Methods, communications device, and network node

Abstract

Operating a communications device (User Equipment 610) configured to communicate with a Radio Access Network (gNB 620 or location management function, LMF), comprises: receiving, information for use b

Description

BACKGROUND Field of Disclosure The present disclosure relates to wireless communications, and particularly to communications devices and network nodes and methods of operating such communications devices and network nodes for the purposes of AI model monitoring. Description of Related Art The “background” description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description which may not otherwise qualify as prior art at the time of filing, are neither expressly or impliedly admitted as prior art against the present invention. Previous generation mobile telecommunication systems, such as those based on the 3GPP defined UMTS and Long Term Evolution (LTE) architecture, are able to support a wider range of services than simple voice and messaging services offered by previous generations of mobile telecommunication systems. For example, with the improved radio interface and enhanced data rates provided by LTE systems, a user is able to enjoy high data rate applications such as mobile video streaming and mobile video conferencing that would previously only have been available via a fixed line data connection. The demand to deploy such networks is therefore strong and the coverage area of these networks, i.e. geographic locations where access to the networks is possible, is expected to continue to increase rapidly. Current and future wireless communications networks are expected to routinely and efficiently support communications with an ever-increasing range of devices associated with a wider range of data traffic profiles and types than existing systems are optimised to support. For example, it is expected future wireless communications networks will be expected to efficiently support communications with devices including reduced complexity devices, machine type communication (MTC) devices, high resolution video displays, virtual reality headsets, Extended Reality (XR) and so on. Some of these different types of devices may be deployed in very large numbers, for example low complexity devices for supporting the “The Internet of Things”, and may typically be associated with the transmissions of relatively small amounts of data with relatively high latency tolerance. Other types of device, for example supporting high-definition video streaming, may be associated with transmissions of relatively large amounts of data with relatively low latency tolerance. Other types of device, for example used for autonomous vehicle communications and for other critical applications, may be characterised by data that should be transmitted through the network with low latency and high reliability. A single device type might also be associated with different traffic profiles / characteristics depending on the application(s) it is running. For example, different considerations may apply for efficiently supporting data exchange with a smartphone when it is running a video streaming application (high downlink data) as compared to when it is running an Internet browsing application (sporadic uplink and downlink data) or being used for voice communications by an emergency responder in an emergency scenario (data subject to stringent reliability and latency requirements). In view of this there is expected to be a desire for current wireless communications networks, for example those which may be referred to as 5G or new radio (NR) systems / new radio access technology (RAT) systems, or indeed future 6G wireless communications, as well as future iterations / releases of existing systems, to efficiently support connectivity for a wide range of devices associated with different applications and different characteristic data traffic profiles and requirements. One example of a new service is referred to as Ultra Reliable Low Latency Communications (URLLC) services which, as its name suggests, requires that a data unit or packet be communicated with a high reliability and with a low communications delay. Another example of a new service is extended Reality (XR), which may be provided by various user equipment such as wearable devices. XR combines real-world and virtual environments, incorporating aspects such as augmented reality (AR), mixed reality (MR), and virtual reality (VR), and thus requires high quality and minimised interaction delay. Services such as URLLC and XR therefore represent a challenging example for both LTE type communications systems and 5G / NR communications systems, as well as future generation communications systems. 5G NR has continuously evolved and the current work plan includes 5G-NR-advanced in which some further enhancements are expected, especially to support new use-cases / scenarios with higher requirements. One of these aspects includes the use of artificial intelligence (AI) or machine learning (ML) to model parameters which can be used to perform certain tasks. The desire to support these new use-cases and scenarios gives rise to new challenges for efficiently handling communications in wireless communications systems that need to be addressed. SUMMARY OF THE DISCLOSURE The present disclosure can help address or mitigate at least some of the issues discussed above. Embodiments of the present technique can provide a method of operating a communications device configured to communicate with a radio access network. The method comprises receiving, from a network node, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence (AI) model used by the communications device to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics, calculating the one or more performance metrics by inputting the input data to the AI model to produce an estimated output, analyzing the estimated output with respect to an expected output, and transmitting, to the network node based on the analysis of the estimated output, a performance monitoring report. Such embodiments of the present technique, which, in addition to methods of operating a communications device (i.e. a UE), relate to methods of operating a network node (e.g. a radio access node such as a gNB or base station, or a core network node such as a location management function (LMF)), to such communications devices and network nodes, to circuitry for such communications devices and network nodes, to wireless communications systems, to computer programs, and to computer-readable storage mediums, can allow for the more efficient and effective operation of communications devices at which AI / ML models are utilised to perform tasks using model inference. Respective aspects and features of the present disclosure are defined in the appended claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary, but are not restrictive, of the present technology. The described embodiments, together with further advantages, will be best understood by reference to the following detailed description taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS A more complete appreciation of the disclosure and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings wherein like reference numerals designate identical or corresponding parts throughout the several views, and wherein: Figure 1 schematically represents some aspects of an LTE-type wireless telecommunication system which may be configured to operate in accordance with certain embodiments of the present disclosure; Figure 2 schematically represents some aspects of a new radio access technology (RAT) wireless telecommunications system which may be configured to operate in accordance with certain embodiments of the present disclosure; Figure 3 is a schematic block diagram of an example infrastructure equipment and communications device which may be configured to operate in accordance with certain embodiments of the present disclosure; Figure 4 schematically illustrates a life cycle management (LCM) architecture for an artificial intelligence (AI) model; Figure 5 schematically illustrates a deployment of Al / machinc learning (ML) positioning; Figure 6 shows a part schematic, part message flow diagram representation of an example wireless communications system comprising a first apparatus and a second apparatus in accordance with embodiments of the present technique; Figure 7 illustrates an example of a performance monitoring operation in accordance with arrangements of embodiments of the present technique; Figure 8 shows a part schematic, part message flow diagram representation of a first example process of communications in a communications system in which a communications device is configured to perform a positioning task by using AI model inference in accordance with embodiments of the present technique; Figure 9 shows a part schematic, part message flow diagram representation of a second example process of communications in a communications system in which a communications device is configured to perform a beam management task by using AI model inference in accordance with embodiments of the present technique; Figure 10 shows a part schematic, part message flow diagram representation of a third example process of communications in a communications system in which a communications device is configured to perform a channel state information (CSI) feedback enhancement task by using AI model inference in accordance with embodiments of the present technique; and Figure 11 shows a flow diagram illustrating an example process of operating a communications device in accordance with embodiments of the present technique. DETAILED DESCRIPTION OF THE EMBODIMENTS Long Term Evolution Advanced Radio Access Technology (4G) Figure 1 provides a schematic diagram illustrating some basic functionality of a mobile telecommunications network / system 6 operating generally in accordance with LTE principles, but which may also support other radio access technologies, and which may be adapted to implement embodiments of the disclosure as described herein. Various elements of Figure 1 and certain aspects of their respective modes of operation are well-known and defined in the relevant standards administered by the 3GPP (RTM) body, and also described in many books on the subject, for example, Holma H. and Toskala A [1], It will be appreciated that operational aspects of the telecommunications networks discussed herein which are not specifically described (for example in relation to specific communication protocols and physical channels for communicating between different elements) may be implemented in accordance with any known techniques, for example according to the relevant standards and known proposed modifications and additions to the relevant standards. The network 6 includes a plurality of base stations 1 connected to a core network 2. Each base station provides a coverage area 3 (i.e. a cell) within which data can be communicated to and from communications devices 4. Although each base station 1 is shown in Figure 1 as a single entity, the skilled person will appreciate that some of the functions of the base station may be carried out by disparate, inter-connected elements, such as antennas (or antennae), remote radio heads, amplifiers, etc. Collectively, one or more base stations may form a radio access network. Data is transmitted from base stations 1 to communications devices 4 within their respective coverage areas 3 via a radio downlink (DL). Data is transmitted from communications devices 4 to the base stations 1 via a radio uplink (UL). The core network 2 routes data to and from the communications devices 4 via the respective base stations 1 and provides functions such as authentication, mobility management, charging and so on. Communications devices may also be referred to as mobile stations, user equipment (UEs), user terminals, mobile radios, mobile terminals, terminal devices, wireless transmit and receive units (WTRUs), and so forth. Services provided by the core network 2 may include connectivity to the internet or to external telephony services. The core network 2 may further track the location of the communications devices 4 so that it can efficiently contact (i.e. page) the communications devices 4 for transmitting downlink data towards the communications devices 4. A base station for 4G LTE, which is an example of network infrastructure equipment, may also be referred to as a transceiver station, a radio access node, e-nodeB, eNB, ng-eNB, an EUTRAN node and so forth. In this regard different terminology is often associated with different generations of wireless telecommunications systems for elements providing broadly comparable functionality. However, certain embodiments of the disclosure may be equally implemented in different generations of wireless telecommunications systems, and for simplicity certain terminology may be used regardless of the underlying network architecture. That is to say, the use of a specific term in relation to certain example implementations is not intended to indicate these implementations are limited to a certain generation of network that may be most associated with that particular terminology. New Radio Access Technology (5G) Systems incorporating NR technology are expected to support different services (or types of services), which may be characterised by different requirements for latency, data rate and / or reliability. For example, Enhanced Mobile Broadband (eMBB) services are characterised by high capacity with a requirement to support up to 20 Gb / s. The requirements for Ultra Reliable and Low Latency Communications (URLLC) services are for one transmission of a 32 byte packet to be transmitted from the radio protocol layer 2 / 3 SDU ingress point to the radio protocol layer 2 / 3 SDU egress point of the radio interface within 1 ms with a reliability of 1 - 10-5 (99.999 %) or higher (99.9999%) [2], Massive Machine Type Communications (mMTC) is another example of a service which may be supported by NR-based communications networks. In addition, systems may be expected to support further enhancements related to Industrial Internet of Things (IIoT) in order to support services with new requirements of high availability, high reliability, low latency, and in some cases, high-accuracy positioning. An example configuration of a wireless communications network which uses some of the terminology proposed for and used in NR and 5G is shown in Figure 2. In Figure 2 a plurality of transmission and reception points (TRPs) 10 are connected to distributed control units (DUs) 41, 42 by a connection interface represented as a line 16. Each of the TRPs 10 is arranged to transmit and receive signals via a wireless access interface within a radio frequency bandwidth available to the wireless communications network. Thus, within a range for performing radio communications via the wireless access interface, each of the TRPs 10, forms a cell of the wireless communications network as represented by a circle 12. As such, wireless communications devices 14 which are within a radio communications range provided by the cells 12 can transmit and receive signals to and from the TRPs 10 via the wireless access interface. Each of the distributed units 41, 42 are connected to a central unit (CU) 40 (which may be referred to as a controlling node) via an interface 46. The central unit 40 is then connected to the core network 20 which may contain all other functions required to transmit data for communicating to and from the wireless communications devices and the core network 20 may be connected to other networks 25. In one or more embodiments disclosed herein, one or more TRP(s) 10, one or more DU(s) and one CU can be included in a base station. The base station for 5G NR, which is an example of network infrastructure equipment, may also be referred to as a radio access node, gNodeB, gNB, en-gNB, NG RAN node and so forth. In one or more embodiments disclosed herein, the DU is a logical node hosting RLC, MAC and PHY layers of the base station. The DU operation is partly controlled by the CU. One DU may support one or multiple cells. One cell may be supported by only one DU. The DU may terminate the intra-base station interface (e.g. Fl interface) connected with the CU. The CU is a logical node hosting RRC, SDAP and PDCP protocols of the base station. The CU may control the operation of one or more DUs. The CU may terminate the intra-base station interface (e.g. Fl interface) connected with the DU. Additionally or alternatively, TRP 10 may be also called as RU (Radio Unit) or RRU (Remote Radio Unit). In one or more embodiments disclosed herein, TRP 10 (e.g. RU or RRU) may host part of the PHY layer (lower PHY layer). In this case, the DU may host the remaining PHY layer (higher PHY layer). One TRP may support one or multiple cells. Alternatively, two or more TRPs may form one or more cells. The elements of the wireless access network shown in Figure 2 may operate in a similar way to corresponding elements of an UTE network as described with regard to the example of Figure 1. It will be appreciated that operational aspects of the telecommunications network represented in Figure 2, and of other networks discussed herein in accordance with embodiments of the disclosure, which are not specifically described (for example in relation to specific communication protocols and physical channels for communicating between different elements) may be implemented in accordance with any known techniques, for example according to currently used approaches for implementing such operational aspects of wireless telecommunications systems, e.g. in accordance with the relevant standards. The TRPs 10 of Figure 2 may in part have a corresponding functionality to a base station or eNodeB of an UTE network, gNodeB of an NR network, or 6G Node B of a 6G network. Similarly, the communications devices 14 may have a functionality corresponding to the UE devices 4 known for operation with an LTE, NR or 6G network. It will be appreciated therefore that operational aspects of a new RAT network (for example in relation to specific communication protocols and physical channels for communicating between different elements) may be different to those known from LTE or other known mobile telecommunications standards. However, it will also be appreciated that each of the core network component, base stations and communications devices of a new RAT network will be functionally similar to, respectively, the core network component, base stations and communications devices of an LTE wireless communications network. In terms of broad top-level functionality, the core network 20 connected to the new RAT telecommunications system represented in Figure 2 may be broadly considered to correspond with the core network 2 represented in Figure 1, and the respective central units 40 and their associated distributed units 41, 42 / TRPs 10 may be broadly considered to provide functionality corresponding to the base stations 1 of Figure 1. The term network infrastructure equipment / access node may be used to encompass these elements and more conventional base station type elements of wireless telecommunications systems. Depending on the application at hand the responsibility for scheduling transmissions which are scheduled on the radio interface between the respective distributed units and the communications devices may lie with the controlling node / central unit and / or the distributed units / TRPs. A communications device 14 is represented in Figure 2 within the coverage area of the first communication cell 12. This communications device 14 may thus exchange signalling with the first central unit 40 in the first communication cell 12 via one of the distributed units / TRPs 10 associated with the first communication cell 12. It will further be appreciated that Figure 2 represents merely one example of a proposed architecture for a new RAT based telecommunications system in which approaches in accordance with the principles described herein may be adopted, and the functionality disclosed herein may also be applied in respect of wireless telecommunications systems having different architectures. Thus, certain embodiments of the disclosure as discussed herein may be implemented in wireless telecommunication systems / networks according to various different architectures, such as the example architectures shown in Figures 1 and 2. It will thus be appreciated the specific wireless telecommunications architecture in any given implementation is not of primary significance to the principles described herein. In this regard, certain embodiments of the disclosure may be described generally in the context of communications between network infrastructure equipment / access nodes and a communications device, wherein the specific nature of the network infrastructure equipment / access node and the communications device will depend on the network infrastructure for the implementation at hand. For example, in some scenarios the network infrastructure equipment / access node may comprise a base station, such as an LTE-type base station 1 as shown in Figure 1 which is adapted to provide functionality in accordance with the principles described herein, and in other examples the network infrastructure equipment may comprise a control unit / controlling node 40 and / or a TRP10 of the kind shown in Figure 2 which is adapted to provide functionality in accordance with the principles described herein. A more detailed diagram of some of the components of the network shown in Figure 2 is provided by Figure 3. In Figure 3, a TRP10 as shown in Figure 2 comprises, as a simplified representation, a transmitter 30, a receiver 32 and a controller or controlling processor 34 which may operate to control the transmitter 30 and the receiver 32 to transmit and receive radio signals to one or more UEs 14 within a cell 12 formed by the TRP10. As shown in Figure 3, an example UE 14 is shown to include a corresponding transmitter 49, a receiver 48 and a controller 44 which is configured to control the transmitter 49 and the receiver 48 to transmit signals representing uplink data to the wireless communications network via the wireless access interface formed by the TRP 10 and to receive downlink data as signals transmitted by the transmitter 30 and received by the receiver 48 in accordance with the conventional operation. The transmitters 30, 49 and the receivers 32, 48 (as well as other transmitters, receivers and transceivers described in relation to examples and embodiments of the present disclosure) may include radio frequency filters and amplifiers as well as signal processing components and devices in order to transmit and receive radio signals in accordance for example with the 5G / NR standard. The controllers 34, 44 (as well as other controllers described in relation to examples and embodiments of the present disclosure) may be, for example, a microprocessor, a CPU, or a dedicated chipset, etc., configured to carry out instructions which are stored on a computer readable medium, such as a non-volatile memory. The processing steps described herein may be carried out by, for example, a microprocessor in conjunction with a random access memory, operating according to instructions stored on a computer readable medium. The transmitters, the receivers and the controllers are schematically shown in Figure 3 as separate elements for ease of representation. However, it will be appreciated that the functionality of these elements can be provided in various different ways, for example using one or more suitably programmed programmable computer(s), or one or more suitably configured application-specific integrated circuit(s) / circuitry / chip(s) / chipset(s). As will be appreciated the infrastructure equipment / TRP / base station as well as the UE / communications device will in general comprise various other elements associated with its operating functionality. As shown in Figure 3, the TRP10 also includes a network interface 50 which connects to the DU 42 via a physical interface 16. The network interface 50 therefore provides a communication link for data and signalling traffic from the TRP 10 via the DU 42 and the CU 40 to the core network 20. In the case of 5G, the interface 46 between the DU 42 and the CU 40 is known as the Fl interface which can be a physical or a logical interface. The Fl interface 46 between CU and DU may operate in accordance with specifications 3GPP TS 38.470 and 3GPP TS 38.473, and may be formed from a fibre optic or other wired or wireless high bandwidth connection. In one example the connection 16 from the TRP 10 to the DU 42 is via fibre optic. The connection between a TRP 10 and the core network 20 can be generally referred to as a backhaul, which comprises the interface 16 from the network interface 50 of the TRP 10 to the DU 42 and the Fl interface 46 from the DU 42 to the CU 40. The core network 20 is connected to the CU 40 via the N2 (also called NG-C) interface for carrying control data and via the N3 (also called NG-U) interface for carrying user data. The core network 20 may comprise core network functions such as a location management function (EMF) for managing a position of communications devices in the wireless communications network. In addition, the core network 20 may comprise one or more network functions for Artificial Intelligence / Machine Eeaming (AI / ME) model management, training, and storage. Although reference is made to 5G networks, the discussions in this specification apply equally to 6G networks (and beyond) where there is expected to be significantly higher throughput, lower latency and higher reliability utilising sub-THz frequencies. In the case of 6G, base stations, which are an example of network infrastructure equipment, may also referred to as 6G NB (6G Node B), 6G RAN node, and so forth. In 6G, the core network 20 may be one or more network functions. Alternatively or additionally, the base station for 5G (e.g., gNodeB, gNB, NG RAN node) can be also used as the base station for 6G. Artificial Intelligence (AI) In existing techniques (also called “legacy techniques”), the position of a UE can be determined by a UE or LMF based on positioning measurements made by the base station or UE. Positioning measurements may be performed by a UE on downlink signals such as positioning reference signals (PRS), or performed by a base station on uplink signals such as sounding reference signals (SRS). Positioning measurements may comprise one or more of time of arrival (TOA), angle of arrival (AOA), angle of departure (AOD), a round trip time (RTT), reference signal received power (RSRP), and any other measurement used in determining the position of a UE. A UE may, for example, receive a plurality of downlink signals, each from a different base station, measure a time of arrival and / or angle of the downlink signals and, based on the measurements and the location information of the base station participating in the positioning measurements, determine its position (e.g. multilateration). In another example, an LMF may determine the target UE position based on the positioning measurements received from the target UE and the location information of the base station participating in the positioning measurements (e.g., multilateration). However, the precision of the position determined by existing techniques is limited. In order to address technical problems in determining a precise location / position estimation of a communications device, the use of Artificial Intelligence / Machine Learning (AI / ML) models for positioning was firstly studied in Release-18 of the 3GPP standards and further developed in later release(s). AI / ML-based positioning tends to outperform other positioning techniques because AI / ML models are configured to collect and process large amounts of positioning measurements and / or other relevant information elements. By performing model training (based on training data), AI / ML models learn and establish an understanding of the environment associated with the positioning measurements. AI / ML models may then be deployed, for example at a UE or base-station (such as a gNB), in order to generate output, such as improved (i.e. more accurate) positioning measurements or a position estimate. This process / operation is also known as AI / ML model inference. For example, the output positioning measurements may be improved in the sense that they are more likely to result in a more accurate position estimate. For example, a UE may receive a DL-PRS from a base station and make positioning measurements on it. However, the UE may not know that the DL-PRS reflected off an object before it reached the UE. The AI / ML model may be configured to correct for such reflections. The AI / ML model can produce output on refined line of sight (LOS) / non-LOS (NLOS) component identification. Additional detail on how AI / ML models can be used to generate more accurate positioning measurements, or generate a position estimate, can be found in [3], the contents of which are hereby incorporated by reference in their entirety. As examples, AI / ML models may utilise one or more of: supervised learning, generative AI, autoencoding, and reinforcement learning. These are explained in detail in the forthcoming paragraphs. Supervised Learning AI / ML models may implement a supervised machine learning model. The supervised learning model is trained using labelled training data to learn a function that maps inputs (typically provided as feature vectors) to outputs (i.e. labels). The labelled training data comprises pairs of inputs and corresponding output labels. The output labels are typically provided by an operator to indicate the desired output for each input. The supervised learning model processes the training data to produce an inferred function that can be used to map new (i.e. unseen) inputs to a label. The input data (during training and / or inference) may comprise various types of data, such as numerical values, images, video, text, or audio. Raw input data may be pre-processed to obtain an appropriate feature vector used as input to the model - for example, features of an image or text input may be extracted to obtain a corresponding feature vector. It will be appreciated that the type of input data and techniques for pre-processing of the data (if required) may be selected based on the specific task the supervised learning model is used for. Once prepared, the labelled training data set is used to train the supervised learning model. During training the model adjusts its internal parameters (e.g. weights) so as to optimize (e.g. minimize) an error function, aiming to minimize the discrepancy between the model’s predicted outputs and the labels provided as part of the training data. In some cases, the error function may include a regularization penalty to reduce overfitting of the model to the training data set. The supervised learning model may use one or more machine learning algorithms in order to learn a mapping between its inputs and outputs. Example suitable learning algorithms include linear regression, logistic regression, artificial neural networks, decision trees, support vector machines (SVM), random forests, and the K-nearest neighbour algorithm. For positioning AI / ML models, the input to the supervised learning model may comprise positioning measurements (for example, measurements of one or more PRSs, or one or more SRSs, such as time of arrival and angle of arrival) and the output of the supervised learning model may comprise a position estimate of the communications device or improved positioning measurements. Once trained, the supervised learning model may be used for inference - i.e. for predicting outputs for previously unseen input data. The supervised learning model may perform classification and / or regression tasks. In a classification task, the supervised learning model predicts discrete class labels for input data, and / or assigns the input data into predetermined categories. In a regression task, the supervised learning model predicts labels that are continuous values. For positioning AI / ML models, the supervised learning model is used to predict an output comprising improved positioning measurements or a position estimate based on an input comprising positioning measurements. In some cases, limited amounts of labelled data may be available for training of the model (e.g. because labelling of the data is expensive or impractical). In such cases, the supervised learning model may be extended to further use unlabelled data and / or to generate labelled data. Considering using unlabelled data, the training data may comprise both labelled and unlabelled training data, and semi-supervised learning may be used to learn a mapping between the model’s inputs and outputs. For example, a graph-based method such as Laplacian regularization may be used to extend a SVM algorithm to Laplacian SVM in order to perform semi-supervised learning on the partially labelled training data. Considering generating labelled data, an active learning model may be used in which the model actively queries an information source (such as a user, or operator) to label data points with the desired outputs. Labels are typically requested for only a subset of the training data set thus reducing the amount of labelling required as compared to fully supervised learning. The model may choose the examples for which labels are requested - for example, the model may request labels for data points that would most change the current model, or that would most reduce the model's generalization error. Semi-supervised learning algorithms may then be used to train the model based on the partially labelled data set. Generative AI AI / ML models may implement generative artificial intelligence (AI). A generative AI system learns patterns and structures in its input training data, in order to then generate new output data which exhibits similar characteristics to the training data. For positioning AI / ML models, the input training data may comprise positioning measurements and the output training data may comprise a position estimate of the communications device or improved positioning measurements. The generative AI system may generate output data based on an input prompt. The prompt may comprise various types of data, such as images, video, text, or audio. The prompt may be of the same or different data type to the model’s training and / or output data. The generative AI / ML model may comprise a generative model trained to learn a probability distribution of the input training data, and generate new output data based on this learned distribution. For example, for a set of data instances / observable variables (X) and a set of labels / target variables (Y) in the training data set, the generative model may learn a joint probability distribution of data instances and labels p(X,Y), and / or a probability distribution of the data instances p(X) (for example where no labels are available). Example suitable generative models for learning a probability distribution of the input training data include Variational Autoencoder (VAEs), transformer-based models, diffusion models (e.g. de-noising diffusion probabilistic models (DDPMs)), Reinforcement Learning (RL), and Generative Adversarial Networks (GANs). The choice of generative model may depend on the specific task performed by the generative AI / ML. The generative model may comprise one or more artificial neural networks. For example, a Variational Autoencoder (VAE) may comprise a pair of neural networks acting as an encoder and a decoder to and from a reduced (i.e. latent space) representation of the training data respectively, and a Generative Adversarial Network (GAN) may comprise a first ‘generator’ neural network that generates new data and a second ‘discriminator’ neural network that learns to discriminate between generated data and real data. The one or more constituent neural networks of the generative model may be trained together or separately. During training the generative model may adjust its internal parameters (e.g. neural network weights) so as to optimize (e.g. minimize) a loss / error function, aiming to minimize discrepancy between the generated output data and desired output data. It will be appreciated that the specific loss function, and algorithm used to optimize the function may vary depending on the nature of the generative model, and its intended application. For example, a mean squared error loss function may be used for an image generation task, and a cross-entropy loss function may be used for a text generation task. These loss functions may be optimized using various existing optimization algorithms, such as gradient descent. Once trained, the generative model may be used to generate new output data based on an input prompt. The input prompt may be provided by a user, or by an appropriate device (e.g. using an application programming interface (API)). Thus, the generative AI / ML model allows generating new based on only a prompt and without requiring detailed instructions for doing so. Autoencoders AI / ML models may implement autoencoding. An autoencoder is a type of an unsupervised machine learning model that uses one or more artificial neural networks to learn an efficient representation of unlabelled input data. The autoencoder may be used to encode various types of data, such as images, video, text, audio, or positioning measurements. The autoencoder may comprise an encoder neural network that encodes input data into a reduced representation (also called a “latent space”), and a decoder neural network that aims to recreate the input data from the encoded reduced representation. The latent space is typically of a lower-dimension than the input data - thus, the latent space generated by the encoder typically provides a more efficient, compressed representation of the input data that requires less memory storage than the original input data. The encoder neural network may comprise one or more layers that transform input data into a reduced representation. The encoder neural network receives input data, and the final layer of the encoder neural network outputs a reduced representation of the input data, i.e. a latent space (also termed a “bottleneck layer”). The decoder neural network comprises one or more layers that transform data from the latent space into output data of the same dimensionality as the data input to the encoder. The decoder aims to reconstruct the data originally input to the encoder neural network from the latent space representation of the data. The encoder and / or decoder neural networks typically comprise a plurality of hidden layers. For example, an encoder may comprise a plurality of hidden layers that progressively extract further reduced representations of the input data. Using deeper neural networks (i.e. with a higher number of hidden layers) for the encoder and / or the decoder may improve performance of the autoencoder, and in some cases may reduce the amount of training data that is required. The encoder and decoder neural networks are typically trained together. During training the autoencoder may adjust its internal parameters (e.g. weights and biases of the encoder and decoder neural networks) so as to optimize (e.g. minimize) a loss / error function, aiming to minimize discrepancy between the data input to the encoder and the output reconstructed data generated by the decoder. It will be appreciated that the specific loss function, and algorithm used to optimize the function may vary depending on the nature of the autoencoder model, and its intended application. In an example, a mean squared error loss function optimized using gradient descent may be used. In some cases, a sparse autoencoder may be used in order to promote sparsity of the latent representation (as compared to the input) and to prevent the autoencoder from learning the identity function - for example, a sparse autoencoder may be implemented by modifying the loss function to include a sparsity regularization penalty. In some cases, the autoencoder may be a Variational Autoencoder (VAE). The VAE is a specific type of auto-encoder in which a probability model is imposed on the encoded representation by the training process (in that deviations from the probability model are penalised by the training process). The VAE may be used for generative artificial intelligence applications to generate new output data which exhibits similar characteristics to the input encoded data by sampling from the learned latent space. For positioning AI / ML models, the input data may comprise positioning measurements and the output data may comprise a position estimate of the communications device or improved positioning measurements. Reinforcement Learning AI / ML models may implement reinforcement learning (RL). Reinforcement learning is a type of machine learning directed to training an artificial intelligence agent to take actions in an environment that maximize the notion of a cumulative reward. During reinforcement learning, the agent interacts with the environment, and learns from the results of its actions, thus allowing the agent to progressively improve its decision-making. An RL model typically comprises an action-reward feedback loop. The feedback loop comprises: an environment, state, agent, policy, action, and reward. The environment is the system with which the agent interacts and in which the agent operates - for example, the environment may be a virtual environment of a video game. The state represents the current conditions in the environment. The agent receives the state as an input and takes an action which may affect the environment and change the state of the environment. The agent takes the action based on its policy which is a mapping from states of the environment to actions of the agent. The policy may be deterministic or stochastic. The reward represents feedback from the environment to the action taken by the agent. The reward provides an indication (typically in the form of a numerical value) of the desirability of the result of the agent’s action. The reward may comprise positive signals to reward desirable behaviour of the agent and / or negative signals to penalize undesirable behaviour of the agent. Through multiple iterations of action-reward feedback loop, the agent aims to maximise the total cumulative reward it receives, thus learning how to take optimal actions in the environment. The reinforcement learning process thus allows the agent to learn an optimal policy that maximizes the cumulative reward. The cumulative award may be estimated using a value function which estimates the expected return starting from a given state or from a given state and action. Using the cumulative reward in the reinforcement learning process allows the agent to consider long-term effects of its policy. A reinforcement learning algorithm may be used to refine the agent’s policy and the value function over iterations of the action-reward feedback loop. The learning algorithm may rely on a model of the environment (e.g. based on Markov Decision Processes (MDPs)) or be model-free. Example suitable model-free reinforcement learning algorithms include Q-leaming, State-Action-Reward-State-Action (SARSA), Deep Q-Networks (DQNs), or Deep Deterministic Policy Gradient (DDPG). It will be appreciated that the agent will typically engage in both exploration and exploitation of the environment in which it operates. In exploration, the agent takes typically random actions to gather information about the environment and identify potentially desirable actions (i.e. actions that maximise cumulative reward). In exploitation, the agent takes actions that are expected to maximise reward (e.g. by selecting the action based on the agent’s latest policy). Various techniques may be used to control the proportion of explorative and exploitative actions taken by the agent - for example, a predetermined probability of taking an explorative action in a given iteration of the feedback loop may be set (and optionally reduced over time to allow the agent to shifts more towards exploitation over time to maximise cumulative reward in view of diminishing returns for further exploration). In some cases, the RL model may be configured to learn from feedback provided by a user. Utilising user feedback in this way may allow the agent to improve its choice of actions and better align with user preferences. For example, reinforcement learning from human feedback (RLHF) techniques may be used. RLHF includes training a reward model based on user feedback and using this model for determining the reward in the reinforcement learning process described above. The user feedback may be received in various forms depending on the specific reinforcement learning problem being solved - for example, the feedback may be received in the form of a user ranking of instances of the agent’s actions. RLHF thus allows incorporating user feedback into the reinforcement learning process. RLHF approaches may be advantageous where it is easier for a user than for an algorithm to assess the quality of the machine learning model’s output (e.g. for generative artificial intelligence RL models). For positioning AI / ML models, the input data may comprise positioning measurements and the output data may comprise a position estimate of the communications device or improved positioning measurements. Although a number of types of AI / ML models have been described above in connection with positioning, the above types of an AI / ML can also be used in beam management or channel state information (CSI) feedback enhancement tasks, or indeed other tasks known to a person skilled in the art. For beam management AI / ML models, input data may comprise one or more of an Ll-RSRP and its associated beam / resource ID. The output data may be one or more of a predicted beam (e.g., a predicted Synchronization Signal / Physical Broadcast Channel Block (SSB), Channel State Information Reference Signal (CSI-RS), Sounding Reference Signal (SRS)), narrow beam, improved beam prediction or a refined Ll-RSRP. The predicted beam here can be associated to the predicted resource ID used for the transmission of the reference signal using a specific beam. For CSIAI / ML models (e.g. CSI measurement and reporting enhancement, CSI compression or CSI prediction), input data may comprise one or more of a signal to interference and noise ratio (SINR) estimation, a Modulation and Coding (MCS) index, Channel Quality Indicator (CQI) index, or a Precoding matrix index (PMI). The output data may be one or more of a refined or predicted MCS, CQI index, PMI index, RI index, or a new type of output. In some examples of CSI compression AI / ML models, input data may be a full CSI compression report and output data may be a reduced size CSI compression report. Life Cycle Management (LCM) Architecture for an AI / ML Model 3 GPP has identified a general AI / ML framework for the NR air interface to facilitate different radio frequency applications, including positioning applications, but also for beam management and CSI feedback enhancements applications. The aim of the framework is to cover a general architecture addressing the whole AI model life cycle, Life Cycle Management (LCM), including such steps as data collection, model training, etc. Here, LCM for AI / ML for the NR air interface is described in the below paragraphs. As those skilled in the art would appreciate, the following description is also applicable to 6G and other wireless communications systems. An example of a life cycle management (LCM) architecture for an artificial intelligence model is schematically illustrated in Figure 4 which has been reproduced from [3], the contents of which are hereby incorporated by reference in their entirety. As shown in Figure 4, LCM architecture comprises a data collection function 402, an inference function 404, a management function 406, a model training function 408 and a model storage function 410. In the case of a UE side model, the one or more functions comprised in the LCM architecture may be equipped in the UE. In one example, the inference function 404 is deployed in the UE. In the case of a NW side model (base station-side model or core network side model), the one or more functions comprised in the LCM architecture may be equipped in the NW (i.e. the base station (e.g. gNB) or the core network function node (e.g. LMF)). In one example, the inference function 404 is deployed in the base station or LMF. The data collection function 402 is configured to provide training data to the model training function 408, to provide monitoring data to the management function 406 and to provide inference data to the inference function 404. The data collection function 402 is a process / function of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics and inference. The inference function 404 is configured to provide an inference output to the management function 406, to receive a management instruction from the management function 406 and to receive a model from the model storage function 410. The inference function 404 is a process / function of using a trained AI / ML model to produce a set of outputs based on a set of inputs. The management function is configured to provide performance feedback and / a retraining request to the model training function 408, and to provide a model delivery request to the model storage unit 410. The model training function 408 is configured to provide an updated model to the model storage unit 410. The model training function 408 is a process / function to train an AI / ML Model (e.g., by learning the input / output relationship) in a data driven manner and obtain the trained AI / ML Model for inference. As shown in Figure 4, the management function 406 represents the core of the LCM architecture. The function of the management function 406 is to monitor model performance at different entities (such as UEs or base stations) and request delivery of updated models. Model management comprises two procedures - model switching and model updating. Existing positioning procedures in wireless communications networks, such as 5G NR networks, involve communications between a UE, a base station and a LMF. The AI / ML model may be deployed at the UE, base station or LMF. An AI / ML model for positioning may be a direct AI / ML positioning model or an AI / ML assisted positioning model. Both direct AI / ML positioning models and AI / ML assisted positioning models use positioning measurements (such as positioning measurements based on received PRS or SRS) as input data. However, the output data for direct AI / ML positioning models is an estimate of a position of the UE (such as a co-ordinate) whereas the output data for AI / ML assisted positioning models is a more accurate positioning measurement or a new set of positioning measurements. Examples of existing positioning techniques using a direct and assisted AI / ML positioning models - which are described in [3] - are illustrated in Figure 5. Segment (A) of Figure 5 (referred to as Case 1 in [3]) illustrates an example of UE-based positioning with a UE-side direct AI / ML model. In this example, one or more gNBs transmit PRS to the UE. The UE performs positioning measurements on the PRS and uses a direct AI / ML model to generate an estimate of a position of the UE based on the positioning measurements. The UE forwards the position estimate to the LMF. Segment (B) of Figure 5 (referred to as Case 2a in [3]) illustrates an example of UE-assisted / LMF-based positioning with a UE-side AI / ML assisted positioning model. In this example, one or more gNBs transmit PRS to the UE. The UE performs positioning measurements on the PRS and uses an AI / ML assisted positioning model to generate improved positioning measurements of the PRS. The UE forwards the improved measurements of the PRS to the LMF. The LMF generates a position estimate of the UE based on the improved measurements of the PRS. Segment (C) of Figure 5 (referred to as Case 2b in [3]) illustrates an example of LMF-based positioning with an LMF-side direct AI / ML model. In this example, one or more gNBs transmit PRS to the UE. The UE performs positioning measurements on the PRS and transmits the positioning measurements of the PRS to the LMF. The LMF then uses the direct AI / ML model generate a position estimate for the UE based on the positioning measurements of the PRS. Segment (D) of Figure 5 (referred to as Case 3a in [3]) illustrates an example of NG-RAN node assisted positioning with a gNB-side AI / ML assisted positioning model. In this example, the UE transmits SRS to one or more gNBs. The gNB performs positioning measurements on the SRS and uses the AI / ML assisted positioning model to generate more improved positioning measurements of the SRS. The gNB then transmits the improved positioning measurements of the SRS to the LMF. The LMF generates a position estimate of the UE based on the improved positioning measurements of the SRS. Segment (E) of Figure 5 (referred to as Case 3b in [3]) illustrates NG-RAN node assisted positioning with an LMF-side direct AI / ML model. In this example, the UE transmits SRS to one or more gNBs. The gNB performs positioning measurements on the SRS and transmits the positioning measurements of the SRS to the LMF. The LMF uses the direct AI / ML model to generate a position estimate of the UE based on the received positioning measurements of the SRS. An AI / ML positioning model may be deployed for a particular area, while another AI / ML positioning model may be deployed for another area. In this way, AI / ML positioning models can be adapted to be effective in the areas in which they are deployed. For example, a particular AI / ML model may be trained under particular environmental conditions because these environmental conditions will be similar to the environmental conditions in which the AI / ML model will be deployed. Having multiple AI / ML models, each adapted for different areas, also facilitates model switching and selection, thus enabling the provision of high accuracy positioning across a diverse range of areas. However, the environmental conditions of an area in which an AI / ML positioning model is deployed may change over time. For example, the position (e.g. layout or constellation) of communications devices relative to passive environmental objects (such as a table or a wall) in the area may change over time. Since the passive environmental objects may reflect / scatter signals transmitted by the communications devices, the change in position of the communications devices relative to passive environmental objects means that different signals will be reflected / scattered in different ways over time. This may affect channel conditions and propagation characteristics such as line-of-sight (LOS) between the transmitter and the receiver in the area. Accordingly, an AI / ML model adapted for a particular area may become outdated over time. If the AI / ML model becomes outdated, then the accuracy of positioning measurements or positioning estimates generated by the AI / ML model decreases to unacceptable levels. The decrease in performance of an AI / ML model over time may be due to data drift and / or model drift. Data drift occurs when the distribution of input data (for example, positioning measurements) to the AI / ML model change over time. This happens, for example, when the distribution of the positioning measurements obtained by a UE deviates from the distribution of the positioning measurements used to train the AI / ML model. For example, when the AI / ML model is trained, it may be assumed that the UEs may evenly spread out in the room. However, in practice or in a reality at a given period of time, UEs tend to cluster or stay in sub-areas of the room (e.g. most UEs may be near the centre of the room). This deviation between the assumed UE statistic (distribution of location and positioning measurements) in training phase and the realistic UE statistic might harm the overall performance. Model drift occurs when a relationship between the input data and output data of the AI / ML model changes. This relationship may change due to a change in environmental conditions. For example, a room may have different reflectors such as tables and chairs. The location of these reflectors may not be fixed all the time. Considering a case where the configuration of the tables and chairs in the room is changed but the UE is still using the same AI / ML model for positioning, then the issue of model drift occurs, leading to compromised positioning performance. Therefore, the decrease in performance of AI / ML problems overtime represents a technical problem. To address the issues of data drift and model drift, a model monitoring procedure can be conducted. Such a model monitoring procedure can be carried out semi-persistently, or can be triggered by either an internal node in the core network or an external entity, such as a third party server (e.g., application server). This process involves gathering new signal measurements (referred to herein as reference information) using, for example, a reference UE known as a Positioning Reference Unit (PRU), collecting information with a Ground Truth (GT) label (also referred to as ground truth (GT) information), and calculating Performance Metrics (PM). Subsequently the results of the calculated PM will be reported to the device at which the AI / ML model is deployed (e.g. the UE, which may be the PRU, or the base station) for further action. Here, as those skilled in the art would understand, a PRU functions similarly to a standard UE by transmitting SRS and receiving PRS. Furthermore, it can also perform and produce positioning measurement results (e.g., based on the received PRS). However, unlike typical UEs, a PRU has a fixed and / or known location. Initially introduced by 3GPP in Release 17 of NR, the PRU’s primary role was to calibrate timing errors in NR positioning. In release 18 and beyond, the PRU’s capabilities are being further explored within the context of AI / ML positioning, where such a PRU may be used to assist in model training and monitoring. Furthermore, a model pool of multiple different AI models providing the same functionality can be utilised, with only one model from the model pool being deployed at the UE or network at any given time. A model pool may consist of a few selected AI models, such as an active AI model (i.e., the one that is currently being used), and one or more selected AI models which are likely to be used to replace the active one. In the event of model or data drift, a more suitable model from the model pool can be selected (e.g. by the LMF) in view of the updated wireless environment. This new model (along with all required parameters for its deployment at the base station or UE), or only its model ID (assuming knowledge of such a model within the model pool is known at the base station or UE, will be then signalled to the base station / UE. These two enhancements described above, relating to model monitoring and model selection, ensure the performance of the deployed model is maintained in a sustainable way. Technical Problem Depending on the operation, model inference can be deployed at the UE, such as in cases 1 and 2a as shown in segments (A) and (B) of Figure 5. In such a case, the AI / ML model is operated at the UE, where the expectation is to improve the output of measurement / estimation processes at the UE. In reality, the AI / ML model deployed and used for inference at the UE side may be a sub-optimal model or even the wrong model. In this case, the output of the AI / ML model could be even worse than the case (i.e. performing the measurement / estimation process) without AI / ML. Hence, there is a need to perform performance monitoring of the deployed AI / ML model. Performance monitoring can be deployed at the same UE that performs / executes model inference using a direct AI / ML model, such as in case 1 as shown in segment (A) of Figure 5. Here, the model inference performed by the UE is such that the UE position estimates to be reported to the network (e.g. then LMF) are accurate, and expected to be better than legacy UE-based positioning estimation without the use of AI / ML models. However, in known solutions the operation of the performance monitoring - including the activation of performance monitoring, the actual computation of performance monitoring, and the handling of the outcome of the performance monitoring - shall be controlled / managed by the network. Here, the performance monitoring shall be operated by ensuring the input is reliable information. Performance monitoring operation shall also be controlled / managed by the network (e.g., base station or LMF) so that the UE behavior is expected to produce an output that can be used / trusted by the base station / LMF. In this case, the network can trust the reported output from the UE. The mechanism / procedure of such operation is not available or unclear. As noted above, the decrease in performance of AI / ML problems over time represents a technical problem. In co-pending United Kingdom patent application number 2402279.0 [4], the contents of which are hereby incorporated by reference, an approach is described where the network node (e.g. gNB) performs PM computation with assistance from the LMF. As those skilled in the art would appreciate, there are advantages and disadvantages to performing the PM computation at various nodes, and the ability for different nodes (both within the radio access network and core network, as well as externally to both) can complement each other and provides options and flexibility for different deployments. In co-pending United Kingdom patent application number 2412107.1 [5], the contents of which are hereby incorporated by reference, an approach is described where a server network node (e.g. the UMF) determines the validity of an AEML model, by performing model monitoring. Here, the operation is initiated by the network node (e.g. the UMF), and the network node also obtains and utilizes the monitoring outcome so as to improve or replace the AI / MU model. As with the solution described in [4], this introduces overheads with respect to the signaling required between the network node and the UE at which the AEME model is deployed, so as to enable the performance monitoring to be carried out. Embodiments of the present technique therefore define further arrangements to those described in [4] and [5] that enable the efficient and effective performance of AEML models deployed at UEs over long periods of time. The solutions provided herein aim to address the above issues, such as ensuring the provision of trustworthy and reliable input data for performance metric computation, efficient signaling, and producing a performance monitoring output that can be provided to network nodes such as the base station and / or LMF. UE-Assisted AI / ML Model Performance Monitoring Figure 6 shows a part schematic, part message flow diagram representation of a wireless communications system comprising a communications device 610 (e.g. a UE) and a network node 620 (e.g. an LMF or a radio access node (e.g. a base station, which may be for example a gNB or 6G-NB)) in accordance with at least some embodiments of the present technique. The communications device 610 is configured to perform AEML model monitoring based on performance metric (PM) computation for an AEML model deployed at the communications device 610. The communications device 610 and the network node 620 each comprise a transceiver (or transceiver circuitry) 611, 621 and a controller (or controller circuitry) 612, 622. Each of the controllers 612, 622 may be, for example, a microprocessor, a CPU, or a dedicated chipset, etc. The controllers 612, 622 may also each be equipped with a memory unit (which is not shown in Figure 6). As those skilled in the art would appreciate the wireless communications system of Figure 6 may include a number of other nodes, such as other communications devices and network nodes, which are not shown in the example of Figure 6 for the purposes of simplicity. As shown in the example of Figure 6, the controller 612 of the communications device 610 is configured in combination with the transceiver 611 of the communications device 610 to receive 630, from the network node 620, information for use by the communications device 610 in calculating one or more performance metrics of an artificial intelligence (AI) model used by the communications device 610 to perform model inference, wherein the received information 650 comprises (at least) input data for use in calculating the one or more performance metrics, to calculate 640 the one or more performance metrics by inputting the input data to the AI model to produce an estimated output, to analyze 650 the estimated output with respect to an expected output, and to transmit 660, to the network node 620 based on the analysis 650 of the estimated output, a performance monitoring report. Here, where reference is made to the model inference performed by the communications device 610 (e.g... a UE), such a model inference task is generally described in accordance with the below arrangements of embodiments of the present technique as a positioning task. However, such a model inference task may be any appropriate model inference task performed by the UE for which utilization of the AI / ML model aids such a model inference task, which includes but is not limited to positioning, beam management, and channel state information (CSI) feedback enhancements. Essentially then, embodiments of the present technique, as exemplified by the example wireless communications system of Figure 6 for example, propose that the communications device (i.e. UE) which is operating model inference using an AEML model itself performs performance monitoring. Here, such performance monitoring involves receiving information (including expected output data) for performance monitoring from a network node (e.g. a radio access node such as a gNB or 6G base station, a core network node, such as Location Management Function (LMF)), performing the performance monitoring operation in accordance with the received information, and transmitting a performance monitoring report (which may provide indications of the calculated performance monitoring metrics) to the network node. In some arrangements of embodiments of the present technique, the UE may also receive the expected output data from the network node, in addition to the input data. In other words, the received information may comprise the expected output data. The input data and output data may be received together as part of the same received information element, though in other arrangements they may be received separately. Additionally, in some arrangements, Model ID information can be included in the received information. Here, the input data and expected output data can be associated with the Model ID. The Model ID information enables UEs which hold multiple AEML models simultaneously to identify which AI / ML model is to be monitored in respect of the received input / output data (which may be received separately as described above) based on the association between the received input / output data and Model ID. In other words, the AI model may be one of a plurality of AI models which the communications device (i.e., UE) is able to use to perform the model inference, and here, the received information may comprise an identifier of the AI model of which the communications device (i.e., UE) is to calculate the one or more performance metrics. In accordance with arrangements of embodiments of the present technique, the said input data may include at least one of the following: • Radio-based measurement results, where such measurement results (including one or more of timing, transmit / received power) and may also include their associated parameter(s), .For example, the measured received power at a given value is with respect to what is being measured (e.g. transmitted by what UE / the base station (e.g. gNB), or using what beam / which resources), and the type of measurement signal (e.g. whether it is based on synchronisation signal blocks (SSBs), channel state information reference signals (CSI-RS), PRS, etc.). In other words, the input data may comprise measurements performed by one of: the communications device (i.e. UE), a positioning reference unit, or a node of the radio access network, where here, the input data may further comprise one or more properties of the measurements; • For positioning-based AEML model inference tasks, the radio-based measurements can be PRS measurements, including channel impulse response (CIR) measurement results and downlink reference signal time difference (DL-RSTD). These measurements are typically captured by PRUs under the coverage of the same serving cell as the target UE. It should be noted here that in the case of radio-based measurement, the UE which holds (and performs monitoring of) the AEML model can obtain the radio-based measurements by itself without receiving any input data from the network node. In other cases, however, the radio-based measurements may be performed by a PRU or other UE, and provided to the UE which is performing the performance monitoring operation by the network node. The UE that is performing the performance monitoring operation may, if it performs its own radio-based measurements, use those measurements in addition to the input data (i.e. radio based measurements performed by a PRU or other UE) that is received from the network node; • For beam management AEML model inference tasks, the radio-based measurement can be synchronization signal blocks (SSBs) or channel state information reference signals (CSI-RS) measurements, including Ll-RSRP measurements or / and the CSI information of a full set / subset / Top-l / Top-K of DL Tx beams, captured by other UEs under the coverage of the same serving cell as the target UE; • Configuration related to the measurements / measurement results described above. In other words, the received information may comprise configuration information for the measurements to be performed by the communications device. For example, this may include an indication of the PRS configuration(s) which were previously used to capture the radio-based measurements, including parameters such as bandwidth and / or comb size of the PRS signal. Here, the expected output may be associated with the measurement configuration information; and • Configuration to perform performance monitoring, including time window parameters, and the procedure / format for transmitting the performance monitoring report to the network, etc. In other words, the received information may comprise configuration information for the calculation of the one or more performance metrics by the communications device. In accordance with arrangements of embodiments of the present technique, the said expected output data may include one (or a combination) of the following: • Ground truth (GT) information, such as UE location information, or such as a refmed / enhanced / more accurate version of PRS measurement. Here, the UE with which the GT information is associated can be a reference UE (i.e. a PRU) or any other UE, and may be the UE which holds (and performs monitoring of) the AI / ML model. In other words, the expected output may be ground truth (GT) information associated with the communications device (i.e. UE); • Identification of the top-l / top-K DL Tx beams (i.e. Beam / resource IDs), associated with another UE in the same serving cell. Alternatively, it can be also in a form of Ll-RSRP, comprising such as the Ll-RSRP of the full-set of beams or a refined version of the Ll-RSRP of the full-set / subset of DL Tx beams; • Radio transmission channel quality, such as an expected error rate (such as the bit error rate (BER) or block error rate (BLER)), or channel state information (CSI) parameters, etc. In other words, the expected output may be an indicator of a quality of the channel between the communications device (i.e. UE) and the radio access network; and • Qualitative report, such as {0,1}, where 0=bad, l=good) or soft values (e.g. a scale from 0-10). In other words, the expected output may be a relative quality score of the output of the AI model. In accordance with arrangements of embodiments of the present technique, the said performing performance monitoring operation can be performed by a UE which holds and uses at least one AI / ML model (e.g. an active AI / ML model). In other words, the AI model of which the communications device is to calculate the one or more performance metrics may be an active AI model (and may be the only AI model or may be an AI model from among a plurality of AI models which the communications device is able to use to perform the model inference), where the active AI model is currently being used by the communications device to perform the model inference. In some arrangements, a UE with a certain capability to hold multiple AUML models can execute performance monitoring on one or more of the other AUML models to the one currently being used to perform inference (i.e. a non-active AUML model). In other words, the AI model of which the communications device is to calculate the one or more performance metrics is a non-active AI model (from among a plurality of AI models which the communications device is able to use to perform the model inference), where the non-active AI model not currently being used by the communications device to perform the model inference. In some arrangements, the performance monitoring operation can be performed either periodically or aperiodically, where in the latter case, it may be triggered by the network node. In other words, the communications device may either: calculate the one or more performance metrics periodically, or calculate the one or more performance metrics in response to receiving a triggering indication from the network node. In other arrangements, the UE may itself trigger the performance monitoring operation. In other words, the communications device may be configured to transmit, to the network node, a request for the communications device to perform performance monitoring of the AI model, where here, upon receiving a response to that request, the performance monitoring operation can be performed either periodically or aperiodically (where for the latter of which, further requests / triggering indications are exchanged for subsequent performance monitoring operation). In some arrangements, this request may comprise an indication of a request for the input data (and, optionally, the expected output). In some arrangements, the performance monitoring operation is also performed within a time window. In other words, the communications device may be configured to calculate the one or more performance metrics within a configured time duration. Here, the time window may be configured by the network, and can be defined as starting from the time at which the UE received the request and ending at the time at which the performance monitoring report is to be provided / transmitted at the latest to the network. In accordance with at least some arrangements of embodiments of the present technique, the performance monitoring report may indicate the calculated performance metrics, where the network node that receives the report (i.e. the LMF or radio access node) is then able to perform further analysis on the performance metrics so as to determine the efficacy of the AI model. In other words, the performance monitoring report may comprise an indication of the one or more calculated performance metrics. In accordance with at least some arrangements of embodiments of the present technique, the analysis performed by the communications device on the estimated output with respect to an expected output may be a comparison of the estimated and expected outputs. Here, in some arrangements, the performance monitoring report may contain an indication of the comparison between the output of the AUML model executed in performance monitoring and the received expected output data (from the network node). In other words, the performance monitoring report may comprise an indication of a comparison performed between the estimated output and the expected output. In some such arrangements where the performance monitoring report comprises an indication of a comparison performed between the estimated output and the expected output, the reported output can be based on an instant computation or based on multiple computations so that the reported output is based on the statistical calculation (for example, based on a computed average or standard deviation of the multiple computations). In some such arrangements where the performance monitoring report comprises an indication of a comparison performed between the estimated output and the expected output, the comparison here can be the “delta” of the output and the expected output. For example, this delta value can be indicated as the positioning estimation error from reference PRU position information. Specifically, the delta value can be configured to indicate the horizontal positioning error or vertical positioning error, for example. In accordance with at least some arrangements of embodiments of the present technique, the performance monitoring report may comprise a simple indication of a request for the network to update / switch the AI / ML model. In other words, the performance monitoring report may comprise a request for the network node to update the AI model. In accordance with arrangements of embodiments of the present technique, based on the received performance monitoring report from the UE, the network node can trigger AI / ML model update at the UE, including: • Indicating that the UE is to switch the AI / ML model. In other words, the communications device may be configured to receive, from the network node in response to transmitting the performance monitoring report, an indication that the communications device is to use a second AI model to perform the model inference instead of the current AI model. Here, the second AI model may already be known to the communications device (e.g. if the communications device holds multiple AI / ML models); • Indicating that the UE is to stop using the current AI / ML model. In other words, the communications device may be configured to receive, from the network node in response to transmitting the performance monitoring report, an indication that the communications device is to terminate the usage of the current AI model; • Indicating that one or more parameters of the AI / ML are to be re-tuned. In other words, the communications device may be configured to receive, from the network node in response to transmitting the performance monitoring report, an indication of new values of one or more parameters of the AI model; • Indicating that the AI / ML model is to be regenerated. In other words, the communications device may be configured to receive, from the network node in response to transmitting the performance monitoring report, an indication that the AI model is to be regenerated; or • Indicating that the UE is to receive a new AI / ML model. In other words, where the communications device may be configured to receive, from the network node in response to transmitting the performance monitoring report, the indication that the communications device is to use the second AI model to perform the model inference instead of the current AI model, this indication may indicate that the communications device is to receive the second AI model from the network node. It would be appreciated by the those skilled in the art that, where a UE is indicated to switch to a different or updated AI / ML model by the network, the UE may not be expected to use this new or updated AI / ML model (which was indicated by the network node to be switched to / retuned / regenerated) until receiving the switch indication or receiving the retuned or regenerated AI / ML model from the network node. In accordance with arrangements of embodiments of the present technique, the network node can be a radio access node (e.g. a base station, an eNB, a gNB, or a 6G base station, etc.) in the radio access network or can be a Location Management Function (LMF) in the core network. For positioning purposes, the LMF is the node that both provides information (e.g. for use in performance monitoring) to the UE and receives the information (e.g. the performance monitoring report) from the UE. For other purposes, such as beam management and CSI feedback enhancements, the network node may be a radio access node (e.g. gNB). In accordance with arrangements of embodiments of the present technique, together with the input data, the network node can indicate to the UE whether the input data was captured by a PRU or a non-PRU UE. In other words, the received information may comprise both the input data and an indication of whether the measurements were performed by the PRU. In principle, the input data from a PRU can reflect the environment more accurately as described above, due to it having a fixed and known location. Thus, such arrangements allow the UE to take the source of the input data into account when judging the trustworthiness of the input data. The performance monitoring operation at the UE side is, in a general sense, illustrated in Figure 7. In accordance with such operation, the UE receives (or may additionally already have, in the case of radio based measurements it has performed itself) input data 702, and receives expected output data 703. The UE then performs analysis on the output of the active AI / ML model 701 when the input data 702 is fed in with respect to the expected output data 703, which may involve a comparison, and transmits a performance monitoring report 705 to the network. Here, it is illustrated that the UE may have more than one AEML model, where one AI / ML model 701 is active and used for the model inference task, and the other model(s) 711 are non-active. The UE may also evaluate one of the non-active models 711 (in addition to the active model 711). The performance monitoring metrics output 705 following the evaluation 704 performed by the UE can be provided to the LMF (for positioning tasks) or radio access node (for CSI feedback enhancement or beam management tasks). Hence, the LMF / radio access node may identify which model is performing the best, and take subsequent actions to improve the AI / ML model inference performed by the UE. Embodiments of the present technique therefore define a proposed method to be applied for AI / ML model monitoring at the UE at which the monitored AI model is held, which is generally described above in respect of being for positioning purposes. As noted above however, in principle, such embodiments of the present technique can equally be applied to other AEML cases, such as AI / ML for beam management, and AEML for CSI feedback enhancements. As those skilled in the art would appreciate, positioning data (i.e., positioning measurements either performed by the UE on PRS or received directly from the network node) would also not be used in these cases, but will instead be replaced by channel information data, such as CSI report, Ll-RSRP of different beams, signal to noise ratio (SNR), channel impulse response (CIR) measurements, etc. The methods described herein are also illustrated in the signalling diagrams shown by Figures 8, 9, and 10, which respectively illustrate the message flow processes for model inference for positioning tasks, beam management tasks, and CSI feedback enhancement tasks. For positioning purposes, where the network node that handles the actions to be taken based on the UE’s transmitted performance monitoring report is the LMF, the signalling is expected to use the LTE positioning protocol (LPP),7.355) while for other purposes, where the network node that handles the actions to be taken based on the UE’s transmitted performance monitoring report is a radio access node (e.g. a gNB), the signalling may be carried by a higher layer protocol such as medium access control (MAC) control element CE and / or radio resource control (RRC). Figure 8 shows a part schematic, part message flow diagram representation of a first example process of communications in a communications system in which a UE 801 is configured to perform a positioning task by using AI model inference in accordance with embodiments of the present technique. Here, the UE 801 first exchanges configuration information 810 and capability signalling 811 with a radio access node (e.g. gNB) 802 and / or LMF 803. In one example, the capability may include an indication of the UE capability in performing performance monitoring, such as the capability in processing the received input data and the expected output data. Hence, when the network node 802 provides such information, it has been tailored to the UE capability in performing performance monitoring. The UE 801 may also receive positioning reference signals 812 from the gNB 802 on which it can perform its own measurements. The UE 801 is currently performing AEML model inference 813 using its active AI / ML model, but then receives input data from the LMF 803 for performance monitoring 814 as well as a triggering indication 815 to perform the performance monitoring (e.g. on the active AI / ML model). The received input data may be transmitted together with, or separately to an expected output for use in the performance monitoring 814. In case these are separately transmitted, both input data and the expected output can be explicitly associated with an association ID, or they may be implicitly associated in time. The UE 801 may furthermore use measurements that it has performed on the received PRS 812 in the performance monitoring 814. Then in step 816 the UE 801 performs the performance monitoring operation, and transmits a performance monitoring report 817 to the LMF 803. The LMF 803 is then able to analyze 818 the performance monitoring metrics received from the UE 801in the performance monitoring report 817, and may subsequently indicate 819 to the UE 801 to either keep, replace, or update the active AEML model. Figure 9 shows a part schematic, part message flow diagram representation of a second example process of communications in a communications system in which a UE 901 is configured to perform a beam management task by using AI model inference in accordance with embodiments of the present technique. Here, the UE 901 first exchanges configuration information 910 and capability signalling 911 with a radio access node (e.g. gNB) 902. In one example, the capability may include an indication of the UE capability in performing performance monitoring, such as the capability in processing the received input data and the expected output data. Hence, when the network node 902 provides such information, it has been tailored to the UE capability in performing performance monitoring. The UE 901 may also receive reference signals 912, transmitted by the gNB 902 via multiple SSBs / beams, on which it can perform its own measurements. The UE 901 is currently performing AEML model inference 913 using its active AEML model, but then receives input data from the gNB 902 for performance monitoring 914 as well as a triggering indication 915 to perform the performance monitoring (e.g. on the active AEML model). The received input data may be transmitted together with, or separately to an expected output for use in the performance monitoring 914. In case these are separately transmitted, both input data and the expected output can be explicitly associated with an association ID, or they may be implicitly associated in time. The UE 901 may furthermore use measurements that it has performed on the received reference signals 912 in the performance monitoring 914. Then in step 916 the UE 901 performs the performance monitoring operation, and transmits a performance monitoring report 917 to the gNB 902. The gNB 902 is then able to analyze 918 the performance monitoring metrics received from the UE 901 in the performance monitoring report 917, and may subsequently indicate 919 to the UE 90 Ito either keep, replace, or update the active AEML model. Figure 10 shows a part schematic, part message flow diagram representation of a third example process of communications in a communications system in which a UE 1001 is configured to perform a channel state information (CSI) feedback enhancement task by using AI model inference in accordance with embodiments of the present technique. Here, the UE 1001 first exchanges configuration information 1010 and capability signalling 1011 with a radio access node (e.g. gNB) 1002. In one example, the capability may include an indication of the UE capability in performing performance monitoring, such as the capability in processing the received input data and the expected output data. Hence, when the network node 1002 provides such information, it has been tailored to the UE capability in performing performance monitoring. The UE 1001 may also receive channel state information reference signals (CSI-RS) 1012 from the gNB 1002, on which it can perform its own measurements. The UE 1001 is currently performing AEML model inference 1013 using its active AEML model, but then receives input data from the gNB 1002 for performance monitoring 1014 as well as a triggering indication 1015 to perform the performance monitoring (e.g. on the active AEML model). The received input data may be transmitted together with, or separately to an expected output for use in the performance monitoring 1014. In case these are separately transmitted, both input data and the expected output can be explicitly associated with an association ID, or they may be implicitly associated in time. The UE 1001 may furthermore use measurements that it has performed on the received CSI RS 1012 in the performance monitoring 1014. Then in step 1016 the UE 1001 performs the performance monitoring operation, and transmits a performance monitoring report 1017 to the gNB 1002. The gNB 1002 is then able to analyze 1018 the performance monitoring metrics received from the UE 1001 in the performance monitoring report 1017, and may subsequently indicate 1019 to the UE 1001 to either keep, replace, or update the active AI / ML model. Figure 11 shows a flow diagram illustrating an example process of communications in a communications system in accordance with embodiments of the present technique. The process shown by Figure 11 is specifically a method of operating a communications device configured to communicate with a radio access network. The method begins in step SI 101. The method comprises, in step SI 102, receiving, from a network node, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence (AI) model used by the communications device to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics. In step SI 103, the process comprises calculating the one or more performance metrics by inputting the input data to the AI model to produce an estimated output. The process then comprises, in step SI 104, analyzing the estimated output with respect to an expected output. In one example, analyzing is performed by comparing the estimated output with respect to the expected output. In step S1105, the method comprises transmitting, to the network node based on the analysis of the estimated output, a performance monitoring report. The process ends in step SI 106. Those skilled in the art would appreciate that the method shown by Figure 11 and the procedures illustrated by Figures 8 to 10 may be adapted in accordance with embodiments of the present technique. For example, other intermediate steps may be included in such methods / procedures, or the steps may be performed in any logical order. Though embodiments of the present technique have been described largely by way of the example communications system shown in Figure 6, it would be clear to those skilled in the art that they could be equally applied to other systems to those described herein, provided that these are within the scope of the claims. Those skilled in the art would further appreciate that such network nodes and / or communications devices as herein defined may be further defined in accordance with the various arrangements and embodiments discussed in the preceding paragraphs. It would be further appreciated by those skilled in the art that such network nodes and communications devices as herein defined and described may form part of communications systems other than those defined by the present disclosure, provided that these are within the scope of the claims. The following numbered paragraphs provide further example aspects and features of the present technique: Paragraph 1. A method of operating a communications device configured to communicate with a radio access network, the method comprising receiving, from a network node, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics, calculating the one or more performance metrics by inputting the input data to the AI model to produce an estimated output, analyzing the estimated output with respect to an expected output, and transmitting, to the network node based on the analysis of the estimated output, a performance monitoring report. Paragraph 2. A method according to Paragraph 1, wherein the received information comprises the expected output data. Paragraph 3. A method according to Paragraph 1 or Paragraph 2, wherein the AI model is one of a plurality of AI models which the communications device is able to use to perform the model inference. Paragraph 4. A method according to Paragraph 3, wherein the received information comprises an identifier of the AI model of which the communications device is to calculate the one or more performance metrics. Paragraph 5. A method according to Paragraph 3 or Paragraph 4, wherein the AI model of which the communications device is to calculate the one or more performance metrics is an active AI model from among the plurality of AI models, the active AI model currently being used by the communications device to perform the model inference. Paragraph 6. A method according to Paragraph 3 or Paragraph 4, wherein the AI model of which the communications device is to calculate the one or more performance metrics is a non-active AI model from among the plurality of AI models, the non-active AI model not currently being used by the communications device to perform the model inference. Paragraph 7. A method according to any of Paragraphs 1 to 6, wherein the input data comprises measurements performed by one of: the communications device, a positioning reference unit, or a node of the radio access network. Paragraph 8. A method according to Paragraph 7, wherein the input data further comprises one or more properties of the measurements. Paragraph 9. A method according to Paragraph 7 or Paragraph 8, wherein the received information comprises the input data, and wherein the received information further comprises an indication of whether the measurements were performed by the positioning reference unit. Paragraph 10. A method according to any of Paragraphs 7 to 9, wherein the received information comprises configuration information for the measurements to be performed by the communications device, wherein the expected output is associated with the measurement configuration information. Paragraph 11. A method according to any of Paragraphs 1 to 10, wherein the received information comprises configuration information for the calculation of the one or more performance metrics by the communications device. Paragraph 12. A method according to any of Paragraphs 1 to 11, wherein the expected output is ground truth, GT, information associated with the communications device. Paragraph 13. A method according to any of Paragraphs 1 to 12, wherein the expected output is an indicator of a quality of the channel between the communications device and the radio access network. Paragraph 14. A method according to any of Paragraphs 1 to 13, wherein the expected output is a relative quality score of the output of the AI model. Paragraph 15. A method according to any of Paragraphs 1 to 14, wherein the communications device calculates the one or more performance metrics periodically. Paragraph 16. A method according to any of Paragraphs 1 to 15, wherein the communications device calculates the one or more performance metrics in response to receiving a triggering indication from the network node. Paragraph 17. A method according to any of Paragraphs 1 to 16, comprising transmitting, to the network node, a request for the communications device to perform performance monitoring of the AI model. Paragraph 18. A method according to Paragraph 17, wherein the request comprises an indication of a request for the input data and the expected output. Paragraph 19. A method according to any of Paragraphs 1 to 18, wherein the communications device calculates the one or more performance metrics within a configured time duration. Paragraph 20. A method according to any of Paragraphs 1 to 19, wherein the performance monitoring report comprises an indication of a comparison performed between the estimated output and the expected output. Paragraph 21. A method according to any of Paragraphs 1 to 20, wherein the performance monitoring report comprises a request for the network node to update the AI model. Paragraph 22. A method according to any of Paragraphs 1 to 21, wherein the performance monitoring report comprises an indication of the one or more calculated performance metrics. Paragraph 23. A method according to any of Paragraphs 1 to 22, comprising receiving, from the network node in response to transmitting the performance monitoring report, an indication that the communications device is to terminate the usage of the current AI model. Paragraph 24. A method according to any of Paragraphs 1 to 23, comprising receiving, from the network node in response to transmitting the performance monitoring report, an indication that the communications device is to use a second AI model to perform the model inference instead of the current AI model. Paragraph 25. A method according to Paragraph 24, wherein the second AI model is already known to the communications device. Paragraph 26. A method according to Paragraph 24 or Paragraph 25, wherein the indication indicates that the communications device is to receive the second AI model from the network node. Paragraph 27. A method according to any of Paragraphs 1 to 26, comprising receiving, from the network node in response to transmitting the performance monitoring report, an indication of new values of one or more parameters of the AI model. Paragraph 28. A method according to any of Paragraphs 1 to 27, comprising receiving, from the network node in response to transmitting the performance monitoring report, an indication that the AI model is to be regenerated. Paragraph 29. A method according to any of Paragraphs 1 to 28, wherein the network node is a node of the radio access network. Paragraph 30. A method according to any of Paragraphs 1 to 28, wherein the network node is a location management function, LMF, of a core network. Paragraph 31. A communications device configured to communicate with a radio access network, the communications device comprising a transceiver configured to transmit and to receive signals, a controller configured in combination with the transceiver to receive, from a network node, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics, to calculate the one or more performance metrics by inputting the input data to the AI model to produce an estimated output, to analyze the estimated output with respect to an expected output, and to transmit, to the network node based on the analysis of the estimated output, a performance monitoring report. Paragraph 32. Circuitry for a communications device configured to communicate with a radio access network, the circuitry comprising transceiver circuitry configured to transmit and to receive signals, controller circuitry configured in combination with the transceiver circuitry to receive, from a network node, information for use by the circuitry in calculating one or more performance metrics of an artificial intelligence, AI, model used by the circuitry to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics, to calculate the one or more performance metrics by inputting the input data to the AI model to produce an estimated output, to analyze the estimated output with respect to an expected output, and to transmit, to the network node based on the analysis of the estimated output, a performance monitoring report. Paragraph 33. A method of operating a network node, the method comprising transmitting, to a communications device, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the transmitted information comprises input data, the input data being for inputting into the AI model to produce an estimated output for analysing with respect to an expected output, and receiving, from the communications device based on the analysis of the estimated output by the communications device, a performance monitoring report. Paragraph 34. A method according to Paragraph 33, wherein the transmitted information comprises the expected output data. Paragraph 35. A method according to Paragraph 33 or Paragraph 34, wherein the AI model is one of a plurality of AI models which the communications device is able to use to perform the model inference. Paragraph 36. A method according to Paragraph 35, wherein the transmitted information comprises an identifier of the AI model of which the communications device is to calculate the one or more performance metrics. Paragraph 37. A method according to Paragraph 35 or Paragraph 36, wherein the AI model of which the communications device is to calculate the one or more performance metrics is an active AI model from among the plurality of AI models, the active AI model currently being used by the communications device to perform the model inference. Paragraph 38. A method according to Paragraph 35 or Paragraph 36, wherein the AI model of which the communications device is to calculate the one or more performance metrics is a non-active AI model from among the plurality of AI models, the non-active AI model not currently being used by the communications device to perform the model inference. Paragraph 39. A method according to any of Paragraphs 33 to 38, wherein the input data comprises measurements performed by one of: the communications device, a positioning reference unit, or a node of the radio access network. Paragraph 40. A method according to Paragraph 39, wherein the input data further comprises one or more properties of the measurements. Paragraph 41. A method according to Paragraph 39 or Paragraph 40, wherein the transmitted information comprises the input data, and wherein the transmitted information further comprises an indication of whether the measurements were performed by the positioning reference unit. Paragraph 42. A method according to any of Paragraphs 39 to 41, wherein the transmitted information comprises configuration information for the measurements to be performed by the communications device, wherein the expected output is associated with the measurement configuration information. Paragraph 43. A method according to any of Paragraphs 33 to 42, wherein the transmitted information comprises configuration information for the calculation of the one or more performance metrics by the communications device. Paragraph 44. A method according to any of Paragraphs 33 to 43, wherein the expected output is ground truth, GT, information associated with the communications device. Paragraph 45. A method according to any of Paragraphs 33 to 44, wherein the expected output is an indicator of a quality of the channel between the communications device and the radio access network. Paragraph 46. A method according to any of Paragraphs 33 to 45, wherein the expected output is a relative quality score of the output of the AI model. Paragraph 47. A method according to any of Paragraphs 33 to 46, comprising determining that the communications device calculates the one or more performance metrics periodically. Paragraph 48. A method according to any of Paragraphs 33 to 47, comprising transmitting, to the communications device, a triggering indication to trigger the communications device to calculate the one or more performance metrics. Paragraph 49. A method according to any of Paragraphs 33 to 48, comprising receiving, from the communications device, a request for the communications device to perform performance monitoring of the AI model. Paragraph 50. A method according to Paragraph 49, wherein the request comprises an indication of a request for the input data and the expected output. Paragraph 51. A method according to any of Paragraphs 33 to 50, comprising determining that the communications device calculates the one or more performance metrics within a configured time duration. Paragraph 52. A method according to any of Paragraphs 33 to 51, wherein the performance monitoring report comprises an indication of a comparison performed between the estimated output and the expected output. Paragraph 53. A method according to any of Paragraphs 33 to 52, wherein the performance monitoring report comprises a request for the network node to update the AI model. Paragraph 54. A method according to any of Paragraphs 33 to 53, wherein the performance monitoring report comprises an indication of the one or more calculated performance metrics. Paragraph 55. A method according to any of Paragraphs 33 to 54, comprising transmitting, to the communications device in response to receiving the performance monitoring report, an indication that the communications device is to terminate the usage of the current AI model. Paragraph 56. A method according to any of Paragraphs 33 to 55, comprising transmitting, to the communications device in response to receiving the performance monitoring report, an indication that the communications device is to use a second AI model to perform the model inference instead of the current AI model. Paragraph 57. A method according to Paragraph 56, wherein the second AI model is already known to the communications device. Paragraph 58. A method according to Paragraph 56 or Paragraph 57, wherein the indication indicates that the communications device is to receive the second AI model from the network node. Paragraph 59. A method according to any of Paragraphs 33 to 58, comprising transmitting, to the communications device in response to receiving the performance monitoring report, an indication of new values of one or more parameters of the AI model. Paragraph 60. A method according to any of Paragraphs 33 to 59, comprising transmitting, to the communications device in response to receiving the performance monitoring report, an indication that the AI model is to be regenerated. Paragraph 61. A method according to any of Paragraphs 33 to 60, wherein the network node is a node of the radio access network. Paragraph 62. A method according to any of Paragraphs 33 to 60, wherein the network node is a location management function, LMF, of a core network. Paragraph 63. A network node comprising a transceiver configured to transmit and to receive signals, a controller configured in combination with the transceiver to transmit, to a communications device, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the transmitted information comprises input data, the input data being for inputting into the AI model to produce an estimated output for analysing with respect to an expected output, and to receive, from the communications device based on the analysis of the estimated output by the communications device, a performance monitoring report. Paragraph 64. Circuitry for a network node, the circuitry comprising transceiver circuitry configured to transmit and to receive signals, controller circuitry configured in combination with the transceiver circuitry to transmit, to a communications device, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the transmitted information comprises input data, the input data being for inputting into the AI model to produce an estimated output for analysing with respect to an expected output, and to receive, from the communications device based on analysis of the estimated output by the communications device, a performance monitoring report. Paragraph 65. A wireless communications system comprising a communications device according to Paragraph 31 and a network node according to Paragraph 63. Paragraph 66. A computer program comprising instructions which, when loaded onto a computer, cause the computer to perform a method according to any of Paragraphs 1 to 30 or Paragraphs 33 to 62. Paragraph 67. A non-transitory computer-readable storage medium storing a computer program according to Paragraph 66. It will be appreciated that the above description for clarity has described embodiments with reference to different functional units, circuitry and / or processors. However, it will be apparent that any suitable distribution of functionality between different functional units, circuitry and / or processors may be used without detracting from the embodiments. Described embodiments may be implemented in any suitable form including hardware, software, firmware or any combination of these. Described embodiments may optionally be implemented at least partly as computer software running on one or more data processors and / or digital signal processors. The elements and components of any embodiment may be physically, functionally and logically implemented in any suitable way. Indeed, the functionality may be implemented in a single unit, in a plurality of units or as part of other functional units. As such, the disclosed embodiments may be implemented in a single unit or may be physically and functionally distributed between different units, circuitry and / or processors. Although the present disclosure has been described in connection with some embodiments, it is not intended to be limited to the specific form set forth herein. Additionally, although a feature may appear to be described in connection with particular embodiments, one skilled in the art would recognise that various features of the described embodiments may be combined in any manner suitable to implement the technique. References [1] Holma H. and Toskala A, “LTE for UMTS OFDMA and SC-FDMA based radio access”, John Wiley and Sons, 2009. [2] TR 38.913, “3rd Generation Partnership Project; Technical Specification Group Radio Access 5 Network; Study on Scenarios and Requirements for Next Generation Access Technologies (Release 14)”, 3GPP, vl4.3.0, August 2017. [3] TR 38.843, “Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR air interface (Release 18)”, 3GPP, vl8.0.0, December 2023. [4] United Kingdom patent application number 2402279.0. 10 [5] United Kingdom patent application number 2412107.1

Claims

What is claimed is:

1. A method of operating a communications device configured to communicate with a radio access network, the method comprisingreceiving, from a network node, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics,calculating the one or more performance metrics by inputting the input data to the AI model to produce an estimated output,analyzing the estimated output with respect to an expected output, andtransmitting, to the network node based on the analysis of the estimated output, a performance monitoring report.

2. A method according to Claim 1, wherein the received information comprises the expected output data.

3. A method according to Claim 1, wherein the AI model is one of a plurality of AI models which the communications device is able to use to perform the model inference.

4. A method according to Claim 3, wherein the received information comprises an identifier of the AI model of which the communications device is to calculate the one or more performance metrics.

5. A method according to Claim 1, wherein the input data comprises measurements performed by one of: the communications device, a positioning reference unit, or a node of the radio access network.

6. A method according to Claim 1, wherein the expected output is ground truth, GT, information associated with the communications device.

7. A method according to Claim 1, wherein the expected output is an indicator of a quality of the channel between the communications device and the radio access network.

8. A method according to Claim 1, wherein the expected output is a relative quality score of the output of the AI model.

9. A method according to Claim 1, wherein the performance monitoring report comprises an indication of a comparison performed between the estimated output and the expected output.

10. A method according to Claim 1, wherein the performance monitoring report comprises a request for the network node to update the AI model.

11. A method according to Claim 1, wherein the performance monitoring report comprises an indication of the one or more calculated performance metrics.

12. A method according to Claim 1, comprisingreceiving, from the network node in response to transmitting the performance monitoring report, an indication that the communications device is to terminate the usage of the current AI model.

13. A method according to Claim 1, comprisingreceiving, from the network node in response to transmitting the performance monitoring report, an indication that the communications device is to use a second AI model to perform the model inference instead of the current AI model.

14. A method according to Claim 1, comprisingreceiving, from the network node in response to transmitting the performance monitoring report, an indication of new values of one or more parameters of the AI model.

15. A method according to Claim 1, comprisingreceiving, from the network node in response to transmitting the performance monitoring report, an indication that the AI model is to be regenerated.

16. A method according to Claim 1, wherein the network node is a node of the radio access network.

17. A method according to Claim 1, wherein the network node is a location management function,LMF, of a core network.

18. A communications device configured to communicate with a radio access network, the communications device comprisinga transceiver configured to transmit and to receive signals,a controller configured in combination with the transceiverto receive, from a network node, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics,to calculate the one or more performance metrics by inputting the input data to the AI model to produce an estimated output,to analyze the estimated output with respect to an expected output, andto transmit, to the network node based on the analysis of the estimated output, a performance monitoring report.

19. Circuitry for a communications device configured to communicate with a radio access network, the circuitry comprisingtransceiver circuitry configured to transmit and to receive signals,controller circuitry configured in combination with the transceiver circuitryto receive, from a network node, information for use by the circuitry in calculating one or more performance metrics of an artificial intelligence, AI, model used by the circuitry to perform model inference, wherein the received information comprises input data for use in calculating the one or more performance metrics,to calculate the one or more performance metrics by inputting the input data to the AI model to produce an estimated output,to analyze the estimated output with respect to an expected output, andto transmit, to the network node based on the analysis of the estimated output, a performance monitoring report.

20. A method of operating a network node, the method comprisingtransmitting, to a communications device, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by thecommunications device to perform model inference, wherein the transmitted information comprises input data, the input data being for inputting into the AI model to produce an estimated output for analysing with respect to an expected output, andreceiving, from the communications device based on the analysis of the estimated output by the communications device, a performance monitoring report.

21. A network node comprisinga transceiver configured to transmit and to receive signals,a controller configured in combination with the transceiverto transmit, to a communications device, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the transmitted information comprises input data, the input data being for inputting into the AI model to produce an estimated output for analysing with respect to an expected output, andto receive, from the communications device based on the analysis of the estimated output by the communications device, a performance monitoring report.

22. Circuitry for a network node, the circuitry comprisingtransceiver circuitry configured to transmit and to receive signals, controller circuitry configured in combination with the transceiver circuitry to transmit, to a communications device, information for use by the communications device in calculating one or more performance metrics of an artificial intelligence, AI, model used by the communications device to perform model inference, wherein the transmitted information comprises input data, the input data being for inputting into the AI model to produce an estimated output for analysing with respect to an expected output, andto receive, from the communications device based on analysis of the estimated output by the communications device, a performance monitoring report.

23. A wireless communications system comprising a communications device according to Claim 18 and a network node according to Claim 21.

24. A computer program comprising instructions which, when loaded onto a computer, cause the computer to perform a method according to Claim 1 or Claim 20.

25. A non-transitory computer-readable storage medium storing a computer program according to Claim 24.

Images