Apparatus, methods and computer programs relating to sensing of objects

Abstract

There is provided a second apparatus comprising means for receiving configuration information for defining sets of data to be reported, a respective set of data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus and means for, in accord with the configuration information, collecting and reporting one or more sets of data to a network entity

Description

[0001] APPARATUS, METHODS AND COMPUTER PROGRAMS RELATING TO SENSING

[0002] OF OBJECTS

[0003] Field

[0004] This disclosure generally relates to communication systems and in particular but not exclusively to apparatus, methods and computer programs relating to sensing of objects.

[0005] Background

[0006] A communication system can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network. A mobile or wireless network is one example of a communication system.

[0007] Such communication systems operate in according with standards such as those provided by 3GPP (Third Generation Partnership Project) or ETSI (European Telecommunications Standards Institute). Examples of standards are the so-called 5G (5thGeneration) standards provided by 3GPP.

[0008] Summary

[0009] Some example embodiments of this disclosure will be described with respect to certain aspects. These aspects are not intended to indicate key or essential features of the embodiments of this disclosure, nor are they intended to be used to limit the scope of thereof. Other features, aspects, and elements will be readily apparent to a person skilled in the art in view of this disclosure.

[0010] According to one aspect there is provided a method comprising receiving configuration information for defining sets of data to be reported, a respective set of data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus and collecting and reporting, in accord with the configuration information, one or more sets of data to a network entity.

[0011] The second apparatus may be configured to collect one or more sets of data relating to one of uplink and downlink features, wherein said first apparatus collects one or more corresponding sets of data relating to the other of uplink and downlink features.

[0012] The second apparatus may be configured to collect a first set of data, wherein said first apparatus is configured to collect a corresponding second set of data, said first set of data and the second set of data providing a training data sample for machine learning. The configuration information may further define one or more consistency checks to be performed on the one or more labels determined by the second apparatus and one or more corresponding labels received from the first apparatus.

[0013] The configuration information may further define one or more changes to be made to one or more labels determined by the second apparatus and / or one or more corresponding labels received from the first apparatus based one or more inconsistencies being determined by the

[0014] The configuration information may define a sample rate for collecting said one or more sets of data.

[0015] The configuration information may define one or more positioning differential measurements to be made by the second apparatus to provide a respective set of data.

[0016] The one or more features of a respective set of data may be for use as an input to a machine learning model and the associated label provides a desired output of the machine learning model.

[0017] The one or more features may be associated with one or more different parameters.

[0018] A respective set of data may comprise a set of data collected at one or more different sampling times.

[0019] The collected one or more sets of data relating to one of uplink and downlink features may be used with the one or more corresponding sets of data relating to the other of uplink and downlink features to determine a round trip time between the first and second apparatus.

[0020] A respective set of data may comprise an associated timestamp.

[0021] The one or more labels may comprise one or more of a position indicator; a line of sight indicator; a range to one or more transmission reception points; and a location indicator.

[0022] The first apparatus may comprise one of user equipment and an access node and the second apparatus may comprise the other of the user equipment and the access node.

[0023] One or more of said features of a respective set of data may comprise one or more measurements of one or more reference signals received from the other of the first and second apparatus.

[0024] According to a further aspect there is provided a method comprising sending configuration information to a second apparatus, for defining sets of data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined by the second apparatus, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus, sending configuration information to the first apparatus, for defining sets data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining if the respective label is based on a label provided by the first apparatus and / or a label received from the second apparatus and receiving a first set of collected data from the second apparatus and a second corresponding set of collected data from the first apparatus, said first and second sets of data comprising one or more same labels.

[0025] The first and second sets of data may provide a training data sample for machine learning.

[0026] According to a further aspect, there is provided a second apparatus comprising at least one processor and at least one memory storing instructions of a network function for a communications system, wherein the instructions, when executed by the at least one processor, cause the second apparatus to at least perform receiving configuration information for defining sets of data to be reported, a respective set of data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus and collecting and reporting, in accord with the configuration information, one or more sets of data to a network entity.

[0027] The second apparatus may be configured to collect one or more sets of data relating to one of uplink and downlink features, wherein said first apparatus collects one or more corresponding sets of data relating to the other of uplink and downlink features.

[0028] The second apparatus may be configured to collect a first set of data, wherein said first apparatus is configured to collect a corresponding second set of data, said first set of data and the second set of data providing a training data sample for machine learning.

[0029] The configuration information may further define one or more consistency checks to be performed on the one or more labels determined by the second apparatus and one or more corresponding labels received from the first apparatus.

[0030] The configuration information may further define one or more changes to be made to one or more labels determined by the second apparatus and / or one or more corresponding labels received from the first apparatus based one or more inconsistencies being determined by the

[0031] The configuration information may define a sample rate for collecting said one or more sets of data.

[0032] The configuration information may define one or more positioning differential measurements to be made by the second apparatus to provide a respective set of data. The one or more features of a respective set of data may be for use as an input to a machine learning model and the associated label provides a desired output of the machine learning model.

[0033] The one or more features may be associated with one or more different parameters.

[0034] A respective set of data may comprise a set of data collected at one or more different sampling times.

[0035] The collected one or more sets of data relating to one of uplink and downlink features may be used with the one or more corresponding sets of data relating to the other of uplink and downlink features to determine a round trip time between the first and second apparatus.

[0036] A respective set of data may comprise an associated timestamp.

[0037] The one or more labels may comprise one or more of a position indicator; a line of sight indicator; a range to one or more transmission reception points; and a location indicator.

[0038] The first apparatus may comprise one of user equipment and an access node and the second apparatus may comprise the other of the user equipment and the access node.

[0039] One or more of said features of a respective set of data may comprise one or more measurements of one or more reference signals received from the other of the first and second apparatus.

[0040] According to a further aspect there is provided a network entity comprising at least one processor and at least one memory storing instructions of a network function for a communications system, wherein the instructions, when executed by the at least one processor, cause the network entity to at least perform sending configuration information to a second apparatus, for defining sets of data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined by the second apparatus, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus, sending configuration information to the first apparatus, for defining sets data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining if the respective label is based on a label provided by the first apparatus and / or a label received from the second apparatus and receiving a first set of collected data from the second apparatus and a second corresponding set of collected data from the first apparatus, said first and second sets of data comprising one or more same labels.

[0041] The first and second sets of data may provide a training data sample for machine learning. According to a further aspect there is provided a second apparatus comprising means for receiving configuration information for defining sets of data to be reported, a respective set of data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from the first apparatus and means for collecting and reporting, in accord with the configuration information, one or more sets of data to a network entity.

[0042] The second apparatus may be configured to collect one or more sets of data relating to one of uplink and downlink features, wherein said first apparatus collects one or more corresponding sets of data relating to the other of uplink and downlink features.

[0043] The second apparatus may be configured to collect a first set of data, wherein said first apparatus is configured to collect a corresponding second set of data, said first set of data and the second set of data providing a training data sample for machine learning.

[0044] The configuration information may further define one or more consistency checks to be performed on the one or more labels determined by the second apparatus and one or more corresponding labels received from the first apparatus.

[0045] The configuration information may further define one or more changes to be made to one or more labels determined by the second apparatus and / or one or more corresponding labels received from the first apparatus based one or more inconsistencies being determined by the

[0046] The configuration information may define a sample rate for collecting said one or more sets of data.

[0047] The configuration information may define one or more positioning differential measurements to be made by the second apparatus to provide a respective set of data.

[0048] The one or more features of a respective set of data may be for use as an input to a machine learning model and the associated label provides a desired output of the machine learning model.

[0049] The one or more features may be associated with one or more different parameters.

[0050] A respective set of data may comprise a set of data collected at one or more different sampling times.

[0051] The collected one or more sets of data relating to one of uplink and downlink features may be used with the one or more corresponding sets of data relating to the other of uplink and downlink features to determine a round trip time between the first and second apparatus.

[0052] A respective set of data may comprise an associated timestamp. The one or more labels may comprise one or more of a position indicator; a line of sight indicator; a range to one or more transmission reception points; and a location indicator.

[0053] The first apparatus may comprise one of user equipment and an access node and the second apparatus may comprise the other of the user equipment and the access node.

[0054] One or more of said features of a respective set of data may comprise one or more measurements of one or more reference signals received from the other of the first and second apparatus.

[0055] According to a further aspect there is provided a network entity comprising means for sending configuration information to a second apparatus, for defining sets of data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined by the second apparatus, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus, means for sending configuration information to the first apparatus, for defining sets data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining if the respective label is based on a label provided by the first apparatus and / or a label received from the second apparatus and means for receiving a first set of collected data from the second apparatus and a second corresponding set of collected data from the first apparatus, said first and second sets of data comprising one or more same labels.

[0056] The first and second sets of data may provide a training data sample for machine learning.

[0057] According to a further aspect, there is provided a computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform any of the methods set out previously.

[0058] According to a further aspect, there is provided a computer program comprising instructions, which when executed cause any of the methods set out previously to be performed.

[0059] According to an aspect there is provided a computer program comprising computer executable code which when run cause any of the methods set out previously to be performed.

[0060] According to an aspect, there is provided a computer readable medium comprising program instructions stored thereon for performing at least one of the above methods.

[0061] According to an aspect, there is provided a non-transitory computer readable medium comprising program instructions which when executed by an apparatus, cause the apparatus to perform any of the methods set out previously. According to an aspect, there is provided a non-transitory computer readable medium comprising program instructions which when executed cause any of the methods set out previously to be performed.

[0062] According to an aspect, there is provided a non-volatile tangible memory medium comprising program instructions stored thereon for performing at least one of the above methods.

[0063] In the above, many different aspects have been described. It should be appreciated that further aspects may be provided by the combination of any two or more of the aspects described above.

[0064] Various other aspects are also described in the following detailed description and in the attached claims.

[0065] Description of Figures

[0066] Embodiments will now be described, by way of example only, with reference to the accompanying Figures in which:

[0067] Figure 1 shows a schematic representation of a 5G system in which some embodiments may be provided;

[0068] Figure 2 shows a schematic representation of an apparatus which may implement a respective network function or an access node;

[0069] Figure 3 shows a schematic representation of a user equipment;

[0070] Figure 4 schematically shows tracking of an object using a first method;

[0071] Figure 5 schematically shows tracking of an object using a second method;

[0072] Figure 6 shows a first example procedure of some embodiments;

[0073] Figure 7 shows a second example procedure of some embodiments;

[0074] Figure 8 shows a third example procedure of some embodiments;

[0075] Figure 9 shows a fourth example procedure of some embodiments;

[0076] Figure 10 shows a first method of some embodiments;

[0077] Figure 11 shows a second method of some embodiments;

[0078] Figure 12 shows a third method of some embodiments; and

[0079] Figure 13 shows a fourth method of some embodiments

[0080] Figure 14 shows a fifth method of some embodiments;

[0081] Figure 15 shows a sixth method of some embodiments; and

[0082] Figure 16 shows a seventh method of some embodiments.

[0083] Detailed description Figure 1 shows a schematic representation of a communication system operating based on a 5thgeneration radio access technology (generally referred to as a 5G system (5GS)) and in which some embodiments may be implemented. The 5GS may comprise a (radio) access network ((R)AN), a 5G core network (5GC), one or more application functions (AF) and one or more data networks (DN). A user equipment (UE) may access or connect to the one or more DNs via the 5GS.

[0084] The 5G (R)AN may comprise one or more access nodes. The access nodes may comprise base stations or radio access network (RAN) nodes, such as a gNodeB (gNB). A base station or RAN node may comprise one or more distributed units connected to a central unit.

[0085] The 5GC may comprise various network functions, such as an access and mobility management function (AMF), a session management function (SMF), an authentication server function (AUSF), a location management function (LMF), a user data management (UDM), a user plane function (UPF), a network repository function (NRF), a network exposure function (NEF), a service communication proxy (SCP), edge application server discovery function (EASDF), policy control function (PCF), network slice access control function (NSACF), network slice specific authentication and authorization function (NSSAAF), and / or network slicing selection function (NSSF).

[0086] Figure 2 illustrates an example of an apparatus 200.

[0087] The apparatus 200 may comprise or implement one or more of the network functions shown in Figure 1. The apparatus 200 may have at least one processor and at least one memory storing instructions of one or more the network functions shown in Figure 1 that, when executed by at least one of the at least one processor cause operations or actions of the one or more network functions to be performed. The network function may be a location management function.

[0088] Alternatively, the apparatus 200 may be provided in or be an access node. The apparatus 200 may have at least one processor and at least one memory storing instructions of an access node that, when executed by at least one of the at least one processor cause operations or actions of the access node to be performed.

[0089] In this example, the apparatus 200 may comprise at least one random access memory (RAM) 211a, and / or at least one read only memory (ROM) 211b. The apparatus 200 may comprise at least one processor 212, 213 and / or a network interface 214. The at least one processor 212, 213 may be coupled to the at least one memory which in this example is the RAM 211a and the ROM 211b. The at least one processor 212, 213 may be configured to execute an appropriate software code 215. The software code 215 may, for example, include software code of one or more of the network functions shown in Figure 1, including software code of the network function, which allows the apparatus to perform one or more operations of one or more of the present aspects.

[0090] Alternatively, the software code may, for example, include software code of an access node, which allows the apparatus to perform one or more operations of one or more of the present aspects.

[0091] Figure 3 illustrates an example of a communication device 300 or terminal. The communication device 300 may be any device capable of sending and receiving radio signals. Non-limiting examples of a communication device 300 comprise a mobile station (MS) or mobile device such as a mobile phone or what is known as a ’smart phone’, a computer provided with a wireless interface card or other wireless interface facility (e.g., USB dongle), a personal data assistant (PDA) or a tablet provided with wireless communication capabilities, a machine-type communications (MTC) device, a Cellular Internet of things (CIoT) device or any combinations of these or the like. The communication device may be an XR (extended reality) device such as a headset or may be capable of supporting XR.

[0092] The communication device 300 may send or receive, for example, radio signals carrying communications. The communications may be one or more of voice, electronic mail (email), text message, multimedia, data, machine data and so on.

[0093] The communication device 300 may receive radio signals over an air or radio interface 307 via a transceiver apparatus 306. The transceiver apparatus 306 may be provided for example by means of a radio part and associated antenna arrangement. The antenna arrangement may be arranged internally or externally to the communication device and may include a single antenna or multiple antennas. The antenna arrangement may be an antenna array comprising a plurality of antenna elements.

[0094] The communication device 300 may be provided with at least one processor 301, and / or at least one memory. The at least one memory may be at least one ROM 302a, and / or at least one RAM 302b. Other possible components 303 may be provided for use in software and hardware aided execution of tasks it is designed to perform, including control of access to and communications with access systems, such as the RAN and / or other communication devices. The at least one processor 301 is coupled to the RAM 302b and the ROM 302a. The at least one processor 301 may be configured to execute instructions of software code 308. Execution of the instructions of the software code 308 may for example allow the communication device 300 to perform one or more operations. The software code 308 may be stored in the ROM 302a. It should be appreciated that in other embodiments, any other suitable memory may be alternatively or additionally used.

[0095] The at least one processor 301, the at least one ROM 302a, and / or the at least one RAM 302b can be provided on an appropriate circuit board, in an integrated circuit, and / or in chipsets. This feature is denoted by reference 304.

[0096] The communication device 300 may optionally have a user interface such as keypad 305, touch sensitive screen or pad, combinations thereof or the like. Optionally, the communication device may have one or more of a display, a speaker and a microphone.

[0097] In the following examples, the term UE or user equipment is used. This term encompasses any of the examples of communication devices 300 previously discussed and / or any other communication device or terminal.

[0098] Some embodiments relate to the collection of a set of data from a user equipment and a corresponding set of data from an access node, for example a gNB. The set of data from the UE and the corresponding set of data from the access node may be used together to determine one or more values of one or more parameters. In the example embodiments described later, the set of data from the UE and the corresponding set of data from the access node may be used together to determine a value for a round trip time.

[0099] A set of data may comprise one or more features and one or more label s. One or more of the features may comprise measurements. The one or more features are inputs to a model and the one or more label are an expected model output when the model is input those features. In some embodiments, a label may be a multidimensional vector.

[0100] In some embodiments the set of the data from the UE and the corresponding set of data from the access node may be used to train a machine learning model. The set of the data from the UE and the corresponding set of data from the access node may together provide a single training data sample.

[0101] The machine learning model may be trained using, for example, a supervised training method. In this example, the label may be used as a desired output of the machine learning model.

[0102] In some embodiments, the label of the set of data of the UE and the label of the corresponding set of data from the access node should be the same if the sets of data for the UE and access node are to be used together in a meaningful manner.

[0103] A single training data sample may comprise the common label, one of more features from the set of data of the UE and one of more features from the set of data of the access node. The UE may collect one or more DL (downlink) features. The access node may collection one or more UL (uplink) features.

[0104] The one or more DL features may be based on a DL PRS (positioning reference signal. One or more measurements may be made with respect to the PRS to provide one or more features of a set of data. In other embodiments, any other suitable signal may be used. The DL signal may be, for example, any other suitable reference signal.

[0105] The one or more UL features may be based on a UL SRS (sounding reference signal). One or more measurements may be made with respect to the SRS to provide one or more features of a set of data. In other embodiments, any other suitable signal may be used. The UL signal may be, for example, any other suitable reference signal.

[0106] When one of the UE and access node is unable to collect one or more features, then there may be a mismatch between the DL and UL features sets.

[0107] In some embodiments, the AI / ML model which is being trained is used to determine RTT.

[0108] The principles of RTT positioning will now be explained with reference to Figure 4. An access node sends a DL PRS over a multipath wireless propagation channel to the target UE. The UE receives the signal copies, detects the DL signal, and obtains a multipath delay profile of the channel. The UE then uses the channel profile to identify which path is the line of sight (LOS) one. Lastly, the time of arrival (i.e., delay) of the LOS path is extracted, and the difference between the delay and the transmission time of the UL SRS is computed and reported as the UE Rx-Tx time difference. The UE then sends the UL SRS and the gNB computes by similar methods the time of arrival (i.e., delay) of the LOS component of the UL signal. The difference between said delay and the transmission time of the initial DL PRS is computed and reported as the gNB Rx-Tx time difference. The UE measurement is subtracted from the gNB measurement and obtains the RTT which is then used to localize the target UE.

[0109] Thus, where feature sets are being used to determine a RTT, a mismatch between the DL and UL features sets would lead to an incorrect determination of a RTT.

[0110] In some embodiments, one or more of the DL and UL measurements or features may be timestamped. To ensure that the training data sample is generated coherently, the DL and UL measurements may be timestamped, and matched by the similarity of their timestamps. It should be appreciated that the measurements may be imperfect or noisy, so they may still not match even if they have the same timestamp.

[0111] In some embodiments, one or more sets of data collected by the UE may be used to train an AI / ML functionality. The AI / ML functionality may be a round trip RT functionality. The UE may train such a functionality. A set of data may comprise one or more DL features and the respective label. The AI / ML functionality may be for example a LOS (line of sight) detection functionality, and / or a PDM (positioning differential measurement) extraction functionality.

[0112] In some embodiments, one or more sets of data collected by the access node may be used to train an AI / ML functionality. The AI / ML functionality may be a RT functionality. The access node may train such a functionality. A set of data may comprise one or more UL features and the respective label.

[0113] In some embodiments, the access node and UE functionalities may be trained jointly. For example, the same AIML RT functionality may be trained using a superset of:

[0114] { (one or more DL features, label), (one or more UL features, label)}

[0115] The trained function may then be deployed at the UE and / or access node. The trained function may be further fine-tuned. The train function may comprise a ML model.

[0116] The UL and DL features may be of the same type, where a superset is used.

[0117] For example, if the UE collects Rx-Tx time differences for multipaths up to a maximum excess delay D, then the access node should do the same and vice-versa.

[0118] In some embodiments, the same label should be associated with the one or more features collected by the UE and the access node respectively.

[0119] Some embodiments may ensure that the same label is attached to both DL and UL features collected at a same observation point.

[0120] When labelling is possible by both entities, label synchronization (i.e., ensuring that the same label is attached to both DL and UL features collected at the same observation point) may be performed. In some embodiments, each of the UE and the access node may generate its own label. In this case, steps may need to be taken to ensure that the labels created by the each of the UE and the access node are synchronised or consistent.

[0121] In some embodiments, one of the UE and the access node may generate the label and provide that label to the other of the UE and the access node.

[0122] In some embodiments, one or more quality indicators may be reported. For example, the UE may provide one or more quality indicators indicating a quality of one or more of the label and the measurements. Alternatively or additionally, the access node may provide one or more quality indicators indicating a quality of one or more of the label and the measurements.

[0123] In the following, some examples are described in which data is collected. By way of example only the data collected is training data for a AI / ML model. In some embodiments the AI / ML model is a use for RT positioning. In some embodiments, the UE and access nodes are collection entities and their data collection needs to be synchronized.

[0124] In some embodiments, the LMF (or another entity) may configure the UE and / or the access node.

[0125] The LMF may provide configuration information to the UE to configure the reference signals to be used by the UE. For example, the reference signals may be UL SRS or any other suitable reference signal.

[0126] The LMF may provide configuration information to the access to configure the reference signals (RS) to be used by the access node. For example, the reference signals may be DL PRS, or any other suitable reference signal.

[0127] The configuration information may be provided by positioning protocol (PP) assistance data. The PP may be LPP (LTE PP) or NRPP (new radio PP) or any other suitable PPL.

[0128] The LMF may provide to the UE and the access node, a common PDM set. These are the features that both the UE and the access node should extract from the DL RS and respectively UL RS.

[0129] The granularity of the PDM may be configured.

[0130] In some embodiments, a common granularity may be set by the LMF, upon learning the UE and access node capabilities. The LMF may configure a granularity per PDM. For example., for Rx-Tx time difference this may be expressed as a multiple of Tc or Ts). The granularity define a sampling rate. If the measurements are done in the spatial domain then the granularity is the resolution in space, for example.

[0131] In other embodiments, an independent granularity, is separated decided by the UE and the access node.

[0132] In some embodiments, the LMF may configure label generation. The LMF may configure the common label. The label(s) may comprises one or more of a position indicator; a line of sight indicator; a positioning differential measurement; a range to one or more transmission reception points (TRP); and a location indicator. For example the common label may be configured to be an Rx-Tx-time difference, and / or a LOS indicator, and / or a 2D location estimation. The Rx-Tx time difference may be a PDM like UE-Rx-Tx time difference, access node Rx-Tx time different.

[0133] As mentioned, a label may be a multidimensional vector. For example, for location, an example label may be (x, y, z, time)

[0134] In some embodiments, the LMF may configure which one or both of the UE and the access node generates the label. In some embodiments, both the UE and the access node generates a label, and the labels are used separately.

[0135] In some embodiments, one of the UE and the access node generates the label and then transfers that label to the other of the UE and the access node.

[0136] In some embodiments, both the UE and the access node generates a label and labels are processed to provide a single label. The processing may use averaging, weighted averaging, filtering, label voting, selecting the most trustworthy label and / or the like.

[0137] In embodiments, where the labels are generated both the by the UE and the access node, the configuration information may define one or more label consistency checks to be made. The configuration information may define which of the UE and the access node are to perform the consistency check. In some embodiments, a consistency check may consist of testing if labels match e.g., LOS indicators are approximately the same at both ends and / or if labels are coherent e.g., RTT obtained from 2D location information is approximately the same as the RTT obtained from the difference of the UE and access node Rx-Tx time difference.

[0138] The measurements of the different sets of day should be coherent in some embodiments. For example, the measurements may need to be extracted with same granularity, over the same observation window, from signals which are sent within the coherence time of the channel, and / or in the coherence bandwidth. The labels generated by the UE and the access node should match. For example, where the label is a position, the distance between labels should be smaller than a threshold. By way of example only, the threshold may be only be a few centimetres.

[0139] The configuration information may define one or more correction strategies which are to be performed if the consistency check indicates that there is no consistency. The configuration information may define which of the UE and the access node are to perform the one or more correction strategies if the consistency check indicates that there is no consistency.

[0140] One example of a correction strategy is may no correction to the label and report both labels, even though inconsistent to each other. However, a label uncertainty measure e.g., LOS probability may be provided with the label.

[0141] The label estimate can be accompanied by a trustworthiness metric. If the label islocation, then the trust may be expressed as a standard deviation. If the label is LOS, then the label itself may be given as a probability, where p = 1 means full LOS certainty, and p = 0 means full NLOS certainty. Another example of a correction strategy is to correct one or both of the labels. For example, one or more of the labels may be re-estimated, or the labels may be combined. Where the labels are combined, they may be combined using averaging or weighted averaging,

[0142] The configuration provided by the LMF to the UE and / or the access node may comprise a strategy to cope with missing entries in one training sample. This may be a result of the UE and / or the access node being unable to acquire the PDM set and / or label.

[0143] For example, the UE and / or the access node may be configured to discard the training sample.

[0144] Alternatively or additionally the UE and / or the access node may be configured to use the training sample but mark it as incomplete.

[0145] Alternatively or additionally the UE and / or the access node may be configured to fill in the missing entries by using the existing entries. In some embodiments, alternatively or additionally, the LMF may fill in the missing entries.

[0146] The configuration information may comprise a strategy to train one or both of the UE AIML RT functionalities and the gNB AIML RT functionalities. For example, the functionalities may be trained separately but using a common configuration set by the LMF. In another example, the functionalities are trained jointly.

[0147] Reference is made to Figure 5 which schematically shows, as referenced 1, the LMF providing to the UE and the access node (e.g. a gNB) configuration information. The configuration information may be one or more of the previously discussed configuration information.

[0148] In one example, a sample of labelled data comprises DL and UL input features and their labels. By way of example only: the input features comprise one or more of DL PRS measurement by the UE, UL SRS measurement by the gNB, and timestamp of the measurement pair to ensure that the Rx-Tx time differences remain representative of the propagation delay UE - gNB; and the label comprises one or more of a. PDM like UE Rx-Tx time difference, gNB Rx-Tx time difference, b. UE LOS indicator, gNB LOS indicator, and / or c. 2D location estimation.

[0149] Reference is made to Figure 6 which shows a procedure which follows on from Figure 5. In this example, the configuration information, as referenced 6.1, provided by the LMF will designate the UE as a user of a label and the access node as the label leader. A label leader is a generator of one or more labels.

[0150] As referenced 6.2, the UE is enabled or configured as a label user. As referenced 6.3, the access node is enabled or configured a label leader. This means that the one or more required labels are generated by the access node.

[0151] As referenced 6.4, the access node shared the one or more labels which have been generated by the access node.

[0152] As referenced 6.5, the UE will use the label from the access node and perform or extract the remaining measurements.

[0153] As referenced 6.6, the UE will report measurements to the LMF. The reported measurements to the LMF will take the form discussed previously and comprise the required one or more input features and the required one or more labels. The one or more labels will be the one more labels provided by the access node.

[0154] As referenced 6.7, the access node will report measurements to the LMF. The reported measurements to the LMF will take the form discussed previously and comprise the required one or more input features and the required one or more labels.

[0155] The labels of the UE and the access node will correspond as they have been generated by the access node and shared with the UE.

[0156] It should be noted that in other embodiments, the roles of the UE and the access node may be swapped so the UE is the leader and the access node is the user.

[0157] Reference is made to Figure 7 which shows a procedure which follows on from Figure 5. In this example, the configuration information, as referenced 7.1, provided by the LMF will designate the UE as a leader of a label and the access node as the label leader. A label leader is a generator of one or more labels. In this example, the UE is further identified as the entity which is configured to check the consistency of the labels and to perform any corrections. The configuration information may define what checks the UE needs to do in order to determine the consistency of the labels. The configuration information may define what correction procedure needs to be performed in the event of an instantly of the labels being determined. The configuration information provided to the access node may indicate to the access node that it should report its labels to the UE.

[0158] As referenced 7.2, the UE generates a label and optionally may generate information indicating uncertainty. The uncertainty may reflect an uncertainty of the accuracy of the label.

[0159] As referenced 7.3, the access node generates a label and optionally may generate information indicating uncertainty. The uncertainty may reflect an uncertainty of the accuracy of the label.

[0160] As referenced 7.4, the access node reports one or more labels which have been generated by the access node to the UE. As referenced 7.5, the UE will perform a consistency check. For example, the UE may check the labels from the UE and the access node match e.g., LOS indicators are approximately the same in both labels. For example, the UE may check the labels from the UE and the access node are coherent e.g., RTT obtained from 2D location information is approximately the same as the RTT obtained from the difference of the UE and gNB Rx-Tx time difference.

[0161] As referenced 7.6, the UE will perform one or more correction processes in the case of label inconsistency, The correction process may comprise no correction to the label and reporting both labels, even though inconsistent to each other. However, label uncertainty information may be provided e e.g., LOS probability information. The correction process may comprise correction by combining (e.g., averaging or weighted averaging) of labels or re- estimating one or more labels.

[0162] As referenced 7.7, the UE will report measurements to the LMF. The reported measurements to the LMF will take the form discussed previously and comprise the required one or more input features and the required one or more labels. The one or more labels may be the corrected labels.

[0163] As referenced 7.8, the access node will report measurements to the LMF. The reported measurements to the LMF will take the form discussed previously and comprise the required one or more input features and the required one or more labels.

[0164] Reference is made to Figure 8 which schematically show the processing provided by the LMF, the UE and the access node. In this example the UE is performing the label consistency checks and corrections. It should be appreciated in this example, LOS indicators are labels.

[0165] Reference is first made to the access node.

[0166] As referenced 800a, an uplink SRS is received by a first TRP (transmission reception point), and is pre-processed. The output is, as reference 802a, subject to machine learning based positioning. This provides a PDM value associated with the 1st TRP and a label which is LOS indicator for the first TRP.

[0167] As referenced 800b, the uplink SRS is received by a further TRP (the 2ndTRP) and is pre-processed. The output is, as reference 802b, subject to machine learning based positioning. This provides a PDM value associated with the t-th TRP and a label which is LOS indicator for the t-th TRP.

[0168] As referenced 800c, the uplink SRS is received by a further TRP (the T-th TRP) and is pre-processed. The output is, as reference 802c, subject to machine learning based positioning. This provides a PDM value associated with the T-th TRP and a label which is LOS indicator for the T-th TRP. The number of TRPs may be more or less than 3.

[0169] As referenced 804, the access node performs a ML based position provided using the received UL SRS signals received by the respective TRPs.

[0170] Reference is now made to the UE.

[0171] As referenced 820, a downlink PRS is received by the UE from each of the TRPs of the access node and pre-processed. The output of the pre-processing is subjected to ML-based positioning, referenced 822 which provides as an output a UE PDM for each of the TRPs, a UE LOS indicator for each of the TRPs and DL PRS-based UE positioning.

[0172] As referenced 806, a determination is made as to whether the LOS indicators provided by the UE for each TRP match those of the access node. The LOS indicators are provides as an output from the ML based processing 822 of the UE and from the respective ML based processing 802a-c of the access node.

[0173] As referenced 808, if there is a discrepancy between a LOS provided by the UE and the corresponding LOS provided by the access node, then one or more correction procedures are performed with respect to those LOS labels. The one or more correction procedures are in line with the configuration information.

[0174] As referenced 810 RTT based positioning is performed based on the PDM output of the ML- based learning 822 of the UE. The RTT based positioning will take into account any correction procedure applied to a LOS indicator. It should be noted that if the LOS indicators matched, then the RTT based positioning may take that information into account. The RTT based positioning is performed also based on the respective PDM outputs of the ML- based learning 802a-c of the access node. The RTT based positioning output is a RTT based UE position.

[0175] The RRT based UE position provided by the RTT based positioning 810 is compared, as referenced 812, to the ML based positioning 804 determined by the access node to determine if there is consistency between the labels, that is the determined positions of the UE.

[0176] Where the labels are not consistent, a label correction procedure may be performed, as referenced 814.

[0177] As referenced 816, a sample for reporting is prepared and sent to the LMF. It should be noted that if the labels are consistent, the UE label is not changed. If the labels are not consistent, then the label use will be the output of the label correction procedure.

[0178] In the LMF, the LMF adds the received sample to its data set as referenced 818.

[0179] Reference is made to Figure 9 which schematically show the processing provided by the LMF, the UE and the access node. In this example the LMF is performing the label consistency checks and corrections. It should be appreciated in this example, LOS indicators and the UE position are labels.

[0180] Reference is first made to the access node.

[0181] As referenced 904, an uplink SRS is received by a respective TRP, and is pre-processed. The output is, as reference 906, subject to machine learning based positioning. This provides a PDM value associated with a respective TRP and a respective label which is LOS indicator for that TRP.

[0182] As referenced 912 the access node performs a ML based position of the UE using the received UL SRS signals received by the respective TRPs.

[0183] Reference is now made to the UE.

[0184] As referenced 900, a downlink PRS is received by the UE from each of the TRPs of the access node and pre-processed. The output of the pre-processing is subjected to ML-based positioning, referenced 902 which provides as an output a UE PDM for each of the TRPs, a UE LOS indicator for each of the TRPs and DL PRS-based UE positioning.

[0185] Reference is now made to the LMF.

[0186] As referenced 908, a determination is made as to whether the LOS indicators provided by the UE for each TRP match those of the access node. The LOS indicators are provides as an output from the ML based processing 902 of the UE and from the ML based processing 906 of the access node.

[0187] As referenced 910, if there is a discrepancy between a LOS provided by the UE and the corresponding LOS provided by the access node, then one or more correction procedures are performed with respect to those LOS labels.

[0188] As referenced 914 RTT based positioning is performed based on the PDM output of the ML- based learning 902 of the UE. The RTT based positioning will take into account any correction procedure applied to a LOS indicator. It should be noted that if the LOS indicators matched, then the RTT based positioning may take that information into account. The RTT based positioning is performed also based on the PDM outputs of the ML- based learning 903 of the access node. The RTT based positioning output is a RTT based UE position.

[0189] The RRT based UE position provided by the RTT based positioning 914 is compared, as referenced 914, to the ML based positioning 912 determined by the access node to determine if there is consistency between the labels, that is the determined positions of the UE.

[0190] Where the labels are not consistent, a label correction procedure may be performed, as referenced 918. As referenced 920, a sample is added to its data set. It should be noted that if the labels are consistent, the UE label is not changed. If the labels are not consistent, then the label used in the sample will be the output of the label correction procedure.

[0191] Some embodiments may ensure that labels match and are consistent between UE and access node involved in the AIML RT data collection.

[0192] Some embodiments may control the reporting overhead since multiple versions of the label do not need to be reported to the LMF. This may be the case where only one of the UE and access node reports the label to the LMF.

[0193] Some embodiments may provide corrective actions in case of label inconsistency on a substantially real-time base. For example problematic measurements may be redone, which is not possible once the reports have been sent to the LMF.

[0194] Some embodiments may be used to provide an AI / ML model which may provide positioning accuracy enhancements for different scenarios including, e.g., those with heavy NLOS (non line of sight)conditions.

[0195] The UE Rx - Tx time difference may be defined as TUE-RX - TUE-TX

[0196] Where:

[0197] TUE-RX is the UE received timing of downlink subframe #i from a Transmission Point (TP)

[0018] , defined by the first detected path in time.

[0198] TUE-TX is the UE transmit timing of uplink subframe #j that is closest in time to the subframe #i received from the TP.

[0199] Multiple DL PRS or CSLRS for tracking resources, as instructed by higher layers, can be used to determine the start of one subframe of the first arrival path of the TP.

[0200] For frequency range 1, the reference point for TUE-RX measurement may be the Rx antenna connector of the UE and the reference point for TUE-RX measurement may be the Tx antenna connector of the UE. For frequency range 2, the reference point for TUE-RX measurement may be the Rx antenna of the UE and the reference point for TUE-RX measurement may be the Tx antenna of the UE.

[0201] The gNB Rx - Tx time difference may be defined as T§NB-RX - TgNB-ix

[0202] Where:

[0203] TgNB-Rx is the Transmission and Reception Point (TRP) received timing of uplink subframe #i containing SRS associated with UE, defined by the first detected path in time.

[0204] TgNB-ixis the TRP transmit timing of downlink subframe #j that is closest in time to the subframe #i received from the UE. Multiple SRS resources can be used to determine the start of one subframe containing

[0205] SRS.

[0206] The reference point for TgNB-R may be the Rx antenna connector, the Rx antenna (i.e. the centre location of the radiating region of the Rx antenna), or the Rx Transceiver Array Boundary connector.

[0207] The reference point for TgNB-Txmay be the Tx antenna connector, the Tx antenna (i.e. the centre location of the radiating region of the Tx antenna), or the Tx transceiver array boundary connector.

[0208] Reference is made to Figure 10 which shows a method of some embodiments.

[0209] This method may be performed by an apparatus. The apparatus may a user equipment. The apparatus may comprise suitable means, such as circuitry for providing the method. Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0210] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 3.

[0211] The method may be provided by computer program code or computer executable instructions.

[0212] The method may comprise as referenced Al, receiving configuration information for defining sets of data to be reported, a respective set of data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from the first apparatus.

[0213] The method may comprise as referenced A2, in accord with the configuration information, collecting and reporting one or more sets of data to a network entity

[0214] It should be appreciated that the method outlined in Figure 10 may be modified to include any of the previously described features.

[0215] Reference is made to Figure 11 which shows a method of some embodiments.

[0216] This method may be performed by an apparatus. The apparatus may a network entity, a network function apparatus. The apparatus may be a location management function. The apparatus may comprise suitable means, such as circuitry for providing the method.

[0217] Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below. Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 2.

[0218] The method may be provided by computer program code or computer executable instructions.

[0219] The method may comprise as referenced Bl, sending configuration information to a second apparatus, for defining sets of data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined by the second apparatus, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from the first apparatus.

[0220] The method may comprise as referenced B2, sending configuration information to a first apparatus, for defining sets data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining if the respective label is based on a label provided by the first apparatus and / or a label received from the second apparatus; and

[0221] The method may comprise, as referenced B3, receiving a first set of collected data from the second apparatus and a second corresponding set of collected data from the first apparatus, said first and second sets of data comprising one or more same labels.

[0222] It should be appreciated that the method outlined in Figure 11 may be modified to include any of the previously described features.

[0223] Reference is made to Figure 12which shows a method of some embodiments.

[0224] This method may be performed by an apparatus. The apparatus may an access node .

[0225] The apparatus may comprise suitable means, such as circuitry for providing the method. Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0226] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 2.

[0227] The method may be provided by computer program code or computer executable instructions.

[0228] The method may comprise as referenced Cl, determining one or more labels for a set of data comprising the one or more labels and one or more features; The method may comprise as referenced C2, collecting one or more features associated with the one or more labels to provide the set of data for reporting to a network entity;

[0229] The method may comprise as referenced C3, sending one or more of the determined one or more labels to a second apparatus for use with one or more corresponding features to be collected by the second apparatus.

[0230] It should be appreciated that the method outlined in Figure 12 may be modified to include any of the previously described features.

[0231] Reference is made to Figure 13 which shows a method of some embodiments.

[0232] This method may be performed by an apparatus. The apparatus may an user equipment. The apparatus may comprise suitable means, such as circuitry for providing the method. Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0233] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 3.

[0234] The method may be provided by computer program code or computer executable instructions.

[0235] The method may comprise as referenced DI, receiving one or more labels from a first apparatus; and

[0236] The method may comprise as referenced D2, collecting one or more features associated with the one or more labels to provide a set of data for reporting to a network entity, the set of data comprising the collected one or more features and the one or more labels received from the first apparatus.

[0237] It should be appreciated that the method outlined in Figure 13 may be modified to include any of the previously described features.

[0238] Reference is made to Figure 14 which shows a method of some embodiments.

[0239] This method may be performed by an apparatus. The apparatus may an access node.

[0240] The apparatus may comprise suitable means, such as circuitry for providing the method.

[0241] Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0242] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 2. The method may be provided by computer program code or computer executable instructions.

[0243] The method may comprise as referenced El, determining one or more labels for a set of data comprising the one or more labels and one or more features;

[0244] The method may comprise as reference E2, collecting one or more features associated with the one or more labels to provide the set of said data to a network entity;

[0245] The method may comprise as referenced E3, sending the one or more label to a second apparatus for checking of a consistency between one or more of the sent labels and a respective one or more labels of a corresponding set of data of the second apparatus.

[0246] It should be appreciated that the method outlined in Figure 14 may be modified to include any of the previously described features.

[0247] Reference is made to Figure 15 which shows a method of some embodiments.

[0248] This method may be performed by an apparatus. The apparatus may a user equipment. The apparatus may comprise suitable means, such as circuitry for providing the method. Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0249] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 3.

[0250] The method may be provided by computer program code or computer executable instructions.

[0251] The method may comprise as referenced Fl, determining one or more labels for a set of data comprising the one or more labels and one or more features;

[0252] The method may comprise as referenced F2, collecting one or more features associated with the one or more labels to provide the set of data to a network entity;

[0253] The method may comprise as referenced F3, receiving one or more labels associated with a corresponding set of data from a first apparatus; and

[0254] The method may comprise as referenced F4, determining consistency between one or more of the determined labels and one or more of the received labels.

[0255] It should be appreciated that the method outlined in Figure 15 may be modified to include any of the previously described features.

[0256] Reference is made to Figure 16 which shows a method of some embodiments.

[0257] This method may be performed by an apparatus. The method may be performed at an access node. The apparatus may comprise suitable means, such as circuitry for providing the method.

[0258] Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0259] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 3.

[0260] The method may be provided by computer program code or computer executable instructions.

[0261] The method may comprise as referenced Gl, receiving a first set of data collected by a first apparatus and a second set of data collected by a second apparatus, each set of said data comprising one or more features and one or more labels, the first and second sets of data being associated with the same one or more respective labels.

[0262] The method may comprise as referenced G2, using the features of the first and second sets of data from the first and second apparatus as one or more inputs to a machine learning model and the respective one or more labels label as one or more desired outputs of the machine learning model.

[0263] It should be appreciated that the method outlined in Figure 16 may be modified to include any of the previously described features.

[0264] Computer program code may be downloaded and stored in one or more memories of the apparatus described herein.

[0265] Therefore, although certain embodiments were described above by way of example with reference to certain example architectures for communication systems operated by mobile network operators, technologies and standards, embodiments may be applied to any other suitable forms of communication systems than those illustrated and described herein.

[0266] 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.

[0267] In general, the various embodiments may be implemented in hardware or special purpose circuitry, software, logic or any combination thereof. Some aspects of the disclosure may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the disclosure is not limited thereto. While various aspects of the disclosure may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0268] As used in this application, the term “circuitry” may refer to one or more or all of the following:

[0269] (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and

[0270] (b) combinations of hardware circuits and software, such as (as applicable):

[0271] (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and

[0272] (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

[0273] (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.”

[0274] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, an integrated circuit such as a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0275] The embodiments of this disclosure may be implemented by computer software executable by a data processor of the mobile device, such as in the processor entity, or by hardware, or by a combination of software and hardware. Computer software or program, also called program product, including software routines, applets and / or macros, may be stored in any apparatus-readable data storage medium and they comprise program instructions to perform particular tasks. A computer program product may comprise one or more computerexecutable components which, when the program is run, are configured to carry out embodiments. The one or more computer-executable components may be at least one software code or portions of it. 1

[0276] Further in this regard it should be noted that any blocks of the logic flow as in the Figures may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on such physical media as memory chips, or memory blocks implemented within the processor, magnetic media such as hard disk or floppy disks, and optical media such as for example DVD and the data variants thereof, CD. The physical media is a non-transitory media.

[0277] 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).

[0278] The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The data processors may be of any type suitable to the local technical environment, and may comprise one or more of general-purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASIC), FPGA, gate level circuits and processors based on multi core processor architecture, as non-limiting examples.

[0279] Embodiments of the disclosure may be practiced in various components such as integrated circuit modules. The design of integrated circuits is by and large a highly automated process. Complex and powerful software tools are available for converting a logic level design into a semiconductor circuit design ready to be etched and formed on a semiconductor substrate.

[0280] The foregoing description has provided by way of non-limiting examples a full and informative description of the exemplary embodiments of this disclosure. However, various modifications and adaptations may become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings and the appended claims. Indeed, there are further embodiments comprising a combination of one or more embodiments with any of the other embodiments previously discussed. The scope of protection sought for some embodiments of the disclosure is set out by the claims. The embodiments and features, if any, described in this specification that do not fall under the scope of the claims are to be interpreted as examples useful for understanding various embodiments of the disclosure. It should be noted that different claims with differing claim scope may be pursued in related applications such as divisional or continuation applications.

Claims

CLAIMS1. A second apparatus comprising: means for receiving configuration information for defining sets of data to be reported, a respective set of data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus; and means for, in accord with the configuration information, collecting and reporting one or more sets of data to a network entity.

2. The second apparatus as claimed in claim 1, wherein the second apparatus is configured to collect one or more sets of data relating to one of uplink and downlink features, wherein said first apparatus collects one or more corresponding sets of data relating to the other of uplink and downlink features.

3. The second apparatus as claimed in claim 1 or 2, wherein the second apparatus is configured to collect a first set of data, wherein said first apparatus is configured to collect a corresponding second set of data, said first set of data and the second set of data providing a training data sample for machine learning.

4. The second apparatus as claimed in any preceding claim, wherein the configuration information further defines one or more consistency checks to be performed on the one or more labels determined by the second apparatus and one or more corresponding labels received from the first apparatus.

5. The second apparatus claim as claimed in claim 4, wherein the configuration information further defines one or more changes to be made to one or more labels determined by the second apparatus and / or one or more corresponding labels received from the first apparatus based one or more inconsistencies being determined by the one or more consistency checks.

6. The second apparatus as claimed in any preceding claim, wherein the configuration information defines a sample rate for collecting said one or more sets of data.

7. The second apparatus as claimed in any preceding claim, wherein the configuration information defines one or more positioning differential measurements to be made by the second apparatus to provide a respective set of data.

8. The second apparatus as claimed in any preceding claim, wherein the one or more features of a respective set of data are for use as an input to a machine learning model and the associated label provides a desired output of the machine learning model.

9. The second apparatus as claimed in any preceding claim, wherein the one or more features are associated with one or more different parameters.

10. The second apparatus as claimed in any preceding claim, wherein a respective set of data comprises a set of data collected at one or more different sampling times.

11. The second apparatus as claimed in any preceding claim, when appended to claim 2, wherein the collected one or more sets of data relating to one of uplink and downlink features is used with the one or more corresponding sets of data relating to the other of uplink and downlink features to determine a round trip time between the first and second apparatus.

12. The second apparatus as claimed in any preceding claim, wherein a respective set of data comprises an associated timestamp.

13. The second apparatus as claimed in any preceding claim, wherein the one or more labels comprises one or more of a position indicator; a line of sight indicator; a range to one or more transmission reception points; and a location indicator.

14. The second apparatus as claimed in any preceding claim, wherein the first apparatus comprises one of user equipment and an access node and the second apparatus comprises the other of the user equipment and the access node.

15. The second apparatus as claimed in any preceding claim, wherein one or more of said features of a respective set of data comprises one or more measurements of one or more reference signals received from the other of the first and second apparatus.

16. A network entity compri sing : means for sending: configuration information to a second apparatus, for defining sets of data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined by the second apparatus, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus; configuration information to the first apparatus, for defining sets data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining if the respective label is based on a label provided by the first apparatus and / or a label received from the second apparatus; and means for receiving a first set of collected data from the second apparatus and a second corresponding set of collected data from the first apparatus, said first and second sets of data comprising one or more same labels.

17. The network entity as claimed in claim 13, wherein the first and second sets of data providing a training data sample for machine learning.

18. A method comprising: receiving configuration information for defining sets of data to be reported, a respective set of data comprising one or more features and one or more labels, said configuration information defining how a respective label is to be determined, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus; and collecting and reporting , in accord with the configuration information, one or more sets of data to a network entity.

19. A method comprising: sending configuration information to a second apparatus, for defining sets of data to be reported, a respective set of said data comprising one or more features and one or more labels,said configuration information defining how a respective label is to be determined by the second apparatus, said configuration information defining if the respective label is based on a label provided by the second apparatus and / or a label received from a first apparatus; sending configuration information to the first apparatus, for defining sets data to be reported, a respective set of said data comprising one or more features and one or more labels, said configuration information defining if the respective label is based on a label provided by the first apparatus and / or a label received from the second apparatus; and receiving a first set of collected data from the second apparatus and a second corresponding set of collected data from the first apparatus, said first and second sets of data comprising one or more same labels.20 A computer program comprising computer executable code which when run cause the method of claim 18 or claim 19 to be performed.

Images