is the time difference between two consecutive samples. Report duration is the time difference between the first and last sample contained in a report. The data collector, the data collector is the entity outside of the UE that receives the UE measurement / data report. For example, the data collector may be a gNB or core network entity such as an LMF. Offline training may require a considerable amount of data, i.e., training samples. Collection of the UE measurements for this purpose may overload the radio resources and interfaces (e.g., Uu interface) used for data transfer. This may be exacerbated if there is a stringent latency requirement is imposed on the UE. In some embodiments, for the collecting of training data the type of measurement, sampling interval and / or report duration may vary from the measurements needed for real-time network operations. For example, the sampling interval duration for a training data collection might be much smaller. It has been proposed that the latency requirement of data collection for model training may be relaxed as compared to other data collection. However, there is an issue with having a more relaxed latency which may be addressed by some embodiments. For example, having no latency or a long latency may lead to a failure in the collection of data. This may be a result of a dynamic RRC state change or a limitation on the capability of the UE to store measurements. One issue may be that a UE may stay in RRC_connected mode for a short time, e.g., seconds. An issue arises with the handling of training data when UE changes its state from RRC_connected to idle / inactive. This may endanger the success of training data collection. Some embodiments may address this issue. Another issue relates to the consistency in collecting of data for a continuous time and space (location). Such consistency may be useful in learning parameters of the channel for enhancing the use cases, e.g., beam management and localization. Some embodiments may address this issue. Some embodiments may keep the collected data for transmission when the UE goes back to RRC_connected state to ensure a successful data delivery for training. The table below summarises some current data collection methods for the collection of training data. This table can be found from TR 38.843-i00. Involved network entity (terminatio n point) RRC state to generat e data Max payload size per reporting* Contents to be collected End-to-End report latency* * Report type Security and Privacy Method: Logged MDT TCE / OAM (Data can be utilized by gNB) IDLE / INACTI VE <9kbyte - L3 cell / beam measurements - location information - sensor information - timing information 1) Procedure latency***: Latency to enter CONNECTED state Latency to receive gNB request signalling (~20ms) 2) Air interface signalling latency****: - ~20ms (RRC) 3) Other latency: Forwarding latency between gNB and TCE Upon gNB request after entering RRC_CONNEC TED AS security via RRC message Privacy via user consent Method: Immediate MDT TCE / OAM (Data can be utilized by gNB) CONNE CTED <9kbyte - L3 cell / beam measurements - location information - sensor information 1) Procedure latency: Report interval: • 120ms~30min for periodic report • TTT for event triggered report 2) Air interface signalling latency: ~20ms (RRC) 3) Other latency: Forwarding latency between gNB and TCE -Event triggered - Periodic reporting AS security via RRC message Privacy via user consent Method: L3 measurements gNB CTED <9kbyte L3 cell / beam measurements 1) Procedure latency: Report interval: • 120ms~30min for periodic report • TTT for event triggered report 2) Air interface signalling latency: - 20ms (RRC) - Event triggered report - Periodic reporting AS security via RRC message Method: LI measurement (CSI reporting) gNB CTED <1706bitin PUCCH <3840bitin PUSCH LI CSI measurement 1) Procedure latency: Report interval: • 4-320 slot for periodic and semi-persistent report • 0-32 slot after reception of DC I for aperiodic report 2) Air interface signalling latency: - Aperiodic report - Semi-persistent report - Periodic report No AS security Method: UE Assistance Information (UAI) gNB CTED <9kbyte Assistance information to show UE preference 1) Procedure latency: Upon generation of UE's preference 2) Air interface signalling latency: ~20ms (RRC) Up to UE implementation when to report AS security via RRC message Method: Early measurements gNB IDLE / INACTI VE <9kbyte L3 cell / beam measurements 1) Procedure latency: Latency to enter CONNECTED state Upon gNB request after entering AS security via RRC message Latency to receive gNB request signalling (~20ms) 2) Air interface signalling latency: - ~20ms (RRC) RRC_CONNEC TED Method: LPP LMF CTED <9kbyte Location information 1) Procedure latency: Latency to get upper layer trigger (for UE triggered) Or latency to receive network request message (~20ms) 2) Air interface signalling latency: - ~20ms (RRC) 3) Other latency: Forwarding latency between gNB and LMF - UE-triggered - Network-triggered AS security via RRC message *: The payload size doesn't consider signalling overhead. **: The End-to-End report latency is the latency from availability of the measurement report at the UE side to the availability of the measurement report at the terminated network entity. The time to generate data or perform measurements depends on RAN1 / RAN4 specification. ***: Procedure latency is the latency caused by procedures, including procedure to ready for reporting (e.g., entering CONNECTED state, report interval). **“: Air interface signalling latency is the latency to transmit one report, e.g., RRC signalling latency or PUCCH signalling latency. As can be seen from the table above, the data collection methods (for example LPP (LTE positioning protocol), MDT (minimization of drive tests), LI (layer 1) and L3 (layer 3) measurement reporting) impose a latency on air interface signaling, e.g., 20ms. However, one issue is that offline training requires a relatively large amount of data. This latency of RRC (for example 20ms) may overload and burdens the air interface. This may affect the overall network operations and performance. This latency requirement may affect the success of data collection for training since, e.g., the rate of UE collaboration to MDT may decrease. This latency requirement may limit the data content that can be collected for training purposes. This may affect the performance of the trained Al / ML models since one of the benefits of using Al / ML is to process large quantities of data and extract the hidden knowledge from that data. This latency requirement may increase energy consumption in case of having weak channel quality because the UE would insist on UE measurement report transmission with the relatively low latency (RRC air interface latency of ~20ms). Some embodiments may address one or more of the above issues. In the following, it should be appreciated that training data collection may be interchangeably referred to as collection of training data, data collection for training and / or the like. Some embodiments may make use of a TDC timer. A TDC timer when activated, keeps track of a maximum reporting latency requirement and is discussed in more detail later. The UE reporting latency for AI / ML training data may be the time difference between the time when a UE measurement report is ready for transmission by the UE until the report reaches the first entity outside of UE, i.e., a data collector. Examples of the data collector are gNB for beam management or LMF for positioning. Other embodiments may use a different data collector. Reference is made to Figure 3 which schematically show UE and data collector behaviour. In this example, the data collector may be a gNB or an LMF. Examples of the data collector are gNB for beam management or LMF for positioning. As referenced 1, the UE provides to the data collector information about the UE capability. The UE may indicate to the data collector availability of a TDC timer. The UE may indicate if it can support a TDC timer. A TDC timer may be supported at the UE for one or more training data collection jobs and logging. This will be called a training data collection (TDC) timer in document. This timer, when activated, keeps track of the latency requirement. There may be more than one TDC timer. The TDC time may continue working during all RRC states. The UE may indicate its capability for TDC logging and / or of storing logged data. The UE may provide information about its storage capacity for TDC. For example, the UE may indicate its maximum buffer for TDC, its maximum memory availability for TDC and / or its maximum logging capacity that can be allocated for training data collection. As referenced 2, the UE may provide UE assistance information. The UE assistance information may be information about one or more of its currently available buffer capacity for TDC, memory capacity for TDC, and / or logging capacity TDC. This may be used to temporarily store measurements made by the UE for the training data collection. It should be noted that the UE assistance information may be dynamically used by the data collector. This UE assistance information may be dynamically used together with UE measurement configuration information by the data collector to indicate and / or adjust the latency requirement for a training data collection job at that given moment. UE capability information and UE assistance information are different. UE capability information is sent upon request of the data collector. The UE assistance information may be sent whenever UE wants. The UE capability information may be sent before RRC connection so that data collection does not configure something that is out of UE capabilities. The UE assistance information is sent after RRC connection is established to assist the data collector in setting / adjusting configuration parameters based on the UE's condition at that moment (current UE condition). Hence, UE assistance information provides dynamic and up-to-date information while UE capabilities are static information. As referenced 3, the data collector may determine a maximum tolerable latency for the reporting of the collected or logged TD. This may be referred to the latency requirement in this document. The data collector can indicate no latency or a too high latency as a first choice. This way the UE has the flexibility to decide when to transmit its collected data. However, if the data collector observes that many training data collection requests are not responded after some time or that there are many incomplete training data collection jobs while the data collectors’ limit for (permanent or temporary) data storage is being reached, the data collector should be able to set a value as the maximum tolerable latency. The data collector may be able to adjust a previously set value to provide an updated or new value for the maximum tolerable latency. The determining of the maximum tolerable latency may take into account one or more of the UE measurement configuration, the UE storage capabilities, and / or the UE assistance information. For example, there are 8 TDC sessions / jobs. Each TDC session needs, e.g., 10 reports to be finished (closed / successful) and then the data collector can forward the data of the session to the next node (e.g., trace collection entity TCE) and delete the corresponding data. Consider the case that 4 of the sessions received 9 reports each of which occupies storage. There are 4 incomplete training data collection sessions / jobs occupying storage and the last report has not been sent yet. The data collector can enforce the UEs to transmit with a stricter latency so that these 4 jobs will be successful, and their data can be transferred to a next node and then deleted from the data collector storage (freeing up space). Note that setting a maximum latency value here enforces the UE to deliver its data in the set time frame and hence, leads to successful training data collection. Consideration of the UE measurement configuration may allow the data collector to have an approximation of how much data should be measured and logged. For event-based measurements, this approximation may be done by making predictions or by trial and error. By considering UE capabilities and / or assistance information, the gNB can set different proper maximum tolerable latencies for different UEs. In another example, if the data collector gets many simultaneous requests from various UEs to receive their collected training data while the control plane radio resources are scarce, the data collector should be able to set a new higher value as the maximum tolerable latency considering UE measurement configuration and UE storage capabilities and assistance information. This latency requirement may enforce the UE to keep the data for a reasonably longer period. The data collector may also consider setting the maximum tolerable latency to a value such that it will minimize the chance of losing data because of UE switch off or detach events. Such events may lead to data deletion. When setting a value for the maximum tolerable latency, UE storage capabilities and assistance information may be taken into account by the data collector. For example, if the UE capability indicates that the data training storage is low, the tolerated latency will be set to a smaller value. Similarly the maximum tolerable latency should be reduced if UE assistance information indicates that the current UE storage capacity is low. Hence, training data collection can be done considering both UE and data collector resource (radio and storage) limitations. When setting a value for the maximum tolerable latency, the data collector may also consider the overhead on a UE and other factors such as mobility. A UE with high mobility is likely to leave the cell and hence setting a lower value for the maximum tolerable latency for its data collection helps with having a successful training data collection from that UE. As referenced 4, the gNB provides a UE measurement configuration for TDC to the UE. This configuration is provided by the gNB to the UE to indicate the transmission timing of the (reference) signals used for TDC (reference signals are transmitted by the gNB). Where the LMF is with the data collector, at least a part of this configuration may be provided or recommended by the LMF. The signals used for TDC may be transmitted: 1) periodically; 2) aperiodically; 3) semi-statically; or 4] event-based. Each transmission scheme may be configured by a set of potential configuration parameters included in a measurement configuration. This configuration should be considered when determining the latency requirement. This configuration may depend on the needs of the training data collection and UE capabilities. As referenced 5, the data collector may provide the UE with a measurement report configuration. This may be for the reporting of the collected TD. The measurement report configuration may indicate at least one value as the maximum tolerable latency to the UE for one or more training data collection job(s). As referenced 6, the UE may start the TDC timer(s) when the UE receives the measurement report configuration. The TDC timer will work in all RRC states. The timer may be started when: the collection of training data is started; the collection of data is started and at least one report is ready for transmission; or at least one report is ready for transmission. The UE may make use of an indicator which indicates when TD is available for collection by the data collector.. This indicator may be, "AvailableTDCindicator": This indicator may be a one-bit representation of existence of training data at the UE, e.g., if the value of this indicator is set to "1", the data collector knows the UE has available training data for retrieval. Optionally, in some embodiments, where the UE is the RRC connected state, the UE may send the collected data directly without sending the indicator beforehand. Whenever the UE returns to RRC connected state (from any state - e.g. idle or inactive] and it wants to transmit available measurement reports related to TDC job(s) with unexpired TDC timer(s), the UE may indicate availability of such data to the data collector by sending the indicator, as referenced 7. The UE may be responsible for transmitting the training data before TDC expires. Hence, if UE has data with close to expiry TDC timer, the UE should return to RRC_connected state - if in the idle or inactive mode- for reporting. The UE should send the indicator indicating that data is available. By returning to the RRC_connected mode and sending the indication of available training data, this prevents TDC failure occurrences in collecting data for training. Before TDC timer expiry, if the UE goes to RRCJdle / inactive mode, the training data may be logged / stored. In some embodiments, if the user equipment determines that it is about to enter an idle or inactive state, and before the user equipment enters the idle or inactive state the collected TD is sent to the data collector. The indicator may be optional in some embodiments. When the data has been collected, the UE sends that data to the data collector without first sending an indicator. The measurement reports should be delivered to their destination / data collector, e.g., gNB before the TDC timer(s) expires, i.e., the maximum tolerable air interface signaling latency is reached. The TDC timer expires if any of the below conditions are met: - If the timer value reaches the latency requirement value. - If all the measurement reports related to this TDC timer are transmitted by the UE (and received by the gNB or other data collector). If the TDC timer expires, the UE informs the data collector. Then data collector can take the next necessaiy steps, i.e., initiate another data collection job if the reports were incomplete or insufficient. Reference is made to Figures 4A and 4B which shows an example procedure in which the gNB is the data collector. The data collected may relate to one or more channel state information, cell measurements, or beam measurements. As referenced 1, the UE receives a request from the gNB for information about the capability of the UE. This may be RRC message. The message may be a UE capability enquiry. As referenced 2, the UE provides the gNB with UE capability information. This UE capability information may be as previously discussed. The UE capability information may comprise one or more of the following: Information about the capability of the UE to indicate its capability to start and expire at least one TDC timer, that is a timer activated for a TDC job. This may imply that UE can provide a TDC indicator, (e.g., available TDC indicator and TDC expiry information) such are previously discussed to the gNB. Alternatively, the UE may explicitly indicate to the gNB its support of the TDC indicator. Where the UE has the capability to run more than one TDC timer, information about that the number of TDC timers that can be active simultaneously; Information indicating if the UE can signal the expiry of the TDC timer(s); Information about the UE buffer and / or storage capability. This may indicate the maximum amount of memory that UE can allocate for training data collection. (It should be appreciated that the available memory of UE for TDC might be impacted dynamically depending on the training data collection jobs to which the UE is contributing and / or other potential operations using the same resource. The impact and dynamicity of the training data collection jobs to which the UE is contributing and / or other potential operations using the same resource are captured by the UE assistance information which discussed in relation to the part of the procedure referenced 4; Information about the capability of the UE to support the feature of performing TDC for offline training. This UE capability or not to support the feature may be indicated by a flag or a binary state; or Information about the at least one of the UE measurement type capabilities, or UE storage / buffer / logging capability. In some embodiments, the UE measurement type capability may indicate the type of signals, for example reference signals that UE can support and / or perform offline TDC. For example, the UE may indicate the capability of being able to perform TDC with (reference) signals A and / or B. In some embodiments, the UE measurement type capability may indicate the set of one or more antenna panel(s) that have been used for performing offline TDC. As referenced 3, the gNB sends a reconfiguration message to the UE. The reconfiguration message may be a RRC reconfiguration message. As referenced 4, the UE sends assistance information to the gNB. The UE assistance information may comprise one or more of the following: Information on power saving and / or heating mitigation; Information regarding a current UE buffer and / or storage capacity for training data collection. If UE is using a certain storage for more than one purpose such as both TDC and keeping logged MDT information, the corresponding limitations can be communicated to the entity (gNB in this example) performing the measurement report configuration. For example, if the UE storage capacity is almost full and not much storage capacity is left for the TDC, the UE informs the gNB via the UE assistance information. As referenced 5, the gNB may set a maximum tolerable latency for different data collection jobs. This may be based on the UE capability information and the UE assistance information. This may be as previously discussed. For example if the assistance information indicates the UE storage capacity is almost full and not much storage capacity is left for the TDC , the gNB may decide to release the UE from the TDC job or determine shorter latency requirements for the UE and / or or allocate better radio resources for quick transmission of UE measurement reports to assist the UE in avoiding overloading the buffer / storage capacity and enable the TDC job. As referenced 6, the gNB provides to the UE a measurement configuration for TDC. This may provide configuration information for the transmission timing of the (reference) signals used at UE for TDC. This may provide a configuration for the reporting of the TDC, For example, the measurement configuration may comprise a channel state information report configuration. The measurement configuration may provide for periodic transmission of the reference signals which are, for example, measured by the UE. For periodic transmission, the measurement configuration may comprise a transmission interval parameter to indicate the timing between consecutive transmissions of the reference signals, offset for the start of the first transmission, and a periodicity parameter to indicate the transmission cycle duration. Periodic transmission may be enabled / disabled by RRC signaling. The measurement configuration may provide for aperiodic transmission of the reference signals. Here, gNB may commit for transmission of plurality of (reference) signal for TDC within a certain window, but exact transmission timing of individual transmissions is indicated to UE before actual transmission. This approach may have an advantage of giving the gNB more flexibility. This approach may require more control signaling overhead. Layer-1 control may be used for indication of exact transmission timing. The measurement configuration may provide for semi-persistent transmission of the reference signals. The UE may be configured with two or more sets of periodic transmission configurations . Each set may get activated / deactivated via layer- 2 signaling such as MAC-CE ( medium access control - control element) The measurement configuration may provide one or more rules and / or one or more conditions for event-based transmission and / or measurement triggering. As referenced 7, the gNB may send to the UE a UE measurement report configuration. This may comprise an indication of the one or more parameters required for TDC. This configuration may be based on the UE capability information and / or the UE assistance information. The gNB may determine a maximum value of TDC timer which is provided to the UE. The UE measurement report configuration may configure different latency requirements, i.e., the maximum tolerable latency for different information elements in UE measurement configuration. The number of different latency requirements may fit the number of TDC timers that can be simultaneously active at the UE. In some embodiments, the values for the different maximum tolerable latencies may be selected from a predefined set of values. In another embodiment, the particular values for the maximum tolerable latencies can be indicated to the UE. If the gNB has no information about the number of TDC timers that can be active simultaneously, the gNB may only indicate one latency requirement for information elements related to the TDC job(s). In some embodiment, this indication may be provided by single bit. For example the value “1” states imposing a relaxed latency while the value for the maximum tolerable latency is agreed to be a specific value or even no maximum latency In another embodiment, the exact value for the maximum tolerable latency can be stated. The value set for the latency requirement may be selected taking into account one or more of the UE measurement configuration, UE capabilities, UE assistance information, and / or available resources (e.g., radio, storage and other training data) at the gNB. When the gNB receives the relevant UE assistance information, the gNB may adjust the latency requirement in the UE measurement report configuration to take the current status of the UE into account and assist the UE in reducing the complexity of the jobs it handles. The UE measurement report configuration may comprise an indication of an expired timer occurrence for at least one measurement. The UE measurement report configuration may indicate that the UE is to inform the gNB when a TDC timer expires. This may allow the gNB, e.g., to recognize failures in transmission of TDC related reports. This may be used to optimize the TDC process, e.g., by adjusting the latency requirement or better UE selection contributing to TDC. As referenced 8, after reception of the UE measurement report configuration from the gNB, the UE starts measuring the data according to the received UE measurement configuration. As discussed previously, the UE measurement report configuration may contain more than one latency requirement (value of maximum tolerable latency). For example latency_requirement#l for data type#X and latency_requirement#2 for data type#Y. When the first UE measurement report with data type#X is ready for transmission, the UE starts one TDC timer for latency_requirement#l. The same holds for latency_requirement#2 and type#Y. The timer continues during all RRC states without interruption. The TDC timer expires if any of the below conditions are met: - If the timer value reaches the latency requirement value. - If all the measurement reports related to this TDC timer are transmitted by the UE (and received by the gNB). The UE can decide when to transmit the UE measurement reports. This may be based on the internal status of the UE such as available power, buffer, etc. The defined one or more latencies are taken into account when determining when to transmit the UE measurement reports. However, the UE should perform the transmission before the corresponding TDC timer expires and the latency requirement becomes violated. All measurements may have timestamps so that gNB can use the time stamps to sort the measurements. As referenced 9, when UE is ready to transmit training data, it sets the value of the TDC indicator to indicate that TD is available. For example the "AvailableTDCindicator” is set to “1” . As referenced 10, the UE transmits the indicator to the gNB. The behaviour when the UE is in an inactive or idle state will now be described with reference to the part of the procedure referenced 11. It is the responsibility of the UE to ensure training data is delivered to the data collector without violating the latency requirement considering its limitations such as storage capacity. Therefore, if a TDC timer is close to expiry while in the RRC Jnactve / idle, i.e., violating a latency requirement, the UE may: a. Return to RRC_connected state b. Sets the value of the TDC indicator to indicate that TD is available - e.g. set the "AvailableTDCindicator" to “1". c. Transmits the indicator to the gNB The gNB may retrieve the training data from the UE with a sense of urgency. As referenced 12, on receipt of the indicator indicating that TD is available for collection, the gNB will retrieve the training data. The training data may comprise the associated time stamp. As referenced 13, the UE may indicate the expiry of a TDC timer set for a specific latency requirement. This may be after the expiry of the TDC timer. The requirement to provide the indication of expiry maybe indicated in the UE measurement report configuration. As referenced 14, this may assist the gNB to evaluate the success of TDC. For example if the TDC is expired but the corresponding data is not received, the TDC is incomplete and should be performed again. One or more parameters such as latency requirement can be adjusted. For example, if the TDC is expired and all data is collected, the data collector may learn from this experience that the parameters of the configuration were well set. Reference is made to Figures 5A and 5B which shows a modification of the procedure shown in Figures 4A and 4B. This shows the relationship to MDT data collection. The procedure is general as set out in relation to Figures 4A and 4B. Signalling for MDT activation (as known) may be provided (not shown). As referenced 15, the gNB may indicate to the trace collection entity (TCE) that an MDT file is ready to be transferred. As referenced 16, the MDT file is transferred. Reference is made to Figures 6A and 6B which shows an example where the data collector is an LMF. The training data collected may relate to, for example positioning. It should be noted that intermediary points between the LMF and the gNB, and between the LMF and the UE have been removed. The UE may be for example a PRU (positioning reference unit) in some embodiments. As referenced 1, the UE receives a request from the LMF for information about the capability of the UE to support LPP.. The message may be a LPP capability enquiry. As referenced 2, the UE provides the LMF with LPP capability information. Alternatively or additionally, the LMF may obtain at least a part of the UE context information from the (Unified Data Management) UDM. This UE capability may comprise UE capability information such as previously discussed. For example, the UE capability information may be as discussed in relation to the part of the procedure of Figures 4A and 4B referenced 2. As referenced 3, the LMF may set a maximum tolerable latency for different data collection jobs. This may be based on the UE capability information and the UE assistance information (not shown but may be received from the gNB over, e.g., NRPPa). (NR positioning protocol A (NRPPa) protocol is to carry the positioning information between NG-RAN and LMF) This may be as previously discussed. To regulate the LPP interface capability and the LMF storage resources while aiming for successful TDC from various UEs with different capabilities and status, the LMF may set a maximum tolerable latency for different data collection jobs. This may take into account UE measurement configuration. The LMF may have knowledge of the UE measurement configuration from the gNB. the UE or the LMF itself. As referenced 4, the LMF provides the gNB with a measurement configuration or measurement configuration recommendation for TDC over NRPPa. The measurement configuration may be as previously described. As referenced 5, the gNB provides to the UE a measurement configuration for TDC. This may provide configuration information for the transmission timing of the (reference) signals used at UE for TDC. This may be based on the measurement configuration or measurement configuration recommendation for TDC from the LMF. The measurement configuration may be as previously described. As referenced 6, the LMF may send to the UE an LLP request location information. This information may comprise an indication of the one or more parameters required for TDC. This information may comprise information about a maximum tolerable latency for reporting of TD. This information may provide a measurement report configuration for location related measurements. The UE may be configured to measure the radio signal for positioning or estimate / measure the location itself. The measurement report configuration may be as previously described. As referenced 7, after reception of the LLP request location information from the gNB, the UE starts measuring the data according to the received LLP request location information. As discussed previously, there may contain more than one latency requirement (value of maximum tolerable latency). For example latency_requirement#l for data type#X and latency_requirement#2 for data type#Y. When the first UE measurement report with data type#X is ready for transmission, the UE starts one TDC timer for latency_requirement#l. The same holds for latency_requirement#2 and type#Y. The timer continues during all RRC states without interruption. The TDC timer expires if any of the below conditions are met: - If the timer value reaches the latency requirement value. - If all the measurement reports related to this TDC timer are transmitted by the UE (and received by the LMF). The UE can decide when to transmit the UE measurement reports. This may be based on the internal status of the UE such as available power, buffer, etc. The defined one or more latencies are taken into account when determining when to transmit the UE measurement reports. However, the UE should perform the transmission before the corresponding TDC timer expires and the latency requirement becomes violated. All measurements may have timestamps so that the LMF can use the time stamps to sort the measurements. As referenced 8, when UE is ready to transmit training data, it sets the value of the TDC indicator to indicate that TD is available. For example the "AvailableTDCindicator” is set to "1”. As referenced 9, the UE transmits the indicator to the LMF. The behaviour when the UE is in an inactive or idle state will now be described with reference to the part of the procedure referenced 10. It is the responsibility of the UE to ensure training data is delivered to the data collector without violating the latency requirement considering its limitations such as storage capacity. Therefore, if a TDC timer is close to expiry while in the RRCJnactive / idle, i.e., violating a latency requirement, the UE may: a. Return to RRC_connected state b. Sets the value of the TDC indicator to indicate that TD is available - e.g. set the "AvailableTDCindicator” to "1”. c. Transmits the indicator to the gNB The LMF may retrieve the training data from the UE with a sense of urgency. As referenced 11, on receipt of the indicator indicating that TD is available for collection, the LMF will retrieve the training data. The training data may comprise the associated time stamp. As referenced 12, the UE may indicate the expiry of a TDC timer set for a specific latency requirement. This may be after the expiry of the TDC timer. As referenced 13, this may assist the LMF to evaluate the success of TDC. For example if the TDC is expired but the corresponding data is not received, the TDC is incomplete and should be performed again. One or more parameters such as latency requirement can be adjusted. For example, if the TDC is expired and all data is collected, the LMF may learn from this experience that the parameters of the configuration were well set. Reference is made to FIGs. 7 to 11 which shows some methods of some example embodiments. The respective methods may be performed by an apparatus. The apparatus may comprise suitable means, such as circuitry for providing the method. Alternatively or additionally, the apparatus may comprise 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 provide the method below. Alternatively or additionally, the apparatus may be such as discussed in relation to FIG. 13. The respective methods may be provided by computer program code or computer executable instructions. Reference is made to Figure 7. The apparatus may be or provided in a user equipment. The method comprises as referenced Al, sending to a network, information about a capability of a user equipment to store collected training data. The method comprises as referenced A2, receiving from the network, information about at least one latency for reporting collected training data to a data collector. The method comprises as referenced A3, collecting training data and further reporting the collected training data to the network, within a time window, based on the at least one latency for reporting collected training data. Reference is made to Figure 8. The apparatus may be or provided in a network node. The network node may be a data collector. The method comprises as referenced Bl, receiving information about a capability of a user equipment to store collected training data. The method comprises as referenced B2, providing information to the user equipment about at least one latency for reporting collected training data to a data collector. The method comprises as referenced B3, receiving collected training data from the user equipment within a time window, based on the at least one latency for reporting collected training data. Reference is made to Figure 9. The apparatus may be or provided in a user equipment. The method comprises as referenced Cl, sending to a base station, information about a capability of the user equipment to store collected training data. The method comprises as referenced C2, receiving from the base station, information about at one latency for reporting collected training data to the base station. The method comprises as referenced C3, collecting training data and reporting the collected training data to the base station, within a time window based on the information about the at least one latency for reporting collected training data. Reference is made to Figure 10. The apparatus may be or provided in a radio access node. The radio access node may be a base station. The method comprises as referenced DI, receiving from a user equipment, information about a capability of the user equipment to store collected training data. The method comprises as referenced D2, providing the user equipment with information about at one latency for reporting collected training data. The method comprises as referenced D3, receiving from the user equipment, collected training data within a time window based on the information about the at least one latency for reporting collected training data. Reference is made to Figure 11. The apparatus may be or provided in a user equipment. The method comprises as referenced El, sending to a location management function, information about the capability of a user equipment to store collected training data relating to location or positioning measurements. The method comprises as referenced E2, receiving from location management function, information about at least one latency for reporting collected training data to the location management function. The method comprises as referenced E3, collecting training data relating to location or positioning measurements and reporting the collected training data to the location management function, within a time window based on the information about the at least one latency for reporting collected training data. Reference is made to Figure 12. The apparatus may provide a location management function. The method comprises as referenced Fl, receiving, information about a capability of the user equipment to store collected training data relating to location or positioning measurements. The method comprises as referenced F2, providing to the user equipment, information about at least one latency for reporting collected training data to the location management function. The method comprises as referenced F3, receiving training data relating to location or positioning measurements within a time window based on the information about the at least one latency for reporting collected training data. Fig. 13 shows, by way of example, a block diagram of an apparatus 10. The apparatus 10 comprises, for example, at least one processor 12 and at least one memory 14 storing instructions 15 that, when executed by the at least one processor, cause the apparatus 10 at least to perform the method or methods as disclosed herein, and any of the embodiments thereof. In an example, the at least one memory and the instructions (e.g. a computer program code, software), are configured, with the at least one processor, to cause the apparatus 10 to perform the method or methods as disclosed herein, and any of the embodiments thereof. A processor 12 may comprise circuitry, or be constituted as circuitry or circuitries, the circuitry or circuitries being configured to perform phases of methods in accordance with example embodiments described herein. 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 circuits] with software / firmware and (ii] any portions of hardware processors] with software (including digital signal processors]], software, and memory(ies] that work together to cause an apparatus, such as a user equipment, to perform various functions] and (c] hardware circuit(s] and or processor's], such as a microprocessors] or a portion of a microprocessors], that requires software (e.g., firmware] for operation, but the software may not be present when it is not needed for operation. 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. The memory 14 may be implemented using any suitable data storage technology. The memory may comprise a database for storing data. The memory 14 may be at least in part external to apparatus 10 but accessible to apparatus 10. The instructions 15 may be comprised in a computer readable medium or a non-transitory computer readable medium. A 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. random access memory, RAM, vs. read only memory, ROM]. For example, the apparatus 10 is a terminal device, such as a UE. As another example, the apparatus is comprised in such a terminal device, e.g. as a chipset configured to control the terminal device. The apparatus 10 may be caused or configured to perform at least the method of Figs. 7, 9 or 11 and / or any one or more of the embodiments described. As another example, the apparatus 10 is a RAN node, e.g. a gNB. In another embodiment, the apparatus is comprised in such a network node, e.g., as a chipset configured to control the network node. The apparatus 10 may be caused or configured to perform at least the method of Fig. 8 or 10 and / or any one or more of the embodiments described. As another example, the apparatus 10 is a LMF or provides an LMF. In another embodiment, the apparatus is comprised in such an LMF, e.g. as a chipset configured to control the network node. The apparatus 10 may be caused or configured to perform at least the method of Fig. 8 or 12 and / or any one or more of the embodiments described. The apparatus may optionally comprise one or more entities of any of protocol layers, such as a MAC entity, an RRC entity, an RLC entity, a PDCP entity or a PHY entity. The apparatus 10 comprises a radio interface 16. The radio interface 16 may provide the apparatus 10 with communication capabilities. The radio interface 16 may comprise a receiver configured to receive information in accordance with at least one cellular or non-cellular standard. The radio interface 16 may comprise a transmitter configured to transmit information in accordance with at least one cellular or non-cellular standard. The receiver may comprise more than one receiver. The transmitter may comprise more than one transmitter. The radio interface 16 may comprise a transceiver configured to receive and transmit information in accordance with at least one cellular or non-cellular standard. The transceiver may comprise more than one transceiver. The apparatus 10 may comprise a user interface 18 comprising, for example, at least one of a keypad, a microphone, a touch display, a display, a speaker, etc. The user interface 18 may be used to control the apparatus by the user. The user interface 18 may be external to the apparatus 10. For example, the apparatus 10 may be connected to another device, such as a computer, either via wireless or wired connection, and the apparatus 10 is controlled by the user via the computer. In an embodiment, at least some of the processes described herein may be carried out by an apparatus comprising means for carrying out at least some of the described processes. Means for performing method steps as disclosed herein may include software and / or hardware components of the apparatus 10. For example, the at least one processor 12, the memory 14, and the computer program code form means for carrying out the method or methods as disclosed herein, and any of the embodiments thereof. As used herein the term “means” is to be construed in singular form, i.e., referring to a single element, or in plural form, i.e. referring to a combination of single elements. Therefore, terminology “means for [performing A, B, C]”, is to be interpreted to cover an apparatus in which there is only one means for performing A, B and C, or where there are separate means for performing A, B and C, or partially or fully overlapping means for performing A, B, C. Further, terminology “means for performing A, means for performing B, means for performing C" is to be interpreted to cover an apparatus in which there is only one means for performing A, B and C, or where there are separate means for performing A, B and C, or partially or fully overlapping means for performing A, B, C. Even though the invention has been described above with reference to an example according to the accompanying drawings, it is clear that the invention is not restricted thereto but can be modified in several ways within the scope of the appended claims. Therefore, all words and expressions should be interpreted broadly and they are intended to illustrate, not to restrict, the embodiment. It will be obvious to a person skilled in the art that, as technology advances, the inventive concept can be implemented in various ways. Further, it is clear to a person skilled in the art that the described embodiments may, but are not required to, be combined with other embodiments in various ways.

Claims

1. A user equipment comprising:means for sending to a location management function, information about a capability of the user equipment to store collected training data relating to location or positioning measurements;means for receiving from a location management function, information about at least one latency for reporting collected training data to the location management function; andmeans for collecting training data relating to location or positioning measurements and reporting the collected training data to the location management function, within a time window based on the information about the at least one latency for reporting collected training data.

2. The user equipment as claimed in claim 1, wherein the means is for receiving from a base station, information about a measurement configuration to be used to collect the training data.

3. The user equipment as claimed in claim 2, wherein the information about the measurement configuration comprises information about one or more of:reference signals to be used for the collecting of the training data; and transmission times of the reference signals to be used for the collecting of the training data.

4. The user equipment as claimed in claim 2 or 3, wherein information about the transmission times of the reference signals to be used for the collecting of the training data indicates that the reference signals are transmitted periodically, aperiodically, semi-statically, or on an event basis.

5. The user equipment as claimed in claim 2, 3, or 4, wherein the information about the measurement configuration to be used to collect the training data is received in a radio resource control message.

6. The user equipment as claimed in any preceding claim, wherein the information about the capability of the user equipment to store collected training data relating to location or positioning measurements is provided in an LTE positioning protocol message.

7. The user equipment as claimed in any preceding claim, wherein the information about at least one latency for reporting collected training data to the location management function is provided in an LTE positioning protocol message.

8. The user equipment as claimed in any preceding claim, wherein information about at least one latency for reporting collected training data to the location management function is provided in a request for location information message.

9. The user equipment as claimed in any preceding claim, wherein the at least one latency for reporting collected training data is dependent on one or more of:transmission times associated with reference signals used for the collecting of training data;the capability of the user equipment to store collected training data;an availability of one or more timers associated with the collecting of the training data;a mobility profile of the user equipment;the amount of collected training data from a user equipment or a group of user equipment;a storage capacity of the location management function;availability of radio resources;availability of control plane radio resources; ora measurement configuration of the user equipment for the collecting of the training data.10 The user equipment as claimed in any preceding claim, wherein the information about the capability of the user equipment to store collected training data comprises information about one or more of:a maximum storage capacity of the user equipment;a maximum storage capacity of the user equipment for training data collection;a currently available storage capacity of the user equipment for training data collection; ora change in the available storage capacity of the user equipment for training data collection.

11. The user equipment as claimed in any preceding claim, comprising means for starting a timer when the collection of training data is started, said timer being based on one of said at least one latency.

12. The user equipment as claimed in claim 11, comprising means for determining that the timer is within a threshold amount of time before expiry of the timer and means for, in response to determining that the timer is within a threshold amount of time before expiry of the time, causing one or more indicators that the collected training data is ready to be reported to be sent to the location management function.

13. The user equipment as claimed in claim 12, comprising means for determining that the user equipment is not in a connected state and the timer is within a threshold amount of time before expiry of the timer and means for, in response to determining that the equipment is not in a connected state and the timer is within a threshold amount of time before expiry of the time, causing the user equipment to enter the connected state.

14. The user equipment as claimed in claim 13, comprising means for, when user equipment enters the connected state, causing one or more indicators that the collected training data is ready to be reported to be sent to the location management function.

15. The user equipment as claimed in claim 11, comprising means for determining that the user equipment is about to enter an idle or inactive state, and before the user equipment enters the idle or inactive state, the means for reporting is for reporting the collected data before the user equipment enters the idle or inactive state16. The user equipment as claimed in any of claims 1 to 14, comprising means for determining that the user equipment is about to enter an idle or inactive state, and meansfor saving, before the user equipment enters the idle or inactive state, the collected data before the user equipment enters the idle or inactive state17. The user equipment as claimed in 11 or any claim appended thereto, wherein the timer is ended if all the collected training data has been reported or if the timer expires.

18. The user equipment as claimed in claim 11 or any claim appended thereto, comprising means for reporting to the location management function, an expiry of the timer.

19. An apparatus providing a location management function, the apparatus comprising means for:receiving, information about a capability of a user equipment to store collected training data relating to location or positioning measurements;providing to the user equipment, information about at least one latency for reporting collected training data to the location management function; andreceiving training data relating to location or positioning measurements within a time window based on the information about the at least one latency for reporting collected training data.

20. The apparatus as claimed in claim 19, wherein the means is for providing the information about at least one latency for reporting collected training data to the location management function in a LTE positioning protocol message,21. The apparatus as claimed in claim 19 or 20, wherein the mean is for receiving the information about the capability of the user equipment to store collected training data relating to location or positioning measurements in a LTE positioning protocol message,22. The apparatus as claimed in claim 19, 20 or 21, wherein the means is for sending measurement configuration information relating to the location or positioning measurements to a base station.

23. A method comprising:sending to a location management function, information about the capability of a user equipment to store collected training data relating to location or positioning measurements;receiving from location management function, information about at least one latency for reporting collected training data to the location management function; andcollecting training data relating to location or positioning measurements and reporting the collected training data to the location management function, within a time window based on the information about the at least one latency for reporting collected training data.

24. A method comprising:receiving, information about a capability of a user equipment to store collected training data relating to location or positioning measurements;providing to the user equipment, information about at least one latency for reporting collected training data to the location management function; andreceiving training data relating to location or positioning measurements within a time window based on the information about the at least one latency for reporting collected training data.

25. A computer program comprising computer executable instructions which when run cause the method of claim 23 or claim 24 to be performed.40

Images