Data collection and inference

Abstract

An apparatus is disclosed for : receiving, from a core network node: first information for performing a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal (PRS) configuration comprising information indicative of entities of a Radio Access Network (RAN) and at least one Identifier (ID) representative of a set of RAN entities comprising the entities; performing the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS received based on the at least one PRS configuration, and sending, to a training entity for training a model, information indicative of the at least one dataset and the at least one ID.

Description

[0001] TITLE

[0002] DATA COLLECTION AND INFERENCE

[0003] TECHNOLOGICAL FIELD

[0004] Certain examples of the disclosure relate to apparatuses, methods, and computer programs for data collection. Certain examples of the disclosure relate to apparatuses, methods, and computer programs for inference. Some examples relate to apparatuses, methods, and computer programs for collecting training data for training an Artificial Intelligence / Machine Learning, AI / ML, model. Some examples relate to apparatuses, methods, and computer programs for performing inference using a trained AI / ML model.

[0005] BACKGROUND

[0006] Conventional apparatuses and procedures for collecting training data for training an AI / ML model (e.g. for use in AI / ML positioning) are not always optimal. In some circumstances, it may be desirable to provide improved apparatuses, method and computer programs for collecting training data for training an AI / ML model.

[0007] Conventional apparatuses and procedures for performing inference using a trained AI / ML model (e.g. for use in AI / ML positioning) are not always optimal. In some circumstances, it may be desirable to provide improved apparatuses, method and computer programs for performing inference using a trained AI / ML model.

[0008] In some circumstances, it may be desirable to provide consistency between training AI / ML models and inference using trained AI / ML models. In some circumstances, it may be desirable to provide consistency between a set(s) of Radio Access Network, RAN, node entities involved in the collection of training data for training AI / ML model(s), and the set(s) of RAN node entities involved in inference using trained AI / ML model(s) (such as a positioning procedure utilising a set of RAN node entities). In some circumstances, it may be desirable to provide consistency between an area in which training data for training AI / ML model(s) was collected, and an area where inference using trained AI / ML model(s) is to be performed. The listing or discussion of any prior-published document or any background in this specification should not necessarily be taken as an acknowledgement that the document or background is part of the state of the art or is common general knowledge. One or more aspects / examples of the present disclosure may or may not address one or more of the background issues.

[0009] BRIEF SUMMARY

[0010] The invention is defined in the independent claims.

[0011] According to various, but not necessarily all, examples of the disclosure there are provided examples as claimed in the appended claims. Any examples and features described in this specification that do not fall under the scope of the independent claims are to be interpreted as examples useful for understanding various embodiments of the invention.

[0012] According to various, but not necessarily all, embodiments there is provided an apparatus comprising at least one processor; and at least one memory including computer program code, the at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform at least the following: receiving, from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; performing the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

[0013] According to various, but not necessarily all, examples of the disclosure there is provided a method comprising: receiving, at an apparatus from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; performing, at the apparatus, the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting, at the apparatus, at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, by the apparatus to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID. According to various, but not necessarily all, examples of the disclosure there is provided a non-transitory computer readable medium encoded with instructions that, when executed by at least one processor, causes the apparatus to perform the above-mentioned method.

[0014] According to various, but not necessarily all, examples of the disclosure there is provided a computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform the above-mentioned method.

[0015] According to at least some examples of the disclosure there is provided an apparatus comprising: means for receiving, from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; means for performing the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

[0016] The following portion of this ‘Brief Summary’ section describes various features that can be features of any of the examples described in the foregoing portion of the ‘Brief Summary’ section mutatis mutandis. The description of a function should additionally be considered to also disclose any means suitable for performing that function, or any instructions stored in at least one memory that, when executed by at least one processor, cause an apparatus to perform that function.

[0017] In some but not necessarily all examples, the first information comprises a plurality of PRS configurations and a plurality of IDs, wherein each ID is representative of a set of entities of the RAN, wherein each PRS configuration is associated with a respective ID of the plurality of IDs, wherein a plurality of datasets are collected, and wherein the apparatus further comprises: means for associating each of the plurality of datasets with one of the plurality of IDs.

[0018] In some but not necessarily all examples, the second information comprises: the plurality of datasets, and the respective ID associated with each dataset of the plurality of datasets.

[0019] In some but not necessarily all examples, the apparatus further comprises: means for sending, to the node of the core network, information indicative of a capability of the UE to support performing a data collection procedure wherein the collected at least one dataset is mapped to the at least one ID.

[0020] In some but not necessarily all examples, the apparatus further comprises: means for sending, to the node of the core network, information indicative of a position of the apparatus; and wherein the ID received from the node of the core network is based at least in part on the position.

[0021] In some but not necessarily all examples, the apparatus further comprises: means for sending, to the node of the core network, information indicative of the at least one ID of the second information.

[0022] In some but not necessarily all examples, the training entity is the apparatus, and wherein the apparatus further comprises: means for developing the model based at least in part on the at least one dataset of the second information, and means for associating the developed model with the at least one ID of the second information.

[0023] According to various, but not necessarily all, embodiments there is provided an apparatus comprising at least one processor; and at least one memory including computer program code, the at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform at least the following: obtaining, from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; selecting at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; generating at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and sending, to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.

[0024] According to various, but not necessarily all, examples of the disclosure there is provided a method comprising: obtaining, at an apparatus from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; selecting, at the apparatus, at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; generating, at the apparatus, at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and sending, from the apparatus to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.

[0025] According to various, but not necessarily all, examples of the disclosure there is provided a non-transitory computer readable medium encoded with instructions that, when executed by at least one processor, causes the apparatus to perform the above-mentioned method.

[0026] According to various, but not necessarily all, examples of the disclosure there is provided a computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform the above-mentioned method.

[0027] According to at least some examples of the disclosure there is provided an apparatus comprising: means for obtaining, from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; means for selecting at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; means for generating at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and means for sending, to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID. The following portion of this ‘Brief Summary’ section describes various features that can be features of any of the examples described in the foregoing portion of the ‘Brief Summary’ section mutatis mutandis. The description of a function should additionally be considered to also disclose any means suitable for performing that function, or any instructions stored in at least one memory that, when executed by at least one processor, cause an apparatus to perform that function.

[0028] In some but not necessarily all examples, the apparatus further comprises: means for receiving, from the UE, information indicative of a capability of the UE to support performing a data collection procedure wherein at least one dataset collected by the UE is mapped to the at least one ID.

[0029] In some but not necessarily all examples, the apparatus further comprises: means for receiving, from the at least one UE, information indicative of: at least one dataset collected by the at least one UE, and at least one ID associated with the at least one dataset.

[0030] In some but not necessarily all examples, the apparatus further comprises: means for selecting one or more of the entities of the RAN to be mapped to the at least one ID, wherein the selecting is based at least in part on determining which one or more of the entities of the RAN was associated with a PRS configuration that was used by the UE to receive at least one PRS in the UE’s collection of the at least one dataset.

[0031] In some but not necessarily all examples, the apparatus further comprises: means for storing a mapping of the one or more of the entities of the RAN to the at least one ID.

[0032] According to various, but not necessarily all, examples of the disclosure there is provided: an apparatus, a module, circuitry, a chipset comprising processing circuitry, a device and / or a system configured to (or comprising means for) perform(ing) at least a part of one or more methods described herein. The description herein of a function and / or action should additionally be considered to also disclose any means suitable for performing that function and / or action. Functions and / or actions described herein can be performed in any suitable way using any suitable method.

[0033] According to various, but not necessarily all, embodiments there is provided examples as claimed in the appended claims.

[0034] While the above examples of the disclosure and optional features are described separately, it is to be understood that their provision in all possible combinations and permutations is contained within the disclosure. It is to be understood that various examples of the disclosure can comprise any or all the features described in respect of other examples of the disclosure, and vice versa. Also, it is to be appreciated that any one or more or all the features, in any combination, may be implemented by / comprised in / performable by an apparatus, a method, and / or computer program instructions as desired, and as appropriate. The description of a function should additionally be considered to also disclose any means suitable for performing that function.

[0035] BRIEF DESCRIPTION

[0036] Some examples will now be described with reference to the accompanying drawings in which: FIG. 1 shows an example of the subject matter described herein;

[0037] FIG. 2 shows another example of the subject matter described herein;

[0038] FIG. 3 shows another example of the subject matter described herein;

[0039] FIG. 4 shows another example of the subject matter described herein;

[0040] FIG. 5 shows another example of the subject matter described herein;

[0041] FIG. 6 shows another example of the subject matter described herein;

[0042] FIG. 7 shows another example of the subject matter described herein;

[0043] FIG. 8 shows another example of the subject matter described herein;

[0044] FIG. 9 shows another example of the subject matter described herein;

[0045] FIG. 10 shows another example of the subject matter described herein; and FIG. 11 shows another example of the subject matter described herein. The figures are not necessarily to scale. Certain features and views of the figures can be shown schematically or exaggerated in scale in the interest of clarity and conciseness. For example, the dimensions of some elements in the figures can be exaggerated relative to other elements to aid explication. Similar reference numerals are used in the figures to designate similar features. For clarity, all reference numerals are not necessarily displayed in all figures.

[0046] In the description and drawings, a reference number without a subscript (e.g. 123) can be used as a generic reference to a feature or class / set of features. A reference number with a subscript (e.g. 123_1 ) can be used as a specific reference, e.g. to differentiate different instances of a feature or class / set of features. The subscript can comprise two digits including a first digit that labels a group of instances and a second digit that labels different instances in the group. A numerical type subscript index (e.g. 123_1) can be used to indicate a specific instance of a class / a member of a set; and a non-specific instance of the class (member of the set) can be referenced using the reference number with a variable type subscript index (e.g. 123_i).

[0047] ABBREVIATIONS / DEFINITIONS

[0048] 3GPP 3rd Generation Partnership Project

[0049] 5G 5th Generation

[0050] BS Base Station gNB Next generation NodeB, 5G / NR base station

[0051] LMF Location Management Function

[0052] LPP LTE Positioning Protocol

[0053] NR New Radio

[0054] NRPP New Radio Positioning Protocol

[0055] NRPPa New Radio Positioning Protocol A

[0056] RAN Radio Access Network

[0057] TRP Transmission Reception Point

[0058] UE User Equipment DETAILED DESCRIPTION

[0059] FIG. 1 schematically illustrates an example of a network 100 suitable for use with examples of the present disclosure. The network (which may be referred to as NW) comprises a plurality of network entities (which may be referred to as NEs), including:

[0060] • terminal apparatuses 110 (which may be referred to as terminal nodes or User Equipment, UE);

[0061] • access apparatuses 120 (which may be referred to as access nodes, gNodeBs, gNBs, or Base Stations, BSs);

[0062] • one or more core network apparatuses 130 (which may be referred to as core nodes, core functions, core entities, core network entities - one core node / function / entity of which being a Location Management Function, LMF 140).

[0063] The terminal nodes 110 and access nodes 120 communicate with each other. The access nodes 120 communicate with the core nodes 130. The access nodes 120 and LMF 140 may communicate directly with each other. One or more access nodes 120 may, in some but not necessarily all examples, communicate with each other. One or more core network nodes 130 may, in some but not necessarily all examples, communicate with each other.

[0064] The network 100, in the example illustrates in FIG. 1 , comprises a radio telecommunications network in which at least some of the terminal nodes 110 and access nodes 120 communicate with each other using transmission / reception of radio waves. In this regard, the network 100 comprises a Radio Access Network, RAN, such as a cellular network comprising a plurality of cells 122 each served by an access node 120. The access nodes 120 comprise cellular radio transceivers. The terminal nodes 110 comprise cellular radio transceivers.

[0065] In the example illustrated and discussed below, the network 100 is a New Radio, NR, network of the Third Generation Partnership Project, 3GPP, and its fifth generation, 5G, New Radio, NR, technology. It is to be appreciated, however, that in other examples, the network 100 may be a network beyond 5G, for example a next generation (i.e. sixth generation, 6G) Radio Network that is currently under development (i.e. an evolution of the NR network and its 5G technology).

[0066] The interfaces between the terminal nodes 110 and the access nodes 120 are radio interfaces 124 (e.g., llu interfaces). The interfaces between the access nodes 120 and one or more core nodes 130 are backhaul interfaces 128 (e.g., S1 and / or Next Generation, NG, interfaces). The interfaces between the one or more location servers 140 and the one or more core nodes 130 are backhaul interface 132 (e.g., NLs interface).

[0067] Depending on the exact deployment scenario, the access nodes 120 may be RAN nodes such as NG-RAN nodes. NG-RAN nodes may be gNodeBs, gNBs, that provide NG user plane and control plane protocol terminations towards the UE. The gNBs are connected by means of NG interfaces to a 5G Core, 5GC, not least for example to an Access and Mobility Management Function, AMF, by means of an NG Control Plane, NG-C, interface and to a User Plane Function, UPF, by means of an NG User Plane, NG-U, interface. The access nodes 120 may be interconnected with each other by means of Xn interfaces 126.

[0068] The cellular network 100 may be configured to operate in licensed frequency bands, or unlicensed frequency bands (not least such as: unlicensed bands that rely upon a transmitting device to sense the radio resources / medium before commencing transmission, such as via a Listen Before Talk, LBT, procedure; and a 60GHz unlicensed band where beamforming may be required to achieve required coverage).

[0069] The access nodes 120 may be deployed in an NG standalone operation / scenario. The access nodes 120 may be deployed in a NG non-standalone operation / scenario. The access nodes 120 may be deployed in a Carrier Aggregation, CA, operation / scenario. The access nodes 120 may be deployed in a Dual Connectivity, DC, operation / scenario, i.e., Multi Radio Access Technology - Dual Connectivity, MR-DC, or NR-DC. The access nodes 120 may be deployed in a Multi Connectivity, MC, operation / scenario.

[0070] In such non-standalone / dual connectivity deployments, the access nodes 120 may be interconnected to each other by means of X2 or Xn interfaces, and connected to an Evolved Packet Core, EPC, by means of an S1 interface or to the 5GC by means of a NG interface. A terminal node 110, in addition to being capable of communicating (i.e. with other terminal nodes) via access nodes 120 of the network 100, may also be capable of and configured to communicate directly with one or more other terminal nodes. In this regard, the terminal node may be capable of and configured to perform device-to-device, D2D, communication - which may be referred to as Sidelink, SL, communication. Such D2D / SL communication may use a PC5 interface. PC5 refers to a reference point where the terminal node communicates directly with another terminal node over a direct channel (i.e. communication via an access node is not required). D2D communications may be short-range, networkless, direct communications. SL in New Radio (NR) is defined in 3GPP’s release 16 of 5G NR.

[0071] In the example of FIG. 1 the core node 130 is shown as a single entity. In some examples the core node 130 could be distributed across a plurality of entities. For example, the core node 130 could be cloud based or distributed in any other suitable manner. The core node / core entities may provide one or more functions, not least such as: User Plane Function UPF, Session Management Function SMF, Policy Control Function PCF, Application Function AF, and Location Management Function 140.

[0072] The access nodes 120 are network elements in the network responsible for radio transmission and reception in one or more cells 122 to or from the terminal nodes 110. The access nodes 120 are the network termination of a radio link. Each access node may be a Transmission Reception Point, TRP, or may host one or more TRPs.

[0073] An access node 120 may be implemented as a single network equipment, or have a split architecture that is disaggregated / distributed over two or more access nodes, such as a Central Unit, CU, a Distributed Unit, DU, a Remote Radio Head-end, RRH, using different functional-split architectures and different interfaces.

[0074] The terminal nodes 110 are network elements in the network that terminate the user side of the radio link. They are devices allowing access to network services. Terminal node 110 functionalities may be performed also by Mobile Termination, MT, part of an Integrated Access and Backhaul, IAB, node. The terminal nodes 110 may be referred to as User Equipment, UE, mobile equipment, mobile terminals, or mobile stations.

[0075] The term ‘User Equipment’ may be used to designate mobile equipment comprising means, such as a smart card, for authentication / encryption etc. such as a Subscriber Identity Module, SIM. A SIM / SIM card can be a memory chip, a module, or a Universal Subscriber Identity Module (USIM). In some examples, the term ‘User Equipment’ can be used to designate a location / position tag, a hyper / smart, a hyper / smart sensor, or a mobile equipment comprising circuitry embedded as part of the user equipment for authentication / encryption such as a software SIM.

[0076] The location server 140 is a device that manages the support of different location services for UEs, including positioning of UEs and delivery of assistance data to UEs. The location server can be connected to the core node and the Internet. The location server can be implemented as one or more servers. The location server is configured to support one or more location services for UEs 110 that can connect to the location server 140 via the core network 130 and / or via the Internet. The location server may be referred to as Location Management Function, LMF, which is a defined network function within the 5GC.

[0077] In the following description, a terminal node may be referred to simply as UE 110.

[0078] In the following description, an access apparatus / access node to a RAN (e.g. a cellular network not least such as a 5G or 6G next generation RAN) may be referred to interchangeably as BS 120 or gNB 120.

[0079] In the following description, a core apparatus / node / functionality for managing and processing location information may be referred to simply as LMF 140.

[0080] There now follows a brief discussion of positioning in a radio telecommunications network, e.g. a RAN.

[0081] The position of a target UE within a RAN can be determined by a positioning server / locations server, such as an LMF, by various conventional network-based positioning techniques (such as using: LTE Positioning Protocol, LPP, [defined in TS 37.355], New Radio Positioning Protocol, NRPP, or NRPPa). Conventional techniques may involve the exchange, over a llu interface in the NR spectra, of RSs (e.g., transmitting Orthogonal Frequency-Division Multiplexing, OFDM, Positioning Reference Signals, PRSs, from a RAN node to the target UE for DL positioning; and transmitting OFDM- Sounding Reference Signals, SRSs, from the target UE to a RAN node for UL positioning). Such Reference Signals, RSs, are received, detected and measured by the gNBs (for UL positioning) or the UE (for DL positioning). The positioning server, receives the measurements from the gNBs or the UE. Such measurement information is received by the positioning server via an Access and Mobility Management Function, AMF, over a backhaul interface (e.g., NLs interface). The positioning server then uses such received measurement information to compute the position of the UE. A NR Positioning Protocol A, NRPPa, carries positioning information between the NG-RAN nodes and the positioning server over a NG control plane interface (e.g., NG-C interface).

[0082] Such Radio Access Technology, RAT, based positioning techniques may utilise one of the following methods: Uplink Angle of Arrival (UL-AoA), Downlink Angle of Departure (DL-AoD), Variance of Time of Arrival (TOA)-based ranging, Uplink Time Difference of Arrival (UL- TDOA), Downlink Time Difference of Arrival (DL-TDOA), and Multi-cell Round Trip Time (Multi-RTT).

[0083] The 5G NR positioning / localization process is standardized in the 5G NR LPP specification. A conventional positioning session relies on a receiver measuring positioning RSs (PRS in DL, and SRS in UL) which are scheduled by the network on specific time-frequency-space- code resources. The allocation of resources for such transmissions is coordinated across multiple UEs and gNBs via LPP and NRPPa interfaces, so that the RSs are ensured to be unique and interference free. This is done to enable the receiver (UE in DL and gNB in UL) to determine / compute / extract positioning measurements which are reported back to the network (in case of UE-assisted positioning) or used locally (for UE-based positioning) to compute the UE location. A target UE can be positioned by such above-mentioned positioning techniques, which may be referred to as NR Uu-based positioning. A target UE can be also be positioned by Artificial Intelligence / Machine Learning, AI / ML, based (or assisted) positioning,.

[0084] There now follows a brief discussion of AI / ML-based, or assisted, positioning.

[0085] AI / ML-based, or assisted, positioning may comprise:

[0086] Direct AI / ML positioning, wherein an AI / ML model’s output is a UE’s location. This could involve, for example, fingerprinting based on channel observations as an input of the AI / ML model. The model could be a UE-side model for UE-based positioning. The model could be an LMF-side model for LMF-based positioning.

[0087] AI / ML assisted positioning, wherein an AI / ML model’s output is a new measurement and / or enhancement of an existing measurement, for example, Line of Sight, LoS, or Non Line of Sight, NLOS, identification, timing and / or angle of measurement, as well as likelihood of measurement. The model could be a UE-side model or a gNB-side model for AI / ML assisted positioning.

[0088] Certain use cases for AI / ML-based, or assisted, positioning include:

[0089] • Case 1: UE-based positioning with a UE-side model for direct AI / ML positioning.

[0090] • Case 2a: UE-assisted / LMF-based positioning with a UE-side model for AI / ML assisted positioning.

[0091] • Case 2b: UE-assisted / LMF-based positioning with an LMF-side model for direct AI / ML positioning

[0092] • Case 3a: NG-RAN node assisted positioning with gNB-side model for AI / ML assisted positioning

[0093] • Case 3b: NG-RAN node assisted positioning with an LMF-side model for direct AI / ML positioning

[0094] An AI / ML model may be trained based on collected training data. The training data may be collected based on measurements of PRSs transmitted from one or more gNBs. In some circumstances, it may be desirous to associate (i.e. link / map / assign) a trained AI / ML model to the gNBs that were used in the collection of the training data for training the AI / ML model. Such an association may enable the model (trained on training data the collection which involved a particular set of gNBs) to be selected when an inference procedure is to be performed which involves the particular set of gNBs.

[0095] In some circumstances, a higher level of granularity may be desired. In this regard, rather than associating a trained model to a set of gNBs (i.e. associating a trained model to a list of Cell IDs), it may be desirous to associate a model to TRPs that were involved in the collection of training data for training the model. In this regard, in some circumstances, it may be desirous to associate (i.e. link / map / assign) a trained AI / ML model to the TRPs that were used in the collection of the training data for training the AI / ML model. Such an association may enable the model (trained on training data the collection which involved a particular set of TRPs) to be selected when an inference procedure is to be performed which involves the particular set of TRPs.

[0096] In some circumstances, it may be desirous to provide a procedure and signaling for associating training data with RAN entities (e.g. TRPs) involved in the collection of training data, i.e. such that a model trained on the collected training data may likewise be associated with the RAN entities that were involved in the collection of training data.

[0097] In some circumstances, it may be desirous to provide a procedure and signaling for selecting a trained model for an inference procedure involving a set of RAN entities, i.e. such that the trained model that is selected is a model that was trained on training data whose collection involved the set of RAN entities (which are to be used on the inference procedure).

[0098] FIG. 2 schematically illustrates an example of a procedure 200 and a signalling framework, between a first apparatus (in this example UE 110) and a second apparatus (in this example an LMF 140), for supporting the procedure. As will be discussed below, the procedure 200 is for signaling a new type of identifier for use in a data collection process, wherein the identifier is representative of a set of a plurality of RAN entities (e.g. TRPs) used in the data collection process. Since each RAN entity may have a fixed / static position, a set RAN entities can be equated to an area - namely an area comprising the set of RAN entities. Hence the identifier representative of a set of RAN entities may also be considered to be an identifier that is representative of an area [i.e. an area where the data collection process took place which encompasses the RAN entities involved in the data collection]. Hereinafter, such an identifier may be referred to interchangeably simply as ID, or “Area ID”.

[0099] In block 201, the UE 110 receives, from the LMF 140, first information 202 for supporting the UE to perform a data collection procedure 207.

[0100] As will be discussed in further detail below, the data collection procedure may be a procedure for collecting training data (i.e. datasets / training datasets) for training an AI / ML model. The data collection procedure may involve not only the collection of one or more datasets, but also associating (implicitly or explicitly) each dataset with an ID 205 wherein the ID represents a set of the RAN entities 206 (e.g. such as a set of RAN entities involved in the data collection procedure itself, for instance the set of RAN entities that transmitted signals, such as PRSs, to the UE as part of the data collections procedure, wherein the UE’s measurements of the received signals form the datasets to be collected.

[0101] The first information 202 may provide: assistance information for assisting the UE in carrying out the data collection process, for collecting training data for training a model 212; and assistance information for associating each dataset, which is collected in the data collection process, with an ID representative of a set of the RAN entities (such as ID also being referred to herein as “Area ID”).

[0102] In this regard, the first information comprises information indicative of one or more Position Reference Signal, PRS, configurations 203, wherein each PRS configuration comprises information indicative of a plurality of entities of a RAN. The entities of the RAN may be one or more: TRPs, gNBs and / or cells. The information indicative of such RAN entities may be a list of individual: TRP IDs, Cell IDs, or NR Cell Global Identities, NCGIs. In this regard, each PRS configuration may comprise a list of individual identifiers of each RAN entity involved in the data collection procedure (the data collection procedure involving the RAN entities transmitting PRSs to the UE for the UE to measure, wherein the collected datasets are based at least in part on the measurements of the PRSs received from each RAN entity). The first information also comprises information indicative of one or more identifiers, IDs 205, wherein each ID is representative of a set of a plurality of RAN entities 206 (e.g. each single ID may represents a set of plural TRPs). Hereinafter such an ID may be referred to an Area ID 205. Each PRS configuration is associated with one or more Area IDs. The association of Area IDs to a PRS configuration may be implicit or explicit, e.g. there may be an explicit indication of an association / link / mapping / assignment of one or more Area IDs to a particular PRS configuration.

[0103] The Area ID can be representative of at least one of the following: a set of RAN entities that are to be used, during the data collection procedure, to transmit a set of PRSs to the UE; a set of TRPs; and an area comprising a set of TRPs.

[0104] The first information may also comprise configuration information for configuring the UE to perform the data collection procedure.

[0105] The LMF may select the RAN entities 204 of each PRS configuration 203 based at least in part on the RAN entities of the set of RAN entities 206 represented by the ID 205 that is associated with the respective PRS configuration. For instance, the LMF may select the RAN entities 204 of each PRS configuration 203 such that they correspond to the RAN entities of the set of RAN entities 206 represented by the ID 205 that is associated with the respective PRS configuration.

[0106] The transfer of information between the LMF and the UE can be via at least one of the following: an interface between the LMF and the UE, such as an N1 interface;

[0107] Non-Access Stratum, NAS, signaling; a non-Radio Resource Control protocol / a higher-level protocol between the LMF and the UE such as an LTE Positioning Protocol, LPP.

[0108] The UE then subsequently (e.g. upon being triggered to do so) performs the data collection procedure 207 based at least in part on the first information 202. As will be discussed further below, the data collection procedure comprises: collecting one or more datasets, and sending the collected datasets, and also an ID associated with each dataset, to a training entity for training a model.

[0109] In block 208, the UE collects one or more datasets 209, where each dataset is based at least in part on one or more PRSs received from a set of RAN entities 204 indicated in one of the PRS configurations 203 received in block 201. In this regard, the UE uses a received PRS configuration to receive PRS signals transmitted from a set of RAN entities (i.e. the entities indicated on the PRS configuration), and the UE performs measurements on the received PRS signals - such measurements forming a dataset. Each dataset is thereby based on measurements of PRS signals received based on a PRS configuration.

[0110] Each dataset may comprise at last one of the following: at least one channel measurement; at least one Reference Signal Received Power, RSRP, measurement; at least one Channel Impulse Response, CIR, measurement; at least one Power Delay Profile, PDP, measurement; or at least one Delay Profile, DP, measurement.

[0111] In block 210, the UE sends second information 211 to a training entity 214 for training a model 212, wherein the second information comprises information indicative of: one or more datasets 209, and one or more of the Area IDs 205 received in block 201.

[0112] In this regard, the second information, which is sent to a training entity 214 for training a model 212, comprises information indicative of one or more datasets 209, and one or more Area IDs associated with each dataset.

[0113] The model may be at least one of the following: an Artificial Intelligence, Al, model; a Machine Learning, ML, model; a model for the UE; and a User Equipment, UE, side model for downlink-based positioning.

[0114] The training entity may be any suitable entity that comprise means for developing (e.g. training and / or updating) the model. The training entity may be the UE itself (e.g. for a UE- sided AI / ML model hosted at the UE itself) or it may be a separate apparatus remote of the UE.

[0115] In some examples, the training entity is the UE itself (e.g. a module thereof), and the UE develops (i.e. trains or updates) the model based at least in part on the dataset(s) and Area ID(s) associated with each dataset. The UE may also associate the developed model with the Area ID(s). In this regard, the UE may explicitly link, tag, or map one or more Area IDs to their respective trained model.

[0116] The association of Area IDs to datasets in block 210 may be implicit or explicit. The UE may provide, in the second information, an explicit indication of an association / link / mapping / assignment of one or more Area IDs to a particular dataset.

[0117] The UE may associate each of collected datasets with one or more Area IDs. In this regard, the UE may associate a particular Area ID to a particular dataset by: determining which particular PRS configuration, of the PRS configurations of the first information received in block 201 , was used to receive the PRSs that were measured to form a particular dataset; determining, based on the first information and its indications of which of Area IDs are associated with which PRS configurations, the Area IDs associated with the determined particular PRS configuration; and associating the determined Area IDs with the particular dataset.

[0118] With the above described procedure 200, a training entity, for training an AI / ML positioning model, may receive not only dataset(s) for training the model, but also Area ID(s) associated with each dataset. Advantageously, this enables the AI / ML positioning model, duly trained with the dataset(s), to be likewise be associated / mapped / linked / assigned with the respective Area ID(s). The Area I D(s), each of which is representative of a model training context - in particular set of RAN entities used in the collection of training data for training a model (and, since each RAN entity may have a fixed location, each Area ID is also effectively representative of a particular area that comprises the particular set of RAN entities) can be used as an indication of whether the trained model is valid / suitable for a particular context, e.g. whether the model is valid / suitable for: performing inference / a positioning procedure involving a certain set of RAN entities, and / or performing inference / a positioning procedure in a certain area.

[0119] As will be discussed below, the provision of trained AI / ML positioning models that are associated with Area ID(s) may enable Area ID-based selection of AI / ML positioning models for performing an inference procedure such as a positioning procedure. For instance, a UE may have a plurality of trained models, each associated with one or more Area IDs. If a DL positioning procedure is to be performed for the UE in a particular area (i.e. such that the positioning procedure would involve a particular set of RAN entities in the particular area), an LMF could determine an Area ID that corresponds to the particular set of RAN entities. The LMF could then provide assistance information to the UE for supporting the UE to perform the DL positioning procedure, wherein the assistance information comprises an indication of the Area ID that the UE is to use in selecting which of its plural AI / ML positioning models to use (each of the UE’s AI / ML positioning models being associated with one or more Area IDs). Advantageously, by linking a dataset collected for training a specific model to an area location where inference using the trained model is to occur, examples of the disclosure may thereby enable consistency between training and inference.

[0120] FIG. 3 schematically illustrates an example of a procedure 300 and a signalling framework, between a first apparatus (in this example LMF 140) and a second apparatus (in this example UE 110), for supporting the procedure. As will be discussed below, the procedure 300 relates to the determination / generation of an identifier (hereinafter referred to as Area ID) representative of a set of a plurality of RAN entities, e.g. TRPs, (and / or representative of an area) to be used in a data collection process, as well as signaling for supporting the same for use in the data collection process.

[0121] In block 301 , an LMF 140 obtains a position 302 of a UE 110. In some example, this may be done by determining the UE’s position via the performance of a positioning procedure. In this regard, for a UE-based positioning procedure, the LMF may receive a position of the UE that the UE has itself determined.

[0122] In block 303, the LMF select a set of RAN entities based at least in part on the position of the UE. For instance, the LMF may select a set of RAN entities (e.g. TRPs) in the vicinity of the UE. In this regard, the UE may define one or more areas, each area comprising a set of TRPs, and assign each area / set of TRPs with an Area ID. Hence the LMF generates and stores a mapping of an Area ID to a particular set of TRPs / a particular area (comprising the particular set of TRPs). As will be discussed further below, an Area ID can effectively be used to serve as an indication of a validity area for model. For instance, a model trained on one or more datasets associated with one or more Area IDs may be valid / suitable for use in inference procedures: that involve the one or more sets of TRPs represented by the one or more Area IDs, and / or within the area(s) corresponding to the Area ID .

[0123] FIG. 4 schematically shows examples of differing areas 401_1 to 401_4, each area encompassing a set of TRPs 206_1 to 206_4, and Area IDs 205_1 to 205_4 assigned to each area / set of TRPs.

[0124] Since positioning procedures are LMF centric, the selection of specific TRPs composing a specific Area ID may be done by the LMF. In this regard, during data collection, the LMF is the entity responsible to select certain TRPs. The LMF can define a specific Area for a specific set of TRPs and assign the same with a specific Area ID. There may be cases where one Area ID is a subset of another Area ID. For example, in FIG. 4 Area ID 3 is a subset of Area ID 1.

[0125] The number of TRPs of one specific Area ID may impact on a model’s generalization capability. I.e. it may impact on a capability of a model, trained on training data collected in a specific area, to be used in one or more other areas (such other areas where the model would be suitable for use in / valid in may be referred to as validity areas for the model). The number of TRPs of an Area ID may also affect Model training / inference performance - since the larger the number of TRPs used in the collection of training data and used in inference, the better the performance / accuracy of the model in a fingerprinting approach for positioning.

[0126] In FIG. 4, there are 3 different validity areas 401_2 to 401_4 with a low number of TRPs, and one validity area 401 _1 with many TRPs. There is be a trade-off between the number of TRPs considered to define a specific validity area and the size of the validity area, both may impact on the generalization capability.

[0127] In block 304, the LMF generates an ID, Area ID, representative of the set of RAN entities (and / or which is also representative of an area encompassing the set of RAN entities). The Area ID is associated to the set of RAN entities / area encompassing the set of RAN entities.

[0128] The LMF may store the association / mapping of each Area ID to its respective set of RAN entities / area encompassing the set of RAN entities.

[0129] It is significant to note that the Area ID itself is a single identifier that represents a set of a plurality of RAN entities. Hence the set can be identified via a single Area ID as compared to defining the set of RAN entities via a list of a plurality of RAN entity IDs (e.g. TRP IDs, Cell IDs). The use of Area ID is a way to avoid listing all RAN entity IDs of a set of RAN entities, instead the set of RAN entities is referred to via a unique identifier / name / label - namely Area ID.

[0130] With regards to the LMF’s identification and determination / generation of: areas and sets of TRPs therein as well as assigning each area / set of TRPs with an Area ID; in some examples, this could be done without requiring block 301. In this regard, block 302’s selection of a set of RAN node entities and / or an area encompassing the set need to be based on a UE’s position. Instead, the LMF may define / identify for itself each set of RAN node entities / each area. The LMF may then determine one or more UEs that are within a particular area (that has been assigned an Area ID) and select such UEs to be used for a data collection process for collecting data from a particular set of RAN node entities / a particular area represented by a particular Area ID. In block 201 (similar to block 201 of FIG. 2) the LMF sends, to the UE, first information 202 for supporting the UE to perform a data collection procedure, wherein the first information comprises information indicative of: at least one PRS configuration 203, and the Area ID 205.

[0131] FIG. 5 illustrates an example of a signaling diagram showing signalling (between an LMF 140 and plural UEs 110_1 to 110_4) and a procedure 500 for using Area IDs for data collection (namely for collecting training data for models for “Case 1” type AI / ML positioning, i.e. direct AI / ML positioning - UE-based positioning with UE-side model; and also for collecting training data for models for “Case 3b” type AI / ML positioning, i.e. direct AI / ML positioning - NG-RAN node assisted positioning with LMF-side model.

[0132] Whilst 4 UEs are shown in the example of FIG. 5, it is to be appreciated that, in other examples, one or more UEs could be used.

[0133] Certain aspects, features and functionality of the procedure 500 are similar to certain aspects, features and functionality of the procedures 200 and 300 of FIGs.2 and 3 as well as various of the other features and functionality described above. Hence, certain aspects, features and functionality of the procedures 200 and 300, as well as various of the other features and functionality described above, may be relevant mutatis mutandis to the procedure 500 and shall not be repeated / reiterated in detail.

[0134] In step 1 , each UE provides a capability report to the LMF to indicate if the UE supports Area IDs. In this regard, each UE indicates its capability of performing a data collection procedure including associating / tagging / mapping each collected dataset with an Area ID, wherein the Area ID represents a set of RAN node entities used in the collection of the dataset (and / or wherein the Area ID represents an area within which the collection of the dataset occurred - such an area comprising the set of RAN node entities used in the data collection procedure). The LMF may determine whether to seek to request that a UE performs a data collection procedure using Area IDs based on whether the UE supports such an operation. In step 2, the LMF provides each UE with assistance data for data collection. Such assistance data may be generic assistance data for supporting the UE in performing a data collection procedure (e.g. conventional assistance data for data collection - as compared to the specific assistance data provided in step 5 comprising an Area ID). The assistance information may comprise PRS configuration information for use in a collecting data (e.g. wherein the collected data comprises one or more datasets comprising measurements of one or more PRS signals transmitted by one or more TRPs).

[0135] In step 3 (which broadly equates to block 301 of FIG. 3), each UE reports its position to the LMF. The provision of each UE’s position to the LMF is to enable the LMF to determine one or more areas that encompass one or more of the UEs. The LMF assigns each area an Area ID (i.e. an identifier for an area - such an identifier also being representative of a set of TRPs contained within the area). The one or more areas, within which training data is to be collected (utilising the respective one or more sets of TRPs within the one or more areas) for training a model, may also define one or more validity areas for such a trained model, i.e. the model is valid / optimised / suitable for use in the one or more areas. Such areas may be referred to as validity areas.

[0136] In step 4 (which broadly equates to blocks 303 and 304 of FIG. 3), the LMF defines one or more validity areas based at least in part on the distribution of the UEs' positions received in step 3. The LMF may define desired granularity of the validity areas (i.e. area size, which also affects the number of TRPs within the area). The LMF is aware of TRPs’ positions and hence can determine which TRPs are within which validity area. Hence the LMF can determine which particular TRPs define a particular set of TRPs within a particular validity area associated with a particular Area ID. The LMF may store an association / mapping of Area IDs and sets of TRPs. In this regard, the LMF may store a list of the one or more Area IDs associated with a set of TRPs. For example, with respect to FIG. 4, TRP set 206_4 is associated with Area ID 4401_4and also Area ID 1 401_1.

[0137] In step 5 (which broadly equates to block 201 of FIGs. 2 and 3), the LMF sends specific assistance data to each UE. In this regard, the LMF sends each UE Area ID information indicative of one or more Area IDs. In step 6 (which broadly equates to block 208 of FIG. 2), the UEs use their respectively received Area ID information in their respective data collection procedures. In this regard, each UE collects one or more datasets (i.e. making use of the assistance information received in step 2) also each collected dataset is tagged with / associated with one of the Area IDs received in step 5. The association of Area IDs to collected data may be effected by including the Area ID as an additional feature in the collected dataset, or the association may part of metadata representing a specific dataset.

[0138] In step 7, the UEs may send, to the LMF, an indication of what Area IDs it used in the data collection procedure.

[0139] In step 8, the LMF uses such feedback of what Area IDs were used in the data collection procedure to check whether the Area IDs received in step 7 match those sent in step 5, or whether the Area IDs received in step 7 are a subset of those sent in step 5. If the Area IDs in step 7 are a subset of those indicated in Step 5, the LMF may update its mapping of TRP sets to Area IDs.

[0140] If a UE were to receive more than one Area ID, it may be the case that, for some reason, the UE uses only a subset of received Area IDs. Step 7 is done in order to report the Area IDs used by the UE, and Step 8 is done to check if the Area IDs are a subset or not of the Area IDs indicated in Step 5. If the area IDs are a subset of those indicated in Step 5, the LMF may update its stored mapping of TRP sets to Area IDs.

[0141] A typical / ideal scenario is that step 8 would confirm that all Area IDs indicated in Step 5 were likewise indicated in step 7. However, if not all Area IDs were used for data collection, the intention of Step 8 is to store / update which Area IDs were actually used with a set of TRPs (e.g. a set of TRPs / the list of TRP IDs defined in the PRS configuration that was used for the data collection procedure). In such a manner, the LMF stores the association / mapping of Area IDs to TRPs, for future utilization e.g. inference. Examples of using Area IDs for inference will now be described.

[0142] FIG. 6 schematically illustrates an example of a procedure 600 and a signalling framework, between a first apparatus (in this example UE 110) and a second apparatus (in this example an LMF 140), for supporting the procedure. As will be discussed below, the procedure 600 is for signaling a new type of identifier for use in inference in AI / ML positioning, wherein the identifier is representative of a set of a plurality of RAN entities (e.g. TRPs) to be used in the inference process. Since each RAN entity may have a fixed / static position, a set RAN entities can be equated to an area - namely an area comprising the set of RAN entities. Hence the identifier representative of a set of RAN entities may also be considered to be an identifier that is representative of an area [i.e. an area where the data collection process took place which encompasses the RAN entities involved in the data collection]. Hereinafter, such an identifier may be referred to interchangeably simply as ID, or “Area ID”.

[0143] The procedure of FIG. 6 is suitable for use in combination with models which have been trained using data collected in accordance with the data collection procedure of FIGs. 2, 3 and 5, such that a UE has available thereto a plurality of trained models, each of which is associated with one or more Area IDs representative of a set of TRPs used in the collection of training data for training the respective model, and / or representative of an area where the data collection occurred. Moreover, the LMF may have stored therein or accessible thereto, a mapping of Area IDs to sets of RAN entities.

[0144] As indicated above, the UE 110 has a plurality of trained AI / ML models 212_u available thereto (e.g. stored at the UE or accessible to the UE). Each of the UE’s models is associated with respective one or more Identifiers, IDs (i.e. Area IDs) 205_u, wherein each ID is representative of a set of RAN entities and / or a validity area as described above. In this regard, each Area ID of each model may be representative of at least one of the following: a set of entities of the RAN that were used in the collection of training data for training the respective model; a set of Transmission Reception Points, TRPs; and an area comprising a set of TRPs.

[0145] The models may be at least one of the following: an Artificial Intelligence, Al, model; a Machine Learning, ML, model; a model for the apparatus; a User Equipment, UE, side model for downlink-based positioning; and a trained model which is associated with / mapped to / tagged with an Area ID, wherein the model was trained at least on part on at least one dataset associated with the Area ID.

[0146] In block 601, the UE sends, to the LMF, information 602 indicative of a plurality of Area IDs 205_u. In this regard, the UE may send information indicative of each of one or more Area IDs associated with each of the UE’s models 212_u.

[0147] The communication between the UE and the LMF may be via at least one of the following: an interface between the LMF and the UE; an N1 interface;

[0148] Non-Access Stratum, NAS, signaling; a non-Radio Resource Control protocol; a higher-level protocol between the LMF and the UE; and an LTE Positioning Protocol, LPP.

[0149] In block 603, the LMF selects an Area ID 205_x from the received plurality of Area IDs 205_u of the UE.

[0150] The selection of the Area ID may comprise the LMF performing the following: selecting a set of entities of the RAN to be used in a positioning procedure; and comparing, for each of the received plurality of Area IDs, the set of entities of the RAN represented by each received Area ID to the selected set of entities of the RAN to be used in a positioning procedure.

[0151] The LMF’s selection of the Area ID may be based at least in part on the comparison. In this regard, the selection of the Area ID may be based at least in part on a degree of matching between: the selected set of entities of the RAN to be used in a positioning procedure, and the set of entities of the RAN represented by an Area ID of the plurality of received Area IDs. In some examples, the UE may send the LMF information indicative of one or more measurements of one or more signals received by the UE from one or more entities of the RAN. Such measurements may comprise at last one of the following:

[0152] Received Signal Strength Indicator, RSSI; at least one channel measurement; at least one Reference Signal Received Power, RSRP, measurement; at least one Channel Impulse Response, CIR, measurement; at least one Power Delay Profile, PDP, measurement; or at least one Delay Profile, DP, measurement.

[0153] The LMF may use such measurements to infer a potential location or a coarse location of where the UE is. The LMF may then use such a potential / coarse location in the LMF’s selection of an Area ID. For instance, the LMF may select an Area ID which is associated with an area in which the UE is deemed to be located.

[0154] In block 604, the UE receives, from the LMF, information 605 for assisting the UE in selecting one of the UE’s models for inference, wherein the information 605 is indicative of the selected Area ID 205_x.

[0155] In block 606, the UE selects, based at least in part on the information 605, and the LMF’s selected one or more Area IDs indicated therein, one of its plurality of models for use for inference.

[0156] The selection of one of the plurality of models may be based at least in part on a degree of matching between: the Area ID of the information 605, and the Area IDs associated with UE’s the plurality of models.

[0157] In this regard, the UE selects one of its plurality of models that has an Area ID that matches (or that most closely matches) the received Area ID 205_x selected by the LMF.

[0158] The UE may receive, from the LMF, configuration information for configuring the apparatus to perform an inference procedure. The configuration information may comprise at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information (e.g. a list of Cell IDs, NCGIs, or TRP IDs) indicative of a plurality of entities (e.g. cells or TRPs) of the RAN to be used in a downlink UE-based positioning procedure.

[0159] The UE may use the selected model to perform the inference procedure. For instance, the inference procedure may be a positioning procedure and the UE may use the selected model to perform AI / ML UE-based positioning.

[0160] With the above described procedure 600, the LMF is able to cause an inference procedure to be performed in a particular area (which may be associated with a particular Area ID) and enable the UE to select one of its trained models (each model being associated with a respective Area ID as discussed above) that is valid / suitable for the particular area where inference is to take place.

[0161] The use of Area ID(s) in the collection of training data and the training of models, in combination of the use of Area ID(s) for inference procedures may enable consistency between training and inference by enabling Area-1 D-based selection of models for inference. The Area IDs can be used for selecting a trained model which is valid / suitable for a particular context, e.g. selecting a model that is valid / suitable for: performing inference / a positioning procedure involving a certain set of RAN entities (e.g. the same set of RAN entities as used in the collection of training data for the selected model - thereby advantageously providing consistency between training and inference), and / or performing inference / a positioning procedure in a certain area (e.g. the same area where the training data for the selected model was collected - again, thereby advantageously providing consistency between training and inference).

[0162] FIG. 7 illustrates an example of a signaling diagram showing signalling (between a UE 110 and an LMF 140) and a procedure 700 for using Area IDs for inference in AI / ML positioning, namely “Case 1” type AI / ML positioning, i.e. direct AI / ML positioning - UE-based positioning with UE-side model. The procedure of FIG. 7 is suitable for use in combination with models which have been trained using data collected in accordance with the data collection procedure of FIGs. 2, 3 and 5, such that a UE has available thereto a plurality of trained models, each of which is associated with one or more Area IDs representative of a set of TRPs used in the collection of training data for training the respective model, and / or representative of an area where the data collection occurred.

[0163] Certain aspects, features and functionality of the procedure 700 are similar to certain aspects, features and functionality of the procedure 600 of FIG. 6 as well as various of the other features and functionality described above. Hence, certain aspects, features and functionality of the procedure 600, as well as various of the other features and functionality described above, may be relevant mutatis mutandis to the procedure 700 and shall not be repeated / reiterated in detail.

[0164] In step 1 , the UE 110 provides a capability report to the LMF 140 to indicate if the UE supports Area IDs. In this regard, the UE indicates its capability of performing inference in AI / ML positioning including Area-ID-based selection of an AI / ML model for performing the AI / ML positioning. The LMF may determine whether to seek to request that a UE performs an inference in AI / ML positioning using Area-IDs based on whether the UE supports such an operation.

[0165] In step 2, the LMF provides the UE with assistance data for inference in AI / ML positioning. Such assistance data may be generic assistance data for supporting the UE in performing inference in AI / ML positioning (e.g. conventional assistance data for inference in AI / ML positioning - as compared to the specific assistance data provided in step 5 comprising an Area ID). The assistance information may comprise PRS configuration information for enabling the UE to receive and measure PRS signals transmitted from TRPs (wherein the PRS measurements may be input to an AI / ML model in order to output a position).

[0166] In step 3 (which broadly equates to block 601 of FIG. 6), the UE reports, to the LMF, a list of each Area ID that is associated with each of the UE’s trained models (wherein each of the UE’s trained models is associated with one or more Area IDs representative of a set of TRPs used in the collection of training data for training the respective model, and / or representative of an area where the data collection occurred).

[0167] In step 4, the LMF assesses the received Area IDs and determines / selects one or more of the received Area IDs that would be suitable for use for the inference in AI / ML positioning procedure that is to be performed.

[0168] The LMF’s assessment of the received Area IDs and selection of one or more of the same may be based on receipt of an RSSI from the UE which may be used by the LMF to infer a potential area where the UE is located and determine one or more Area IDs associated with the inferred area. If the Area IDs received from the UE included an Area ID corresponding to the inferred area, the LMF may select such an Area ID as being an available Area ID, i.e. an Area ID that would be suitable for the UE to use in the AI / ML positioning procedure.

[0169] In step 5, the LMF sends, to the UE, Area ID information indicative of the one of more selected Area IDs, i.e. the one or more available Area IDs.

[0170] In step 6, the UE selects one of its models based on the received Area ID information.

[0171] In step 7, the UE signals to the LMF that it is ready to perform the inference in an AI / ML positioning procedure using the model selected by the UE in step 6.

[0172] In step 8, the LMF signals, to the UE, a functionality activation signal, e.g. to indicate to the UE to perform the inference in AI / ML positioning procedure using the model selected by the UE in step 6. Following receipt of the signal, the UE may proceed to perform the inference in AI / ML positioning procedure using the selected model.

[0173] FIG. 8 schematically illustrates an example of a procedure 800 and a signalling framework (between: a UE 110, LMF 140 and gNB 120) for supporting the procedure. As will be discussed below, the procedure 800 is for signaling a new type of identifier for use in inference in AI / ML positioning, namely “Case 3a” type AI / ML positioning, i.e. AI / ML assisted positioning - NG-RAN node assisted positioning with gNB-side model. The identifier is representative of a set of a plurality of RAN entities (e.g. TRPs) to be used in the inference process. Since each RAN entity may have a fixed / static position, a set RAN entities can be equated to an area - namely an area comprising the set of RAN entities. Hence the identifier representative of a set of RAN entities may also be considered to be an identifier that is representative of an area [i.e. an area where a data collection process took place which encompasses the RAN entities involved in the data collection]. Hereinafter, such an identifier may be referred to interchangeably simply as ID, or “Area ID”.

[0174] The procedure of FIG. 8 is suitable for use in combination with models (e.g. gNB-side models) which have been trained, e.g. using data collected in accordance with the data collection procedure of FIGs. 2, 3 and 5, such that the trained models are associated with one or more Area IDs. Moreover, the LMF may have stored therein or accessible thereto, a mapping of Area IDs to sets of RAN entities.

[0175] The UE and gNB respectively have UE-side models 212_u and gNB-side models 212_g available thereto (e.g. stored at the gNB / UE or accessible to the gNB / UE). Each model is associated with one or more Area IDs, i.e. 205_g for the gNB-side models 212_g; and 205_u for the UE-side models 212_u). Each Area ID of each model may be representative of at least one of the following: a set of entities of the RAN that were used in the collection of training data for training the respective model; a set of Transmission Reception Points, TRPs; and an area comprising a set of TRPs.

[0176] In block 801 , the UE sends, to the LMF, information 802 indicative of a plurality of Area IDs 205_u. In this regard, the UE may send information indicative of each of one or more Area IDs associated with each of the UE’s models 212_u.

[0177] The communication between the UE and the LMF may be via at least one of the following: an interface between the LMF and the UE; an N1 interface;

[0178] Non-Access Stratum, NAS, signaling; a non-Radio Resource Control protocol; a higher-level protocol between the LMF and the UE; and an LTE Positioning Protocol, LPP.

[0179] In block 803, the LMF selects an Area ID 205_x.

[0180] In this regard, the LMF may select an Area ID 205_x from the plurality of Area IDs 205_u of the UE that were received in block 801.

[0181] The selection of the Area ID 205_x may comprise: selecting, by the LMF, a set of entities of the RAN to be used in a positioning procedure; and comparing, for each of the received plurality of Area IDs, the set of entities of the RAN represented by each received Area ID to the selected set of entities of the RAN to be used in a positioning procedure.

[0182] The LMF’s selection of the Area ID may be based at least in part on the comparison.

[0183] The selection of the Area ID may be based at least in part on a degree of matching between: a set of entities of the RAN selected by the LMF to be used in a positioning procedure, and the set of entities of the RAN represented by an Area ID of the plurality of received Area IDs.

[0184] In some examples, in addition to or instead of block 801, the UE may send the LMF information indicative of one or more measurements of one or more signals received by the UE from one or more entities of the RAN. Such measurements may comprise at last one of the following:

[0185] Received Signal Strength Indicator, RSSI; at least one channel measurement; at least one Reference Signal Received Power, RSRP, measurement; at least one Channel Impulse Response, CIR, measurement; at least one Power Delay Profile, PDP, measurement; or at least one Delay Profile, DP, measurement.

[0186] The LMF may use such measurements to infer a potential location or a coarse location of where the UE is. The LMF may then use such a potential / coarse location in the LMF’s selection of an Area ID 205_x in block 803. For instance, the LMF may select an Area ID which is associated with an area in which the UE is deemed to be located.

[0187] In block 804, the gNB receives, from the LMF, information 805 for assisting the gNB in selecting one of the gNB’s models for inference, wherein the information 805 is indicative of the Area ID 205_x selected by the LMF.

[0188] The communication between the gNB and the LMF may be via at least one of the following: an interface between the gNB and the LMF; an NG interface; and

[0189] New Radio Positioning Protocol A, NRPPa.

[0190] In block 806, the gNB selects, based at least in part on the information 805 received in block 804, one of its plurality of models for use for inference.

[0191] The selection of one of the plurality of gNB models may be based at least in part on a degree of matching between: the Area ID 205_x of the information 805, and the Area IDs associated with gNB’s the plurality of models.

[0192] In this regard, the gNB selects one of its plurality of models that has an Area ID that matches (or that most closely matches) the received Area ID 205_x selected by the LMF.

[0193] The gNB may receive, from the LMF, configuration information for configuring the gNB to perform an inference procedure, e.g. AI / ML positioning.

[0194] The gNB may use the selected model to perform the inference procedure. For instance, the inference procedure may be a positioning procedure and the gNB may use the selected model to perform AI / ML NG-RAN assisted positioning for uplink positioning wherein a target UE transmits SRSs to be received and measured by the gNB. With the above described procedure 800, the LMF is able to cause an inference procedure to be performed in a particular area (which may be associated with a particular Area ID) and enable the gNB to select one of its trained models (each model being associated with a respective Area ID as discussed above) that is valid / suitable for the particular area where inference is to take place.

[0195] The use of Area ID(s) in the collection of training data and the training of models, in combination of the use of Area ID(s) for inference procedures may enable consistency between training and inference by enabling Area-1 D-based selection of models for inference. The Area IDs can be used for selecting a trained model which is valid / suitable for a particular context, e.g. selecting a model that is valid / suitable for: performing inference / a positioning procedure involving a certain set of RAN entities (e.g. the same set of RAN entities as used in the collection of training data for the selected model - thereby advantageously providing consistency between training and inference), and / or performing inference / a positioning procedure in a certain area (e.g. the same area where the training data for the selected model was collected - again, thereby advantageously providing consistency between training and inference).

[0196] FIG. 9 illustrates an example of a signaling diagram showing signalling (between a UE 110, a gNB 120 and an LMF 140) and a procedure 900 for using Area IDs for inference in AI / ML positioning namely “Case 3a” type AI / ML positioning, i.e. AI / ML assisted positioning - NG- RAN node assisted positioning with gNB-side model.

[0197] Certain aspects, features and functionality of the procedure 900 are similar to certain aspects, features and functionality of the procedure 800 of FIG. 8 as well as various of the other features and functionality described above. Hence, certain aspects, features and functionality of the procedure 800, as well as various of the other features and functionality described above, may be relevant mutatis mutandis to the procedure 900 and shall not be repeated / reiterated in detail.

[0198] In step 1 , there is an interchange of messages between the gNB and the LMF. Such messages may be for providing assistance information and / or configuration information to the gNB for supporting the gNB in performing an inference in AI / ML positioning procedure using Area IDs. In step 1, the gNB may indicate to the LMF the gNB’s support of Area IDs.

[0199] In step 2, the UE provides a capability report to the LMF to indicate if the UE supports Area IDs. In this regard, the UE indicates its capability of performing an inference procedure using Area IDs.

[0200] In step 3, the LMF provides the UE with assistance data for inference. Such assistance data may be generic assistance data for supporting the UE in performing an inference procedure (e.g. conventional assistance data for inference).

[0201] In step 4, the UE reports one or more Area IDs to the LMF. In this regard, the UE may determine RSSI of DL signals received from TRPs in the UE’s vicinity. The UE may, via an implementation method, determine a ranking of all available TRPs around itself. The UE may determine one or more subsets of the available TRPs (e.g. based on the TRPs’ RSSI / ranking. The selected one or more sub-sets of TRPs may define / select one or more Area IDs, which may be used for inference (a similar approach may be applied for data collection, e.g. step 3 of FIG.5). The subset(s) of TRPs determined by the UE may provide information that is useful to the LMF because a larger number of TRPs may receive the UL SRS, and a subset of these TRPs may be mapped to one of the subset defined / selected by the UE. The UE signals its selected Area IDs to the LMF.

[0202] In step 5, the LMF performs an assessment of the Area-ID(s) received from the UE. The LMF determines one or more preferred Area-ID(s) based on the one or more Area-ID(s) received from the UE. In this regard, the LMF determines / selects one or more of the Area IDs that would be suitable to use by the gNB in selecting one of its models for the inference in AI / ML positioning procedure that is to be performed.

[0203] The LMF’s selection / determination of one or more preferred Area-ID(s) may be done based at least in part on an availability of radio resources (e.g. radio resources available at one or more TRPs or gNBs). The LMF’s selection may also be based on pre-stored information about Area IDs that were used in a data collection procedure (e.g. during which training data was collected to train the various models), such pre-stored information about Area IDs may include a pre-determined mapping / association an Area ID to a set of TRPs. The LMF may also do a confirmation or complementary indication of the TRPs linked to the specific Area- ID(s) suggested by UE in step 4.

[0204] In some examples, the LMF’s assessment of which one or more Area IDs to choose / select may be based on receipt of an RSSI from a target UE (i.e. the UE whose position is to be determined and which is to generate and transmit UL-SRSs). The RSSI may be used by the LMF to infer a potential / provisional / coarse location of the Target UE which can be used to infer an area within which the target UE is located. The one or more selected / preferred Area IDs in step 5 may be those whose associated area matches or most closely corresponds to the inferred area.

[0205] In step 6, the LMF sends, to the gNB, Area ID information indicative of the one of more Area IDs selected by the LMF as being preferred one of more Area IDs.

[0206] In step 7, the gNB selects one of its models based on the received Area ID information.

[0207] Following on from the above flow of signals, the gNB may proceed to perform the inference in AI / ML positioning procedure for Case 3a (AI / ML assisted positioning with NG-RAN node assisted positioning using gNB-side model) in step 8 using the gNB-side model selected in step 6. In this regard, the gNB may perform measurements of SRSs transmitted from the UE and input the measurements input into the selected gNB-side model. However, rather than outputting a position directly, the gNB-side model's output is used to enhance or refine the measurement data, i.e. for input into a conventional (non-AI / ML) positioning module that computes the actual position (with a higher accuracy or reliability due to the to the gNB-side model's preprocessing.

[0208] The signalling diagrams of FIGs. 2, 3, and 5 to 9 can be considered to illustrate a plurality of methods, in the sense that each signalling diagram can be considered to illustrate one or more actions, processes or procedures performed by / at a plurality of actors / entities (e.g. UE 110, LMF 140 and gNB 120). The signalling diagrams can therefore be considered to illustrate a plurality of individual methods performed by each respective individual actor / entity of the plurality of the actors / entities. The above described component blocks and step (e.g. of the signalling diagrams) are functional and the functions, along with the further functions / functionalities described above, can be performed by a single physical entity (such as an apparatus as is described with reference to FIG. 10 - embodied in a UE, LMF or gNB). The functions described can also be implemented by a computer program (such as is described with reference to FIG. 11 - for execution by a processor of a UE, LMF of gNB).

[0209] FIG. 10 schematically illustrates a block diagram of an apparatus 10 for performing the methods, processes, procedures and signaling described in the present disclosure and illustrated in FIGs. 2, 3, and 5 to 9. In this regard the apparatus can perform the roles of an entity (such as: UE, LMF of gNB) in the illustrated and described methods.

[0210] The component blocks of FIG. 01 are functional and the functions described can be performed by a single physical entity, not least such as a UE, LMF or gNB.

[0211] The apparatus comprises a controller 11, which could be provided within a device / entity, not least such as a UE, LMF or gNB.

[0212] The controller 11 can be embodied by a computing device, not least such as those mentioned above. In some, but not necessarily all examples, the apparatus can be embodied as a chip, chip set, circuitry or module, i.e. for use in any of the foregoing. As used here ‘module’ refers to a unit or apparatus that excludes certain parts / components that would be added by an end manufacturer or a user.

[0213] Implementation of the controller 11 can be as controller circuitry. The controller 11 can be implemented in hardware alone, have certain aspects in software including firmware alone or can be a combination of hardware and software (including firmware).

[0214] The controller 11 can be implemented using instructions that enable hardware functionality, for example, by using executable instructions of a computer program 14 in a general- purpose or special-purpose processor 12 that can be stored on a computer readable storage medium 13, for example memory, or disk etc, to be executed by such a processor 12. The processor 12 is configured to read from and write to the memory 13. The processor 12 can also comprise an output interface via which data and / or commands are output by the processor 12 and an input interface via which data and / or commands are input to the processor 12. The apparatus can be coupled to or comprise one or more other components 15 (not least for example: a radio transceiver, sensors, input / output user interface elements and / or other modules / devices / components for inputting and outputting data / commands).

[0215] The memory 13 stores instructions such as a computer program 14 comprising such instructions (e.g. computer program instructions / code) that controls the operation of the apparatus 10 when loaded into the processor 12. The instructions of the computer program 14, provide the logic and routines that enables the apparatus to perform the methods, processes and procedures described in the present disclosure and illustrated in FIGs. 2, 3, and 5 to 9. The processor 12 by reading the memory 13 is able to load and execute the computer program 14.

[0216] The instructions may be comprised in a computer program, a non-transitory computer readable medium, a computer program product, a machine readable medium. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e. tangible, not a signal) as opposed to a limitation on data storage persistency (e.g. RAM vs. ROM). In some but not necessarily all examples, the computer program instructions may be distributed over more than one computer program.

[0217] Although the memory 13 is illustrated as a single component / circuitry it can be implemented as one or more separate components / circuitry some or all of which can be integrated / removable and / or can provide permanent / semi-permanent / dynamic / cached storage.

[0218] Although the processor 12 is illustrated as a single component / circuitry it can be implemented as one or more separate components / circuitry some or all of which can be integrated / removable. The processor 12 can be a single core or multi-core processor. The apparatus can include one or more components for effecting the methods, processes and procedures described in the present disclosure and illustrated in FIGs. 2, 3, and 5 to 9. It is contemplated that the functions of these components can be combined in one or more components or performed by other components of equivalent functionality. The description of a function should additionally be considered to also disclose any means suitable for performing that function.

[0219] Where a structural feature has been described, it can be replaced by means for performing one or more of the functions of the structural feature whether that function or those functions are explicitly or implicitly described.

[0220] Although examples of the apparatus have been described above in terms of comprising various components, it should be understood that the components can be embodied as or otherwise controlled by a corresponding controller or circuitry such as one or more processing elements or processors of the apparatus. In this regard, each of the components described above can be one or more of any device, means or circuitry embodied in hardware, software or a combination of hardware and software that is configured to perform the corresponding functions of the respective components as described above.

[0221] The apparatus can, for example, be: a user equipment, base station or network node of a mobile cellular telecommunication system. The apparatus can be embodied by a computing device, not least such as those mentioned above. However, in some examples, the apparatus can be embodied as a chip, chip set, circuitry or module, i.e. for use in any of the foregoing.

[0222] In one example, the apparatus is embodied on a client device, a UE, a mobile cellular telephone, a hand held portable electronic device, a mobile communication device, a wearable computing device or a personal digital assistant, that can additionally provide one or more audio / text / video communication functions (for example tele-communication, videocommunication, and / or text transmission (Short Message Service (SMS) / Multimedia Message Service (MMS) / emailing) functions), interactive / non-interactive viewing functions (for example web-browsing, navigation, TV / program viewing functions), music recording / playing functions (for example Moving Picture Experts Group-1 Audio Layer 3 (MP3) or other format and / or (frequency modulation / amplitude modulation) radio broadcast recording / playing), downloading / sending of data functions, image capture function (for example using a (for example in-built) digital camera), and gaming functions, or any combination thereof.

[0223] In some examples (such as wherein the apparatus is provided within a UE 110), the apparatus 10 comprises: at least one processor 12; and at least one memory 13 storing instructions that, when executed by the at least one processor 12, cause the apparatus to perform at least the following: receiving, from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; performing the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

[0224] In some examples (such as wherein the apparatus is provided within an LMF 140), the apparatus 10 comprises: at least one processor 12; and at least one memory 13 storing instructions that, when executed by the at least one processor 12, cause the apparatus to perform at least the following: obtaining, from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; selecting at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; generating at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and sending, to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.

[0225] The above described examples find application as enabling components of: telecommunication systems; tracking systems, automotive systems; electronic systems including consumer electronic products; distributed computing systems; media systems for generating or rendering media content including audio, visual and audio visual content and mixed, mediated, virtual and / or augmented reality; personal systems including personal health systems or personal fitness systems; navigation systems; user interfaces also known as human machine interfaces; networks including cellular, non-cellular, and optical networks; ad-hoc networks; the internet; the internet of things (IOT); Vehicle-to-everything (V2X), virtualized networks; and related software and services.

[0226] The apparatus can be provided in an electronic device, for example, a mobile terminal, according to an example of the present disclosure. It should be understood, however, that a mobile terminal is merely illustrative of an electronic device that would benefit from examples of implementations of the present disclosure and, therefore, should not be taken to limit the scope of the present disclosure to the same. While in certain implementation examples, the apparatus can be provided in a mobile terminal, other types of electronic devices, such as, but not limited to: mobile communication devices, hand portable electronic devices, wearable computing devices, portable digital assistants (PDAs), pagers, mobile computers, desktop computers, televisions, gaming devices, laptop computers, cameras, video recorders, GPS devices and other types of electronic systems, can readily employ examples of the present disclosure. Furthermore, devices can readily employ examples of the present disclosure regardless of their intent to provide mobility.

[0227] FIG. 11 , illustrates a computer program 14 which may be conveyed via a delivery mechanism 20. The delivery mechanism 20 can be any suitable delivery mechanism, for example, a machine readable medium, a computer-readable medium, a non-transitory computer-readable storage medium, a computer program product, a memory device, a solid- state memory, a record medium such as a Compact Disc Read-Only Memory (CD-ROM) or a Digital Versatile Disc (DVD) or an article of manufacture that comprises or tangibly embodies the computer program 14. The delivery mechanism can be a signal configured to reliably transfer the computer program. An apparatus can receive, propagate or transmit the computer program as a computer data signal.

[0228] In certain examples of the present disclosure, there is provided a computer program comprising instructions, which when executed by an apparatus (e.g. UE 110), cause the apparatus to perform at least the following or for causing performing at least the following: receiving, at the apparatus from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; performing, at the apparatus, the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting, at the apparatus, at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, by the apparatus to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

[0229] In certain examples of the present disclosure, there is provided a computer program comprising instructions, which when executed by an apparatus (e.g. LMF 140), cause the apparatus to perform at least the following or for causing performing at least the following: obtaining, at the apparatus from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; selecting, at the apparatus, at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; generating, at the apparatus, at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and sending, from the apparatus to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.

[0230] References to ‘computer program’, ‘computer-readable storage medium’, ‘computer program product’, ‘tangibly embodied computer program’ etc. or a ‘controller’, ‘computer’, ‘processor’ etc. should be understood to encompass not only computers having different architectures such as single / multi- processor architectures and sequential (Von Neumann) / parallel architectures but also specialized circuits such as field-programmable gate arrays (FPGA), application specific circuits (ASIC), signal processing devices and other devices. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.

[0231] As used in this application, the term ‘circuitry’ can refer to one or more or all of the following:

[0232] (a) hardware-only circuitry implementations (such as implementations in only analog and / or digital circuitry) and

[0233] (b) combinations of hardware circuits and software, such as (as applicable):

[0234] (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and

[0235] (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions and

[0236] (c) hardware circuit(s) and / or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (for example firmware) for operation, but the software may not be present when it is not needed for operation.

[0237] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to a particular claim element, a baseband integrated circuit for a mobile device or a similar integrated circuit in a server, a cellular network device, or other computing or network device.

[0238] Although various examples of the present disclosure have been described in the preceding paragraphs, it should be appreciated that modifications to the examples given can be made without departing from the scope of the invention as set out in the claims. The blocks illustrated in FIGs. 2, 3, and 5 to 9 can represent actions in a method, functionality performed by an apparatus, and / or sections of instructions / code in a computer program. The illustration of a particular order to the blocks does not necessarily imply that there is a required or preferred order for the blocks and the order and arrangement of the block may be varied. Furthermore, it may be possible for some blocks to be omitted.

[0239] It will be understood that each block and combinations of blocks illustrated in FIGs. 2, 3, and 5 to 9 as well as the further functionality described above, can be implemented by various means, such as hardware, firmware, and / or software including one or more computer program instructions. For example, one or more of the functions described above can be performed by a duly configured apparatus (such as an apparatus [as shown in FIG. 10] comprising means for performing the above described functionality). One or more of the functions / functionality described above can be embodied by a duly configured computer program (such as a computer program [as shown in FIG. 11] comprising computer program instructions which embody the functions / functionality described above and which can be stored by a memory storage device and performed by a processor).

[0240] As will be appreciated, any such computer program instructions can be loaded onto a computer or other programmable apparatus (i.e. hardware) to produce a machine, such that the instructions when performed on the programmable apparatus create means for implementing the functions / functionality specified in the blocks. These computer program instructions can also be stored in a computer-readable medium that can direct a programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the blocks. The computer program instructions can also be loaded onto a programmable apparatus to cause a series of operational actions to be performed on the programmable apparatus to produce a computer- implemented process such that the instructions which are performed on the programmable apparatus provide actions for implementing the functions / functionality specified in the blocks.

[0241] Various, but not necessarily all, examples of the present disclosure can take the form of a method, an apparatus, or a computer program. Accordingly, various, but not necessarily all, examples can be implemented in hardware, software or a combination of hardware and software.

[0242] Various, but not necessarily all, examples of the present disclosure are described using flowchart illustrations and schematic block diagrams. It will be understood that each block (of the flowchart illustrations and block diagrams), and combinations of blocks, can be implemented by computer program instructions of a computer program. These program instructions can be provided to one or more processor(s), processing circuitry or controller(s) such that the instructions which execute on the same create means for causing implementing the functions specified in the block or blocks, i.e. such that the method can be computer implemented. The computer program instructions can be executed by the processor(s) to cause a series of operational block / steps / actions to be performed by the processor(s) to produce a computer implemented process such that the instructions which execute on the processor(s) provide block / steps for implementing the functions specified in the block or blocks.

[0243] Accordingly, the blocks support: combinations of means for performing the specified functions; combinations of actions for performing the specified functions; and computer program instructions / algorithm for performing the specified functions. It will also be understood that each block, and combinations of blocks, can be implemented by special purpose hardware-based systems which perform the specified functions or actions, or combinations of special purpose hardware and computer program instructions.

[0244] Various, but not necessarily all, examples of the present disclosure provide both a method and corresponding apparatus comprising various modules, means or circuitry that provide the functionality for performing / applying the actions of the method. The modules, means or circuitry can be implemented as hardware, or can be implemented as software or firmware to be performed by a computer processor. In the case of firmware or software, examples of the present disclosure can be provided as a computer program product including a computer readable storage structure embodying computer program instructions (i.e. the software or firmware) thereon for performing by the computer processor. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

[0245] Features described in the preceding description can be used in combinations other than the combinations explicitly described.

[0246] Although functions have been described with reference to certain features, those functions can be performable by other features whether described or not.

[0247] Although features have been described with reference to certain examples, those features can also be present in other examples whether described or not. Accordingly, features described in relation to one example / aspect of the disclosure can include any or all of the features described in relation to another example / aspect of the disclosure, and vice versa, to the extent that they are not mutually inconsistent.

[0248] The term ‘comprise’ is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising Y indicates that X can comprise only one Y or can comprise more than one Y. If it is intended to use ‘comprise’ with an exclusive meaning then it will be made clear in the context by referring to “comprising only one ...” or by using “consisting”.

[0249] In this description, the wording ‘connect’ and ‘communication’ and their derivatives mean operationally connected / in communication. It should be appreciated that any number or combination of intervening components can exist (including no intervening components), i.e. so as to provide direct or indirect connection / coupling / communication. Any such intervening components can include hardware and / or software components.

[0250] As used herein, the term "determine / determining" (and grammatical variants thereof) can include, not least: evaluating, calculating, computing, processing, deriving, measuring, investigating, identifying, looking up (for example, looking up in a table, a database or another data structure), ascertaining and the like. Also, "determining" can include receiving (for example, receiving information), retrieving / accessing (for example, retrieving / accessing data in a memory), obtaining and the like. Also, " determine / determining" can include resolving, selecting, choosing, establishing, inferring and the like.

[0251] As used herein, a description of an action should also be considered to disclose enabling, and / or causing, and / or controlling that action. For example, a description of transmitting information should also be considered to disclose enabling, and / or causing, and / or controlling transmitting information. Similarly, for example, a description of an apparatus transmitting information should also be considered to disclose at least one means or controller of the apparatus enabling, and / or causing, and / or controlling the apparatus to transmit the information.”

[0252] The term “means” as used in the description and in the claims may refer to one or more individual elements configured to perform the corresponding recited functionality or functionalities, or it may refer to several elements that perform such functionality or functionalities. Furthermore, several functionalities recited in the claims may be performed by the same individual means or the same combination of means. For example performing such functionality or functionalities may be caused in an apparatus by a processor that executes instructions stored in a memory of the apparatus.

[0253] References to a parameter, or value of a parameter, should be understood to refer to “data indicative of”, “data defining” or “data representative of” the relevant parameter / parameter value if not explicitly stated (unless the context demands otherwise). The data may be in any way indicative of the relevant parameter / parameter value, and may be directly or indirectly indicative thereof.

[0254] In this description, reference has been made to various examples. The description of features or functions in relation to an example indicates that those features or functions are present in that example. The use of the term ’example’ or ‘for example’, ‘can’ or ‘may’ in the text denotes, whether explicitly stated or not, that such features or functions are present in at least the described example, whether described as an example or not, and that they can be, but are not necessarily, present in some or all other examples. Thus ‘example’, ‘for example’, ‘can’ or ‘may’ refers to a particular instance in a class of examples. A property of the instance can be a property of only that instance or a property of the class or a property of a sub-class of the class that includes some but not all of the instances in the class.

[0255] In this description, references to “a / an / the” [feature, element, component, means ...] are used with an inclusive not an exclusive meaning and are to be interpreted as “at least one” [feature, element, component, means ...] unless explicitly stated otherwise. That is any reference to X comprising a / the Y indicates that X can comprise only one Y or can comprise more than one Y unless the context clearly indicates the contrary. If it is intended to use ‘a’ or ‘the’ with an exclusive meaning then it will be made clear in the context. In some circumstances the use of ‘at least one’ or ‘one or more’ can be used to emphasise an inclusive meaning but the absence of these terms should not be taken to infer any exclusive meaning. As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0256] The presence of a feature (or combination of features) in a claim is a reference to that feature (or combination of features) itself and also to features that achieve substantially the same technical effect (equivalent features). The equivalent features include, for example, features that are variants and achieve substantially the same result in substantially the same way. The equivalent features include, for example, features that perform substantially the same function, in substantially the same way to achieve substantially the same result.

[0257] In this description, reference has been made to various examples using adjectives or adjectival phrases to describe characteristics of the examples. Such a description of a characteristic in relation to an example indicates that the characteristic is present in some examples exactly as described and is present in other examples substantially as described.

[0258] In the above description, the apparatus described can alternatively or in addition comprise an apparatus which in some other examples comprises a distributed system of apparatus, for example, a client / server apparatus system. In examples where an apparatus provided forms (or a method is implemented as) a distributed system, each apparatus forming a component and / or part of the system provides (or implements) one or more features which collectively implement an example of the present disclosure. In some examples, an apparatus is re-configured by an entity other than its initial manufacturer to implement an example of the present disclosure by being provided with additional software, for example by a user downloading such software, which when executed causes the apparatus to implement an example of the present disclosure (such implementation being either entirely by the apparatus or as part of a system of apparatus as mentioned hereinabove).

[0259] The above description describes some examples of the present disclosure however those of ordinary skill in the art will be aware of possible alternative structures and method features which offer equivalent functionality to the specific examples of such structures and features described herein above and which for the sake of brevity and clarity have been omitted from the above description. Nonetheless, the above description should be read as implicitly including reference to such alternative structures and method features which provide equivalent functionality unless such alternative structures or method features are explicitly excluded in the above description of the examples of the present disclosure.

[0260] Whilst endeavouring in the foregoing specification to draw attention to those features of examples of the present disclosure believed to be of particular importance it should be understood that the applicant claims protection in respect of any patentable feature or combination of features hereinbefore referred to and / or shown in the drawings whether or not particular emphasis has been placed thereon.

[0261] The examples of the present disclosure and the accompanying claims can be suitably combined in any manner apparent to one of ordinary skill in the art. Separate references to an “example”, “in some examples” and / or the like in the description do not necessarily refer to the same example and are also not mutually exclusive unless so stated and / or except as will be readily apparent to those skilled in the art from the description. For instance, a feature, structure, process, block, step, action, or the like described in one example may also be included in other examples, but is not necessarily included.

[0262] Each and every claim is incorporated as further disclosure into the specification and the claims are embodiment(s) of the present disclosure. Further, while the claims herein are provided as comprising specific dependencies, it is contemplated that any claims can depend from any other claims and that to the extent that any alternative embodiments can result from combining, integrating, and / or omitting features of the various claims and / or changing dependencies of claims, any such alternative embodiments and their equivalents are also within the scope of the disclosure.

Claims

CLAIMS1. An apparatus comprising: at least one processor; and at least one memory including computer program code, the at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform at least the following: receiving, from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; performing the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

2. The apparatus of claim 1 , wherein the first information comprises a plurality of PRS configurations and a plurality of IDs, wherein each ID is representative of a set of entities of the RAN, wherein each PRS configuration is associated with a respective ID of the plurality of IDs, wherein a plurality of datasets are collected, and wherein the at least one memory furtherstores instructions that, when executed by the at least one processor, cause the apparatus to perform: associating each of the plurality of datasets with one of the plurality of IDs.

3. The apparatus of claim 2, wherein the second information comprises: the plurality of datasets, and the respective ID associated with each dataset of the plurality of datasets.

4. The apparatus of any previous claim, wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: sending, to the node of the core network, information indicative of a capability of the UE to support performing a data collection procedure wherein the collected at least one dataset is mapped to the at least one ID.

5. The apparatus of any previous claim, wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: sending, to the node of the core network, information indicative of a position of the apparatus; and wherein the ID received from the node of the core network is based at least in part on the position.

6. The apparatus of any previous claim, wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: sending, to the node of the core network, information indicative of the at least one ID of the second information.

567. The apparatus of any previous claim, wherein the training entity is the apparatus, and wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: developing the model based at least in part on the at least one dataset of the second information, and associating the developed model with the at least one ID of the second information.

8. A method comprising: receiving, at an apparatus from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; performing, at the apparatus, the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting, at the apparatus, at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, by the apparatus to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

9. A non-transitory computer readable medium encoded with instructions that, when executed by at least one processor, causes the apparatus to perform the method of claim 8.

10. An apparatus comprising: at least one processor; and57at least one memory including computer program code, the at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform at least the following: obtaining, from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; selecting at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; generating at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and sending, to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.11 . The apparatus of claim 10, wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: receiving, from the UE, information indicative of a capability of the UE to support performing a data collection procedure wherein at least one dataset collected by the UE is mapped to the at least one ID.

12. The apparatus of any of previous claims 10 to 11 , wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: receiving, from the at least one UE, information indicative of: at least one dataset collected by the at least one UE, and at least one ID associated with the at least one dataset.5813. The apparatus of claim 12, wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: selecting one or more of the entities of the RAN to be mapped to the at least one ID, wherein the selecting is based at least in part on determining which one or more of the entities of the RAN was associated with a PRS configuration that was used by the UE to receive at least one PRS in the UE’s collection of the at least one dataset.

14. The apparatus of claim 13, wherein the at least one memory further stores instructions that, when executed by the at least one processor, cause the apparatus to perform: storing a mapping of the one or more of the entities of the RAN to the at least one ID.

15. A method comprising: obtaining, at an apparatus from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; selecting, at the apparatus, at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; generating, at the apparatus, at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and sending, from the apparatus to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.

16. A non-transitory computer readable medium encoded with instructions that, when executed by at least one processor, causes the apparatus to perform the method of claim 15.

17. An apparatus comprising: means for receiving, from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; means for performing the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises: collecting at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

18. The apparatus of claim 17, wherein the first information comprises a plurality of PRS configurations and a plurality of IDs, wherein each ID is representative of a set of entities of the RAN, wherein each PRS configuration is associated with a respective ID of the plurality of IDs, wherein a plurality of datasets are collected, and wherein the apparatus further comprises: means for associating each of the plurality of datasets with one of the plurality of IDs.

19. The apparatus of claim 18, wherein the second information comprises: the plurality of datasets, and the respective ID associated with each dataset of the plurality of datasets.

20. The apparatus of any of previous claims 17 to 19, further comprising:means for sending, to the node of the core network, information indicative of a capability of the UE to support performing a data collection procedure wherein the collected at least one dataset is mapped to the at least one ID.21 . The apparatus of any of previous claims 17 to 20, further comprising: means for sending, to the node of the core network, information indicative of a position of the apparatus; and wherein the ID received from the node of the core network is based at least in part on the position.

22. The apparatus of any of previous claims 17 to 21 , further comprising: means for sending, to the node of the core network, information indicative of the at least one ID of the second information.

23. The apparatus of any of previous claims 17 to 22, wherein the training entity is the apparatus, and wherein the apparatus further comprises: means for developing the model based at least in part on the at least one dataset of the second information, and means for associating the developed model with the at least one ID of the second information.

24. A method comprising: receiving, at an apparatus from a node of a core network, first information for supporting the apparatus to perform a data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of a plurality of entities of a Radio Access Network, RAN, and at least one Identifier, ID, wherein the at least one ID is representative of a set of entities of the RAN, wherein the set of entities comprises the plurality of entities; performing, at the apparatus, the data collection procedure based at least in part on the first information, wherein the data collection procedure comprises:collecting, at the apparatus, at least one dataset based at least in part on at least one PRS received from at least one entity of the set of entities, wherein the at least one PRS is received based at least in part on the at least one PRS configuration, and sending, by the apparatus to a training entity for training a model, second information wherein the second information comprises information indicative of: the at least one dataset, and the at least one ID.

25. A computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform the method of claim 24.

26. An apparatus comprising: means for obtaining, from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; means for selecting at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; means for generating at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and means for sending, to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.

27. The apparatus of claim 26, further comprising: means for receiving, from the UE, information indicative of a capability of the UE to support performing a data collection procedure wherein at least one dataset collected by the UE is mapped to the at least one ID.6228. The apparatus of any of previous claims 26 to 27, further comprising: means for receiving, from the at least one UE, information indicative of: at least one dataset collected by the at least one UE, and at least one ID associated with the at least one dataset.

29. The apparatus of claim 28, further comprising: means for selecting one or more of the entities of the RAN to be mapped to the at least one ID, wherein the selecting is based at least in part on determining which one or more of the entities of the RAN was associated with a PRS configuration that was used by the UE to receive at least one PRS in the UE’s collection of the at least one dataset.

30. The apparatus of claim 29, further comprising: means for storing a mapping of the one or more of the entities of the RAN to the at least one ID.

31. A method comprising: obtaining, at an apparatus from at least one User Equipment, UE, information indicative of at least one position of the at least one UE; selecting, at the apparatus, at least one set of entities of a Radio Access Network, RAN, wherein the selection is based at least in part on the at least on position of the at least one UE; generating, at the apparatus, at least one Identifier, ID, wherein the at least one ID is representative of the at least one set of entities of the RAN; and sending, from the apparatus to the at least one UE, first information for supporting the at least one UE to perform at least one data collection procedure, wherein the first information comprises information indicative of: at least one Position Reference Signal, PRS, configuration, wherein the at least one PRS configuration comprises information indicative of the at least one set of entities, and the at least one ID.6332. A computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform the method of claim 31.64

Images