Data collection for training network-implemented machine learning model to determine user equipment location

Abstract

A method in a user equipment (UE 130) includes: receiving a message requesting 306 bulk reporting of channel measurements and UE locations of the UE; obtaining a plurality of channel measurements 308 of at least one transmission reception point, TRP; obtaining 309 a plurality of UE locations; associating the UE locations with the channel measurements; and transmitting at least one message comprising the plurality of channel measurements and UE locations. The received message comprises: a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements. The method may comprise: aggregating 310 the plurality of channel measurements and plurality of UE locations over a plurality of time windows for channel measurements. Also disclosed in a core network entity (e.g. a Location Management Function, LMF 122): receiving, from an entity configured to train a machine learning (ML) model (Model Training Network Function, MTNF 123) for inferring a location of UE or configured to determine accuracy of the ML model, a request for bulk reporting of channel measurements and UE locations, the bulk reporting to be performed by at least one UE or radio access network (RAN 125) node, the request comprising a specified target area in which to obtain channel measurements and UE locations; selecting a RAN node 303 based on the target area; and transmitting 304 to the RAN node, the request for bulk reporting. The request comprises: an indication to use UE-assisted positioning mode or RAN-node assisted positioning mode.

Description

FIELD

[0001] Various example embodiments relate generally to wireless networks and, more particularly, to data collection for training a network-implemented machine learning model to determine user equipment location. BACKGROUND

[0002] The location management function (LMF) is a network function in a core network that provides location services. There have been proposals for an LMF to provide, for example, a service that determines the location of a particular user equipment (UE). However, the implementation for doing so is undeveloped. Such a service may be beneficial when there is need to locate a UE, such as in the case where a UE is stolen or lost SUMMARY

[0003] In accordance with aspects of the present disclosure, a method in a user equipment (UE) includes: receiving a message including a request for bulk reporting of channel measurements and UE locations of the UE; obtaining a plurality of channel measurements of at least one transmission reception point; obtaining a plurality of UE locations of the UE; associating the plurality of UE locations with the plurality of channel measurements; and transmitting, in response to the request for bulk reporting, at least one message including the plurality of channel measurements and the plurality of UE locations.

[0004] In aspects of the method in a UE, the received message includes at least one of: a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements, and the plurality of channel measurements and the plurality of UE locations are obtained in accordance with the at least one of: the target time window for channel measurements, the target number of channel measurements, or the target rate of channel measurements.

[0005] In aspects of the method in a UE, the method further includes: determining a time to obtain the plurality of channel measurements and the plurality of UE locations based on at least one of: UE load at the UE, battery status at the UE, or radio load.

[0006] In aspects of the method in a UE, the at least one transmitted message further includes at least one of: UE configuration information, number of transmission reception points the UE is configured to use, a type allocation code of the UE, or a cell identifier of a radio cell where the UE is located.

[0007] In aspects of the method in a UE, the message including the request further includes a target address to which the at least one message is to be transmitted; and the at least one message is transmitted towards the target address.

[0008] In aspects of the method in a UE, the method further includes: aggregating the plurality of channel measurements and the plurality of UE locations over a plurality of time windows for channel measurements, where the at least one transmitted message includes the plurality of channel measurements and the plurality of UE locations aggregated over the plurality of time windows.

[0009] In accordance with aspects of the present disclosure, a method in a core network entity includes: receiving, from an entity configured to train a machine learning (ML) model for inferring a location of a user equipment or configured to determine accuracy of the ML model, a request for bulk reporting of channel measurements and user equipment (UE) locations, where the bulk reporting is to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, where the request for bulk reporting includes a specified target area in which to obtain the channel measurements and UE locations; in response to the request, selecting at least one RAN node based at least on the specified target area; and transmitting, to the selected at least one RAN node, a message including the request for bulk reporting of channel measurements and UE locations.

[0010] In aspects of the method in a core network entity, the received request includes at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements for at least one transmission reception point, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

[0011] In aspects of the method in a core network entity, the selecting the at least one RAN node includes at least one of identifying RAN nodes that are capable of supporting the RAN-node assisted positioning mode, or identifying RAN nodes that are capable of supporting the UE-assisted positioning mode.

[0012] In aspects of the method in a core network entity, the method further includes: determining that a portion of the specified target area has no RAN nodes that are available to support the RAN-node assisted positioning node; and transmitting, to the entity, a message rejecting the portion of the specified target area for the bulk reporting.

[0013] In aspects of the method in a core network entity, the determining that the portion of the specified target area has no RAN nodes that are available to support the RAN-node assisted positioning mode, is based on at least one of: information indicating which RAN nodes in the specified target area are capable of supporting RAN-node assisted positioning mode, or information indicating load of RAN nodes in the specified target area.

[0014] In accordance with aspects of the present disclosure, a method in a radio access network (RAN) node includes: receiving, from a core network entity, a message including a request for bulk reporting of channel measurements and UE locations, where the bulk reporting is to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, where the request for bulk reporting includes a specified target area in which to obtain the channel measurements and UE locations; in response to the request, selecting at least one UE based at least on the specified target area; and transmitting, to each of the selected at least one UE, a message including a request for the UE to perform reporting of at least UE locations.

[0015] In aspects of the method in a RAN node, the message including the request for bulk reporting further includes at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

[0016] In aspects of the method in a RAN node, the method further includes: determining a time for transmitting the at least one message including the request for the selected at least one UE to perform reporting, and a number of the at least one message, where the determining is based on at least one of: the received target time window for channel measurements, the received target number of channel measurements, a received target rate of channel measurements, a load of the RAN node, a capacity of the RAN node, a load of radio cells in the specified target area, or a capacity of radio cells in the specified target area.

[0017] In aspects of the method in a RAN node, the selected at least one UE is selected based on at least one of: a capability reported by the UE to obtain UE locations, a capability reported by the UE to perform channel measurements, an indication received from a core network entity that the UE is capable of performing suitable channel measurements, an indication received from a core network entity that the UE is capable of obtaining suitable UE locations, load of a UE, or capacity of a UE.

[0018] In aspects of the method in a RAN node, the request for the at least one UE to perform reporting includes at least one of: a specified time window for channel measurements, a specified number of channel measurements, or a specified rate of channel measurements. The specified time window for channel measurements, the specified target number of channel measurements, or the specified target rate of channel measurements are determined based on at least one of: the received target time window for channel measurements, the received target number of channel measurements, the received target rate of channel measurements, or a number of the selected at least one UE.

[0019] In aspects of the method in a RAN node, the method further includes: receiving, from the at least one UE, a UE location; obtaining, by the RAN node, channel measurements of at least one transmission reception point; and associating the UE location with the channel measurements.

[0020] In aspects of the method in a RAN node, the method further includes: aggregating a plurality of channel measurements and a plurality of UE locations over a plurality of time windows for channel measurements; and transmitting, to the core network entity, at least one message including the plurality of channel measurements and the plurality of UE locations aggregated over the plurality of time windows.

[0021] In aspects of the present disclosure, an apparatus includes at least one processor, and at least one memory storing instructions. The instructions, when executed by the at least one processor, cause the apparatus at least to perform a method as in any one of the preceding aspects.

[0022] In aspects of the present disclosure, a processor-readable medium stores instructions which, when executed by at least one processor of an apparatus, cause the apparatus at least to perform a method as in any one of the preceding aspects.

[0023] According to some aspects, there is provided the subject matter of the independent claims. Some further aspects are defined in the dependent claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Some example embodiments will now be described with reference to the accompanying drawings.

[0025] FIG. 1 is a diagram of example components of a network system, according to one illustrated aspect of the disclosure;

[0026] FIG 2 is a diagram of example operations for training a network-implemented machine learning (ML) model using training data provided by a radio access network (RAN), according to one illustrated aspect of the disclosure;

[0027] FIG. 3 is a diagram of example operations for training a network-implemented ML model using training data provided by a user equipment (UE), according to one illustrated aspect of the disclosure;

[0028] FIG. 4 is a diagram of example operations of selecting UEs to provide the training data provided in FIG. 3, according to one illustrated aspect of the disclosure;

[0029] FIG 5 is a diagram of example operations of executing a trained network-implemented ML model, using data from a RAN, to provide an inferred location of a UE, according to one illustrated aspect of the disclosure;

[0030] FIG. 6 is a diagram of example operations of executing a trained network-implemented ML model, using data from a UE, to provide an inferred location of the UE, according to one illustrated aspect of the disclosure;

[0031] FIG. 7 is a diagram of example operations of determining accuracy of a trained network-implemented ML model in providing inferred locations of UE using data from a RAN, according to one illustrated aspect of the disclosure; and

[0032] FIG. 8 is a diagram of example components of an apparatus, according to one illustrated aspect of the disclosure. DETAILED DESCRIPTION

[0033] In the following description, certain specific details are set forth in order to provide a thorough understanding of disclosed aspects. However, one skilled in the relevant art will recognize that aspects may be practiced without one or more of these specific details or with other methods, components, materials, etc. In other instances, well-known structures associated with transmitters, receivers, or transceivers have not been shown or described in detail to avoid unnecessarily obscuring descriptions of the aspects.

[0034] Reference throughout this specification to “one aspect” or “an aspect” means that a particular feature, structure, or characteristic described in connection with the aspect is included in at least one aspect. Thus, the appearances of the phrases “in one aspect” or “in an aspect” in various places throughout this specification are not necessarily all referring to the same aspect. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more aspects.

[0035] Embodiments described in the present disclosure may be implemented in wireless networking apparatuses, such as, without limitation, apparatuses utilizing Worldwide Interoperability for Microwave Access (WiMAX), Global System for Mobile communications (GSM, 2G), GSM EDGE radio access Network (GERAN), General Packet Radio Service (GRPS), Universal Mobile Telecommunication System (UMTS, 3G) based on basic wideband-code division multiple access (W-CDMA), high-speed packet access (HSPA), Long Term Evolution (LTE), LTE-Advanced, enhanced LTE (eLTE), 5G New Radio (5G NR), 5G Advance, next generation radio access network (NG-RAN), 6G (and beyond) and 802.11 ax (Wi-Fi 6), among other wireless networking systems. The term £eLTE’ here denotes the LTE evolution that connects to a 5G core. LTE is also known as evolved UMTS terrestrial radio access (EUTRA) or as evolved UMTS terrestrial radio access network (EUTRAN). As used herein, the term “RAN,” as used in connection with a described operation, refers to any radio access network that is capable of performing the described operation, such as, e.g., a NG-RAN.

[0036] The present disclosure may use the term “serving network device” to refer to a network node or network device (or a portion thereof) that services a UE. As used herein, the terms “transmit to,” “receive from,” and “cooperate with,” (and their variations) include communications that may or may not involve communications through one or more intermediate devices or nodes. The term “acquire” (and its variations) includes acquiring in the first instance or reacquiring after the first instance. The term “connection” may mean a physical connection or a logical connection.

[0037] The present disclosure uses 5G NR as an example of a wireless network and may use smartphones and / or extended reality headsets as an example of UEs. It is intended and shall be understood that such examples are merely illustrative, and the present disclosure is applicable to other wireless networks and user equipment.

[0038] FIG 1 is a diagram depicting an example of wireless networking involving a network system and a user equipment (UE) 130. The network system includes network nodes. The following description provides further details of examples of network nodes. In a 5G NR network, a gNodeB (also known as gNB) may include, e.g., a node that provides new radio (NR) user plane and control plane protocol terminations towards the UE and that is connected via a NG interface to the 5G core (5GC) 110, e.g., according to 3GPP TS 38.300 V16.6.0 (2021-06) section 3.2, which is hereby incorporated by reference herein.

[0039] A gNB supports various protocol layers, e.g., Layer 1 (LI) - physical layer, Layer 2 (L2), and Layer 3 (L3).

[0040] The layer 2 (L2) of NR is split into the following sublayers: Medium Access Control (MAC), Radio Link Control (RLC), Packet Data Convergence Protocol (PDCP) and Service Data Adaptation Protocol (SDAP), where, e.g.: o The physical layer offers to the MAC sublayer transport channels; o The MAC sublayer offers to the RLC sublayer logical channels; o The RLC sublayer offers to the PDCP sublayer RLC channels; o The PDCP sublayer offers to the SDAP sublayer radio bearers; o The SDAP sublayer offers to 5GC quality of service (QoS) flows; o Control channels include broadcast control channel (BCCH) and physical control channel (PCCH).

[0041] Layer 3 (L3) includes, e.g., radio resource control (RRC), e.g., according to 3GPP TS 38.300 V16.6.0 (2021-06) section 6, which is hereby incorporated by reference herein.

[0042] A gNB central unit (gNB-CU) includes, e.g., a logical node hosting, e.g., radio resource control (RRC), service data adaptation protocol (SDAP), and packet data convergence protocol (PDCP) protocols of the gNB or RRC and PDCP protocols of the en-gNB, that controls the operation of one or more gNB distributed units (gNB-DUs). The gNB-CU terminates the Fl interface connected with the gNB-DU. A gNB-CU may also be referred to herein as a CU, a central unit, a centralized unit, or a control unit.

[0043] A gNB Distributed Unit (gNB-DU) includes, e.g., a logical node hosting, e.g., radio link control (RLC), media access control (MAC), and physical (PHY) layers of the gNB or en-gNB, and its operation is partly controlled by the gNB-CU. One gNB-DU supports one or multiple cells. One cell is supported by only one gNB-DU. The gNB-DU terminates the Fl interface connected with the gNB-CU. A gNB-DU may also be referred to herein as DU or a distributed unit.

[0044] As used herein, the term “network node” may refer to any of a gNB, a gNB-CU, or a gNB-DU, or any combination of them. A RAN (radio access network) node or network node such as, e.g., a gNB, gNB-CU, or gNB-DU, or parts thereof, may be implemented using, e.g., an apparatus with at least one processor and / or at least one memory with processor-readable instructions (“program”) configured to support and / or provision and / or process CU and / or DU related functionality and / or features, and / or at least one protocol (sub-)layer of a RAN (radio access network), e.g., layer 2 and / or layer 3. Different functional splits between the central and distributed unit are possible.

[0045] The gNB-CU and gNB-DU parts may, e.g., be co-located or physically separated. The gNB-DU may even be split further, e.g., into two parts, e.g., one including processing equipment and one including an antenna. A central unit (CU) may also be called baseband unit / radio equipment controller / cloud-RAN / virtual-RAN (BBU / REC / C-RAN / V-RAN), open-RAN (O-RAN), or part thereof. A distributed unit (DU) may also be called remote radio head / remote radio unit / radio equipment / radio unit (RRH / RRU / RE / RU), or part thereof. Hereinafter, in various example embodiments of the present disclosure, a network node, which supports at least one of central unit functionality or a layer 3 protocol of a radio access network, may be, e.g., a gNB-CU. Similarly, a network node, which supports at least one of distributed unit functionality or a layer 2 protocol of the radio access network, may be, e.g., a gNB-DU.

[0046] A gNB-CU may support one or multiple gNB-DUs. A gNB-DU may support one or multiple cells and, thus, could support a serving cell for a user equipment (UE) or support a candidate cell for handover, dual connectivity, and / or carrier aggregation, among other procedures.

[0047] The user equipment (UE) 130 may be or include a wireless or mobile device, an apparatus with a radio interface to interact with a RAN 125 (radio access network), a smartphone, an in-vehicle apparatus, an loT device, or a M2M device, among other types of user equipment 130. Such UE 130 may include: at least one processor; and at least one memory including program code; where the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform certain operations, such as, e.g., RRC connection to the RAN 125. An example of components of a UE 30 will be described in connection with FIG. 8. In embodiments, the UE 130 may be configured to generate a message (e.g., including a cell ID) to be transmitted via radio towards a RAN 125 (e.g., to reach and communicate with a serving cell). In embodiments, the UE 130 may generate and transmit and receive RRC messages containing one or more RRC PDUs (packet data units). Persons skilled in the art will understand RRC protocol as well as other procedures a UE 130 may perform.

[0048] With continuing reference to FIG. 1, in the example of a 5G NR network, the network system provides one or more cells, which define a coverage area of the network system. As described above, the network system may include a gNB of a 5G NR network or may include any other apparatus configured to control radio communication and manage radio resources within a cell. As used herein, the term “resource” may refer to radio resources, such as a resource block (RB), a physical resource block (PRB), a radio frame, a subframe, a time slot, a sub-band, a frequency region, a sub-carrier, a beam, etc. In embodiments, the network node may be called a base station.

[0049] With continuing reference to FIG. 1, the network system may operate such that the UE 130 is in communication with the network system through the radio access network 125. Additionally, the network system may be divided into user plane components and functions and control plane components and functions, as shown and described herein. Unless indicated otherwise, the terms “component”, “function”, and “service” may be used interchangeably herein, and they may refer to and be implemented by instructions executed by one or more processors.

[0050] Example functions of the components are described below. The example functions are merely illustrative, and it shall be understood that additional operations and functions may be performed by the components described herein. Additionally, the connections between components may be virtual connections over service-based interfaces such that any component may communicate with any other component. In this manner, any component may act as a service “producer,” for any other component that is a service “consumer,” to provide services for network functions.

[0051] For example, a core network 110 is described in the control plane of the network system. The core network 110 may include an access and mobility function (AMF) 112 and a session management function (SMF) 113. The core network 110 also includes a network data analytics function (NWDAF) 120, an analytics data repository function (ADRF) 121, a location management function (LMF) 122, and a model training network function (NTNF) 123. In various embodiments, the LMF 122 may serve as the MTNF 123. In various embodiments, the LMF 122 and the MTNF 123 are separate network functions.

[0052] The user plane includes the UE 130, a radio access network (RAN) 125, a user plane function (UPF) 126, and a data network (DN) 127. The RAN 125 may include one or more components described above, such as one or more network nodes. However, the RAN 125 may not be limited to such components. The UPF 126 provides connection for data being transmitted over the RAN 125. The DN 126 identifies services from service providers, Internet access, and third party services, for example.

[0053] The AMF 112 processes connection and mobility tasks. The SMF 213 conducts packet data unit (PDU) session management, as well as manages session context with the UPF 226.

[0054] The NWDAF 120 collects data (e.g., from the UE 130 and the network system) to perform network analytics and provide insight to functions that utilize the analytics in the providing of services. The ADRF 121 allows the storage, retrieval, and removal of data and analytics by consumers. The LMF 122 provides location services and can provide a service for determining the location of the UE 130. The MTNF 123 operates to train a network-implemented ML model that outputs the inferred location of a UE. In various embodiments, the LMF 122 can serve as the MTNF 123. In various embodiments, a model training logical function (MTLF) of the NWDAF 120 can serve as the MTNF 123.

[0055] In various embodiments, the ML model receives channel measurements for one or more transmission reception points (TRPs) and outputs an inferred location of a UE based on the channel measurements. In such embodiments, channel measurements for the TRP(s) are used to determine a UE location. The following description will refer to such an implementation of a network-implemented ML model. However, it is contemplated that a ML model that outputs UE location may receive and use other data, as well. In the following description, a reference to “channel measurement” shall mean channel measurement for one or more TRP(s). As used herein, “obtaining a UE location” shall mean obtaining one or more geographical coordinates of where a UE is geographically located, such as, without limitation, latitude and longitude coordinates.

[0056] FIG. 1 is merely an example of components of a network system, and variations are contemplated to be within the scope of the present disclosure. In embodiments, the network system may include other components not illustrated in FIG. 1. In embodiments, the network system may not include every component illustrated in FIG. 1. In embodiments, the components and connections may be implemented with different connections than those illustrated in FIG. 1. Such and other embodiments are contemplated to be within the scope of the present disclosure.

[0057] The disclosed technology will be described in connection with FIGS. 2 7. Certain aspects are now described below.

[0058] A network-implemented ML model will closely relate to topologies and antennae in an area or a radio cell and, thus, will be specific to an area or cell or will use the cell for input data. In accordance with aspects of the present disclosure, a network-implemented ML model may use channel measurements from a UE in a cell or may use channel measurements from RAN nodes associated with a cell. Where a UE provides channel measurements for the network-implemented ML model, and the network-implemented ML model provides an inferred location of a UE based on such channel measurements, such an approach will be referred to herein as “UE-assisted positioning.” Where a RAN node provides channel measurements for the network-implemented ML model, and the network-implemented ML model provides an inferred location of a UE based on such channel measurements, such an approach will be referred to herein as “RAN-node assisted positioning.” For network-implemented ML models using UE channel measurements, the details of the UE (such as number of transmission reception points) may be considered; this can be reflected in separate ML models or reflected in the input data to the ML model. In various embodiments, separate ML models may be used for UE-assisted positioning and for RAN-node assisted positioning.

[0059] For the model training, in addition to channel measurements, ground truth data for UE location is also obtained. The ground truth data may be Global Navigation Satellite System (GNSS) information, such as Global Positioning System (GPS) information provided by a UE. Training a network-implemented ML model would use correlated data (e.g., at the same point in time) that includes ground truth data (e.g. GPS coordinates) reported by a UE and channel measurements for TRPs measured by the same UE or by an RAN node servicing the UE.

[0060] The present disclosure provides details of UE-assisted positioning operations and RAN-node assisted positioning operations for collecting data for a network-implemented ML model and provides operations for assessing accuracy of a network-implemented ML model. The particular implementation of the network-implemented ML model is outside the scope of the present disclosure.

[0061] The reporting of ground truth data requires special capabilities of the UE. There is a capability indication from UE to RAN that indicates the capability to report location information.

[0062] For UE-assisted positioning, the reporting of measurements by the UE involves additional UE capabilities. Generally, it is desirable to select UE models / types that are known to be capable of obtaining suitable locations (e.g., capable of obtaining accurate location coordinates) to enhance the quality of ground truth data. The Permanent Equipment Identifier (PEI) (containing IMSEEISMEISV with Type Allocation Code (TAC), see TS 23.003) of UEs could be used to select suitable UEs, which is available in the AMF. In accordance with aspects of the present disclosure, only UEs in a target area / cell are used to gather training data for training a network-implemented ML model for that target area / cell. Because RAN nodes know which UEs they are serving, RAN nodes can select UEs for UE-assisted positioning.

[0063] In aspects of the present disclosure, when a UE registers, the AMF determines based on the Permanent Equipment Identifier (PEI) (and in particular the Type Allocation code (TAC) which is part of an International Mobile Equipment Identity (IMEI) or IMEISC used as PEI) whether the UE is suitable to report its location (e.g., with sufficient accuracy) for model training and whether the UE is suitable to perform channel measurements for UE-assisted positioning. For example, certain PEI are known to be associated with UE having highly accurate GPS receivers. Such known associations can be used to identify UEs that are capable of providing suitable UE location determinations (e.g., highly accurate location determinations). The AMF provides that information (whether a UE is capable of providing suitable UE location) to the RAN, and the RAN stores this information as part of the UE context and may subsequently use it to select UEs.

[0064] For RAN-node assisted positioning, the approach involves RAN nodes with special capabilities to support the channel measurements and report related ground truth location data from a UE.

[0065] The channel measurement and location reporting can lead to considerable load, and it is desirable to perform them when there is sufficient capacity in RAN nodes and / or in UEs. In accordance with aspects of the present disclosure, to address capacity, RAN nodes can select times for gathering channel measurements, such as when they are less loaded. To reduce signaling load, a bulk subscription to training data (e.g., channel measurements, ground truth location) and a bulk reporting of training data can be implemented. In various embodiments, direct reporting from a UE to a MTNF (e.g., LMF) via the user plane can be supported.

[0066] In aspects of the present disclosure, the MTNF (e g., LMF or NWDAF / MTLF) performs a bulk subscription request for bulk reporting of machine learning model training measurements towards the AMF. The request denotes a target area, a target time window for measurements, a target number of measurements, and / or a target rate of measurements. In various embodiments, the bulk subscription request can include an indication of whether measurements for UE-assisted positioning or for RAN-node assisted positioning are requested. In various embodiments, the bulk subscription request can be only for UE-assisted positioning. In various embodiments, the bulk subscription request can be only for RAN-node assisted positioning. The request can also denote a destination address to which measurements are to be provided.

[0067] In aspects of the present disclosure, the AMF selects RAN node(s) based on the capabilities of the RAN nodes and their load and the target area and forwards the request to the selected RAN nodes. It may reject requests or parts of the target area if there are no suitable RAN nodes.

[0068] In aspects of the present disclosure, the RAN node may select appropriate times for measurements based its load, radio load, and / or the availability of suitable UEs. The RAN node selects UEs that are capable of reporting ground truth location and, for UE-assisted measurements, that are capable of performing such measurements.

[0069] In aspects of the present disclosure, for RAN-node assisted positioning, the RAN node performs channel measurements for each of the selected UEs and requests the selected UE to report its location. The RAN node reports the measured parameters and location reported by the UE, possibly in combination with the cell ID where the UE was located, via the AMF to the MTNF.

[0070] In aspects of the present disclosure, for UE-assisted positioning, the RAN node requests the UE to perform channel measurements and provide them, and also request the related UE to report its location. The RAN node may request the UE to perform multiple measurements and indicate a time window. The RAN node also provides a destination address to which the data is to be communicated. The UE determines its location and also performs the requested channel measurements. The UE performs the requested number of measurements and determines the times for measurements and for reporting based on its load, battery status, and / or radio load. The UE reports information about its location, channel measurement, and information about its configuration (e.g. number of transmission reception points) towards the target address provided by the RAN node via a data connection.

[0071] In aspects of the present disclosure, the MTNF may store the input data received from RAN node or UE at the ADRF together with information about target area, measurement method (UE-assisted positioning or RAN-node assisted positioning).

[0072] In aspects of the present disclosure, the MTNF trains the network-implemented ML model with the input data and may store the trained ML model at the ADRF using a special “location” Analytics ID. The MTNF may stores information about target area and measurement method (UE-assisted positioning or RAN-assisted positioning) together with the trained ML model.

[0073] In aspects of the present disclosure, the LMF, acting as service provider of UE location, may retrieve trained network-implemented ML models from the ADRF. The LMF requests and / or selects trained network-implemented ML models based on the target area and the measurement method. When receiving a request to determine the location of a UE, the LMF sends a request for a channel measurement to the RAN via AMF and indicates the measurement method (UE-assisted positioning or RAN-node assisted positioning). For RAN-node assisted measurement, RAN performs the measurement. For UE-assisted measurements, RAN requests the UE to perform and report the measurement along with information about its configuration (e.g. number of transmission reception points). RAN provides the measurement to the LMF via the AMF.

[0074] Aspects of the present disclosure provide approaches to determine the accuracy of inferred locations generated by the network-implemented ML models while they are in use. A model accuracy determining entity (e.g., LMF or NWDAF / MTLF) sends a request via AMF to a RAN node to provide measurements and ground truth locations indicating a lower rate of channel measurements than the rate of channel measurements for the ML model training. The model accuracy determining entity uses the reported measurements to calculate location using the ML model and compares the calculated locations with the reported locations to determine the accuracy of the model. If the accuracy of the model degrades, it may trigger a re-training of the ML model.

[0075] Referring now to FIG. 2, there is shown a diagram of example operations for training a network-implemented machine learning (ML) model using training data provided by a next-generation radio access network (RAN), according to one illustrated aspect of the disclosure. As shown in FIG. 2, the operations involve a UE, a RAN node, an AMF, a LMF, and an ADRF, which were described in connection with FIG. 1 above.

[0076] At operation 201, the RAN nodes inform the AMF about their capability to support RAN-node assisted positioning, and the AMF receives the information from the RAN nodes. The RAN nodes may also provide periodic reports about their load and / or send indications when they are overloaded.

[0077] At operation 202, the MTNF (e.g., a model training logical function (MTLF) inside NWDAF, or an LMF) sends a request to an AMF to provide measurements and locations for training the network-implemented ML model, and the AMF receives the request from the MTNF. The request denotes a target area and may denote a target time period, a target number of measurements, and / or a target rate of measurements. The request also denotes RAN-node assisted positioning as the desired measurement method.

[0078] At operation 203, the AMF selects RAN node(s) based on the capabilities of the RAN nodes and their load and the target area. The AMF may reject requests or parts of the target area if there are no suitable RAN nodes.

[0079] At operation 204, the AMF forwards the request to the selected RAN nodes, and the RAN nodes receive the request from the AMF.

[0080] At operation 205, the RAN node selects UEs in the target area that indicated a capability to report location information. The RAN node may determine the times and rates of measurements in the requests to the UE, considering the load and available capacity of itself, of related radio cells, and / or of selected UEs.

[0081] At operation 206, for each selected UE and each related measurement time, the RAN node requests the UE to report its location, and the UE receives the request from the RAN node. The UE determines its location and reports its location to the RAN node, and the RAN node receives the report of the UE location.

[0082] At operation 207, for each selected UE and at each measurement time, the RAN node performs a channel measurement.

[0083] At operation 208, the RAN node may, optionally, aggregate multiple measurements into one report.

[0084] At operation 209, the RAN node reports the channel measurements, the UE locations reported by the UE, and the cell ID where the UE was located, to the AMF. The AMF receives the report from the RAN node.

[0085] At operation 210, the AMF forwards the information received at operation 209 to the MTNF, and the MTNF receives the information from the AMF. The AMF may aggregate multiple received reports and forward them together to the MTNF.

[0086] At operation 211, the MTNF may, optionally, store the input data received in operation 210 at the ADRF together with information about target area and measurement method (UE-assisted positioning or RAN-node assisted positioning). The MTNF may subsequently retrieve the stored information for the ML model training.

[0087] At operation 212, the MTNF trains the ML model with the information received in operation 210. The trained ML model operates to output an inferred UE location based on the channel measurements.

[0088] At operation 213, the MTNF may, optionally, store the trained ML model at the ADRF using a special “location” Analytics ID. The MTNF may store information about target area and measurement method (UE-assisted positioning or RAN-node assisted positioning) together with the model. The MTNF may also store an identifier of the stored input data that have been used to train the ML model.

[0089] The operations of FIG. 2 are merely illustrative, and variations are contemplated to be within the scope of the present disclosure. In embodiments, the operations may include other operations not illustrated in FIG. 2. In embodiments, the operations may not include every operation illustrated in FIG. 2. In embodiments, the operations may be implemented in a different order than that illustrated in FIG. 2. Such and other embodiments are contemplated to be within the scope of the present disclosure. Persons of skill in the art will appreciate that, although various example components are described as perform various functions, other components may perform those functions described in FIG. 2.

[0090] FIG. 3 is a diagram of example operations for training a network-implemented ML model using training data provided by a user equipment (UE), according to one illustrated aspect of the disclosure. As shown in FIG. 3, the operations involve a UE, a RAN node, an AMF, a LMF, and an ADRF, which were described in connection with FIG. 1 above.

[0091] At operation 301, the RAN nodes inform the AMF about their capability to support UE-assisted positioning, and the AMF receives the information from the RAN nodes. The RAN nodes may also provide periodic reports about their load and / or send indications when being in overload.

[0092] At operation 302, the MTNF (e g. MTLF inside NWDAF, or an LMF) sends a request to an AMF to provide channel measurements and locations for training a ML model, and the AMF receives the request from the MTNF. The request denotes a target area and may denote a target time period, a target number of measurements, and / or a target rate of measurements. The request also denotes a notification address to which the measurements are to be communicated (e.g., either a data storage entity or the model training entity). The request also denotes UE-assisted positioning as the desired measurement method.

[0093] At operation 303, the AMF selects RAN node(s) based on the capabilities of the RAN nodes and their load and the target area. The AMF may reject requests or parts of the target area if there are no suitable RAN nodes.

[0094] At operation 304, the AMF forwards the request to the selected RAN nodes, and the RAN nodes receive the request from the AMF.

[0095] At operation 305, the RAN node selects UEs in the target area that indicated a capability to report location information and a capability to perform channel measurements for UE-assisted positioning. The RAN node may determine the times and rates of measurements and of requests to the UE, considering the load and available capacity of itself, related radio cells, and / or of selected UEs.

[0096] At operation 306, for each selected UE, the RAN node requests the UE to perform channel measurements for UE-assisted positioning and to report its location, and the UE receives the request from the RAN nodes. The RAN node may request the UE to perform multiple measurements and may also indicate a desired number of measurements, a related time window, and / or a desired rate of measurements. The RAN node may also provide a notification address to which the results should be reported. The UE may reject the request if it is overloaded or needs to save power due to low battery status.

[0097] At operation 307, the UE may determine the times for obtaining channel measurements and for reporting the measurements based on its own load, battery status, and / or radio load.

[0098] At operation 308, for each measurement time, the UE performs a channel measurement.

[0099] At operation 309, for each measurement time, the UE determines its location.

[00100] At operation 310, the UE node may, optionally, aggregate multiple channel measurements and location determinations into one report

[00101] At operation 311, the UE reports the channel measurements, the locations, and the cell ID where the UE was located, to the notification address via a data connection (e.g., PDU session). The UE may additionally report information related to its antenna configuration (e.g. number of transmission reception points) and / or about its model / type (e.g. PEI or TAC).

[00102] At operation 312, the MTNF may, optionally, store the input data received from the UE at operation 311 at the ADRF together with information about target area and measurement method (UE-assisted positioning or RAN-node assisted positioning). The MTNF may subsequently retrieve the stored information to train the ML model.

[00103] At operation 313, the MTNF trains the ML model with the information received at operation 311. The trained ML model operates to output an inferred UE location based on the channel measurements.

[00104] At operation 314, the MTNF may, optionally, store the trained ML model at the ADRF using a special “location” Analytics ID. The MTNF may store information about target area and measurement method (UE-assisted positioning or RAN-node assisted positioning) together with the trained ML model. The MTNF may also store an identifier of the stored input data that have been used to train the ML model.

[00105] The operations of FIG. 3 are merely illustrative, and variations are contemplated to be within the scope of the present disclosure. In embodiments, the operations may include other operations not illustrated in FIG. 3. In embodiments, the operations may not include every operation illustrated in FIG. 3. In embodiments, the operations may be implemented in a different order than that illustrated in FIG. 3. Such and other embodiments are contemplated to be within the scope of the present disclosure. Persons of skill in the art will appreciate that, although various example components are described as perform various functions, other components may perform those functions described in FIG. 3.

[00106] FIG. 4 is a diagram of example operations of selecting UEs to provide the training data provided in FIG. 3, according to one illustrated aspect of the disclosure. As shown in FIG. 4, the operations involve a UE, a RAN node, and an AMF, which were described in connection with FIG. 1 above.

[00107] At operation 401, the UE registers via RAN node at an AMF.

[00108] At operation 402, the AMF enquires about the Permanent Equipment Identifier (PEI) of the UE, and the UE provides its PEI.

[00109] At operation 403, the AMF uses configured information and the Type Allocation code (TAC), which is part of an IMEI or IMEISC within the PEI, to determine whether the UE is suitable to provide location reports for the purpose of ML model training and / or whether the UE is suitable to perform channel measurements for UE-assisted positioning.

[00110] At operation 404, the AMF indicates to the RAN node whether the UE is suitable to provide location reports for the purpose of ML model training and / or whether the UE is suitable to perform channel measurements for UE-assisted positioning. The AMF may indication such information to the RAN, for example, within the UE registration procedure.

[00111] At operation 405, the RAN stores this information as part of the UE context and uses that information when selecting UEs, e.g., in operation 205 of FIG. 2 or in operation 305 of FIG. 3.

[00112] The operations of FIG. 4 are merely illustrative, and variations are contemplated to be within the scope of the present disclosure. In embodiments, the operations may include other operations not illustrated in FIG. 4. In embodiments, the operations may not include every operation illustrated in FIG. 4. In embodiments, the operations may be implemented in a different order than that illustrated in FIG. 4. Such and other embodiments are contemplated to be within the scope of the present disclosure. Persons of skill in the art will appreciate that, although various example components are described as perform various functions, other components may perform those functions described in FIG. 4.

[00113] FIG. 5 is a diagram of example operations of executing a trained network-implemented ML model, using data from a RAN, to provide an inferred location of a UE, according to one illustrated aspect of the disclosure. As shown in FIG. 5, the operations involve a UE, a RAN node, an AMF, and a LMF, which were described in connection with FIG. 1 above.

[00114] At operation 501, when the LMF receives a request to determine the location of a UE and determines to use RAN-node assisted positioning with a network-implemented ML model, the LMF sends a request to the AMF for a RAN node related to the UE. The AMF receives the request from the LMF.

[00115] Operations 502 and 503 involve a network triggered service request and a network positioning message, and they are the same as such operations in Figure 6.11.2-1 of 3GPP TS 23.273; e.g., the AMF sends the request to the RAN, and the RAN receives the request from the AMF.

[00116] At operation 504, the RAN performs the channel measurements.

[00117] Operations 505 and 506 are the same as such operations in Figure 6.11.2-1 of 3GPP TS 23.273; e.g., the RAN node reports the channel measurements and the cell ID to the AMF, and the AMF receives the reports from the RAN node; the AMF sends the reports to the LMF, and the LMF receives the reports from the AMF.

[00118] At operation 507, the LMF retrieves the network-implemented trained ML model from MTNF or from the ADRF. The LMF may request the trained ML model using a special “location” Analytics ID, the target area, and measurement method (UE-assisted positioning or RAN-node assisted positioning).

[00119] At operation 508. The LMF provides the inferred UE location using the trained ML model and the information received in at operation 506.

[00120] The operations of FIG. 5 are merely illustrative, and variations are contemplated to be within the scope of the present disclosure. In embodiments, the operations may include other operations not illustrated in FIG. 5. In embodiments, the operations may not include every operation illustrated in FIG. 5. In embodiments, the operations may be implemented in a different order than that illustrated in FIG. 5. Such and other embodiments are contemplated to be within the scope of the present disclosure. Persons of skill in the art will appreciate that, although various example components are described as perform various functions, other components may perform those functions described in FIG. 5.

[00121] FIG. 6 is a diagram of example operations of executing a trained network-implemented ML model, using data from a UE, to provide an inferred location of the UE, according to one illustrated aspect of the disclosure. As shown in FIG. 6, the operations involve a UE, a RAN node, an AMF, and a LMF, which were described in connection with FIG. 1 above.

[00122] At operation 601, when the LMF receives a request to determine the location of a UE and determines to use UE-assisted positioning with a network-implemented ML model, the LMF sends a request for a UE-assisted positioning related to the UE.

[00123] Operations 602 and 603 involve a network triggered service request and a downlink positioning message, and they are the same as such operations in Figure 6.11.1-1 of 3GPP TS 23.273; e.g., the AMF sends the request to the UE, and the UE receives the request from the AMF.

[00124] At operation 604, the UE performs the channel measurements.

[00125] Operations 605-607 are the same as such operations in Figure 6.11.1-1 of 3GPP TS 23.273; e.g., the UE reports the measurements, the cell ID, and information related to its antenna configuration (e.g. number of transmission reception points) and / or about its model / type to the AMF, and the AMF receives the reports from the UE; the AMF sends the reports to the LMF, and the LMF receives the reports from the AMF.

[00126] At operation 608, the LMF may retrieve the trained ML model from the MTNF or from the ADRF The request for the trained ML model may use a special “location” Analytics ID, the target area, and measurement method (UE-assisted positioning or RAN-node assisted positioning).

[00127] At operation 609, the LMF provides the inferred UE location using the trained ML model and the information received in operation 607.

[00128] The operations of FIG. 6 are merely illustrative, and variations are contemplated to be within the scope of the present disclosure. In embodiments, the operations may include other operations not illustrated in FIG. 6. In embodiments, the operations may not include every operation illustrated in FIG. 6. In embodiments, the operations may be implemented in a different order than that illustrated in FIG. 6. Such and other embodiments are contemplated to be within the scope of the present disclosure. Persons of skill in the art will appreciate that, although various example components are described as perform various functions, other components may perform those functions described in FIG. 6.

[00129] FIG. 7 is a diagram of example operations of determining accuracy of a trained network-implemented ML model in providing inferred UE locations using data from a RAN, according to one illustrated aspect of the disclosure. As shown in FIG. 7, the operations involve a UE, a RAN node, an AMF, a model accuracy determining NF (which may be LMF or MTLF), and an ADRF.

[00130] Operation 701-710 are the same as operations 201-210 of FIG. 2, except that the MTNF is replaced by the model accuracy determining NF, which may be the same as the MTNF or may be a different entity. In various embodiments, the model accuracy determining NF may be an LMF or a NWDAF / MTLF. The model accuracy determining NF preferably requests a lower rate of measurements than the rate requested in operation 202.

[00131] At operation 711, the model accuracy determining NF retrieves the trained ML model from the MTNF or from the ADRF. The model accuracy determining NF can request the trained ML model using a special “location” Analytics ID, the target area, and measurement method (UE-assisted positioning or RAN-node assisted positioning).

[00132] At operation 712, the model accuracy determining NF uses the reported channel measurements received at operation 710 to provide an inferred UE location using the trained ML model and the channel measurements.

[00133] At operation 713, the model accuracy determining NF compares the inferred UE location with the reported UE location received at operation 710 to determine the accuracy of the trained ML model.

[00134] At operation 714, if the accuracy of the trained ML model degrades, the model accuracy determining NF can trigger a retraining of the ML model.

[00135] The operations of FIG. 7 are merely illustrative, and variations are contemplated to be within the scope of the present disclosure. In embodiments, the operations may include other operations not illustrated in FIG. 7. In embodiments, the operations may not include every operation illustrated in FIG. 7. In embodiments, the operations may be implemented in a different order than that illustrated in FIG. 7. Such and other embodiments are contemplated to be within the scope of the present disclosure. Persons of skill in the art will appreciate that, although various example components are described as perform various functions, other components may perform those functions described in FIG. 7.

[00136] The following describes operations from the perspective of a UE, from the perspective of a core network entity, and from the perspective of a RAN node.

[00137] From the perspective of a UE, a method in a user equipment (UE) includes: receiving a message comprising a request for bulk reporting of channel measurements and UE locations of the UE (e.g., 306, FIG. 3); obtaining a plurality of channel measurements of at least one transmission reception point (e.g., 308, FIG. 3); obtaining a plurality of UE locations of the UE (e.g., 309, FIG. 3); associating the plurality of UE locations with the plurality of channel measurements (e.g., 310 / 311, FIG. 3); and transmitting, in response to the request for bulk reporting, at least one message comprising the plurality of channel measurements and the plurality of UE locations (e.g., 311, FIG. 3).

[00138] From the perspective of a core network entity (e.g., AMF), a method in a core network entity includes: receiving, from an entity configured to train a machine learning (ML) model for inferring a location of a user equipment or configured to determine accuracy of the ML model, a request for bulk reporting of channel measurements and user equipment (UE) locations, where the bulk reporting is to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, where the request for bulk reporting comprises a specified target area in which to obtain the channel measurements and UE locations (e.g., 202, FIG. 2; 302, FIG. 3); in response to the request, selecting at least one RAN node based at least on the specified target area (e.g., 203, FIG. 2; 303, FIG. 3); and transmitting, to the selected at least one RAN node, a message comprising the request for bulk reporting of channel measurements and UE locations (e.g., 204, FIG. 2; 304, FIG. 3).

[00139] From the perspective of a core network entity (e.g., AMF), a method in a core network entity includes: receiving a registration request from a user equipment (UE) (e.g., 401, FIG. 4); obtaining a Permanent Equipment Identifier (PEI) from the UE (e.g., 402, FIG. 4); determining, based on the PEI, at least one of whether the user equipment is capable of performing suitable channel measurements, or whether the user equipment is capable of obtaining suitable UE locations (e.g., 403, FIG. 4); and based on the determination, transmitting, to a radio access network (RAN) node servicing the UE, at least one of: an indication that the UE is capable of obtaining suitable channel measurements, or an indication that the UE is capable of obtaining UE locations (404; FIG. 4).

[00140] From the perspective of a core network entity (e.g., MTNF or model accuracy determining NF), a method in a core network entity includes: transmitting a request for bulk reporting of channel measurements and user equipment (UE) locations, where the bulk reporting is to be performed by at least one UEs or at least one radio access network (RAN) node, where the request for bulk reporting comprises a specified target area in which to obtain the channel measurements and UE locations (e.g., 202, FIG. 2; 302, FIG. 3; 702; FIG. 7); in response to the request, receiving at least one message comprising a plurality of channel measurements and a plurality of UE locations (e.g., 210, FIG. 2; 311, FIG. 3; 710; FIG. 7); and performing at least one of: training a machine learning (ML) model using the received plurality of channel measurements and plurality of UE locations, or determining accuracy of a trained ML model using the received plurality of channel measurement and plurality of UE locations (e.g., 212, FIG. 2; 313, FIG. 3; 713; FIG. 7).

[00141] From the perspective of a core network entity (e.g., ADRF), a method in a core network entity includes: receiving a request to store information of: at least one of: a target area, a radio cell identifier, a configuration information of UEs, a number of transmission reception points of UEs, a type allocation code of UEs, an indication that UE-assisted positioning mode was used, or an indication that RAN-node assisted positioning mode was used, and at least one of: a trained machine learning (ML) model, or input data for a ML model (e.g., 211, 213, FIG. 2; 312, 314, FIG. 3); storing the information (e.g., 211, 213, FIG. 2; 312, 314, FIG. 3); receiving a request for a stored ML model, where the request for the stored ML model comprising at least one of: the target area, the radio cell identifier, the configuration information of related UEs, the number of transmission reception points of related UEs, the type allocation code of related UEs, an indication that a model where UE-assisted positioning mode was used is requested, or an indication that a model where RAN-node assisted positioning mode was used is requested (e.g., 507, FIG. 5; 608, FIG. 6; 711, FIG. 7); selecting a stored ML model based on the request for the stored ML model (e.g., 507, FIG. 5; 608, FIG. 6; 711, FIG. 7); and providing, in response to the request for the stored ML model, information related to the selected ML model (e.g., 507, FIG. 5; 608, FIG. 6; 711, FIG. 7).

[00142] From the perspective of a RAN node, a method includes: receiving, from a core network entity, a message comprising a request for bulk reporting of channel measurements and UE locations, where the bulk reporting is to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, where the request for bulk reporting comprising a specified target area in which to obtain the channel measurements and UE locations (e.g., 204, FIG. 2; 304, FIG. 3; 704, FIG. 7); in response to the request, selecting at least one UE based at least on the specified target area (e.g., 205, FIG. 2; 305, FIG. 3; 705, FIG. 7); and transmitting, to each of the selected at least one UE, a message comprising a request for the UE to perform reporting of at least UE locations (e.g., 206, FIG. 2; 306, FIG. 3; 706, FIG. 7).

[00143] Referring now to FIG. 8, there is shown a block diagram of example components of a UE or a network apparatus (e.g., of a RAN or a core network). The apparatus includes an electronic storage 810, a processor 820, a network interface 840, and a memory 850. The various components may be communicatively coupled with each other. The processor 820 may be and may include any type of processor, such as a single-core central processing unit (CPU), a multi-core CPU, a microprocessor, a digital signal processor (DSP), a System-on-Chip (SoC), or any other type of processor. The memory 850 may be a volatile type of memory, e.g., RAM, or a non-volatile type of memory, e.g., NAND flash memory. The memory 850 includes processor-readable instructions that are executable by the processor 820 to cause the apparatus to perform various operations, including those mentioned herein, such as the operations described in FIGS. 3-7.

[00144] The electronic storage 810 may be and include any type of electronic storage used for storing data, such as hard disk drive, solid state drive, optical disc, and / or other non-transitory computer-readable mediums, among other types of electronic storage. The electronic storage 810 stores processor-readable instructions for causing or configured for causing the apparatus to perform its operations and also stores data associated with such operations, such as storing data relating to 5GNR standards, among other data. The network interface 840 may implement wireless networking technologies such as 5G NR and / or other wireless networking technologies.

[00145] The components shown in FIG. 8 are merely examples, and persons skilled in the art will understand that an apparatus includes other components not illustrated and may include multiples of any of the illustrated components. Such and other embodiments are contemplated to be within the scope of the present disclosure. For example, a transmitter and a receiver may be included as components for transmitting and receiving signals.

[00146] Further embodiments of the present disclosure include the following examples. In the following examples, a “means” may be a processor that executes processor-readable instructions. More than one means may refer to the same processor or may refer to different processors.

[00147] Example 1.1. An apparatus comprising: means for receiving a message comprising a request for bulk reporting of channel measurements and UE locations of the UE; means for obtaining a plurality of channel measurements of at least one transmission reception point; means for obtaining a plurality of UE locations of the UE; means for associating the plurality of UE locations with the plurality of channel measurements; and means for transmitting, in response to the request for bulk reporting, at least one message comprising the plurality of channel measurements and the plurality of UE locations.

[00148] Example 1.2. The apparatus as in Example 1.1, wherein the received message comprises at least one of: a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements, and wherein the plurality of channel measurements and the plurality of UE locations are obtained in accordance with the at least one of: the target time window for channel measurements, the target number of channel measurements, or the target rate of channel measurements.

[00149] Example 1.3. The apparatus as in any one of the preceding Examples, further comprising: means for determining a time to obtain the plurality of channel measurements and the plurality of UE locations based on at least one of: UE load at the UE, battery status at the UE, or radio load.

[00150] Example 1.4. The apparatus as in any one of the preceding Examples, wherein the at least one transmitted message further comprises at least one of: UE configuration information, number of transmission reception points the UE is configured to use, a type allocation code of the UE, or a cell identifier of a radio cell where the UE is located.

[00151] Example 1.5. The apparatus as in any one of the preceding Examples, wherein the message comprising the request further comprises a target address to which the at least one message is to be transmitted; and wherein the at least one message is transmitted towards the target address.

[00152] Example 1.6. The apparatus as in Example 1.5, further comprising: means for aggregating the plurality of channel measurements and the plurality of UE locations over a plurality of time windows for channel measurements, wherein the at least one transmitted message comprises the plurality of channel measurements and the plurality of UE locations aggregated over the plurality of time windows.

[00153] Example 2.1. An apparatus comprising: means for receiving, from an entity configured to train a machine learning (ML) model for inferring a location of a user equipment or configured to determine accuracy of the ML model, a request for bulk reporting of channel measurements and user equipment (UE) locations, the bulk reporting to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, the request for bulk reporting comprising a specified target area in which to obtain the channel measurements and UE locations; means for, in response to the request, selecting at least one RAN node based at least on the specified target area; and means for transmitting, to the selected at least one RAN node, a message comprising the request for bulk reporting of channel measurements and UE locations.

[00154] Example 2.2. The apparatus as in Example 2.1, wherein the received request comprises at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements for at least one transmission reception point, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

[00155] Example 2.3. The apparatus as in any one of the preceding Examples, wherein the selecting the at least one RAN node comprises at least one of identifying RAN nodes that are capable of supporting the RAN-node assisted positioning mode or identifying RAN nodes that are capable of supporting the UE-assisted positioning mode.

[00156] Example 2.4. The apparatus as in Example 2.3, further comprising: means for determining that a portion of the specified target area has no RAN nodes that are available to support the RAN-node assisted positioning node; and means for transmitting, to the entity, a message rejecting the portion of the specified target area for the bulk reporting.

[00157] Example 2.5. The apparatus of Example 2.4, wherein the determining that the portion of the specified target area has no RAN nodes that are available to support the RAN-node assisted positioning mode, is based on at least one of: information indicating which RAN nodes in the specified target area are capable of supporting RAN-node assisted positioning mode, or information indicating load of RAN nodes in the specified target area.

[00158] Example 2.6. An apparatus comprising: means for receiving a registration request from a user equipment (UE); means for obtaining a Permanent Equipment Identifier (PEI) from the UE; means for determining, based on the PEI, at least one of: whether the user equipment is capable of performing suitable channel measurements, or whether the user equipment is capable of obtaining suitable UE locations; and means for, based on the determination, transmitting, to a radio access network (RAN) node servicing the UE, at least one of: an indication that the UE is capable of obtaining suitable channel measurements, an indication that the UE is capable of obtaining UE locations.

[00159] Example 2.7. The apparatus of Example 2.6, wherein the determination is based on a Type Allocation Code (TAC) within the PEI.

[00160] Example 2.8. The apparatus of Example 2.6, wherein the determination uses configured information indicating at least one of: Type Allocation Codes (TAC) associated with UEs that are capable of performing suitable channel measurements, or Type Allocation Codes (TAC) associated with UEs that are capable of obtaining suitable UE locations.

[00161] Example 2.9. A method in a core network entity, the method comprising receiving a registration request from a user equipment (UE); obtaining a Permanent Equipment Identifier (PEI) from the UE; determining, based on the PEI, at least one of: whether the user equipment is capable of performing suitable channel measurements, or whether the user equipment is capable of obtaining suitable UE locations; and based on the determination, transmitting, to a radio access network (RAN) node servicing the UE, at least one of: an indication that the UE is capable of obtaining suitable channel measurements, an indication that the UE is capable of obtaining UE locations.

[00162] Example 2.10. The method of Example 2.9, wherein the determination is based on a Type Allocation Code (TAC) within the PEI.

[00163] Example 2.11. The method of Example 2.10, wherein the determination uses configured information indicating at least one of: Type Allocation Codes (TAC) associated with UEs that are capable of performing suitable channel measurements, or Type Allocation Codes (TAC) associated with UEs that are capable of obtaining suitable UE locations.

[00164] Example 2.12. An apparatus comprising: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to perform a method as in any one of Example 2.9-2.11.

[00165] Example 2.13. A processor-readable medium storing instructions which, when executed by at least one processor of an apparatus, cause the apparatus at least to perform a method as in any one of Example 2.9-2.11.

[00166] Example 3.1. An apparatus comprising: means for receiving, from a core network entity, a message comprising a request for bulk reporting of channel measurements and UE locations, the bulk reporting to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, the request for bulk reporting comprising a specified target area in which to obtain the channel measurements and UE locations; means for, in response to the request, selecting at least one UE based at least on the specified target area; and means for transmitting, to each of the selected at least one UE, a message comprising a request for the UE to perform reporting of at least UE locations.

[00167] Example 3.2. The apparatus as in Example 3.1, wherein the message comprising the request for bulk reporting further comprises at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

[00168] Example 3.3 The apparatus as in Example 3.1 or Example 3.2, further comprising: means for determining a time for transmitting the at least one message comprising a request for the selected at least one UE to perform reporting and a number of the at least one message, wherein the determining is based on at least one of the received target time window for channel measurements, the received target number of channel measurements, a received target rate of channel measurements, a load of the RAN node, a capacity of the RAN node, a load of radio cells in the specified target area, or a capacity of radio cells in the specified target area.

[00169] Example 3.4. The apparatus of Example 3.1 or 3.2, wherein the selected at least one UE is selected based on at least one of: a capability reported by the UE to obtain UE locations, a capability reported by the UE to perform channel measurements, an indication received from a core network entity that the UE is capable of performing suitable channel measurements, an indication received from a core network entity that the UE is capable of obtaining suitable UE locations, load of a UE, or capacity of a UE.

[00170] Example 3.5. The apparatus as in Example 3.2, wherein the request for the at least one UE to perform reporting comprises at least one of: a specified time window for channel measurements, a specified number of channel measurements, or a specified rate of channel measurements, and wherein the specified time window for channel measurements, the specified target number of channel measurements, or the specified target rate of channel measurements are determined based on at least one of: the received target time window for channel measurements, the received target number of channel measurements, the received target rate of channel measurements, or a number of the selected at least one UE.

[00171] Example 3.6. The apparatus as in Example 3.1, further comprising: means for receiving, from the at least one UE, a UE location; means for obtaining, by the RAN node, channel measurements of at least one transmission reception point; and means for associating the UE location with the channel measurements.

[00172] Example 3.7. The apparatus as in Example 3.6, further comprising: means for aggregating a plurality of channel measurements and a plurality of UE locations over a plurality of time windows for channel measurements; and means for transmitting, to the core network entity, at least one message comprising the plurality of channel measurements and the plurality of UE locations aggregated over the plurality of time windows.

[00173] Example 4.1. A method in a core network entity, the method comprising: transmitting a request for bulk reporting of channel measurements and user equipment (UE) locations, the bulk reporting to be performed by at least one UEs or at least one radio access network (RAN) node, the request for bulk reporting comprising a specified target area in which to obtain the channel measurements and UE locations, in response to the request, receiving at least one message comprising a plurality of channel measurements and a plurality of UE locations; and performing at least one of: training a machine learning (ML) model using the received plurality of channel measurements and plurality of UE locations, or determining accuracy of a trained ML model using the received plurality of channel measurement and plurality of UE locations.

[00174] Example 4.2. The method as in Example 4.1, wherein the request for bulk reporting further comprises at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

[00175] Example 4.3. The method as in Example 4.1 or Example 4.2, wherein the at least one message further comprises information including at least one of: UE configuration information, a number of transmission reception points a UE is configured to use, a type allocation code of a UE, or a cell identifier of a radio cell, and

[00176] wherein the information is used for at least one of: selecting a trained ML model, training a ML model, or determining accuracy of a trained ML model.

[00177] Example 4.4. The method as in Example 4.2 or Example 4.3, further comprising storing, at an analytics data repository function (ARDF):

[00178] at least one of: the specified target area, a radio cell identifier, configuration information of UEs, a number of transmission reception points of UEs, a type allocation code of UEs, an indication that UE-assisted positioning mode was used, or an indication that RAN-node assisted positioning mode was used; and at least one of: the trained machine learning model, or the at least one message.

[00179] Example 4.5. The method as in any one of the preceding Examples, wherein the determining the accuracy of the trained ML model comprises: calculating a UE location based on the trained ML model and the plurality of channel measurements; and calculating a distance between the calculated UE location and at least one of the received plurality of UE locations.

[00180] Example 4.6. The method as in any one of the preceding Examples, further comprising: receiving a request for trained ML model, the request for the trained ML model comprising at least one of: a target area, a radio cell identifier, a configuration information of UEs, a number of transmission reception points of UEs, a type allocation code of UEs, an indication that a trained ML model where UE-assisted positioning mode was used is requested, or an indication that a trained ML model where RAN-node assisted positioning mode was used is requested; selecting a trained ML model based on the request for a trained ML model; and providing, in response to the request for a trained ML model, information related to the selected ML model.

[00181] Example 4.7. An apparatus, comprising: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to perform a method as in any one of Example 4.1-4.6.

[00182] Example 4.8. A processor-readable medium storing instructions which, when executed by at least one processor of an apparatus, cause the apparatus at least to perform a method as in any one of Example 4.1-4.6.

[00183] Example 4.9. An apparatus comprising: means for transmitting a request for bulk reporting of channel measurements and user equipment (UE) locations, the bulk reporting to be performed by at least one UEs or at least one radio access network (RAN) node, the request for bulk reporting comprising a specified target area in which to obtain the channel measurements and UE locations, means for, in response to the request, receiving at least one message comprising a plurality of channel measurements and a plurality of UE locations; and means for performing at least one of: training a machine learning (ML) model using the received plurality of channel measurements and plurality of UE locations, or determining accuracy of a trained ML model using the received plurality of channel measurement and plurality of UE locations.

[00184] Example 4.10. The apparatus as in Example 4.9, wherein the request for bulk reporting further comprises at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

[00185] Example 4.11. The apparatus as in Example 4.9 or 4.10, wherein the at least one message further comprises information including at least one of: UE configuration information, a number of transmission reception points a UE is configured to use, a type allocation code of a UE, or a cell identifier of a radio cell, and wherein the information is used for at least one of: selecting a trained ML model, training a ML model, or determining accuracy of a trained ML model.

[00186] Example 4.12. The apparatus as in Example 4.10 or Example 4.11, further comprising storing, at an analytics data repository function (ARDF): at least one of: the specified target area, a radio cell identifier, configuration information of UEs, a number of transmission reception points of UEs, a type allocation code of UEs, an indication that UE-assisted positioning mode was used, or an indication that RAN-node assisted positioning mode was used; and at least one of: the trained machine learning model, or the at least one message.

[00187] Example 4.13. The apparatus as in any one of the preceding Examples, wherein the determining the accuracy of the trained ML model comprises: means for calculating a UE location based on the trained ML model and the plurality of channel measurements; and means for calculating a distance between the calculated UE location and at least one of the received plurality of UE locations.

[00188] Example 4.14. The apparatus as in any one of the preceding Examples, further comprising: means for receiving a request for trained ML model, the request for the trained ML model comprising at least one of: a target area, a radio cell identifier, a configuration information of UEs, a number of transmission reception points of UEs, a type allocation code of UEs, an indication that a trained ML model where UE-assisted positioning mode was used is requested, or an indication that a trained ML model where RAN-node assisted positioning mode was used is requested; means for selecting a trained ML model based on the request for a trained ML model; and means for providing, in response to the request for a trained ML model, information related to the selected ML model.

[00189] Example 5.1. A method in a core network entity, the method comprising: receiving a request to store information of: at least one of: a target area, a radio cell identifier, a configuration information of UEs, a number of transmission reception points of UEs, a type allocation code of UEs, an indication that UE-assisted positioning mode was used, or an indication that RAN-node assisted positioning mode was used, and at least one of: a trained machine learning (ML) model, or input data for a ML model; storing the information; receiving a request for a stored ML model, the request for the stored ML model comprising at least one of the target area, the radio cell identifier, the configuration information of related UEs, the number of transmission reception points of related UEs, the type allocation code of related UEs, an indication that a model where UE-assisted positioning mode was used is requested, or an indication that a model where RAN-node assisted positioning mode was used is requested; selecting a stored ML model based on the request for the stored ML model; and providing, in response to the request for the stored ML model, information related to the selected ML model.

[00190] Example 5.2. An apparatus, comprising: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to perform a method as in Example 5.1.

[00191] Example 5.3. A processor-readable medium storing instructions which, when executed by at least one processor of an apparatus, cause the apparatus at least to perform a method as in Example 5.1.

[00192] Example 5.4. An apparatus comprising: means for receiving a request to store information of: at least one of: a target area, a radio cell identifier, a configuration information of UEs, a number of transmission reception points of UEs, a type allocation code of UEs, an indication that UE-assisted positioning mode was used, or an indication that RAN-node assisted positioning mode was used, and at least one of: a trained machine learning (ML) model, or input data for a ML model; means for storing the information; means for receiving a request for a stored ML model, the request for the stored ML model comprising at least one of the target area, the radio cell identifier, the configuration information of related UEs, the number of transmission reception points of related UEs, the type allocation code of related UEs, an indication that a model where UE-assisted positioning mode was used is requested, or an indication that a model where RAN-node assisted positioning mode was used is requested; means for selecting a stored ML model based on the request for the stored ML model; and means for providing, in response to the request for the stored ML model, information related to the selected ML model.

[00193] The embodiments and aspects disclosed herein are examples of the present disclosure and may be embodied in various forms. For instance, although certain embodiments herein are described as separate embodiments, each of the embodiments herein may be combined with one or more of the other embodiments herein. Specific structural and functional details disclosed herein are not to be interpreted as limiting, but as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present disclosure in virtually any appropriately detailed structure. Like reference numerals may refer to similar or identical elements throughout the description of the figures.

[00194] The phrases “in an aspect,” “in aspects,” “in various aspects,” “in some aspects,” or “in other aspects” may each refer to one or more of the same or different aspects in accordance with this present disclosure. The phrase “a plurality of’ may refer to two or more.

[00195] In various embodiments, the terms “first message” and “second message”, as well as any subsequent messages may refer to any messages that are transmitted or received in an order and are not necessarily limited to any particular message.

[00196] The phrases “in an embodiment,” “in embodiments,” “in various embodiments,” “in some embodiments,” or “in other embodiments” may each refer to one or more of the same or different embodiments in accordance with the present disclosure. A phrase in the form “A or B” means “(A), (B), or (A and B)” A phrase in the form “at least one of A, B, or C” means “(A); (B); (C); (AandB); (A and C); (B andC); or (A, B, and C)”

[00197] Any of the herein described methods, programs, algorithms or codes may be converted to, or expressed in, a programming language or computer program. The terms “programming language” and “computer program,” as used herein, each include any language used to specify instructions to a computer, and include (but is not limited to) the following languages and their derivatives: Assembler, Basic, Batch files, BCPL, C, C+, C++, Delphi, Fortran, Java, JavaScript, machine code, operating system command languages, Pascal, Perl, PL1, Python, scripting languages, Visual Basic, metalanguages which themselves specify programs, and all first, second, third, fourth, fifth, or further generation computer languages. Also included are database and other data schemas, and any other meta-languages. No distinction is made between languages which are interpreted, compiled, or use both compiled and interpreted approaches. No distinction is made between compiled and source versions of a program. Thus, reference to a program, where the programming language could exist in more than one state (such as source, compiled, object, or linked) is a reference to any and all such states. Reference to a program may encompass the actual instructions and / or the intent of those instructions.

[00198] While aspects of the present disclosure have been shown in the drawings, it is not intended that the present disclosure be limited thereto, as it is intended that the present disclosure be as broad in scope as the art will allow and that the specification be read likewise. Therefore, the above description should not be construed as limiting, but merely as exemplifications of particular aspects. Those skilled in the art will envision other modifications within the scope and spirit of the claims appended hereto.

Claims

1. A method in a user equipment (UE), the method comprising:receiving a message comprising a request for bulk reporting of channel measurements and UE locations of the UE;obtaining a plurality of channel measurements of at least one transmission reception point;obtaining a plurality of UE locations of the UE;associating the plurality of UE locations with the plurality of channel measurements; andtransmitting, in response to the request for bulk reporting, at least one message comprising the plurality of channel measurements and the plurality of UE locations.

2. The method as in claim 1, wherein the received message comprises at least one of: a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements, andwherein the plurality of channel measurements and the plurality of UE locations are obtained in accordance with the at least one of: the target time window for channel measurements, the target number of channel measurements, or the target rate of channel measurements.

3. The method as in any one of the preceding claims, further comprising:determining a time to obtain the plurality of channel measurements and the plurality of UE locations based on at least one of: UE load at the UE, battery status at the UE, or radio load.

4. The method as in any one of the preceding claims, wherein the at least one transmitted message further comprises at least one of: UE configuration information, number of transmission reception points the UE is configured to use, a type allocation code of the UE, or a cell identifier of a radio cell where the UE is located.

5. The method as in any one of the preceding claims, wherein the message comprising the request further comprises a target address to which the at least one message is to be transmitted; andwherein the at least one message is transmitted towards the target address.

6. The method as in claim 5, further comprising:aggregating the plurality of channel measurements and the plurality of UE locations over a plurality of time windows for channel measurements,wherein the at least one transmitted message comprises the plurality of channel measurements and the plurality of UE locations aggregated over the plurality of time windows.

7. An apparatus, comprising:at least one processor; andat least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to perform a method as in any one of claims 1-6.

8. A processor-readable medium storing instructions which, when executed by at least one processor of an apparatus, cause the apparatus at least to perform a method as in any one of claims 1-6.

9. A method in a core network entity, the method comprising:receiving, from an entity configured to train a machine learning (ML) model for inferring a location of a user equipment or configured to determine accuracy of the ML model, a request for bulk reporting of channel measurements and user equipment (UE) locations, the bulk reporting to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, the request for bulk reporting comprising a specified target area in which to obtain the channel measurements and UE locations;in response to the request, selecting at least one RAN node based at least on the specified target area; andtransmitting, to the selected at least one RAN node, a message comprising the request for bulk reporting of channel measurements and UE locations.

10. The method as in claim 9, wherein the received request comprises at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements for at leastone transmission reception point, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

11. The method as in claim 9 or claim 10, wherein the selecting the at least one RAN node comprises at least one of identifying RAN nodes that are capable of supporting the RAN-node assisted positioning mode or identifying RAN nodes that are capable of supporting the UE-assisted positioning mode.

12. The method as in claim 11, further comprising:determining that a portion of the specified target area has no RAN nodes that are available to support the RAN-node assisted positioning node; andtransmitting, to the entity, a message rejecting the portion of the specified target area for the bulk reporting.

13. The method of claim 12, wherein the determining that the portion of the specified target area has no RAN nodes that are available to support the RAN-node assisted positioning mode, is based on at least one of:information indicating which RAN nodes in the specified target area are capable of supporting RAN-node assisted positioning mode, orinformation indicating load of RAN nodes in the specified target area.

14. An apparatus, comprising:at least one processor; andat least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to perform a method as in any one of claims 9-13.

15. A processor-readable medium storing instructions which, when executed by at least one processor of an apparatus, cause the apparatus at least to perform a method as in any one of claims 9-13.

16. A method in a radio access network (RAN) node, the method comprising: receiving, from a core network entity, a message comprising a request for bulk reporting of channel measurements and UE locations, the bulk reporting to be performed by at least one user equipment (UE) or at least one radio access network (RAN) node, therequest for bulk reporting comprising a specified target area in which to obtain the channel measurements and UE locations;in response to the request, selecting at least one UE based at least on the specified target area; andtransmitting, to each of the selected at least one UE, a message comprising a request for the UE to perform reporting of at least UE locations.

17. The method as in claim 16, wherein the message comprising the request for bulk reporting further comprises at least one of: an indication to use a UE-assisted positioning mode in which a UE performs channel measurements for at least one transmission reception point, an indication to use a RAN-node assisted positioning mode in which a RAN node performs channel measurements, a target time window for channel measurements, a target number of channel measurements, or a target rate of channel measurements.

18. The method as in claim 16 or claim 17, further comprising:determining a time for transmitting the at least one message comprising a request for the selected at least one UE to perform reporting and a number of the at least one message, wherein the determining is based on at least one of the received target time window for channel measurements, the received target number of channel measurements, a received target rate of channel measurements, a load of the RAN node, a capacity of the RAN node, a load of radio cells in the specified target area, or a capacity of radio cells in the specified target area.

19. The method as in claim 16 or 17, wherein the selected at least one UE is selected based on at least one of: a capability reported by the UE to obtain UE locations, a capability reported by the UE to perform channel measurements, an indication received from a core network entity that the UE is capable of performing suitable channel measurements, an indication received from a core network entity that the UE is capable of obtaining suitable UE locations, load of a UE, or capacity of a UE.

20. The method as in claim 17, wherein the request for the at least one UE to perform reporting comprises at least one of: a specified time window for channel measurements, a specified number of channel measurements, or a specified rate of channel measurements, andwherein the specified time window for channel measurements, the specified target number of channel measurements, or the specified target rate of channel measurements are determined based on at least one of: the received target time window for channel measurements, the received target number of channel measurements, the received target rate of channel measurements, or a number of the selected at least one UE.

21. The method as in claim 16, further comprising:receiving, from the at least one UE, a UE location;obtaining, by the RAN node, channel measurements of at least one transmission reception point; andassociating the UE location with the channel measurements.

22. The method as in claim 21, further comprising:aggregating a plurality of channel measurements and a plurality of UE locations over a plurality of time windows for channel measurements; andtransmitting, to the core network entity, at least one message comprising the plurality of channel measurements and the plurality of UE locations aggregated over the plurality of time windows.

23. An apparatus, comprising:at least one processor; andat least one memory storing instructions which, when executed by the at least one processor, cause the apparatus at least to perform a method as in any one of claims 16-22.

24. A processor-readable medium storing instructions which, when executed by at least one processor of an apparatus, cause the apparatus at least to perform a method as in any one of claims 16-22.

Images