Apparatus, methods and computer programs for positioning user equipment

Abstract

Examples of the disclosure relate to positioning User Equipment (UE) using machine learning models. In examples of the disclosure a UE can be configured to transmit an indication of a capability for supporting a positioning signal transmission scheme (PSTS) and receive and store a PSTS that conforms to the indicated capability. The PSTS indicates timings for transmission by the UE of uplink reference signals and timings for reception by the UE of downlink reference signals. The UE can also be configured to transmit uplink reference signals with timings in accordance with the stored PSTS for generating data samples for training a reference model. The UE can also be configured to receive and store a reference model and receive downlink reference signals with timings in accordance with the stored PSTS for supervised training of the reference model to position the UE.

Description

[0001] TITLE

[0002] Apparatus, Methods and Computer Programs for Positioning User Equipment

[0003] TECHNOLOGICAL FIELD

[0004] Examples of the disclosure relate to apparatus, methods and computer programs for positioning User Equipment. Some relate to methods and computer programs for positioning User Equipment using machine learning models.

[0005] BACKGROUND

[0006] Radio signals can be used for the positioning of User Equipments. Artificial Intelligence (Al) / Machine Learning (ML) models can be used to improve the accuracy of the positioning.

[0007] BRIEF SUMMARY

[0008] According to various, but not necessarily all, examples of the disclosure there may be provided a User Equipment comprising: means for transmitting to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; means for receiving and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; means for transmitting uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; means for receiving and storing a reference model; and means for receiving downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

[0009] The User Equipment may comprise at least one of: means for transmitting a request to perform supervised training of a target model for positioning of the User Equipment; means for receiving a request to perform supervised training of a target model for positioning of the User Equipment.

[0010] The indication of a capability for supporting a positioning signal transmission scheme may comprise at least one of: downlink measurement capability of the User Equipment; downlink labelling capability of the User Equipment.

[0011] The positioning signal transmission scheme may indicate timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the reception of downlink reference signals and the transmission of uplink reference signals occur in consecutive subframes.

[0012] The positioning signal transmission scheme may indicate timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the reception of downlink reference signals has a different periodicity to the transmission of uplink reference signals.

[0013] The positioning signal transmission scheme may indicate timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the periodicity of the reception of downlink reference signals is specific to the User Equipment.

[0014] The positioning signal transmission scheme may comprise an indication of downlink data samples that are to be labelled by the network entity. The positioning signal transmission scheme may be received using one or more information elements in a positioning assistance data message.

[0015] Supervised training may comprise using the reference model and labelled data samples from the received downlink signals to obtain a target model to position the User Equipment.

[0016] The reference model may comprise one or more learned patterns wherein the patterns relate to one or more physical characteristics of a wireless propagation channel and are derived from data samples from the uplink reference signals.

[0017] The downlink reference signals may comprise positioning reference signals.

[0018] The uplink reference signals may comprise sounding reference signals.

[0019] According to various, but not necessarily all, examples of the disclosure there may be provided a method comprising: transmitting to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; receiving and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; transmitting uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; receiving and storing a reference model; and receiving downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

[0020] According to various, but not necessarily all, examples of the disclosure there may be provided a computer program comprising instructions which, when executed by a User Equipment, cause the User Equipment to perform at least: transmitting to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; receiving and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; transmitting uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; receiving and storing a reference model; and receiving downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

[0021] According to various, but not necessarily all, examples of the disclosure there may be provided a network entity comprising: means for receiving an indication of capability from one or more User Equipments wherein the indication of capability is for supporting a positioning signal transmission scheme; means for transmitting a positioning signal transmission scheme to the one or more User Equipments where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; means for receiving data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and means for transmitting a reference model to one or more User Equipments, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments.

[0022] The network entity may comprise at least one of: means for transmitting a request to perform supervised training of a target model for positioning of the User Equipment; means for receiving a request to perform supervised training of a target model for positioning of the User Equipment.

[0023] The indication of a capability for supporting a positioning signal transmission scheme may comprise at least one of: downlink measurement capability of the User Equipment; downlink labelling capability of the User Equipment.

[0024] The positioning signal transmission scheme may indicate timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the reception of downlink reference signals and the transmission of uplink reference signals occur in consecutive subframes.

[0025] The positioning signal transmission scheme may indicate timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the reception of downlink reference signals has a different periodicity to the transmission of uplink reference signals.

[0026] The positioning signal transmission scheme may indicate timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the periodicity of the reception of downlink reference signals is specific to the User Equipment.

[0027] The positioning signal transmission scheme may comprise an indication of downlink data samples that are to be labelled by the network entity.

[0028] The network entity may comprise means for receiving one or more downlink data samples from the User Equipment for labelling and means for transmitting one or more labelled data samples to the User Equipment.

[0029] The positioning signal transmission scheme may be transmitted using one or more information elements in a positioning assistance data message. The network entity may comprise means for learning patterns in the received data samples wherein the patterns relate to physical characteristics of a wireless propagation channel.

[0030] The reference model may comprise one or more learned patterns wherein the patterns relate to physical characteristic of a wireless propagation channel and are derived from data samples from the uplink reference signals.

[0031] The network entity may comprise means for training the reference model using the received data samples wherein training comprises organizing the received data samples into multidimensional vectors and splitting the multidimensional vectors into patches wherein the patches are indexed so that the index represents a location of the patch in the multidimensional vector.

[0032] The downlink reference signals may comprise positioning reference signals.

[0033] The uplink reference signals may comprise sounding reference signals.

[0034] According to various, but not necessarily all, examples of the disclosure there may be provided a method comprising: receiving an indication of capability from one or more User Equipments wherein the indication of capability is for supporting a positioning signal transmission scheme; transmitting a positioning signal transmission scheme to the one or more User Equipments where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; receiving data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and transmitting a reference model to one or more User Equipments, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments. According to various, but not necessarily all, examples of the disclosure there may be provided a computer program comprising instructions which, when executed by a network entity cause the network entity to perform at least: receiving an indication of capability from one or more User Equipments wherein the indication of capability is for supporting a positioning signal transmission scheme; transmitting a positioning signal transmission scheme to the one or more User Equipments where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; receiving data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and transmitting a reference model to one or more User Equipments, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments.

[0035] 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 of 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 of 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.

[0036] BRIEF DESCRIPTION

[0037] Some examples will now be described with reference to the accompanying drawings in which:

[0038] FIG. 1 shows example network;

[0039] FIG. 2 shows an example method;

[0040] FIG. 3 shows an example method;

[0041] FIG. 4 shows an example reference model and target model;

[0042] FIG. 5 shows an example signaling chart; and FIG. 6 shows an example controller.

[0043] 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. Corresponding reference numerals are used in the figures to designate corresponding features. For clarity, all reference numerals are not necessarily displayed in all figures.

[0044] DEFINITIONS

[0045] Al Artificial Intelligence

[0046] DL Downlink

[0047] IE Information Element

[0048] LMF Location Management Function

[0049] LPP LTE Positioning Protocol

[0050] LTE Long Term Evolution

[0051] ML Machine Learning

[0052] NR New Radio

[0053] NRPPa NR Positioning Protocol a

[0054] PRS Positioning Reference Signals

[0055] PSTS Positioning Signal Transmission Scheme

[0056] RAN Radio Access Network

[0057] RE Resource Element

[0058] RRC Radio Resource Control

[0059] SIM Subscriber Identity Module

[0060] SRS Sounding Reference Signals

[0061] TRP Transmission Reception Point

[0062] TX Transmission

[0063] UE User Equipment

[0064] UL Uplink

[0065] DETAILED DESCRIPTION Fig. 1 illustrates an example of a network 100 such as a 5G NR network. The network 100 comprises a plurality of terminal apparatus 110 and a plurality of network entities 120, 130. The network entities 120, 130 can comprise one or more node apparatus 120 that can be configured to communicate with the terminal apparatus 110. The network entities can also comprise one or more core network apparatus 130. The one or more core network apparatus 130 communicate with the node apparatus 120. In some examples the one or more core network apparatus 130 communicate with the terminal apparatus 110.

[0066] The one or more core network apparatus 130 can, in some examples, communicate with each other. The one or more node apparatus 120 can, in some examples, communicate with each other.

[0067] The network 100 can be a cellular network comprising a plurality of cells 122 each served by a node apparatus 120. In this example, the interface between the terminal apparatus 110 and a node apparatus 120 defining a cell 122 is a wireless interface 124.

[0068] The node apparatus 120 comprises one or more cellular radio transceivers. The terminal apparatus 110 comprises one or more cellular radio transceivers.

[0069] In the example illustrated the cellular network 100 is a third generation Partnership Project (3GPP) network in which the terminal apparatus 110 are user equipment (UE) and the node apparatus 120 can be access nodes such as base stations.

[0070] The term ‘user equipment’ is used to designate mobile equipment comprising a smart card for authentication / encryption etc. such as a Subscriber Identity Module (SIM). In some examples the term ‘user equipment’ is used to designate mobile equipment comprising circuitry embedded as part of the user equipment for authentication / encryption such as software SIM.

[0071] The node apparatus 120 can be any suitable base station. A base station is an access node. It can be a network entity responsible for radio transmission and reception in one or more cells to or from the UE 110. The node apparatus 120 can be a network element in a Radio Access Network (RAN), an Open-Radio Access Network (O-RAN), a E-LITRA (Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access) network, or any other suitable type of network.

[0072] The core network apparatus 130 can be part of a core network. The core network apparatus 130 can be configured to manage functions relating to connectivity for the UEs 110. For example, the core network apparatus 130 can be configured to manage functions such as positioning, connectivity, mobility, authentication, authorization and / or other suitable functions.

[0073] In some examples the core network apparatus 130 can comprise a Location Management Function (LMF). The LMF can be configured to perform functions relating to the positioning of UEs 110 such as determining a position of the UE 110, training AI / ML models for use in positioning the UE 110, configuring the UE 110 for measurements for positioning, and / or any other suitable function.

[0074] In the example of Fig. 1 the core network apparatus 130 is shown as a single entity. In some examples the core network apparatus 130 could be distributed across a plurality of entities. For example, the core network apparatus 130 could be cloud based or distributed in any other suitable manner.

[0075] The network 100 can be a 4G or 5G network, for example. It can for example be a New Radio (NR) network that uses gNB or eNB as access nodes 120. New Radio is the 3GPP name for 5G technology. In such cases the node apparatus 120 can comprise gNodeBs (gNBs) 120 configured to provide user plane and control plane protocol terminations towards the UE 110 and / or to perform any other suitable functions. The gNBs 120 are interconnected with each other by means of an X2 / Xn interface 126. The gNBs are also connected by means of the N2 interface 128 to the core network apparatus 130. Other types of networks and interfaces could be used in other examples. Other types of networks could comprise next generation mobile and communication network, for example, a 6G network. Networks, such as the network 100 in Fig. 1 , can be used for positioning UEs 110 or to provide location based services. To improve the accuracy of the positioning AI / ML based models can be used.

[0076] AI / ML gives computers the ability to learn without being explicitly programmed. The computer learns from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E. The computer can often learn from prior training data to make predictions on future data. AI / ML models can use wholly or partially supervised learning and wholly or partially unsupervised learning. It may enable discrete outputs (for example classification, clustering) and continuous outputs (for example regression). AI / ML models can be implemented using different approaches such as cost function minimization, artificial neural networks, support vector machines and Bayesian networks for example. Cost function minimization may, for example, be used in linear and polynomial regression and K-means clustering. Artificial neural networks, for example with one or more hidden layers, model complex relationship between input vectors and output vectors. Support vector machines may be used for supervised learning.

[0077] To use AI / ML models for positioning UEs 110 labelled data for the air-interface is needed. Such data is scarce because labels for training data are not easily accessible. For instance, labelling a measurement with the UE 110 location requires that the location of the UE 110 is readily accessible and / or can be estimated by the UE 110 or other network entity. Also labels often need to be obtained via dedicated procedures and synchronized to the input features. This requires additional signaling overhead and coordination procedures which makes large data collection problematic. In addition to this the labels can be noisy. Labels are most often estimated quantities and their accuracy is dependent on the capability of the entity producing the label. It is possible for the same input feature set to be labeled differently by two different labeling entities.

[0078] Given the above challenges, examples of the disclosure address the issue of labelled data scarcity when developing and deploying supervised AIM L solutions for positioning UEs 110. Fig. 2 shows an example method that can be used in examples of the disclosure. The example method of Fig. 2 could be implemented by a UE 110 or by any other suitable entity.

[0079] At block 200 the method comprises transmitting an indication of a capability for supporting a positioning signal transmission scheme (PSTS). The indication of the capability can be transmitted to a network entity 130 such as an LMF.

[0080] In some examples the indication of a capability can be transmitted in response to the UE 110 receiving a request to perform supervised training of a target model for positioning of the UE 110. In such examples, the request could be received from a network entity 130. In other examples the UE 110 could transmit the request to perform supervised training of a target model for positioning of the UE 110. In such examples, the request can be transmitted to the network entity 130.

[0081] The indication of a capability to support a PSTS can indicate any capabilities of the UE 110 that can be used to implement the PSTS and / or perform positioning of the UE 110. For instance, the indication of a capability can comprise an indication of DL measurement capability of the UE 110, DL labelling capability of the UE 110, and / or any other suitable information.

[0082] At block 202 the method comprises receiving and storing a PSTS. The PSTS can be received from the network entity 130. The PSTS conforms to the indicated capability.

[0083] The PSTS can schedule reference signals that can be used for obtaining data samples for use in positioning the UE 110. For example, the PSTS can indicate timings for transmission by the UE 110 of uplink (UL) reference signals and timings for reception by the UE 110 of downlink (DL) reference signals. The PSTS can allocate the timings of the respective UL and DL signals such that the reception of DL reference signals and the transmission of UL reference signals occur in consecutive subframes. For example, the reception of a DL reference signal could occur in a subframe that immediately precedes the transmission of a UL reference signal or the reception of a DL reference signal could occur in a subframe that immediately follows the transmission of a UL reference signal. Having the reception of DL reference signals and the transmission of UL reference signals occur in consecutive subframes can ensure that channel reciprocity holds for the respective measurements.

[0084] In some examples the PSTS can allocate the timing of the respective UL and DL signals such that the reception of DL reference signals has a different periodicity to the transmission of UL reference signals. This helps to ensure that the UE 110 is only receiving DL reference signals that it has the capability to label. The periodicity of the reception of DL reference signals can be specific to a UE 110. That is the PSTS can allocate different periodicities for DL reference signals to different UEs 110.

[0085] The PSTS can be received using one or more information elements in a positioning assistance data message. The positioning assistance data message could be an LTE Positioning Protocol (LPP) message or any other suitable type of message. One or more new Information Elements (IE) in the LPP message can be used to indicate the PSTS.

[0086] At block 204 the method comprises transmitting UL reference signals. The UL reference signals are transmitted with timings in accordance with the stored PSTS. The UL reference signals can be used by the network entity 130 to obtain unlabelled data samples.

[0087] At block 206 the method comprises receiving and storing a reference model. The reference model can be received using any suitable signalling. In some examples the reference model can be received using a positioning protocol such as LPP.

[0088] The reference model is for use in training a target model for positioning of the UE 110. The target model can be an AI / ML model. The reference model can be a pretext model.

[0089] The reference model can comprise one or more learned patterns. The patterns can relate to physical characteristics of a wireless propagation channel and can be derived from data samples from the UL reference signals. The reference model can be generated by the network entity 130 based on the UL reference signals that have been transmitted by one or more UEs 110.

[0090] In some examples the reference model that is received by the UE 110 could be just part of the reference model. For example, it could be just the first few layers of the reference model.

[0091] At block 208 the method comprises receiving DL reference signals. The DL reference signals can be received with timings in accordance with the stored PSTS. The DL reference signals are used to obtain data samples that can be used for supervised training of the target model to position the UE 110.

[0092] The supervised training of the target model can comprise using the reference model and labelled data samples from the received DL signals to obtain an accurate target model to position the UE 110.

[0093] In some examples the DL data samples can be labelled by the UE 110. In some examples, at least some of, the DL data samples can be labelled by the network entity 130. If the network entity 130 is to perform labelling then the PSTS can comprise an indication of DL data samples that are to be labelled by the network entity 130.

[0094] Fig. 3 shows another example method that can be used in examples of the disclosure. The example method of Fig. 3 could be implemented by a network entity 130 such as an LMF or by any other suitable entity.

[0095] The method comprises, at block 300, receiving an indication of capability from one or more UEs 110. The indication of capability is for supporting a PSTS.

[0096] In some examples the indication of a capability can be received following a request from the UE 110 to perform supervised training of a target model for positioning of the UE 110. In other examples the network entity 130 could transmit the request to the UE 110 to perform supervised training of a target model for positioning of the UE 110. The indication of a capability to support a PSTS can indicate any capabilities of the UE 110 that can be used to implement the PSTS and / or perform positioning of the UE 110. For instance, the indication of a capability can comprise an indication of DL measurement capability of the UE 110, DL labelling capability of the UE 110, and / or any other suitable information.

[0097] At block 302 the method comprises transmitting a PSTS to the one or more UEs 110. The PSTS conforms to the indicated capability and indicates timings for transmission by the UE 110 of UL reference signals and timings for reception by the UE 110 of DL reference signals.

[0098] The PSTS can schedule reference signals that can be used for obtaining data samples for use in positioning the UE 110. For example, the PSTS can indicate timings for transmission by the UE 110 of uplink (UL) reference signals and timings for reception by the UE 110 of downlink (DL) reference signals. The PSTS can allocate the timings of the respective UL and DL signals such that the reception of DL reference signals and the transmission of UL reference signals occur in consecutive subframes. For example, the reception of a DL reference signal could occur in a subframe that immediately precedes the transmission of a UL reference signal or the reception of a DL reference signal could occur in a subframe that immediately follows the transmission of a UL reference signal. Having the reception of DL reference signals and the transmission of UL reference signals occur in consecutive subframes can ensure that channel reciprocity holds for the respective measurements.

[0099] In some examples the PSTS can allocate the timing of the respective UL and DL signals such that the reception of DL reference signals has a different periodicity to the transmission of UL reference signals. This helps to ensure that the UE 110 is only receiving DL reference signals that it has the capability to label. The periodicity of the reception of DL reference signals can be specific to a UE 110. That is the PSTS can allocate different periodicities for DL reference signals to different UEs 110.

[0100] The PSTS can be transmitted using one or more information elements in a positioning assistance data message. The positioning assistance data message could be an LPP message or any other suitable type of message. One or more new lEs in the LPP message can be used to indicate the PSTS.

[0101] At block 304 the method comprises receiving data samples from UL reference signals transmitted with timings in accordance with the PSTS.

[0102] At block 306 the method comprises transmitting a reference model, or at least part of a reference model, to one or more UEs 110. The reference model is trained on at least, data samples obtained from the transmitted UL reference signals and is for supervised training of a target model for positioning one or more of the UEs 110.

[0103] The reference model can be transmitted using any suitable signalling. In some examples the reference model can be transmitted using a positioning protocol such as LPP.

[0104] The reference model can be used to enable patterns in unlabelled data samples to be recognised. The reference model is for use in training a target model for positioning of the UE 110. The target model can be an AI / ML model.

[0105] The reference model can be a pretext model.

[0106] The reference model can comprise one or more learned patterns. The patterns can relate to physical characteristics of a wireless propagation channel and can be derived from data samples from the UL reference signals. The reference model can be generated by the network entity 130 based on the UL reference signals that have been received at block 304. The UL reference signals can be received from multiple UEs 110.

[0107] In some examples the training of the reference model can comprise organizing the received data samples into multidimensional vectors and splitting the multidimensional vectors into patches wherein the patches are indexed so that the index represents a location of the patch in the multidimensional vector. In some examples the reference model that is transmitted to the UE 110 could be just part of the reference model. For example, it could be just the first few layers of the reference model.

[0108] In some examples the DL data samples can be labelled by the UE 110. In such examples the method of Fig. 3 would comprise the additional blocks of receiving one or more DL data samples from the UE 110 for labelling and transmitting one or more labelled data samples to the UE 110. If the network entity 130 is to perform labelling then the PSTS can comprise an indication of DL data samples that are to be labelled by the network entity 130.

[0109] The UL reference signals and the DL reference signals can comprise any suitable signals that can be used to generate data samples for training the reference model and / or the target model. In some examples the DL reference signals can comprise positioning reference signals (PRS). In some examples the UL reference signals can comprise sounding reference signals (SRS).

[0110] The SRS signal is a reference signal that can be transmitted from the UE 110 to a network entity. The SRS signal is used to monitor characteristics of a UL channel. The SRS signal is used to monitor characteristics of a UL channel across the bandwidth of the system. The UE 110 can transmit the SRS as configured by the LMF or other network entity. The SRS configuration can be transmitted to the UE 110 using Radio Resource Control (RRC) messages. The SRS configuration can be arranged to reduce interference by configuring a UE 110 with different SRS instances. The SRS configuration can define UL SRS resource sets for positioning. The respective sets can comprise multiple SRS resources for positioning. The SRS resources for positioning can comprise number of symbols, transmission bandwidth, Resource element (RE) pattern, time offset and any other suitable information. The SRS can be associated with a specific UE TX beam.

[0111] The PRS signal is a reference signal that can be transmitted from a network entity to the UE 110. The PRS signal can be used to monitor characteristics of a DL channel. The PRS signal can be used to monitor characteristics of a DL channel across the bandwidth of the system. The LMF or other suitable network entity 130 can control the PRS configuration. The PRS configuration can be provided to UE 110 as part of UE assistance information or in any other suitable messages. The PRS configuration can be arranged so that the PRS signals are allocated and transmitted periodically with configurable periodicity and time offset.

[0112] Fig. 4 schematically shows training of an example reference model 400 and an example target model 402.

[0113] In examples of the disclosure large amounts of unlabeled data 404 are collected. The unlabeled data can comprise UL data samples. The UL data samples can be obtained from UL SRS signals or any other suitable types of signals. The UL data can be obtained from UL SRS signals transmitted from multiple UEs 110. The data from the UL SRS signals can be collected by one or more Transmission Reception Points (TRP) and aggregated by a network entity 130 such as an LMF.

[0114] In some examples the unlabeled data 404 can also comprise other types of data samples. For instance, some DL data samples could be included within the unlabeled data 404.

[0115] The large amount of unlabeled data 404 can comprise any suitable number of samples. In some examples the large amount of unlabeled data 404 can comprise as much data as is requested by the LMF. In some examples the large amount of unlabeled data 404 can comprise thousands of samples.

[0116] The large amount of unlabeled data 404 is used to train the reference model 400. The reference model 400 can comprise an AI / ML model. The reference model 400 can comprise a neural network or any other suitable type of AI / ML model. The reference model 400 can be trained to learn patterns in the unlabeled data 404.

[0117] The reference model 400 can be trained by the network entity 130. The training of the reference model 400 can comprise learning data patterns from the unlabeled data 404.

[0118] In some examples the training of the reference model 400 can comprise organizing the unlabeled data 404 into one or more multi-dimensional vectors that are split into patches. The patches can then be indexed where the index represents the patch location in the multi-dimensional vector. The patches are then input to the reference model 400 so that it can be trained to output the index of each patch or the location of one patch relative to another patch.

[0119] The trained reference model 400, or at least part of the trained reference model 400, can then be transmitted to one or more UEs 110.

[0120] Small amount of labelled data 406 are also collected. The small amounts of labelled data 406 can be collected the respective UEs 110 that receive the reference model 400.

[0121] The amount of labelled data 406 that is collected can be small relative to the amount of unlabeled data 404 that is collected. For example, the amount of labelled data 406 that is collected could comprise less than ten percent or less than one percent of the number of samples of the unlabeled data 404. For instance, the labelled data 406 could comprise hundreds of samples or tens of samples. The number of samples used in the labelled data 406 might depend on the use case scenario or any other factors.

[0122] The labelled data 406 can comprise DL data samples. The DL data samples can be obtained from PRS signals that are received by the UE 110 or any other suitable type of reference signals. The DL data samples can be labelled by the UE 110 or by the network to entity to generate the labelled data 406.

[0123] The small amounts of labelled data 406 and the received reference model 400 can be used for training the target model 402 for positioning of the UE 110.

[0124] The UE 110 can either use part of the reference model 400 or the whole of the reference model 400 for the training of the target model 402. The UE 110 can determine whether to use part of the reference model 400 or the whole of the reference model 400. If the UE 110 determines that it only needs to use part of the reference model 400 the UE 110 can also determine which part of the reference model 400 to use. For example, if the reference model 400 comprises a neural network it could determine which layers of the neural network are to be used. The target model 402 is trained to perform the specific task of positioning the UE 110.

[0125] The target model 402 can be an AI / ML model such as a neural network.

[0126] Fig. 5 shows an example signaling chart that can be used to implement examples of the disclosure.

[0127] At block 500 self-supervision AI / ML positioning of the UE 110 is set up. To set up selfsupervision AI / ML positioning of the UE 110 the LMF and the UE 110 agree on the procedure that is to be used. For example, the LMF and the UE 110 can agree that the LMF is to generate a reference model 400 using unlabeled UL SRS data, and that the UE 110 is to use the reference model 400 and labelled DL data to update its own target model 402. The UE 110 therefore agrees to the UL SRS transmission as configured by the LMF

[0128] Either the UE 110 or the LMF can trigger the setting up of the self-supervision AI / ML positioning. For example, either the UE 110 can transmit a request to set up selfsupervision AI / ML positioning to the LMF or the LMF could transmit such as request to the UE 110.

[0129] In some examples the set up of self-supervision AI / ML positioning can be triggered using an IE in an LPP message. The LPP message could be an assistance data message, a location information message or any other suitable type of message.

[0130] In such examples, the IE that is used can comprise any suitable type of IE. In some examples the IE could comprise a binary flag indicating the request to set up selfsupervision AI / ML positioning.

[0131] The setting up of the self-supervision AI / ML positioning of the UE 110 can also comprise the UE 110 transmitting an indication of one or more capabilities of the UE 110 to the LMF. The capabilities can comprise the capabilities of the UE 110 for supporting a PSTS. In some examples the indicated capabilities can comprise the DL measurement capability of the UE 110. The DL measurement capability could comprise the minimum periodicity with which the UE can measure a DL PRS. Other capabilities could be indicated in other examples.

[0132] In such examples, the indicated capabilities can comprise the DL labelling capability of the UE 110. This could be an indication of the minimum periodicity with which the UE 110 can generate labels for the DL data samples. This information can be used to ensure that the periodicity used for the PRS enables the UE 110 to both measure the PRS and label them.

[0133] In some examples the setting up of the self-supervision AI / ML positioning of the UE 110 can also comprise the LMF transmitting an indication of one or more capabilities of the LMF to the UE. In such examples, the indicated capabilities can comprise the DL labelling capability of the LMF. The DL labelling capability could comprise the minimum periodicity with which the LMF can generated labels for the DL data samples.

[0134] At block 502 the LMF designs a PSTS. The PSTS can be designed using any relevant capability information that has been exchanged at block 500 so that the PSTS conforms to the relevant capabilities.

[0135] The PSTS can comprise timings for UL SRS and DL PRS. The PSTS can comprise an interleaved pattern for UL SRS and DL PRS. The pattern can be arranged so that the respective UEs 110 can both measure and label the DL PRS instances. For instance, the periodicities with which the DL PRS signals are transmitted can be selected based on the indicated capabilities of the respective UEs 110. Different UEs 110 can have different capabilities and so different periodicities for the DL PRS can be used for different UEs 110.

[0136] An example PSTS could reuse an existing SRS / PRS configuration but could define a sequential behavior in which UL SRS signals from multiple UE 110 are multiplexed in time / frequency / space and are all configured with the same periodicity T1. Channel information from the respective UL signals can be extracted without labeling the UL signal. The DL PRS are configured so that transmission of the SRS signals and transmission of the PRS signals occur in consecutive frames. For example, DL PRS can be configured to follow specific instances of the UL SRS. The DL PRS can be transmitted with periodicity T2. The periodicity T2 is different to the periodicity T1. For example, if the UL SRS transmission happens in sub-frame 1 , 3, 5, 7 (T1 = 2 sub-frames), the DL PRS may be scheduled for sub-frame 2, 6, ... (T2 = 4 sub frames). Channel information from each DL PRS is labelled. The labelling can be performed either by the UE 110 or by the LMF. If the LMF performs the labelling then PSTS is configured so that the DL PRS transmission is followed by the transmission of a label, where the label is indexed with the PRS index, so that the UE 110 can match the signal to the correct label.

[0137] The DL PRS measurement periodicity can be specific to a UE 110. The DL PRS can be scheduled to serve multiple UEs 110 so that multiple UEs 110 can each train their own target models 402 using the same DL PRS. Some UEs 110 may need to measure DL PRS more often than others or may have capabilities to measure and / or label DL PRS more often than others. The measurement periodicity Tm_prs can be indicated by the UE 110 to the LMF at block 500. Tm_prs can be used to generate synchronized labels, either by the UE 110 or by the LMF.

[0138] At block 504 the LMF agrees the PSTS with the serving gNB for each UE 110. The LMF the timing of the UL SRS and DL PRS with the respective serving gNBs. The PSTS can be agreed between the LMF and the gNB using an NRPPa interface.

[0139] After the PSTS has been agreed the PSTS can be transmitted to the respective UEs and TRPs. At block 506 the PSTS is transmitted to a first UE 110, at block 506 the PSTS is transmitted to a second UE 110 and at block 510 the PSTS is transmitted to a TRP. The PSTS indicates the configuration of the interleaved UL and DL transmission. The PSTS can be indicated using a new IE in an LPP assistance data message or in any other suitable message.

[0140] The PSTS describes the time-frequency-code allocation for each of the UL SRS and DL PRS. If the LMF is to perform labelling of the data samples then the PSTS will also inform the UE 110 which of the DL PRS instances are being labeled. The DL PRS instances that are to be labelled by the LMF can be indicated with a binary flag, for example, label = 1. If the labeling is periodic, then the LMF can identify the first labeled DL PRS instance and specify a labeling periodicity TJabel.

[0141] At block 512 the first UE 110 transmits a UL SRS to the TRP and at block 514 the second UE 110 transmits a UL SRS to the TRP. The transmission of the respective UL SRS can be in accordance with the PSTS. The data from the UL SRS signals can be collected by the TRP.

[0142] At block 516 the TRP transmits DL PRS to the first UE 110 and at block 518 the first UE 110 collects the DL data samples. At block 520 the TRP transmits DL PRS to the second UE 110 and at block 522 the second UE 110 collects the DL data samples.

[0143] At block 524 the data samples for the UL SRS signals that have been collected by the TRP are transmitted to the LMF.

[0144] At block 526 the LMF collects and organizes all unlabeled UL SRS samples into an n dimensional vector.

[0145] At block 528 the n dimensional vector is used to train a reference model 400. The reference model 400 can be trained to learn patterns in the n dimensional vectors. The reference model 400 can be tasked with arranging randomly arriving portions and / or patches of the n dimensional vector so that the original vector is reconstructed.

[0146] Other methods for generating the reference model 400 can be used in other examples. For instance, an unsupervised training procedure such as auto-encoder or stacked auto-encoder architecture can be used to extract the patterns in the unlabeled data 404. The auto-encoder can comprise two models. The first model is an encoder to compress the input signal and the second model is a decoder to reconstruct the original input to the encoder using the compressed information. As the encoder outputs should include the information that is necessary for reconstruction by the decoder, the encoder model can be used as a reference model for extraction of features or patterns. At block 530 the reference model 400 is transferred from the LMF to the respective UEs 110. The reference model 400 can be transferred totally or partially. The reference model 400 can be transferred using LPP signaling or any other suitable type of signaling.

[0147] The reference model 400 that is transferred can comprise input size and shape, layers type, number of outputs per layer, and / or any other suitable information.

[0148] The reference model 400 can also be explained to the UE 110. That is the LMF can indicate information such as input / output, activation function, loss used to train the model, or any other suitable information to the UE 110.

[0149] At block 532 the first UE 110 uses its labeled DL PRS data and the received reference model 400 to update its own target model 402 for positioning. Similarly at block 534 the second UE 110 uses its labeled DL PRS data and the received reference model 400 to update its own target model 402 for positioning

[0150] Although the labeled datasets used by the respective UEs 110 is not large, the fine- tuning of the target models 402 can result in good performance, due to the availability of a well-trained reference model 400. The first layers of the UE-specific target model 402, as feature / pattern extractors, can be initialized with the parameters from the reference model 400. Based on the positioning objective (assistance data or location information), the last layers of the target model 402, as the regression / classification layers, can be initialized randomly. Training and / or fine-tuning the target model 402 with the labeled data helps to use the well-trained extracted features from the reference model 400 for the UE-specific positioning task.

[0151] Fig. 6 illustrates an example of a controller 600. The controller 600 could be provided within an apparatus such as a UE 110 or a network entity 130 such as an LMF. Implementation of a controller 600 may be as controller circuitry. The controller 600 may be implemented in hardware alone, have certain aspects in software including firmware alone or can be a combination of hardware and software (including firmware). As illustrated in Fig. 6 the controller 600 can be implemented using instructions that enable hardware functionality, for example, by using executable instructions of a computer program 606 in a general-purpose or special-purpose processor 602 that may be stored on a computer readable storage medium (disk, memory etc.) to be executed by such a processor 602.

[0152] The processor 602 is configured to read from and write to the memory 604. The processor 602 may also comprise an output interface via which data and / or commands are output by the processor 602 and an input interface via which data and / or commands are input to the processor 602.

[0153] The memory 604 stores a computer program 606 comprising computer program instructions (computer program code) that controls the operation of the apparatus when loaded into the processor 602. The computer program instructions, of the computer program 606, provide the logic and routines that enables the apparatus to perform the methods illustrated in the Figs. The processor 602 by reading the memory 604 is able to load and execute the computer program 606.

[0154] In examples where the controller 600 is provided within a UE 110 the controller 600 therefore comprises: at least one processor 602; and at least one memory 604 storing instructions that, when executed by the at least one processor 602, cause a UE 110 at least to perform: transmitting 200 to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; receiving 202 and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; transmitting 204 uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; receiving 206 and storing a reference model; and receiving 208 downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

[0155] In examples where the controller 600 is provided within a network entity such as an LMF the controller 600 therefore comprises: at least one processor 602; and at least one memory 604 storing instructions that, when executed by the at least one processor 602, cause the network entity at least to perform: receiving 300 an indication of capability from one or more User Equipments 110 wherein the indication of capability is for supporting a positioning signal transmission scheme; transmitting 302 a positioning signal transmission scheme to the one or more User Equipments 110 where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment 110 of uplink reference signals and timings for reception by the User Equipment 110 of downlink reference signals; receiving 304 data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and transmitting 306 a reference model to one or more User Equipments 110, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments 110.

[0156] The computer program 606 may arrive at the UE 110 via any suitable delivery mechanism 608. The delivery mechanism 608 may be, 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 record medium such as a Compact Disc Read-Only Memory (CD-ROM) or a Digital Versatile Disc (DVD) or a solid-state memory, an article of manufacture that comprises or tangibly embodies the computer program 606. The delivery mechanism may be a signal configured to reliably transfer the computer program 606. The apparatus may propagate or transmit the computer program 606 as a computer data signal. The computer program 606 can comprise computer program instructions for causing a UE 110 to perform at least the following or for performing at least the following: transmitting 200 to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; receiving 202 and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; transmitting 204 uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; receiving 206 and storing a reference model; and receiving 208 downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

[0157] The computer program 606 can comprise computer program instructions for causing a network entity to perform at least the following or for performing at least the following: receiving 300 an indication of capability from one or more User Equipments 110 wherein the indication of capability is for supporting a positioning signal transmission scheme; transmitting 302 a positioning signal transmission scheme to the one or more User Equipments 110 where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment 110 of uplink reference signals and timings for reception by the User Equipment 110 of downlink reference signals; receiving 304 data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and transmitting 306 a reference model to one or more User Equipments 110, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments 110. The computer program instructions may be comprised in a computer program, a non- transitory computer readable medium, a computer program product, a machine- readable medium. In some but not necessarily all examples, the computer program instructions may be distributed over more than one computer program.

[0158] Although the memory 604 is illustrated as a single component / circuitry it may be implemented as one or more separate components / circuitry some or all of which may be integrated / removable and / or may provide permanent / semi-permanent / dynamic / cached storage.

[0159] Although the processor 602 is illustrated as a single component / circuitry it may be implemented as one or more separate components / circuitry some or all of which may be integrated / removable. The processor 602 may be a single core or multi-core processor.

[0160] References to ‘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 processing circuitry. 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.

[0161] As used in this application, the term ‘circuitry’ may refer to one or more or all of the following:

[0162] (a) hardware-only circuitry implementations (such as implementations in only analog and / or digital circuitry) and

[0163] (b) combinations of hardware circuits and software, such as (as applicable):

[0164] (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions and

[0165] (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g. firmware) for operation, but the software may not be present when it is not needed for operation.

[0166] 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 the 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.

[0167] The stages illustrated in the Figs, can represent steps in a method and / or sections of code in the computer program 606. 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 can be possible for some blocks to be omitted.

[0168] 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 may comprise only one Y or may 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”.

[0169] In this description, the wording ‘connect’, ‘couple’ and ‘communication’ and their derivatives mean operationally connected / coupled / 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. As used herein, the term "determine / determining" (and grammatical variants thereof) can include, not least: 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), accessing (for example, accessing data in a memory), obtaining and the like. Also, " determine / determining" can include resolving, selecting, choosing, establishing, and the like.

[0170] 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’ or ‘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 of 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. It is therefore implicitly disclosed that a feature described with reference to one example but not with reference to another example, can where possible be used in that other example as part of a working combination but does not necessarily have to be used in that other example.

[0171] Although examples have been described in the preceding paragraphs with reference to various examples, it should be appreciated that modifications to the examples given can be made without departing from the scope of the claims.

[0172] Features described in the preceding description may be used in combinations other than the combinations explicitly described above.

[0173] Although functions have been described with reference to certain features, those functions may be performable by other features whether described or not.

[0174] Although features have been described with reference to certain examples, those features may also be present in other examples whether described or not. The term ‘a’, ‘an’ or ‘the’ is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising a / an / the Y indicates that X may comprise only one Y or may comprise more than one Y unless the context clearly indicates the contrary. If it is intended to use ‘a’, ‘an’ 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’ may be used to emphasis an inclusive meaning but the absence of these terms should not be taken to infer any exclusive meaning.

[0175] 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.

[0176] 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.

[0177] 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. Whilst endeavoring in the foregoing specification to draw attention to those features believed to be of importance it should be understood that the Applicant may seek protection via the claims in respect of any patentable feature or combination of features hereinbefore referred to and / or shown in the drawings whether or not emphasis has been placed thereon. l / we claim:

Claims

CLAIMS1 . A User Equipment comprising: means for transmitting to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; means for receiving and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; means for transmitting uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; means for receiving and storing a reference model; and means for receiving downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

2. A User Equipment as claimed in claim 1 wherein the User Equipment comprises at least one of: means for transmitting a request to perform supervised training of a target model for positioning of the User Equipment; means for receiving a request to perform supervised training of a target model for positioning of the User Equipment.

3. A User Equipment as claimed in any preceding claim wherein the indication of a capability for supporting a positioning signal transmission scheme comprises at least one of: downlink measurement capability of the User Equipment; downlink labelling capability of the User Equipment.

4. A User Equipment as claimed in any preceding claim wherein the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlinkreference signals such that the reception of downlink reference signals and the transmission of uplink reference signals occur in consecutive subframes.

5. A User Equipment as claimed in any preceding claim wherein the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the reception of downlink reference signals has a different periodicity to the transmission of uplink reference signals.

6. A User Equipment as claimed in any preceding claim wherein the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals such that the periodicity of the reception of downlink reference signals is specific to the User Equipment.

7. A User Equipment as claimed in any preceding claim wherein the positioning signal transmission scheme comprises an indication of downlink data samples that are to be labelled by the network entity.

8. A User Equipment as claimed in any preceding claim wherein the positioning signal transmission scheme is received using one or more information elements in a positioning assistance data message.

9. A User Equipment as claimed in any preceding claim wherein supervised training comprises using the reference model and labelled data samples from the received downlink signals to obtain a target model to position the User Equipment.

10. A User Equipment as claimed in any preceding claim wherein the reference model comprises one or more learned patterns wherein the patterns relate to one or more physical characteristics of a wireless propagation channel and are derived from data samples from the uplink reference signals.

11. A User Equipment as claimed in any preceding claim wherein the downlink reference signals comprise positioning reference signals and / or wherein the uplink reference signals comprise sounding reference signals.

12. A method comprising: transmitting to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; receiving and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; transmitting uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; receiving and storing a reference model; and receiving downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

13. A computer program comprising instructions which, when executed by a User Equipment, cause the User Equipment to perform at least: transmitting to a network entity of an indication of a capability for supporting a positioning signal transmission scheme; receiving and storing a positioning signal transmission scheme that conforms to the indicated capability where the positioning signal transmission scheme indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; transmitting uplink reference signals with timings in accordance with the stored positioning signal transmission scheme for generating data samples for training a reference model; receiving and storing a reference model; and receiving downlink reference signals with timings in accordance with the stored positioning signal transmission scheme for supervised training of the reference model to position the User Equipment.

14. A network entity comprising: means for receiving an indication of capability from one or more User Equipments wherein the indication of capability is for supporting a positioning signal transmission scheme; means for transmitting a positioning signal transmission scheme to the one or more User Equipments where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; means for receiving data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and means for transmitting a reference model to one or more User Equipments, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments.

15. A network entity as claimed in claim 14 wherein the network entity comprises means for receiving one or more downlink data samples from the User Equipment for labelling and means for transmitting one or more labelled data samples to the User Equipment.

16. A network entity as claimed in any of claims 14 to 15 comprising means for learning patterns in the received data samples wherein the patterns relate to physical characteristics of a wireless propagation channel.

17. A network entity as claimed in any of claims 14 to 16 wherein the reference model comprises one or more learned patterns wherein the patterns relate to physical characteristic of a wireless propagation channel and are derived from data samples from the uplink reference signals.

18. A network entity as claimed in in any of claims 14 to 17 comprising means for training the reference model using the received data samples wherein training comprises organizing the received data samples into multidimensional vectors andsplitting the multidimensional vectors into patches wherein the patches are indexed so that the index represents a location of the patch in the multidimensional vector.

19. A method comprising: receiving an indication of capability from one or more User Equipments wherein the indication of capability is for supporting a positioning signal transmission scheme; transmitting a positioning signal transmission scheme to the one or more User Equipments where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; receiving data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and transmitting a reference model to one or more User Equipments, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments.

20. A computer program comprising instructions which, when executed by a network entity cause the network entity to perform at least: receiving an indication of capability from one or more User Equipments wherein the indication of capability is for supporting a positioning signal transmission scheme; transmitting a positioning signal transmission scheme to the one or more User Equipments where the positioning signal transmission scheme conforms to the indicated capability and indicates timings for transmission by the User Equipment of uplink reference signals and timings for reception by the User Equipment of downlink reference signals; receiving data samples from uplink reference signals transmitted with timings in accordance with the positioning signal transmission scheme; and transmitting a reference model to one or more User Equipments, where the reference model is trained on at least, data samples obtained from the transmitted uplink reference signals and is for supervised training of a target model for positioning one or more of the User Equipments.

Images