Automatic label generation for positioning training data in network-based positioning systems

Abstract

A method (2000) for improving UE positioning by a first network node (1110) includes generating at least one positioning-related report associated with at least one machine learning (ML) model. The first network node transmits (2004) the at least one positioning-related report to a second network node (1110, 502) operating as a position generating entity. The first network node receives (2006) feedback from the second network node indicating a quality level of the at least one positioning-related report. The first network node performs (2008) at least one action based on the feedback indicating the quality level of the at least one positioning-related report.

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates generally to wireless communications, and more particularly to a system and method for automatic label generation for positioning training data in a network-based positioning system. [Background technology]

[0002] Artificial intelligence (AI) and machine learning (ML) are being investigated in both academia and industry as promising tools for optimizing the design of air interfaces in wireless communication networks. Exemplary use cases include using autoencoders for channel state information (CSI) compression to reduce feedback overhead and improve channel prediction accuracy, using deep neural networks to classify line-of-sight (LoS) and non-line-of-sight (NLoS) conditions to improve positioning accuracy, using reinforcement learning for beam selection on the network side and / or user equipment (UE) side to reduce signaling overhead and beam alignment latency, and using deep reinforcement learning to learn optimal precoding policies for complex multiple-input multiple-output (MIMO) precoding problems.

[0003] Building an AI / ML model involves several development steps, where the actual training of the AI ​​model is just one step in the training pipeline. An important part of AI / ML development is the lifecycle management of the AI / ML model.

[0004] Figure 1 shows the training and inference pipelines and their interaction within the model lifecycle management procedure. Lifecycle management of an AI model typically consists of: ● Training (retraining) pipeline: o Data ingestion refers to collecting raw (training) data from data storage. After data ingestion, there may be a step to control the validity of the collected data. o Data preprocessing refers to any feature engineering applied to the collected data. For example, it may include data normalization and possibly data transformations required for input data to an AI / ML model. ○ Model training step. o Model evaluation refers to benchmarking performance against a baseline. The iterative steps of model training and model evaluation continue until an acceptable level of performance is achieved. o Model registration refers to registering an AI / ML model, including any corresponding AI / ML metadata that provides information about how the AI / ML model was developed and, in some cases, performance results of AI / ML model evaluations. ● The deployment stage makes the trained (or retrained) AI / ML model part of the inference pipeline. ● Inference Pipeline: o Data ingestion refers to the collection of raw (inferred) data from data storage. o The data pre-processing stage is typically identical to the corresponding processing that occurs in the training pipeline. o Model operation refers to using a trained and deployed model in operational mode. o Data and model monitoring refers to verifying that the inference data comes from a distribution that is well aligned with the training data, and monitoring the model output to detect any performance or operational drift. • The drift detection stage notifies about any drift in the model operation.

[0005] If the operating environment is found to drift too much from that of the training dataset, the model needs to be retrained or retuned to perform properly in this new environment.

[0006] User equipment (UE) positioning is at the core of location-based services and has a variety of commercial applications, from entertainment to healthcare, and geo-targeted advertising, smartphone factories, and smartphone warehouses. Furthermore, with the emergence of extended reality (XR), UE positioning becomes more important. Positioning accuracy requirements vary depending on the application. For example, positioning accuracy requirements for industrial applications may be from the centimeter level, while those for emergency calls may be up to a few meters of accuracy.

[0007] 3GPP TS 36.305 provides a list of positioning techniques. Some representative methods are listed below: ● Extended Cell Identifier (ID): This technique uses the cellular network's knowledge of information about the UE's serving cell (ie, cell ID and other information) to determine location. ● Assisted Global Navigation Satellite System (GNSS): The UE retrieves GNSS information to determine its position. ● Observed Time Difference of Arrival (OTDoA): Using this technique, the UE estimates the time difference of reference signals from different base stations and reports this information to the network for multilateration. ● Uplink Time Difference of Arrival (UTDoA): This technique uses received signals from the UE at multiple known locations, e.g., gNBs, to estimate the relative Time of Arrival (ToA) at different Transmission / Reception Points (TRPs), and then performs a multilateration operation on the network side to obtain the estimated UE location.

[0008] Current signal processing techniques can generally be applied by a UE, BS, or TRP to generate positioning-related reports in an operating environment with a sufficient line-of-sight (LoS) link. To proceed, ToA is used as a primary example. With the known speed of radio waves, ToA estimates can be converted into 3D distance estimates between a Transmit / Transmission (TX) node and a Receive / Reception (RX) node.

[0009] In a wireless environment, a transmitted signal may travel directly from the transmitter to the receiver, resulting in an LoS path. However, the transmitted signal may also be reflected or scattered by the environment, resulting in multiple NLoS paths. For example, Figure 2 shows a multipath wireless environment between a UE and two TRPs. For TRP A, an LoS path exists between the UE's transmitter and TRP A's receiver. However, for TRP B, due to blockers in the environment, only an NLoS path exists between the UE's transmitter and TRP B's receiver.

[0010] For LoS paths, conventional signal processing techniques can be applied to obtain accurate ToA estimates, which are obtained as the timing of the first observed path in the received signal. For these LoS paths, ToA is determined by the 3D distance d between TX and RX via the speed of radio waves c. 3D represents the correct representation of: TIFF2026506628000002.tif10143

[0011] However, for NLoS paths such as those shown in Figure 2, the radio waves travel indirect paths and potentially reach RX via two or more reflections. Therefore, a direct estimation of the ToA as the first observed path in the received signal will give an incorrect estimate of the 3D distance between TX and RX: TIFF2026506628000003.tif9143

[0012] 3A and 3B show example magnitudes of the LoS and NLoS channel impulse responses (CIR), respectively. More specifically, FIGS. 3A and 3B show the first observed path ToA, τ , as the delay of the first path in the received CIR for the LoS and NLoS cases in an InF-DH {40%, 2m, 2m} wireless environment. obs More specifically, the first observation path ToA for the LoS case shown in FIG. 3A may be calculated as follows: Example of LoS τ obs = τ dp = 18.5 taps

[0013] The first observation path ToA illustrated for the NLoS case illustrated in FIG. 3B can be computed as follows: NLoS example τ obs = 79.4 > τ dp = 30.2 taps In conventional positioning solutions based on triangulation operations, using these overestimated ToAs, or equivalently using 3D distances, will result in erroneous localization of the UE position.

[0014] Additionally, AI / ML models can be employed to infer the correct direct path ToA from the received signal, regardless of whether the signal arrives via a LoS or NLoS path: TIFF2026506628000004.tif11143 That is, the direct path ToA is the time it takes for a radio wave to travel directly from TX to RX, ignoring potential blockers in between.

[0015] Such types of AI / ML models perform what is known as wireless environment fingerprinting. That is, through training with sufficient data, the AI / ML model gains an understanding of the correspondence between received signals and the wireless environment. If the wireless environment remains static or changes only slightly, the AI / ML model may continue to correct or refine ToA estimates sufficient for conventional positioning algorithms to compute UE position within accuracy requirements. However, if the wireless environment changes excessively over time, the AI / ML model may generate inadequate ToA estimates for accurate positioning. Therefore, it is important to monitor the performance of the AI / ML model over time to identify whether the AI / ML model needs to be updated or retrained.

[0016] However, certain challenges currently exist, such as the need to run costly and time-consuming campaigns to collect new and / or more training data in new operating environments in order to retrain or retune ML models. Summary of the Invention

[0017] Certain aspects of the present disclosure and their embodiments may provide solutions to these and other problems. For example, according to certain embodiments, the methods and systems disclosed herein automatically compile useful new training data sets from routine positioning operations.

[0018] According to an embodiment, a method by a first network node for improved UE positioning includes generating at least one positioning-related report associated with at least one machine learning (ML) model, transmitting the at least one positioning-related report to a second network node acting as a position generating entity, receiving feedback from the second network node indicative of a quality level of the at least one positioning-related report, and performing at least one action based on the feedback indicative of the quality level of the at least one positioning-related report.

[0019] According to some embodiments, a first network node for improved UE positioning is configured to generate at least one positioning-related report associated with at least one machine learning (ML) model. The first network node is configured to transmit the at least one positioning-related report to a second network node acting as a position generating entity. The first network node is configured to receive feedback from the second network node indicative of a quality level of the at least one positioning-related report. The first network node is configured to perform at least one action based on the feedback indicative of a quality level of the at least one positioning-related report.

[0020] According to an embodiment, a method for improved assisted positioning by a second network node acting as a position generating entity includes receiving, from a first network node acting as a positioning-related report generating entity, a first set of positioning-related reports generated based on at least one radio signal transmitted on a downlink channel. The second network node determines a position of the UE based on the first set of positioning-related reports. The second network node transmits feedback to the first network node acting as a positioning-related report generating entity, the feedback indicating a quality of the at least one positioning-related report.

[0021] According to an embodiment, a second network node acting as a position generating entity for improved assisted positioning is configured to receive, from a first network node acting as a positioning-related report generating entity, a first set of positioning-related reports generated based on at least one radio signal transmitted on a downlink channel. The second network node is configured to determine a position of the UE based on the first set of positioning-related reports. The second network node is configured to send feedback to the first network node acting as a positioning-related report generating entity, the feedback indicating a quality of the at least one positioning-related report.

[0022] Certain embodiments may provide one or more of the following technical advantages. For example, certain embodiments may provide the technical advantage of automatically compiling useful new training data sets from normal positioning operations, thereby eliminating or reducing the need to run extensive and dedicated campaigns of new training data collection. This allows AI / ML models to be trained and updated incrementally so that they can adapt to gradual environmental changes and continue to provide accurate position estimates of target UEs in the deployed environment.

[0023] As another example, certain embodiments may provide the technical advantage of using automatically compiled new training datasets to perform continuous training or tuning of an ML model, so that the model automatically follows or captures the changing characteristics of the operating environment. Accordingly, a further technical advantage of certain embodiments may be improved reliability of the ML model in such time-varying operating environments.

[0024] Other advantages may be readily apparent to those skilled in the art. Certain embodiments may have none, some, or all of the listed advantages. [Brief explanation of the drawings]

[0025] For a more complete understanding of the disclosed embodiments and their features and advantages, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, in which:

[0026] [Figure 1] Figure 1 shows the training and inference pipelines and their interaction within the model lifecycle management procedure. [Figure 2] FIG. 2 shows the multipath radio environment between the UE and two TRPs. [Figure 3A] , [Figure 3B] 3A and 3B show exemplary magnitudes of the LoS and NLoS CIR, respectively. [Figure 4] FIG. 4 illustrates a positioning architecture in 5GS according to an embodiment. [Figure 5] FIG. 5 illustrates an exemplary method performed by a position generation entity, according to an embodiment. [Figure 6] FIG. 6 illustrates an exemplary iterative method performed by a position generation entity, according to an embodiment. [Figure 7] FIG. 7 shows an example of ideal trilateration in 2D space, according to one embodiment. [Figure 8]FIG. 8 illustrates one such example of trilateration with inaccurate positioning reports, according to one embodiment. [Figure 9] FIG. 9 illustrates an exemplary high-level architecture in which a position generation entity (node ​​B) provides positioning-related labels to a positioning-related training data collection entity (node ​​C), according to an embodiment. [Figure 10] FIG. 10 illustrates another exemplary high-level architecture with model update functionality implemented by node D, according to an embodiment. [Figure 11] FIG. 11 illustrates another exemplary architecture in which the location method is UE-assisted and location management function-based, according to an embodiment. [Figure 12] FIG. 12 illustrates another exemplary architecture in which the location method is UE-based, according to an embodiment. [Figure 13] Figure 13 shows another exemplary architecture in which a single gNB functions as both a positioning-related report generating entity (Node A) and a location generating entity (Node B) and a split architecture is used at the gNB, according to an embodiment. [Figure 14] FIG. 14 illustrates another exemplary architecture in which a position generating entity (node ​​B) 902 provides quality feedback about positioning-related reports to a positioning-related report generating entity (node ​​A), according to an embodiment. [Figure 15] FIG. 15 illustrates an exemplary communication system, according to an embodiment. [Figure 16] FIG. 16 illustrates an exemplary UE, according to an embodiment. [Figure 17] FIG. 17 illustrates an exemplary network node, according to an embodiment. [Figure 18] FIG. 18 illustrates a block diagram of a host, according to one embodiment. [Figure 19] FIG. 19 illustrates a virtualization environment in which functionality implemented by some embodiments may be virtualized, according to an embodiment. [Figure 20]FIG. 20 illustrates a host communicating with a UE via a network node over a partial wireless connection, according to an embodiment. [Figure 21] FIG. 21 illustrates an exemplary method by a UE or a network node for improved UE positioning, according to an embodiment. [Figure 22] FIG. 22 illustrates another method by a UE for improved UE positioning, according to an embodiment. [Figure 23] FIG. 23 illustrates another method by a network node for improved UE positioning, according to an embodiment. [Figure 24] FIG. 24 illustrates another method by a UE for improved positioning, according to an embodiment. [Figure 25] FIG. 25 illustrates a method by a network node acting as a position generating entity for improved positioning, according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0027] Some of the embodiments contemplated herein are described in more detail below with reference to the accompanying drawings, in which: The embodiments are provided as examples to convey the scope of the subject matter to those skilled in the art.

[0028] As used herein, a "node" may be a network node or a UE. Examples of a network node include a Node B, a base station (BS), a multi-standard radio (MSR), an eNodeB (eNodeB), a master eNB (MeNB), a secondary eNB (SeNB), an integrated access backhaul (IAB) node, a network controller, a radio network controller (RNC), a relay, a donor node controlling relay, a base transceiver station (BTS), a central unit (e.g., in a gNB), a distributed unit, a central baseband, a C-RAN, an access point (AP), a transmitting node, a remote radio unit (RRU), a node in a distributed antenna system (DAS), a core network node (e.g., a mobile switching center (MSC), a mobility management entity (MME), etc.), an operation and maintenance (O&M), an operation support system (OSS), a self-organizing network (SON), a positioning node (e.g., an e-SMLC), etc. The terms network node and radio network node are used interchangeably herein.

[0029] Another example of a node is the non-limiting term user equipment (UE), which refers to any type of wireless device that communicates with network nodes and / or other UEs in a cellular or mobile communication system. Examples of UEs include target devices, device-to-device (D2D) UEs, vehicle-to-vehicle (V2V) UEs, machine-type UEs, MTC UEs or UEs capable of machine-to-machine (M2M) communications, personal digital assistants (PDAs), tablets, mobile terminals, smartphones, laptop embedded devices (LEEs), laptop mounted devices (LMEs), unified serial bus (USB) dongles, etc.

[0030] The term Radio Access Technology (RAT) may refer to any RAT, such as Universal Terrestrial Radio Access Network (UTRA), Evolved Universal Terrestrial Radio Access Network (E-UTRA), Narrowband Internet of Things (NB-IoT), WiFi, Bluetooth, Next Generation RAT, NR, 4G, 5G, etc. Any of the devices denoted by the terms node, network node, or radio network node may be capable of supporting a single or multiple RATs.

[0031] The term signal or radio signal as used herein may refer to any physical signal or physical channel. Examples of downlink (DL) physical signals are reference signals (RSs), such as primary synchronization signals (PSSs), secondary synchronization signals (SSSs), channel state information-reference signals (CSI-RSs), demodulation reference signals (DMRSs) in SS / PBCH blocks (SSBs), discovery reference signals (DRSs), cell-specific reference signals (CRSs), and positioning reference signals (PRSs), and the RSs may be periodic. For example, RS opportunities carrying one or more RSs may occur at a certain period (e.g., 20 ms, 40 ms, etc.). The RSs may also be aperiodic.

[0032] Each SSB carries a New Radio-Primary Synchronization Signal (NR-PASS), a New Radio-Secondary Synchronization Signal (NR-SSS), and a New Radio-Physical Broadcast Channel (NR-PBCH) in four consecutive symbols. One or more synchronization signal blocks (SSBs) are transmitted in an SSB burst that repeats with a specific periodicity, such as 5 ms, 10 ms, 20 ms, 40 ms, 80 ms, and 160 ms. UEs are configured with information about SSBs on a particular carrier frequency cell through one or more SS / PBCH Block Measurement Timing Configuration (SMTC) configurations. SMTC configurations include parameters such as SMTC periodicity, SMTC opportunity length in time or duration, and SMTC time offset with respect to a reference time (e.g., the SFN of the serving cell). Therefore, SMTC opportunities may also occur at specific periods (e.g., 5 ms, 10 ms, 20 ms, 40 ms, 80 ms, and 160 ms). Examples of uplink (UL) physical signals are reference signals such as sounding reference signals (SRS), demodulation reference signals (DMRS), etc. The term physical channel refers to any channel that carries higher layer information (e.g., data, control, etc.). Examples of physical channels are the physical broadcast channel (PBCH), physical downlink control channel (PDCCH), physical downlink shared channel (PDSCH), physical uplink shared channel (PUSCH), physical uplink control channel (PUCCH), physical uplink shared channel (PUSCH), short PUSCH (sPDSCH), short PUCCH (sPDSCH), short PUCCH (sPUCCH), short PUSCH (sPUSCH), MTC PDCCH (MPDCCH), narrowband PBCH (NPBCH), narrowband PDCCH (NPDCCH), narrowband PDSCH (NPDSCH), narrowband PUSCH (NPUSCH), enhanced PDCCH (E-PDCCH), etc.

[0033] The term time resource as used herein may correspond to any type of physical or radio resource expressed in terms of a length of time, such as a symbol, time slot, subframe, radio frame, transmission time interval (TTI), interleaving time, slot, subslot, minislot, system frame number (SFN) cycle, hyper SFN (H-SFN) cycle, etc.

[0034] According to certain embodiments, the methods and systems disclosed herein automatically compile useful new training data sets from normal positioning operations. For example, according to certain embodiments, a system and method for UE positioning uses an initial position estimate based on a first set of positioning-related reports to evaluate the relevance scores of different positioning-related reports. In certain embodiments, a positioning-related report is identified as being below expected quality if its relevance score is not better than a threshold. The corresponding ML model generating the identified positioning-related report is further identified as requiring potential retraining or retuning. A network node executing the identified ML model is notified to retain the input data used to generate the identified positioning-related report. A new target positioning-related report label for the retained input data used to generate the identified positioning-related report is computed. The retained input data and the new target positioning-related report label for the retained input data are combined as new training samples for the identified ML model.

[0035] 4 illustrates a positioning architecture 50 in 5GS according to an embodiment. The present invention is applicable to positioning of UEs with New Radio (NR) or E-UTRA access.

[0036] The AMF 55 receives a request for some location services associated with a particular target UE 60 from another entity (e.g., a GMLC or a UE), or the AMF 55 itself decides to initiate some location services on behalf of a particular target UE 60 (e.g., for an IMS emergency call from the UE). The AMF 55 then sends the location service request to the LMF 65. The LMF 65 processes the location service request, which may include forwarding assistance data to the target UE 60 to assist in UE-based positioning and / or UE-assisted positioning, and / or may include positioning of the target UE 60. The LMF 65 then returns the location service results (e.g., a position estimate for the UE 60) to the AMF 55. In the case of location services requested by an entity other than the AMF 55 (e.g., a GMLC or a UE), the AMF 55 returns the location service results to this entity.

[0037] The NG-RAN node 70 may control several TRPs / TPs, such as remote radio heads or DL-PRS-only TPs, to support PRS-based TBS. In the case of a split gNB architecture, the gNB-DU may include the TRP functionality.

[0038] The most important signaling protocols to support UE positioning include: ● UE terminated protocol: ○ LTE Positioning Protocol (LPP) Radio Resource Control (RRC) for NR ● NG-RAN node termination protocol: NR Positioning Protocol A (NRPPa).

[0039] The LTE Positioning Protocol (LPP) is terminated between the target device and the positioning server. In the context of 3GPP UE positioning, the target device is the UE 60 (or may sometimes be referred to as the target UE) and the positioning server is the LMF 65. LPP messages are carried as transparent PDUs over intermediate network interfaces using appropriate protocols. Operations supported by the LPP procedure include: ● Exchange of positioning capabilities; ● Transfer of assistance data; ● Transfer of location information (positioning measurements and / or location estimates); ● Error handling;

[0040] The NRPPa protocol is between the LMF 65 and the NG-RAN node 70. In the case of a split gNB architecture, the NRPPa protocol is terminated in the gNB-CU and the F1 interface is used to support the exchange of positioning information between the gNB-DU and gNB-CU. There are two types of NRPPa procedures: ● UE-related procedures, i.e., transfer of information for a specific UE, including procedures supporting positioning information transfer; ● Non-UE related procedures, i.e., transfer of information applicable to NG-RAN nodes and associated TRPs, including procedures supporting OTDOA information transfer, assistance information transfer, TRP information transfer, and measurement information transfer functions.

[0041] The RRC protocol for NR is terminated between the gNB and the UE. It provides transport for LPP messages over the NR-Uu interface. Additionally, it supports the transfer of measurements that can be used for positioning purposes. The RRC protocol for NR is also used to configure the UE with a Sounding Reference Signal (SRS) for SRS transmission in RRC_CONNECTED and RRC_INACTIVE to support NG-RAN measurements for NR positioning and configuration for DL-PRS measurements in the UE.

[0042] A number of positioning-related reports are provided by at least one positioning-related report generating entity to the position generating entity. In this specification, a typical positioning-related report may include at least one of the following: ● ToA of DL or UL signal, ● For example, DL reference signal time difference (DL RSTD) and UL relative arrival time (T UL-RTOA ) TDoA of DL or UL signals, ● Timing Advance (T ADV ), ● DL or UL angle of departure (AoD), ● DL or UL angle of arrival (AoA), ● Reference signal received power (RSRP), such as DL-Positioning Reference Signal-Reference Signal Received Power (DL-PRS-RSRP) and UL-Sounding Reference Signal-Reference Signal Received Power (UL SRS-RSRP). - Reference signal received path power, for example DL-PRS-Reference Signal Received Path Power (DL-PRS-RSRPP) and UL-SRS-Reference Signal Received Path Power (UL-SRS-RSRPP); ● Cell ID and TRP related information (e.g., Reference Signal (RS) resource and / or resource set ID); ● Carrier phase difference, and / or ● Round Trip Time (RTT) measurement obtained by combining the gNB Rx-Tx time difference and the UE Rx-Tx time difference.

[0043] Although certain embodiments described below relate to timing-based reports, it will be apparent to those skilled in the art that the present teachings are not limited to timing-based reports. Rather, the methods and techniques disclosed herein may be applied to any type of positioning-related report, such as received power measurements or angle measurements, for example.

[0044] According to certain embodiments, two broad positioning scenarios are considered in the examples described below. In the first positioning scenario, which may be referred to as a network-based scenario, it is assumed that positioning-related reports are generated by the UE, the BS, or the TRP. These positioning-related reports are reported to a centralized node in the network to determine the UE's location. For example, according to certain embodiments, the network configures the UE to transmit an uplink SRS and configures two or more TRPs to receive SRS signals. Each of the TRPs processes the received signals to generate reports that can be used by the network to determine the UE's location. As another example, according to certain embodiments, the UE receives downlink PRSs from a set of TRPs. The UE processes these received signals to generate reports that can be used by the network to determine the UE's location.

[0045] In a second positioning scenario, which may be referred to as a UE-based scenario, positioning-related reports are generated by the UE. These positioning-related reports are further utilized by the UE to determine its own position. For example, according to one embodiment, the UE receives DL PRS from a set of TRPs. The UE processes these received signals to generate reports that can be further used by the UE to determine its own position.

[0046] Current signal processing techniques are typically applied by a UE, BS, or TRP to generate positioning-related reports in operating environments with LoS links. In certain embodiments described below, ToA is used as the primary example. Using the known speed of radio waves, a ToA estimate can be converted into a 3D distance estimate between a transmitter / transmitter / transmitter (TX) node and a receiver / receiver / receiver (RX) node. However, the methods, systems, and embodiments described herein are not limited to timing-based reports. Rather, the methods, systems, and embodiments are applicable to any other positioning-related reports, such as received power measurements or angle measurements.

[0047] As used herein, the term "position generating entity" refers to an entity or node responsible for performing positioning operations for a target UE. Note that the term "positioning-related report" is used, but is intended to cover both the first case where the positioning-related report generating entity is different from the position generating entity, and the second case where the positioning-related report generating entity is also the position generating entity.

[0048] For the first case, a positioning-related report containing measurements is explicitly formulated and sent from the measuring entity to the position generating entity: - In the case of network-based positioning, the position generating entity typically resides within the LMF. In the case of network-based positioning, the positioning-related report generation entity may be a BS or a TRP. For example, the network may configure the UE to transmit UL SRS and configure two or more TRPs to receive SRS signals. Each of the TRPs processes the received signals to generate reports that can be used by the network to determine the UE position. In the case of UE-assisted positioning, the positioning-related report generation entity may be the UE. For example, the UE receives DL PRS from a set of TRPs. The UE processes these received signals to generate a report that can be used by the network to determine the UE position.

[0049] For the second case, it is not necessary that a positioning-related report containing measurements is sent from one entity to another, and it is up to the implementation how the notion of a positioning-related report is realized (implicitly or explicitly): In the case of UE-based location, such positioning related reports are generated by the UE and are further used by said UE to determine its own location.

[0050] According to an embodiment described herein, the number of positioning-related reports provided to the position generation entity is referred to as a first set of positioning-related reports.

[0051] 5 illustrates an exemplary method 100 performed by a position generation entity, according to an embodiment. As shown in FIG. 5, the position generation entity may perform one or more of the following steps: Step 102 - Perform a positioning operation using the first set of positioning related reports to obtain an initial UE position estimate. Step 104 - Compute a suitability score of the multiple positioning related reports with respect to the initial UE position estimate. ● Step 106 - Obtain a second set of positioning related reports by including positioning related reports with a relevance score better than a relevance threshold, and obtain a third set of positioning related reports by including positioning related reports with a relevance score worse than a relevance threshold. The second set of positioning related reports may partially or completely overlap with the first set of positioning related reports. The third set of positioning related reports may or may not be an empty set and does not overlap with the second set. Step 108 - Using the second set of positioning related reports, perform a positioning operation to obtain a final UE position estimate. Step 110 - Using the final UE position estimate, obtain a new target positioning-related report label for the positioning-related report in the third set of positioning-related reports. ● Step 112 - Providing a notification of under-performance to the positioning-related report generation entity(ies) and providing a new target positioning-related report label for the positioning-related report in the third set of positioning-related reports to the positioning-related training data collection entity.

[0052] According to certain other embodiments, certain steps may be performed iteratively. Figure 6 illustrates an exemplary iterative method performed by the location generation entity 200, according to one embodiment. As shown in Figure 6, the location generation entity may perform the following steps: Step 202 - Perform a positioning operation to obtain an initial UE position estimate using the first set of positioning related reports. Step 204 - Compute a suitability score of the multiple positioning related reports with respect to the initial UE position estimate. ● STEP 206 - Obtain a second set of positioning related reports by including positioning related reports with a relevance score better than a relevance threshold, and obtain a third set of positioning related reports by including positioning related reports with a relevance score worse than a relevance threshold. The second set of positioning related reports may partially or completely overlap with the first set of positioning related reports. The third set of positioning related reports may or may not be an empty set and does not overlap with the second set. Step 208 - Determine whether the second set is less than the first set. If it is determined in step 208 that the second set of positioning related reports obtained in step 206 is smaller than the first set of positioning related reports, the method proceeds to step 210 . ● Step 210 - The first set of positioning related reports is replaced with the second set of positioning related reports, after which the method returns to steps 202 and 204. In particular, the second set of positioning related reports is used to obtain a modified third set of positioning related reports in step 206. However, if in step 208 it is determined that the second set of positioning related reports is not smaller than (or is the same as) the first set of positioning related reports, the method proceeds to step 212 . Step 212 - Set the final UE position estimate to the initial UE position estimate determined in step 202. Step 214 - Using the final UE position estimate, obtain a new target positioning related report label for the positioning related report in the third set of positioning related reports. ● Step 216 - Providing notification of the performance shortfall to the positioning-related report generation entity(ies) and providing new target positioning-related report labels for the positioning-related reports in the third set of positioning-related reports to the positioning-related training data collection entity.

[0053] In a particular exemplary embodiment, the third set of positioning-related reports is initialized as an empty set.

[0054] In certain embodiments, a third set of positioning-related reports is accumulated during the iterative process described above. For example, if the third set of positioning-related reports already includes positioning-related reports #2 and #4 from a previous iteration, and positioning-related report #7 is identified as below the suitability threshold during the current iteration, the third set of positioning-related reports is updated to include positioning-related reports #2, #4, and #7.

[0055] Here, ToA is used as the primary example. With the known speed of the radio waves, the ToA estimate can be equivalently converted into a 3D distance estimate between the TX and RX nodes. However, it will be apparent to those skilled in the art that the methods and techniques described herein can also be applied to any other positioning-related report.

[0056] Without loss of generality, unless explicitly stated, ToA estimates are used as an example to represent various timing-based metrics, including relative timing (e.g., UL RTOA), timing difference (e.g., DL RSTD), gNB Rx-Tx time difference, and UE Rx-Tx time difference. It is known that in practical deployments, clocks are not precisely synchronized between TRPs and UEs and / or between TRPs. For this reason, ToA is often converted to timing metrics in other formats to combat implementation imperfections. However, it will be apparent to those skilled in the art that the same methods and techniques disclosed herein can be easily modified to apply to timing-based metrics in general.

[0057] The steps of Figures 5 and 6 are described in more detail below.

[0058] Step 102 / 202—Perform a positioning operation using the first set of positioning-related reports to obtain an initial UE position estimate. The process of combining positioning reports, e.g., ToAs, to determine the UE location using distances between nodes (i.e., instead of angles) is called trilateration. Distances to at least three known, non-collinear network nodes are sufficient to determine an accurate 2D UE location.

[0059] 7 illustrates an example 300 of idealized trilateration in 2D space, according to an embodiment. As shown in FIG. 7, if the positioning-related reports are accurate, each TRP 302A, 302B, and 302C is at the center of a circle, and the intersection of the circles identifies the location of the UE 304. In 3D space, each TRP 302A, 302B, and 302C is at the center of a sphere, and at least four non-coplanar, known network node locations are required to perform trilateration.

[0060] However, in real-world scenarios, the estimated distance to a known location may be inaccurate, resulting in an incomplete trilateration. Figure 8 shows one such example 400 of trilateration with inaccurate positioning reports, according to an embodiment. As shown in Figure 8, each TRP 402A, 402B, and 402C is at the center of a respective circle. However, while the location of the UE 404 would ideally be at the intersection, the actual location of the UE 404 is slightly offset and not at the circle intersection.

[0061] A non-limiting example implementation of this positioning step includes: (a) providing a UE position estimate; TIFF2026506628000005.tif7143 and TRP, p TRP Distance between (i) TIFF2026506628000006.tif7143, and (b) the reported distances between UE 404 and TRPs 402A, 402B, and 402C. The goal is to find the UE position estimate that minimizes the sum of losses between the TIFF2026506628000008.tif11143 where, TIFF2026506628000009.tif5143 can be an L1 or L2 loss function, and i is the index of the positioning report in the set.

[0062] The L1 loss function, also known as Least Absolute Deviations (LAD), is a function thati and predicted value TIFF2026506628000010.tif6143 is the sum of all absolute differences between TIFF2026506628000011.tif13143

[0063] The L2 loss function, also known as least squares error (LS), is used to find the true value y i and predicted value TIFF2026506628000012.tif7143 is the sum of all squared differences between TIFF2026506628000013.tif12143

[0064] In another particular embodiment, a non-limiting example implementation of this positioning step is to compensate for potential UE timing error or jitter in the estimated ToA. This is achieved by adding a UE timing error related term to be searched jointly with the hypothesized UE location: TIFF2026506628000014.tif11143

[0065] In yet another particular embodiment, a non-limiting example implementation of this positioning step is to assume that the reported timing measurements are for TDoA instead of ToA, where TDoA(i,r) is obtained from the measurements and c×TDoA(i,r) is TIFF2026506628000015.tif6143, where c is the speed of light. When using such TDoA, the TRPs are assumed to be synchronized. The advantage of TDoA is that the clock offset (or clock drift) at the UE is canceled by measuring the difference between (a) the ToA between TRP i and the UE and (b) the ToA between a reference TRP r and the UE, where i ≠ r. The UE's location can then be estimated by considering (a) the distance difference between the UE positioning and a known TRP with index i, and (b) the distance difference between the UE positioning and a reference TRP with index r. TIFF2026506628000016.tif10143

[0066] Using the various types of loss functions provided above, an optimizer (or optimization algorithm, e.g., gradient descent) can be used to find the best UE location estimate that achieves a minimum of the loss function. Note that neural networks are typically not involved in this step, and thus the above loss functions are not to be confused with loss functions used to train neural networks.

[0067] Step 104 / 204 - Compute a suitability score for multiple positioning related reports with respect to the initial UE position estimate. The fitness score of a positioning related report is based on the estimated UE location. TIFF2026506628000017.tif7143 and location knowledge of known network nodes. Thus, using the UE position estimates obtained in steps 102 and 202, a relevance score for the positioning related report is computed in steps 104 and 204, respectively.

[0068] In certain embodiments, non-limiting examples of such functions include: (a) a UE position estimate; TIFF2026506628000018.tif7143 and known locations of TRPs TRP Distance between (i) TIFF2026506628000019.tif6143 and (b) the reported distance between the UE and the TRP. The squared difference between TIFF2026506628000020.tif6143 is: TIFF2026506628000021.tif8143

[0069] In another particular embodiment, a non-limiting example of the function is: (a) a UE position estimate; TIFF2026506628000022.tif7143 and known locations of TRPs TRP Distance between (i) TIFF2026506628000023.tif7143 and (b) the reported distance between the UE and the above TRP. The absolute difference between TIFF2026506628000024.tif6143 is: TIFF2026506628000025.tif7143

[0070] UE timing error estimate If TIFF2026506628000026.tif6143 is available, yet another non-limiting exemplary embodiment of the above function is: (a) UE position estimate TIFF2026506628000027.tif7143 and known locations of TRPs TRP Distance between (i) TIFF2026506628000028.tif7143 and (b) the reported distance between the UE and the above TRP. tif6143 and the sum of the UE timing error related estimates: TIFF2026506628000030.tif7143 or TIFF2026506628000031.tif6143

[0071] If the reported timing measurement is for a TDoA instead of a ToA, a further non-limiting exemplary embodiment of the above function is the square or absolute value of the distance difference between (a) the UE positioning and a known TRP with index i, and (b) the UE positioning and a reference TRP with index r: TIFF2026506628000032.tif9143 or It should be noted that using the known speed of radio waves, the ToA estimate can be equivalently converted into a 3D distance estimate between the TX and RX nodes. It will be apparent to those skilled in the art that a compatibility score can also be calculated based on the ToA.

[0072] In yet another particular embodiment, a non-limiting example of the function includes computing a relevance score according to any of the above and ranking the relevance scores from lowest to highest, where the ranking order of the positioning-related reports is defined as the final relevance score of the positioning-related reports.

[0073] Using these non-limiting and exemplary fitness scores, a smaller fitness score indicates a lower UE position estimate. Shows greater compatibility with TIFF2026506628000034.tif7143.

[0074] Step 106 / 206—Obtaining a second set of positioning-related reports by including positioning-related reports with a relevance score better than a relevance threshold, and obtaining a third set of positioning-related reports by including positioning-related reports with a relevance score worse than a relevance threshold. According to one embodiment, in steps 106 and 206, a second set of positioning-related reports is constructed by including positioning-related reports from the first set of positioning-related reports that have a relevance score better than a relevance threshold.

[0075] In a non-limiting example embodiment of the relevance scoring function provided above, a positioning-related report is included in the second set of positioning-related reports if its relevance score CS(i) is less than a threshold value.

[0076] According to certain other embodiments, in steps 106 and 206, the second set of positioning related reports includes a UE position estimate. TIFF2026506628000035.tif7143 and the M most relevant positioning related reports. As disclosed in steps 104 and 204, the relevance threshold is a ranking of the relevance scores.

[0077] In a further exemplary embodiment of steps 106 and 206, the second set of positioning related reports is derived from the first set of positioning related reports by The relevance threshold is constructed by filtering out the N positioning related reports that have the lowest relevance to TIFF2026506628000036.tif7143. As disclosed in steps 104 and 204, the relevance threshold is a ranking of the relevance scores.

[0078] In yet another exemplary embodiment of steps 106 and 206, a second set of positioning-related reports is constructed by obtaining M positioning-related reports that have associated quality estimates (or confidence levels) better than a certain threshold while also satisfying conformance requirements. For timing-related metrics, the quality of the timing values ​​may be reported as the uncertainty of the timing values ​​in meters, where timing values ​​with better quality correspond to smaller uncertainty values.

[0079] Positioning-related reports from the first set of positioning-related reports that have a relevance score worse than a relevance threshold are added to a third set of positioning-related reports.

[0080] In a non-limiting example embodiment of the suitability scoring function provided above, a positioning-related report is added to a third set of positioning-related reports if its suitability score CS(i) is greater than a threshold. In another example embodiment of steps 106 and 206, the third set of positioning-related reports is added to a third set of positioning-related reports if its suitability score CS(i) is greater than a threshold. TIFF2026506628000037.tif7143 is constructed by adding the N positioning related reports that have the lowest matches with TIFF2026506628000037.tif7143. In a further exemplary embodiment of steps 106 and 206, any positioning related reports that are in the first set of positioning related reports but not in the second set of positioning related reports are added to a third set of positioning related reports.

[0081] The relevance score threshold may be determined from the distribution of relevance scores.

[0082] The suitability score threshold may be determined from the performance of the improved positioning algorithm disclosed herein using different suitability score thresholds.

[0083] The suitability score threshold may be set to different values ​​for different wireless environments.

[0084] The fitness score threshold may be set to different values ​​for different iterations when certain steps of the main embodiment are performed iteratively.

[0085] The relevance score threshold may be set to a different value when the positioning-related reports are provided by different approaches, for example, when the positioning-related reports are provided by an advanced ML model, the relevance score threshold may be set to a different value than when the positioning-related reports are provided by a traditional signal processing algorithm.

[0086] The relevance score threshold may be set to a different value when the positioning-related reports are provided by different advanced ML models, for example, the relevance score threshold may be set to a different value when the positioning-related reports are provided by a centralized ML model than when the positioning-related reports are provided by a distributed ML model.

[0087] Final execution of steps 108 and 202—performing positioning operations to obtain a final UE position estimate using the second set of positioning-related reports The basic positioning calculation method is the same as that used in the initial execution of steps 102 and 202, except that a second set of positioning-related reports is used as input in the second iteration of steps 108 and 202, respectively.

[0088] Step 110 of FIG. 5 / Step 214 of FIG. 6 - Using the final UE position estimate, obtain a new target positioning-related report label for the positioning-related report in the third set of positioning-related reports. Assume that the positioning related report with index i is included in the third set of positioning related reports. Given TIFF2026506628000038.tif7143, a new target positioning related report contains at least the final UE position estimate and the known position p of the i-th TRP that receives or transmits at least one radio signal for positioning. TRP (i) is calculated based on the distance between: TIFF2026506628000039.tif6143

[0089] As one non-limiting example for an ML model that generates target direct path ToAs, new target labels are computed as follows: TIFF2026506628000040.tif10143Here, c is the speed of the wireless signal.

[0090] UE timing error related estimates If TIFF2026506628000041.tif6143 is available, the new target label is calculated as follows: TIFF2026506628000042.tif10143

[0091] Alternatively, if the ML model generates an output for TDoA(s) between TRP i and TRP r, the new target label is computed as TIFF2026506628000043.tif11143Here, TRP r is the reference TRP.

[0092] Step 112 / Step 216 of FIG. 5 of FIG. 6—Providing notification of performance shortfall to positioning-related report generation entity(ies) and providing new target positioning-related report labels to positioning-related training data collection entity for positioning-related reports in the third set of positioning-related reports. In certain embodiments, the position generating entity may provide an all-clear signal to the positioning-related report generating entity if the positioning-related report generated by the positioning-related report generating entity is not included in the third set of positioning-related reports.

[0093] In an alternative particular embodiment, the position generation entity does not provide signaling to the positioning related report generation entity if the positioning related report generated by the above positioning related report generation entity is not included in the third set of positioning related reports.

[0094] In this exemplary embodiment, a predetermined timeout period is utilized to allow the positioning-related report generating entity to discard its received radio signals and / or its pre-processed data. - The above-mentioned predetermined timeout period may be set by the network for the position generating entity and / or the positioning related report generating entity. - The above-mentioned predetermined timeout period may be set by the position generating entity to the positioning-related report generating entity. The above predetermined timeout period may be described in the system operation specification.

[0095] <General Architecture> In general, a new target positioning-related report for a positioning-related report in the third set may be provided to improve subsequent report label estimations of the third set. The new target positioning-related report is sent from node B to node C if the positioning-related training data collection entity (node ​​C) is different from the position generation entity (node ​​B). Otherwise (i.e., the same node fulfills the functions of node B and node C), the new target positioning-related report is stored directly by such node.

[0096] The training data collection entity may provide an updated training data set to train (or retrain, or fine-tune) an updated AI / ML model for the positioning-related report generation entity (Node A). The goal is that Node A can use the updated AI / ML model to generate more accurate report label estimates, thereby improving the location estimation accuracy of the target UE.

[0097] 9 illustrates an exemplary high-level architecture 500 in which a position generation entity (Node B) 502 provides positioning-related labels to a positioning-related training data collection entity (Node C) 504, according to one embodiment. As shown, Node C 504 has a model update function and may provide updated AI / ML models to a positioning-related report generation entity (Node A) 506. While three entities are shown in FIG. 9 as Node A, Node B, and Node C, it will be appreciated that two or more entities may be realized by the same functional node.

[0098] 10 illustrates another exemplary high-level architecture 600, according to one embodiment. Similar to FIG. 9, architecture 600 includes node A 506, node B 502, and node C 504. However, in the illustrated example, the model update functionality is realized by node D 608, which is separate from the positioning-related training data collection entity (node ​​C) 504, according to one embodiment.

[0099] In the following description, for simplicity, we will assume the simpler diagram of FIG. 9, with the understanding that the model update function may be implemented by a separate node, as shown in FIG.

[0100] The basic functionality of a node in at least one particular embodiment is described below: Node A 506 (positioning-related report generating entity) performs AI / ML model inference to generate positioning-related reports. Typically, the same Node A 506 also performs the function of measuring wireless signals to obtain input data for model inference. Alternatively, a separate node (e.g., TRP, RP, gNB-DU) performs the function of measuring wireless signals to obtain input data for model inference and then transmits the obtained input data to Node A 508 (e.g., gNB-CU) to perform model inference. Node B 502 (location generation entity) is responsible for computing the estimated location of the target UE. Node C 504 (positioning related training data collection entity) processes and stores information to build training datasets for the AI / ML models in Node A 506. Node D 602 ​​(positioning-related model update entity) uses the stored training dataset to train an updated AI / ML model, which can be used by Node A 506 to generate positioning-related reports. As mentioned above, the functionality of Node D 602 ​​may be embedded as a sub-function in Node C 504 or may be fulfilled by a node separate from Node C 504.

[0101] Using the example of ToA as the measurement report sent from Node A 506 to Node B 502, if a new positioning-related report label (ToA) is generated by Node B 502 for the TRP in the third set for measurements performed at time T1, the new label Yj (T1) is sent to node C for TRP-j with a timestamp of T1. Node C 504 also receives from node A 506 a channel measurement X associated with time T1. j (T1) is obtained. j (T1), Y j (T1)} pair together create a training data sample for TRP-j, and the pair is stored by node C 504.

[0102] If node A 506 is a network node, then the UL channel measurement X j (t) is made by the TRP based on the UL signal (e.g., SRS) transmitted by the target UE, and the measurement type corresponds to that required as input for the AI / ML model in Node A 506 (e.g., channel impulse response (CIR), or RSRP, or RSRPP). The AI / ML model uses the UL channel measurement X of a single TRP. j (t) as input, or the AI / ML model can use multiple UL channel measurements X from multiple TRPs. j (t) can be taken as input.

[0103] If node A 506 is the UE, then the DL channel measurement X j (t) is made by the UE based on the DL signal (e.g., PRS) transmitted by the TRP, and the measurement type corresponds to that required as input for the AI / ML model in the UE (e.g., channel impulse response (CIR), or RSRP, or RSRPP). The AI / ML model is based on the DL channel measurement X of a single TRP. j (t) as input, or the AI / ML model can use multiple DL channel measurements X corresponding to multiple TRPs. j (t) can be taken as input.

[0104] Various embodiments of the high-level architecture of FIG. 9 are described in more detail below.

[0105] <Node A is a gNB and Node B is a location server (e.g., LMF)> 11 illustrates an example architecture 700 in which the location method is NG-RAN node-assisted and LMF-based. Specifically, in FIG. 11, an NG-RAN node (i.e., gNB) functions as Node A 706 and provides positioning-related reports to a location server (e.g., LMF), which in this example is Node B 702. The LMF operates to compute an estimated UE location. For a given UE, the LMF may receive multiple positioning-related reports associated with multiple TRPs. One or more gNBs may send positioning-related reports to the LMF via interface NRPPa.

[0106] <Node A is a gNB and Node B is also a gNB> 12 shows an example architecture 800 of a single gNB operating as both a positioning-related report generation entity (Node A) 806 for providing positioning-related labels and as a position generation entity (Node B) 802. Additionally or alternatively, the single gNB functions as both a position generation entity (Node B) 802 and a positioning-related training data collection entity (Node C) 804.

[0107] This is possible because a gNB can be connected to multiple TRPs. In the case of Release 17, a gNB can have up to 65,535 TRPs. A single gNB may therefore perform UL measurements of a UE from multiple TRPs, and a positioning-related report is generated for each TRP. The gNB can use the multiple positioning-related reports to calculate the UE position, thus fulfilling the function of a Node B.

[0108] When a split architecture is used in a gNB, the gNB-DU can operate as Node A, while the gNB-CU can operate as Node B. Positioning-related reports generated for multiple TRPs can be sent from the gNB-DU to the gNB-CU via the F1 interface. FIG. 13 shows that a single gNB operates as both a positioning-related report generation entity (Node A) 906 and a positioning generation entity (Node B) 902, and the split architecture is used in the gNB.

[0109] In yet another embodiment, if the TRP of the gNB has baseband processing capabilities, one (or more) TRP operates as Node A for generating positioning-related reports, while other higher-layer stream components of the gNB (e.g., gNB-DU or gNB-CU) can operate as Node B for determining the UE position.

[0110] <The NG-RAN operates as a positioning-related report generation entity> According to an embodiment, the positioning-related report generation entity executes the following steps to provide at least one positioning-related report to the position generation entity, and when instructed by the position generation entity, compiles new training data based on the already received radio signals. In an embodiment, the positioning-related report generation entity (Node A) exists on the network side. Its function can be realized by various types of network nodes, such as a base station, gNB, or TRP, an RP including only a receiving point (RP) for UL-SRS:

[0111] ● Step 1 - Receive at least one radio signal in the uplink. ● Step 2 - Process the at least one received radio signal to generate at least one positioning-related report associated with at least one ML model. ● Step 3 - Signal the at least one positioning-related report to the position generation entity. Step 4 - Receive signaling from the location generation entity. - Discarding said at least one received radio signal or pre-processed data thereof if no signaling is received from said location generation entity after a predetermined period of time. Step 5 - Compile new training data based on said received signaling from said position generation entity and forward said data to a positioning related training data collection entity. ● If signaling from the position generation entity indicates insufficient performance of the at least one positioning-related report having corresponding at least one new target positioning-related report label, combine the at least one received radio signal or its preprocessed data with the at least one new target positioning-related report label as at least one new training sample, and add the at least one new training sample to the training dataset. otherwise, discarding said at least one received radio signal or its pre-processed data.

[0112] To provide further details of certain exemplary embodiments, ToA is the primary example of a positioning-related report. Using the known speed of the radio waves, the ToA estimate can be equivalently converted into a 3D distance estimate between the TX and RX nodes. However, it will be apparent to one skilled in the art that the present teachings can also be applied to any other positioning-related report (e.g., other timing-based reports, or received power-based reports, or angle-based reports).

[0113] For other timing-based reports, the timing estimates may be represented in other formats, for example where the positioning-related report generating entity (node ​​A) is a network-side node. ● A typical report is UL relative arrival time (T UL-RTOA ) UL relative arrival time (T UL-RTOA) is the beginning of subframe i, which contains the SRS received at reception point (RP) j. Another typical report is the gNB Rx-Tx time difference. gNB-RX -T gNB-TX Define T gNB-RX is the transmission / reception point (TRP) reception timing of uplink subframe #i containing the SRS associated with the UE, and is defined by the first detected path. gNB-TX is the TRP transmission timing of the downlink subframe #j that is closest in time to the subframe #i received from the UE.

[0114] Additionally, while only one element (i.e., ToA) is used as a representative example to illustrate the methodology, it is understood that the main positioning-related report may include multiple elements (e.g., two or more of the following types) derived from measurements of UL radio signals: ● Timing information of the received radio signal (e.g., ToA, UL TDoA, gNB Rx-Tx time difference of the UL radio signal at the network node). ● Reference signal received power (e.g., UL SRS reference signal received power (UL SRS-RSRP)) ● Reference signal receive path power (e.g., UL SRS reference signal receive path power (UL SRS-RSRPP)) ● UL Angle of Arrival (AoA) (Azimuth and / or Elevation) ● LoS / NLoS information ● A quality estimate for one or more of the measurements above.

[0115] Step 1 - Receive at least one radio signal on the uplink. The signal receiving entity receives at least UL radio signals, which are used in step 2 to generate at least positioning related reports.

[0116] For NG-RAN node-assisted positioning, the signal receiving entity may be a BS, a gNB, a TRP, or a Reception Point (RP). For example, the network may configure the UE to transmit an UL SRS and configure two or more TRPs to receive the SRS signals. Each of the TRPs processes the received signals to generate a report that can be used by the network to determine the UE's location.

[0117] The radio signal on the uplink is typically an SRS, which may further be of a type specifically designed for positioning purposes (e.g., a positioning SRS).

[0118] Step 2 - Processing the at least one received wireless signal to generate at least one positioning-related report using at least one ML model. The positioning-related report generating entity (node ​​A) uses the ML model to generate at least a positioning-related report based on the received radio signals. The positioning-related report generating entity resides on the network side. It may or may not be realized by the same node as the signal receiving entity, depending on the range of functions fulfilled by the network node. ● Examples of the same network node are signal receiving entities and positioning related report generating entities: base stations, gNBs. Examples of different network nodes for signal receiving entity and positioning related report generating entity: o The TRP or RP is the signal receiving entity and the gNB-DU is the positioning-related report generating entity.

[0119] Using the case of NG-RAN node-assisted positioning as a non-limiting example, the TRP receives SRS transmitted from the UE on different frequencies as follows: R[k] = H[k] S[k] + N[k] where: ● S[k] is the SRS for frequency index k. ● H[k] is the frequency domain channel response for frequency index k. ● N[k] denotes the noise and / or interference for frequency index k.

[0120] The ML model may take received signals at multiple frequencies R[k] and corresponding SRS signals S[k] as inputs and generate ToA estimates as outputs.

[0121] However, in modern broadband communication systems, the size of the number of inputs for such models can become prohibitively large in ML models, requiring high computational complexity. Alternatively, ML models can be constructed to take preprocessed data as input instead.

[0122] As a non-limiting example, a frequency domain channel response (FD CR) may be estimated from received SRS signals at different frequencies: TIFF2026506628000044.tif6143 where S * [k] denotes the complex conjugate of the SRS signal S[k]. The time-domain channel impulse response (TD CIR) may be estimated by passing the frequency-domain channel response through an inverse fast Fourier transform (FFT), resulting in a series of n with time-domain tap indexes. TIFF2026506628000045.tif7143 is obtained. Because wireless signal strength attenuates with travel distance, the time-domain channel impulse response typically has a meaningful response only for a limited number of taps. That is, the time-domain channel impulse response may be shortened to a shorter length. Such a shortened time-domain channel impulse response estimate is a non-limiting example of preprocessed data of at least one received wireless signal.

[0123] Using such properly designed preprocessed data as input, an ML model can achieve similar or better performance at lower computational complexity than an ML model that takes at least one received radio signal directly as input.

[0124] Step 3 - Signaling said at least one positioning related report to a position generating entity. At least one positioning related report generated by node A may be signaled to a position generating entity (node ​​B) using existing system protocols or procedures.

[0125] Positioning-related reports mainly carry UL radio signal measurement results (e.g., ToA estimates generated by ML models). In addition, other auxiliary information may be carried as part of the report as well. Such auxiliary information provides context information for the measurement results rather than the measurement results directly. The auxiliary information may include the following information for the measurement results: timestamp, cell ID, TRP ID, ARP (Antenna Reference Point) ID, antenna beam information, received SRS information (including SRS resource ID, SRS configuration), etc.

[0126] When transmitting at least one positioning-related report from a positioning-related report generating entity (node ​​A) to a position generating entity (node ​​B), the report may traverse one or more other intermediate network nodes in between.

[0127] In one embodiment, the report is encapsulated and sent as is from node A to node B without modification by intermediate nodes (if any).

[0128] Alternatively, the reports may be repackaged by an intermediate node on the way from Node A to Node B. For example, if a gNB uses a split architecture and Node A is realized by one or more gNB-DUs, the positioning-related reports generated by the one or more gNB-DUs are transmitted to the gNB-CU (i.e., an intermediate node) via the F1 interface. The gNB-CU then collects the positioning-related reports into a measurement report according to the message format of the NRPPa interface. The measurement report is then transmitted from the gNB-CU to the LMF via the NRPPa interface, where the LMF is the position generating entity (Node B).

[0129] Step 4 - Receive signaling from the location generation entity. As mentioned above, the location generating entity (Node B) receives at least one positioning-related report from the positioning-related report generating entity (Node A) and attempts to determine the location of the target UE using the positioning-related report(s). In connection with the step of determining the location of the target UE, the location generating entity (Node B) may further determine the quality of the positioning-related report(s) and generate signaling related to the quality. The quality signaling may be sent to the positioning-related report generating entity (Node A), and / or the training data collection entity (Node C), and / or the model monitoring entity. The training data collection entity (Node C) is preferably a network-side server.

[0130] The signaling can take two values ​​for the report quality: ● Signaling value = "poor quality report". If a positioning-related report is determined to have an unacceptably large estimation error, the position generating entity (node ​​B) may mark it as a "poor quality report" and send such signaling to other nodes. Such a quality estimation is an indication that the ML model, which is being used to generate at least one positioning-related report in node A, needs improvement. o If the signaling value = "poor quality report", Node B may further generate a new target positioning related report label for the associated report and send the new label to Node C. ● Signaling value = "good quality report". If the signaling from the position generation entity indicates "good quality report", this means that the positioning related reports have a small estimation error and the ML model at node A is working properly.

[0131] Signaling is a judgment about the quality of a given positioning related report, and such signaling may be continuously collected and observed by a model monitoring entity to determine whether and when to trigger a model update. In a preferred embodiment, signaling is continuously collected and observed for a duration T m A moving monitoring window is defined. If the number of signalings indicating poor quality ("poor quality reports") within the moving window exceeds a threshold, the model monitoring entity may trigger an action to modify the associated ML model. The action taken may be one or more of the following: a) Deactivation, i.e., the existing ML model should be stopped from generating positioning-related reports. After deactivation, a fallback method (e.g., a conventional non-AI / ML method) can be used for determining the UE position instead. b) Model Update, i.e., the existing ML model should be updated so that a new and improved model can be used for future generation of positioning-related reports. The new model can be obtained by retraining or fine-tuning the model with a new dataset, or by model distribution from another entity.

[0132] In addition to the signaling to node C, signaling also needs to be sent from node B to node A. The purpose of the signaling to node A is to retrieve from node A the received wireless signal (and / or its pre-processed data) associated with the "poor quality report." The retrieved signal and / or data corresponds to the ML model input and is then transmitted from node A to node C.

[0133] If no signaling is received from the position generating entity (node ​​B) after a predetermined timeout period, the positioning-related report generating entity (node ​​A) may discard the at least one received radio signal and / or its pre-processed data. - The above-mentioned predetermined timeout period may be set by the network for the position generating entity and / or the positioning related report generating entity. - The above-mentioned predetermined timeout period may be set by the position generating entity to the positioning-related report generating entity. The above predetermined timeout period may be described in the system operation specification.

[0134] Step 5 - Compile new training data based on the received signaling from the position generation entity and forward said data to a positioning related training data collection entity. If signaling from the position generating entity (Node B) indicates poor performance of the at least one positioning-related report (i.e., a “poor quality report”) and provides at least one corresponding new target positioning-related report label, the positioning-related training data collecting entity (Node C) may combine Info#X (i.e., the at least one received radio signal and / or its pre-processed data) with Info#Y (i.e., the at least one new target positioning-related report label) as at least one new training sample and add the at least one new training sample to a training dataset. Node C (training data collecting entity) obtains Info#X from Node A (positioning-related report generating entity), and Node C obtains Info#Y from Node B (position generating entity).

[0135] Using the simplified example of ToA as a measurement report sent from node A to node B, we will now describe the procedure in more concrete terms. If a new positioning related report label (ToA) is generated by node B for TRP-j for measurements performed at time T1, then the new label Y j (T1) is Info#Y, which is sent to node C together with the aiding information {timestamp of T1, TRP-j}. Using this aiding information, node C further receives channel measurement value X from node A. j (T1), where X j (T1) is the measurement value of the wireless signal (and / or its preprocessed data) at time T1 and TRP-j. j (T1), Y j (T1)} pair together create a training data sample for TRP-j, and the pair is stored by node C 504.

[0136] The new target positioning related report label must be accompanied by auxiliary information carried in the positioning related report so that the new label (Info#Y) can be matched with the corresponding sample of Info#X (radio signal reception or its pre-processed data), e.g., a measured radio signal with the correct timestamp, TRP ID, and SRS settings.

[0137] If the signaling from the position generation entity indicates a "good quality report" of the at least one positioning-related report, it means that the positioning-related report has a small estimation error and the ML model in node A is working properly. Therefore, the positioning-related training data collection entity (node ​​C) may not add new training samples to the training dataset from the corresponding received wireless signals and / or their pre-processed data.

[0138] FIG. 14 illustrates and / or relates to steps 1-5 described above. Specifically, FIG. 14 illustrates an exemplary architecture 1000 in which a position generating entity (Node B) provides quality feedback about a positioning-related report to a positioning-related report generating entity (Node A) 1006. For a report determined to be a "poor quality report," Node B 1002 generates and sends Info#Y to a positioning-related training data collecting entity (Node C), while Node A 1006 sends the corresponding Info#X to Node C 1004. Node C 1004 pairs {Info#X, Info#Y} to construct a new training sample and add it to the training dataset. After the model update, a new ML model can be provided to Node A 1006.

[0139] 15 illustrates an example of a communications system 1100 according to some embodiments. In this example, the communications system 1100 includes a telecommunications network 1102 including an access network 1104, such as a radio access network (RAN), and a core network 1106 including one or more core network nodes 1108. The access network 1104 includes one or more access network nodes, such as network nodes 1110a and 1110b (one or more of which may be generally referred to as network nodes 1110), or some other similar 3GPP access node or non-3GPP access point. The network nodes 1110 facilitate direct or indirect connectivity of user equipment (UE), such as connecting UEs 1112a, 1112b, 1112c, and 1112d (one or more of which may be generally referred to as UEs 1112), to the core network 1106 over one or more wireless connections.

[0140] Exemplary wireless communications over wireless connections include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for carrying information without the use of wires, cables, or other material conductors. Moreover, in various embodiments, communications system 1100 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals, whether via wired or wireless connections. Communications system 1100 may include and / or interface with any type of communications, telecommunications, data, cellular, wireless networks, and / or other similar types of systems.

[0141] The UE 1112 may be any of a wide variety of communication devices, including a wireless device, that is positioned, configured, and / or operable to communicate wirelessly with the network node 1110 and other communication devices. Similarly, the network node 1110 is positioned, capable, configured, and / or operable to communicate, directly or indirectly, with the UE 1112 and / or with other network nodes or equipment within the telecommunications network 1102 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as management within the telecommunications network 1102.

[0142] In the illustrated example, the core network 1106 connects the network node 1110 to one or more hosts, such as the host 1116. The connections may be direct or indirect through one or more intermediate networks or devices. In other examples, the network nodes may be directly coupled to the hosts. The core network 1106 includes one or more core network nodes (e.g., the core network node 1108) structured with hardware and software components. The functionality of those components may be substantially similar to that described with respect to the UEs, network nodes, and / or hosts, and thus those descriptions are generally applicable to the corresponding components of the core network node 1108. Exemplary core network nodes include one or more of a Mobile Switching Center (MSC), a Mobility Management Entity (MME), a Home Subscriber Server (HSS), an Access and Mobility Management Function (AMF), a Session Management Function (SMF), an Authentication Server Function (AUSF), a Subscription Identifier Deciphering Function (SIDF), a Unified Data Management (UDM), a Security Edge Protection Proxy (SEPP), a Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0143] Host 1116 may be owned or controlled by, and operated by or for, a service provider other than the operator or provider of access network 1104 and / or telecommunications network 1102. Host 1116 may host a variety of applications to provide one or more services. Examples of such applications include live and pre-recorded audio / video content, data collection services such as acquiring and compiling data about various ambient conditions sensed by multiple UEs, analytics functionality, social media, functionality for controlling or otherwise interacting with remote devices, functionality for alarm and monitoring centers, or any other such functionality performed by a server.

[0144] 15 enables connectivity between UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as a particular standard, including, but not limited to, Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G), a wireless local area network (WLAN) standard, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard (WiFi), and / or any other suitable wireless communication standard, such as Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC), ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standard, such as LoRa and Sigfox.

[0145] In some examples, the telecommunications network 1102 is a cellular network that implements functions standardized by 3GPP. Thus, the telecommunications network 1102 may support network slicing to provide different logical networks to different devices connected to the telecommunications network 1102. For example, the telecommunications network 1102 may provide Ultra-Reliable Low Latency Communications (URLLC) services to some UEs, while providing enhanced Mobile Broadband (eMBB) services to other UEs and / or providing Massive Machine Type Communications (mMTC) / Massive IoT services to additional UEs.

[0146] In some examples, the UE 1112 is configured to transmit and / or receive information without direct human interaction. For example, the UE may be designed to transmit information to the access network 1104 on a predetermined schedule, when triggered by an internal or external event, or in response to a request from the access network 1104. Additionally, the UE may be configured to operate in a single or multi-RAT or multi-standard mode. For example, the UE may be configured and operate in any one or combination of Wi-Fi, NR (New Radio), and LTE, i.e., for Multi-Radio Dual Connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio-Dual Connectivity (EN-DC).

[0147] In the above example, the hub 1114 communicates with the access network 1104 to facilitate indirect communication between one or more UEs (e.g., UEs 1112c and / or 1112d) and a network node (e.g., network node 1110b). In some examples, the hub 1114 may be a controller, a router, a content source, an analytics, or any of the other communication devices described herein with respect to a UE. For example, the hub 1114 may be a broadband router that enables access to the core network 1106 for the UE. As another example, the hub 1114 may be a controller that sends commands or instructions to one or more actuators in the UE. The commands or instructions may be received from the UE or the network node 1110 or may be accepted by executable code, scripts, processes, or other instructions in the hub 1114. As another example, the hub 1114 may be a data collector that acts as a temporary storage for UE data and, in some embodiments, may perform analysis or other processing of that data. As another example, the hub 1114 may be a content source. For example, for UEs that are VR headsets, displays, loudspeakers, or other media delivery devices, the hub 1114 may obtain media or data related to VR assets, video, audio, or other sensory information via a network node, and then provide it to the UE either directly, after performing local processing, and / or adding additional local content. In yet another example, the hub 1114 acts as a proxy server or orchestrator for the UEs, particularly if one or more of the UEs are low-energy IoT devices.

[0148] The hub 1114 may have a constant / permanent or intermittent connection to the network node 1110b. The hub 1114 may also enable different communication schemes and / or schedules between the hub 1114 and UEs (e.g., UEs 1112c and / or 1112d) and between the hub 1114 and the core network 1106. In other examples, the hub 1114 is connected to the core network 1106 and / or one or more UEs via a wired connection. Moreover, the hub 1114 may be configured to connect to an M2M service provider over the access network 1104 and / or to other UEs over a direct connection. In some scenarios, a UE may establish a wireless connection with the network node 1110b while still being connected via the hub 1114 via a wired or wireless connection. In some embodiments, the hub 1114 may be a dedicated hub, i.e., a hub whose primary function is to route communications between UEs and the network node 1110b. In other embodiments, the hub 1114 may be a non-dedicated hub, i.e., a device that is operable to route communications between the UE and the network node 1110b, but that is also operable as a communication origination and / or termination point for any data channel.

[0149] 16 illustrates a UE 1200 according to some embodiments. As used herein, a UE refers to a device capable of, configured, arranged, and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smartphone, a mobile phone, a cell phone, a Voice over IP (VoIP) phone, a wireless local loop phone, a desktop computer, a personal digital assistant (PDA), a wireless camera, a game console or device, a music storage device, a playback appliance, a wearable terminal device, a wireless endpoint, a mobile station, a tablet, a laptop, a laptop embedded equipment (LEE), a laptop mounted equipment (LME), a smart device, a wireless customer premises equipment (CPE), a vehicle, an in-vehicle or vehicle embedded / integrated wireless device, etc. Other examples include a Narrowband Internet of Things (NB-IoT) UE, a Machine Type Communication (MTC) UE, and / or any UE identified by the 3rd Generation Partnership Project (3GPP), including an enhanced MTC (eMTC) UE.

[0150] A UE may support device-to-device (D2D) communications, for example, by implementing 3GPP standards for sidelink communications, dedicated short-range communications (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human being who owns and / or operates the associated device. Instead, a UE may represent a device (e.g., a smart sprinkler controller) that is intended for sale to or operation by a human user, but that may not, at least initially, be associated with a particular human user. Alternatively, a UE may represent a device (e.g., a smart power meter) that is not intended for sale to or operation by an end user, but that may be associated with or operated for the benefit of a user.

[0151] The UE 1200 includes a processing circuit 1202 operatively coupled via a bus 1204 to an input / output interface 1206, a power source 1208, a memory 1210, a communication interface 1212, and / or any other components, or any combination thereof. A given UE may utilize all or a subset of the components shown in FIG. 16 . The level of integration between components may vary from one UE to another. Furthermore, a given UE may include multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0152] Processing circuitry 1202 is configured to process instructions and data, and may be configured to implement any sequential state machine operable to execute instructions stored as a machine-readable computer program in memory 1210. Processing circuitry 1202 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc.), programmable logic with appropriate firmware, one or more stored computer programs, a general-purpose processor such as a microprocessor or digital signal processor (DSP) with appropriate software, or any combination of the above. For example, processing circuitry 1202 may include multiple central processing units (CPUs).

[0153] In the above examples, the input / output interface 1206 may be configured to provide one or more interfaces to an input device, an output device, or one or more input and / or output devices. Examples of output devices include speakers, sound cards, video cards, displays, monitors, printers, actuators, emitters, smart cards, other output devices, or any combination thereof. The input devices may enable a user to capture information for the UE 1200. Examples of input devices include touch-sensitive or presence-sensitive displays, cameras (e.g., digital cameras, digital video cameras, webcams, etc.), microphones, sensors, mice, trackballs, directional pads, trackpads, scroll wheels, smart cards, etc. The presence-sensitive displays may include capacitive or resistive touch sensors for sensing input from a user. The sensors may be, for example, accelerometers, gyroscopes, tilt sensors, force sensors, magnetic sensors, optical sensors, proximity sensors, biometric sensors, etc., or any combination thereof. The output devices may use the same type of interface port as the input devices. For example, a Universal Serial Bus (USB) port may be used to provide input and output devices.

[0154] In some embodiments, the power source 1208 is structured as a battery or battery pack. Other types of power sources may be used, such as an external power source (e.g., an electrical outlet), a solar-powered device, or batteries. The power source 1208 may further include power circuitry for transferring power from the power source 1208 itself and / or the external power source to various portions of the UE 1200 via interfaces such as input circuits or power cables. The power transfer may be for charging the power source 1208, for example. The power circuitry may perform some shaping, conversion, or other modification of the power from the power source 1208 to make it suitable for the respective components of the UE 1200 that it powers.

[0155] The memory 1210 may be or may be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disk, optical disk, hard disk, removable cartridge, and flash drive. In one example, the memory 1210 includes one or more application programs 1214, such as an operating system, a web browser application, a widget, a gadget engine, or other applications, and corresponding data 1216. The memory 1210 may store any of a wide variety of operating systems or combinations of operating systems for use by the UE 1200.

[0156] The memory 1210 may be configured to include multiple physical drive units such as a redundant array of independent disks (RAID), flash memory, a USB flash drive, an external hard disk drive, a thumb drive, a pen drive, a key drive, a high-density digital versatile disc (HD-DVD), an optical disk drive, an internal hard disk drive, a Blu-ray optical disk drive, a holographic digital data storage (HDDS) optical disk drive, an external mini-DI MM (Dual In-Line Memory Module), a synchronous dynamic random access memory (SDRAM), an external micro-DIMM SDRAM, a smart card memory such as a tamper-resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs) such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may be, for example, an embedded UICC (eUICC), an integrated UICC (iUICC), or a removable UICC commonly known as a "SIM card." Memory 1210 may enable UE 1200 to access instructions, application programs, and the like stored on a temporary or non-transitory storage medium to offload or upload data. An item of manufacture, such as one utilizing a communication system, may be tangibly embodied as or within memory 1210, which may be or include a device-readable storage medium.

[0157] The processing circuit 1202 may be configured to communicate with an access network or other networks using a communication interface 1212. The communication interface 1212 may include one or more communication subsystems and may include or be communicatively coupled to an antenna 1222. The communication interface 1212 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of other devices capable of wireless communication (e.g., other UEs or network nodes within the access network). Each transceiver may include a transmitter 1218 and / or a receiver 1220 appropriate for providing network communications (e.g., optical, electrical, frequency-assigned, etc.). Moreover, the transmitter 1218 and receiver 1220 may be coupled to one or more antennas (e.g., antenna 1222), which may share circuit components, software, or firmware, or may alternatively be implemented separately.

[0158] In the illustrated embodiment, the communication capabilities of communication interface 1212 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communication such as Bluetooth, near-field communication, location-based communication such as using the Global Positioning System (GPS) to determine location, other similar communication capabilities, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as, for example, IEEE 802.11, Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, Transmission Control Protocol / Internet Protocol (TCP / IP), Synchronous Optical Networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), etc.

[0159] Regardless of the type of sensor, the UE may provide an output of data captured by its sensors to a network node via a wireless connection through its communications interface 1212. Data captured by the UE's sensors may be communicated via other UEs to the network node via a wireless connection. The output may be periodic (e.g., once every 15 minutes when reporting sensed temperature), random (e.g., to balance the load of notifications from multiple sensors), in response to a triggering event (e.g., moisture is detected and an alert is sent), on request (e.g., a user-initiated request), or as a continuous stream (e.g., a live video feed of a patient).

[0160] As another example, the UE may include an actuator, motor, or switch associated with a communications interface configured to receive wireless input from a network node via a wireless connection. The state of the actuator, motor, or switch may change in response to the received wireless input. For example, the UE may include a motor that adjusts a control surface or rotor of a drone in flight in accordance with the received input, or a robotic arm that performs a medical procedure in accordance with the received input.

[0161] If the UE is in the form of an Internet of Things (IoT) device, it may be a device for use in one or more application domains, including but not limited to wearable technology in the city, extended industrial applications, and healthcare. Non-limiting examples of such IoT devices are or are incorporated into devices such as a connected refrigerator or freezer, a TV, a connected lighting fixture, an electric meter, a robot vacuum cleaner, a voice-controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electric door lock, a connected doorbell, an air conditioning system such as a heat pump, an autonomous vehicle, a surveillance system, a weather monitor, a vehicle parking monitor, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for augmented reality (AR) or virtual reality (VR), a wearable for haptic augmentation or sensory enhancement, a water sprinkler, an animal or object tracking device, a sensor for monitoring plants or animals, an industrial robot, an unmanned aerial vehicle (UAV), and any type of medical device such as a heart rate monitor or a remote-controlled surgical robot. A UE in the form of an IoT device comprises other components such as those described in connection with the UE 1200 shown in FIG. 16, in addition to circuitry and / or software depending on the intended application of the IoT device.

[0162] As yet another specific example, in an IoT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements and transmits results of such monitoring and / or measurements to other UEs and / or network nodes. The UE, in this case, may be an M2M device, which may also be referred to as an MTC device in the 3GPP context. As one particular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, bus, truck, ship, or aircraft, or other equipment capable of monitoring and / or reporting its operational status or other functions associated with its operation.

[0163] In practice, any number of UEs may be used together for a single use case. For example, a first UE may be a drone or integrated into a drone and provide drone speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When a user makes changes from the remote controller, the first UE may adjust the drone's throttle (e.g., by controlling an actuator) to increase or decrease the drone's speed. The first and / or second UE may also include more than one of the above-described functionalities. For example, a UE may include a sensor and an actuator and handle communication of data for both the speed sensor and the actuator.

[0164] 17 illustrates a network node 1300 according to some embodiments. As used herein, a network node refers to a device that is capable of, configured, arranged, and / or operable to communicate directly or indirectly with UEs and / or other network nodes or devices in a telecommunications network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., wireless access points) and base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs), and NR Node Bs (gNBs)).

[0165] Base stations may be categorized based on the amount of coverage they provide (or, stated another way, their transmit power levels), and thus may be referred to as femto, pico, micro, or macro base stations, depending on the amount of coverage provided. A base station may also be a relay node or a relay donor node that controls a relay. A network node may also include one or more (or all) parts of a distributed radio base station, such as a centralized digital unit and / or a remote radio unit (RRU), sometimes called a remote radio head (RRH). Such remote radio units may or may not be integrated with an antenna, such as an antenna-integrated radio. Some distributed radio base stations may also be referred to as nodes in a distributed antenna system (DAS).

[0166] Other examples of network nodes include multi-transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as an MSR BS, a network controller such as a radio network controller (RNC) or base station controller (BSC), a base transceiver station (BTS), a transmission point, a transmitting node, a multi-cell / multicast coordination entity (MCE), an operation and maintenance (O&M) node, an operation support system (OSS) node, a self-organizing network (SON) node, a positioning node (e.g., an evolved serving mobile location center (E-SMLC) and / or a minimized drive test (MDT).

[0167] The network node 1300 includes a processing circuit 1302, a memory 1304, a communication interface 1306, and a power source 1308. The network node 1300 may be composed of multiple physically separate components (e.g., a Node B component and an RNC component, or a BTS component and a BSC component), each of which may have its own respective components. In some scenarios in which the network node 1300 includes multiple separate components (e.g., a BTS and a BSC component), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple Node Bs. In such scenarios, each unique pair of Node B and RNC may, in some examples, be considered a single separate network node. In some embodiments, the network node 1300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be redundant (e.g., separate memories 1304 for different RATs) and some components may be reused (e.g., the same antenna 1310 may be shared by different RATs). Network node 1300 may also include multiple sets of the various illustrated components for different wireless technologies, such as GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, RFID (Radio Frequency Identification), or Bluetooth wireless technologies, that are integrated into network node 1300. The wireless technologies may be integrated into the same or different chips or sets of chips and other components within network node 1300.

[0168] The processing circuitry 1302 may include one or more combinations of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application specific integrated circuit, field programmable gate array, or other suitable computing device, resources, or combination of hardware, software, and / or coded logic operable, alone or in conjunction with other network node 1300 components, such as memory 1304, to provide the functionality of the network node 1300.

[0169] In some embodiments, the processing circuit 1302 comprises a system on a chip (SOC). In some embodiments, the processing circuit 1302 includes one or more of a radio frequency (RF) transceiver circuit 1312 and a baseband processing circuit 1314. In some embodiments, the RF transceiver circuit 1312 and the baseband processing circuit 1314 may be on separate chips (or set of chips), boards, or units, such as a radio unit and a digital unit. In alternative embodiments, some or all of the RF transceiver circuit 1312 and the baseband processing circuit 1314 may be on the same chip or set of chips, board, or unit.

[0170] The memory 1304 may include any type of volatile or non-volatile computer-readable memory, including, but not limited to, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (e.g., hard disk), removable storage media (e.g., flash drive, compact disc (CD) or digital video disc (DVD)), and / or any other volatile or non-volatile non-transitory device-readable and / or computer-executable memory device that stores information, data, and / or instructions that may be used by the processing circuit 1302. The memory 1304 may store any suitable instructions, data, or information, including applications, including one or more of computer programs, software, logic, rules, code, tables, and / or other instructions, that are executable by the processing circuit 1302 and usable by the network node 1300. The memory 1304 may be used to store any computational results produced by the processing circuit 1302 and / or any data received via the communication interface 1306. In some embodiments, the processing circuit 1302 and the memory 1304 are integrated.

[0171] The communication interface 1306 is used for wired or wireless communication of signaling and / or data between network nodes, access networks, and / or the UE. As shown, the communication interface 1306 includes a port / terminal 1316 for transmitting and receiving data to and from a network over a wired connection, for example. The communication interface 1306 also includes radio front-end circuitry 1318, which is coupled to an antenna 1310 or, in some embodiments, may be part of the antenna 1310. The radio front-end circuitry 1318 includes a filter 1320 and an amplifier 1322. The radio front-end circuitry 1318 may be connected to the antenna 1310 and the processing circuitry 1302. The radio front-end circuitry may be configured to condition signals communicated between the antenna 1310 and the processing circuitry 1302. The radio front-end circuitry 1318 may accept digital data to be sent to another network node or the UE over a wireless connection. The radio front-end circuitry 1318 may convert the digital data into a radio signal having appropriate channel and bandwidth parameters using a combination of filters 1320 and / or amplifiers 1322. The radio signal may then be transmitted via the antenna 1310. Similarly, when data is received, the antenna 1310 may collect the radio signal, which may then be converted into digital data by the radio front-end circuitry 1318. The digital data may be passed to the processing circuitry 1302. In other embodiments, the communication interface may include different components and / or different combinations of components.

[0172] In an alternative embodiment, the network node 1300 does not include a separate radio front-end circuit 1318; rather, the processing circuit 1302 includes the radio front-end circuitry and is connected to the antenna 1310. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1312 is part of the communications interface 1306. In yet another embodiment, the communications interface 1306 includes one or more ports or terminals 1316, the radio front-end circuitry 1318, and the RF transceiver circuitry 1312 as part of a radio unit (not shown), and the communications interface 1306 communicates with baseband processing circuitry 1314 that is part of a digital unit (not shown).

[0173] Antenna 1310 may include one or more antennas or antenna arrays configured to transmit and / or receive wireless signals. Antenna 1310 may be coupled to radio front-end circuitry 1318 and may be any type of antenna capable of wirelessly transmitting and receiving data and / or signals. In some embodiments, antenna 1310 is separate from network node 1300 and connectable to network node 1300 through an interface or port.

[0174] The antenna 1310, the communication interface 1306, and / or the processing circuit 1302 may be configured to perform any receiving operations and / or certain acquisition operations described herein as being performed by a network node. Any information, data, and / or signals may be received from a UE, another network node, and / or any other network equipment. Similarly, the antenna 1310, the communication interface 1306, and / or the processing circuit 1302 may be configured to perform any transmitting operations described herein as being performed by a network node. Any information, data, and / or signals may be transmitted to a UE, another network node, and / or any other network equipment.

[0175] The power source 1308 provides power to the various components of the network node 1300 in a format appropriate for each component (e.g., at the voltage and current levels required for each component). The power source 1308 may further include, or be coupled to, power management circuitry for providing power to the components of the network node 1300 to perform the functionality described herein. For example, the network node 1300 may be connectable to an external power source (e.g., a power grid, an electrical outlet) via an input circuit or interface, such as an electrical cable, whereby the external power source provides power to the power circuitry of the power source 1308. As a further example, the power source 1308 may include a source of power in the form of a battery or battery pack connected to or integrated into the power circuitry. The battery may provide backup power in case of failure of the external power source.

[0176] Embodiments of network node 1300 may include additional components other than those shown in Figure 17 to provide certain aspects of the network node's functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, network node 1300 may include user interface devices that allow information to be input into network node 1300 and information to be output from network node 1300. This may enable a user to perform diagnostic, maintenance, repair, and other administrative functions on network node 1300.

[0177] 18 is a block diagram of a host 1400, which may be an embodiment of the host 1116 of FIG. 15, in accordance with various aspects described herein. As used herein, the host 1400 may be or include various combinations of hardware and / or software, including a standalone server, a blade server, a cloud-implemented server, a distributed server, a virtual machine, a container, or processing resources within a server farm. The host 1400 may provide one or more services to one or more UEs.

[0178] Host 1400 includes a processing circuit 1402 operably coupled via a bus 1404 to an input / output interface 1406, a network interface 1408, a power supply 1410, and memory 1412. In other embodiments, other components may be included, the functionality of which may be substantially similar to those described with respect to the devices of the previous figures, and therefore those descriptions are generally applicable to the corresponding components of host 1400.

[0179] Memory 1412 may include one or more computer programs, including one or more host application programs 1414, and data 1416, which may include user data, such as data generated by a UE for host 1400 or data generated by host 1400 for a UE. An embodiment of host 1400 may utilize only a subset or all of the illustrated components. Host application programs 1414 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Versatile Video Coding (VVC), High Efficiency Video Coding (HEVC), Advanced Video Coding (AVC), MPEG, VP9) and audio codecs (e.g., FLAC, Advanced Audio Coding (AAC), MPEG, G.711), including transcoding for different UE classes, types, or implementations (e.g., handsets, desktop computers, wearable display systems, heads-up display systems). The host application program 1414 may also provide user authentication and license checks, and may periodically report health, route, and content availability to a central node, such as a device in or at the edge of the core network. Thus, the host 1400 may select and / or point to different hosts for over-the-top services for the UE. The host application program 1414 may support a variety of protocols, such as HTTP Live Streaming (HLS) protocol, Real-Time Messaging Protocol (RTMP), Real-Time Streaming Protocol (RTSP), Dynamic Adaptive Streaming over HTTP (MPEG-DASH), etc.

[0180] FIG. 19 is a block diagram illustrating a virtualization environment 1500 in which functionality implemented according to some embodiments may be virtualized. In this context, virtualization means for creating a virtual version of an apparatus or device may include a virtualized hardware platform, storage devices, and networking resources. As used herein, virtualization may apply to any device or component thereof described herein and refers to implementations in which at least a portion of its functionality is implemented as one or more virtual components. Some or all of the functionality described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented within one or more virtual environments 1500 hosted by one or more hardware nodes, such as a network node, a UE, a core network node, or a hardware computing device acting as a host. Furthermore, in embodiments in which a virtualized node does not require wireless connectivity (e.g., a core network node or host), the node may be virtualized in its entirety.

[0181] An application 1502 (which may alternatively be referred to as a software instance, a virtual appliance, a network function, a virtual node, a virtual network function, etc.) runs in the virtualized environment 1500 to implement some of the features, functions and / or benefits of some of the embodiments disclosed herein.

[0182] The hardware 1504 may include processing circuitry, memory for storing software and / or instructions executable by the processing circuitry, and / or hardware devices as described herein, such as network interfaces and input / output interfaces. Software is executed by the processing circuitry to instantiate one or more virtualization layers 1506 (also referred to as a hypervisor or virtual machine monitor (VMM)), provide VMs 1508a and 1508b (one or more of which may be generally referred to as VMs 1508), and / or perform any of the functions, features, and / or benefits described in connection with some embodiments described herein. The virtualization layer 1506 may present a virtual operating platform that appears to the VMs 1508 as networking hardware.

[0183] The VMs 1508 may include virtual processing, virtual memory, virtual networking or interfaces, and virtual storage, and may be executed by a corresponding virtualization layer 1506. Various embodiments of instances of virtual appliances 1502 may be implemented in one or more of the VMs 1508, and the implementation may be done in various ways. Hardware virtualization is referred to in some contexts as network functions virtualization (NFV). NFV may be used to aggregate many network equipment types into industry-standard, high-capacity server hardware, physical switches, and physical storage that may be located in data centers and customer premises equipment.

[0184] In the context of NFV, a VM 1508 may be a software implementation of a physical machine that runs programs as if they were running on a physical, non-virtualized machine. Each VM 1508 and the portion of hardware 1504 on which it runs, whether the hardware is dedicated to that VM and / or shared by that VM with other VMs, forms a separate virtual network element. Also in the context of NFV, a virtual network function is responsible for handling specific network functions running in one or more VMs 1508 on top of the hardware 1504 and corresponds to the application 1502.

[0185] The hardware 1504 may be implemented in a standalone network node with generic or proprietary components. The hardware 1504 may implement some functions via virtualization. Alternatively, the hardware 1504 may be part of a larger hardware cluster (e.g., in a data center or CPE) where multiple hardware nodes cooperate and are managed via management and orchestration 1510, which oversees, among other things, the lifecycle management of the application 1502. In some embodiments, the hardware 1504 is coupled to one or more radio units, each including one or more transmitters and one or more receivers, which may be coupled to one or more antennas. The radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces or may be used in combination with virtual components, such as radio access nodes or base stations, to provide wireless capabilities to virtual nodes. In some embodiments, some signaling may be provided with the use of a control system 1512, which may alternatively be used for communication between the hardware nodes and the radio units.

[0186] Figure 20 shows a communication diagram of a host 1602 communicating with a UE 1606 via a network node 1604 over a connection that includes a wireless portion, according to some embodiments. Exemplary implementations, according to various embodiments, of the UE (UE 1112a of Figure 15 and / or UE 1200 of Figure 16), network node (network node 1110a of Figure 15 and / or network node 1300 of Figure 17), and host (host 1116 of Figure 15 and / or host 1400 of Figure 18) discussed in the previous paragraphs will now be described with reference to Figure 20.

[0187] Similar to host 1400, an embodiment of host 1602 includes hardware such as a communications interface, processing circuitry, and memory. Host 1602 also includes software stored within or accessible by host 1602 and executable by the processing circuitry. The software includes a host application that may be operable to provide services to a remote user, such as UE 1606, connecting via an over-the-top (OTT) connection 1650 extending between UE 1606 and host computer 1602. During the provision of services to the remote user, the host application may provide user data that is transmitted using OTT connection 1650.

[0188] The network node 1604 includes hardware that enables communication with the host 1602 and the UE 1606. The connection 1660 may be direct or may pass through one or more other intermediate networks, such as a core network (such as the core network 1106 of FIG. 15) and / or one or more public, private, or hosted networks. For example, the intermediate network may be a backbone network or the Internet.

[0189] The UE 1606 includes software stored within or accessible by the UE 1606 and executable by the UE's processing circuitry. This software includes a client application, such as a web browser or operator-specific "app," that may be operable, with support from the host 1602, to provide services to a human or non-human user via the UE 1606. Host applications running on the host 1602 may communicate with client applications running on the UE 1606 via an OTT connection 1650 that terminates at the UE 1606 and the host 1602. During the provision of services to the user, the client applications on the UE may receive request data from the host applications on the host and provide user data in response to the request data. The OTT connection 1650 may transport both the request data and the user data. The client applications on the UE may interact with the user to generate the user data that they provide to the host applications over the OTT connection 1650.

[0190] The OTT connection 1650 may extend via a connection 1660 between the host 1602 and the network node 1604 and via a wireless connection 1670 between the network node 1604 and the UE 1606, providing connectivity between the host 1602 and the UE 1606. The connection 1660 and the wireless connection 1670 over which the OTT connection 1650 may be provided are depicted abstractly to illustrate communication between the host 1602 and the UE 1606 via the network node 1604 without explicit reference to any intermediate devices and the precise routing of messages through those devices.

[0191] As an example of transmitting data over the OTT connection 1650, in step 1608, the host 1602 provides user data, which may be performed by executing a host application. In some embodiments, the user data is associated with a specific human user interacting with the UE 1606. In other embodiments, the user data is associated with the UE 1606 sharing data with the host 1602 without explicit human interaction. In step 1610, the host 1602 initiates a transmission to the UE 1606 carrying user data. The host 1602 may initiate the transmission in response to a request sent by the UE 1606. The request may be triggered by human interaction with the UE 1606 or by the operation of a client application running on the UE 1606. The transmission may pass through the network node 1604 in accordance with the teachings of embodiments described throughout this disclosure. In response, at step 1612, the network node 1604 transmits the user data carried in the transmission initiated by the host 1602 to the UE 1606, in accordance with the teachings of embodiments described throughout this disclosure. At step 1614, the UE 1606 receives the user data carried in the transmission, which may be performed by a client application executing on the UE 1606 that is associated with a host application executed by the host 1602.

[0192] In some examples, the UE 1606 executes a client application, which provides user data destined for the host 1602. The user data may be provided in reaction or response to receiving the data from the host 1602. In response, the UE 1606 may provide the user data at step 1616, which may be done by executing the client application. During the provision of the user data, the client application may further consider user input received from a user via an input / output interface of the UE 1606. Regardless of the specific manner in which the user data is provided, the UE 1606 initiates transmission of the user data to the host 1602 via the network node 1604 at step 1618. At step 1620, in accordance with the teachings of embodiments described throughout this disclosure, the network node 1604 receives the user data from the UE 1606 and initiates transmission of the received user data to the host 1602. At step 1622, the host 1602 receives the user data carried in the transmission initiated by the UE 1606.

[0193] One or more of various embodiments improve the performance of OTT services provided to UE 1606 using OTT connection 1650, of which wireless connection 1670 forms the final segment. More precisely, the teachings of these embodiments may improve, for example, one or more of data rate, latency, and / or power consumption, thereby providing benefits such as, for example, reduced user wait time, relaxed constraints on file size, improved content resolution, better responsiveness, and / or increased battery life.

[0194] In an exemplary scenario, factory status information may be collected and analyzed by the host 1602. As another example, the host 1602 may process audio and video data, possibly obtained from UEs, for use in generating maps. As another example, the host 1602 may collect and analyze real-time data to assist in traffic congestion control (e.g., traffic light control). As another example, the host 1602 may store surveillance video uploaded by UEs. As another example, the host 1602 may store or control access to media content, such as video, audio, VR, or AR, that may be broadcast, multicast, or unicast to UEs. As another example, the host 1602 may be used for energy pricing, remote control of non-time-critical power loads for balancing power generation needs, location services, presentation services (e.g., compiling diagrams from data collected from remote devices), or any other function that collects, acquires, stores, analyzes, and / or transmits data.

[0195] In some examples, measurement procedures may be provided to monitor data rates, latency, and other factors that may be improved by one or more embodiments. There may also be optional network functionality for reconfiguring the OTT connection 1650 between the host 1602 and the UE 1606 in response to measurement fluctuations. The measurement procedures and / or network functionality for reconfiguring the OTT connection may be implemented in software and hardware in the host 1602 and / or the UE 1606. In some embodiments, sensors (not shown) may be deployed in or associated with other devices through which the OTT connection 1650 passes, and these sensors may participate in the measurement procedures by providing values ​​for the monitored quantities exemplified above or other physical quantities from which the monitored quantities may be calculated or estimated by software. Reconfiguration of the OTT connection 1650 may include message formats, retransmission settings, preferred routing, etc., and the reconfiguration need not directly change the operation of the network node 1604. Such procedures and functionality may be known or practiced in the art. In one embodiment, the measurements may involve proprietary UE signaling that facilitates measurements of throughput, propagation time, latency, etc. by the host 1602. The measurements may be implemented by software sending messages over the OTT connection 1650, specifically empty or "dummy" messages, while monitoring propagation time, errors, etc.

[0196] 21 illustrates an exemplary method 1700 by a UE 1112 or a network node 1110 for improved UE positioning, according to an embodiment. In the illustrated embodiment, the method includes an executing step at 1702, a determining step at 1704, an identifying step at 1706, and an executing step at 1708.

[0197] For example, in a UE-implemented method, the method may begin at step 1702 when the UE 1112 performs a positioning operation to obtain a first UE position estimate based on a first set of positioning-related reports. At step 1704, the UE 1112 may determine a suitability score for each positioning-related report in the first set of positioning-related reports. Based on the suitability score for each positioning-related report in the first set of positioning-related reports, the UE 1112 may identify a second set of positioning-related reports and a third set of positioning reports at step 1706. Based on the second set of positioning-related reports, the UE 1112 may perform a positioning operation to obtain a second UE position estimate.

[0198] As another example, in a network node-implemented method, the method may begin at step 1702 when, based on a first set of positioning-related reports, the network node 1110 performs a positioning operation to obtain a first UE position estimate. At step 1704, the network node 1110 may determine a suitability score for each positioning-related report in the first set of positioning-related reports. Based on the suitability score for each positioning-related report in the first set of positioning-related reports, the network node 1110 may identify a second set of positioning-related reports and a third set of positioning reports at step 1706. Based on the second set of positioning-related reports, the network node 1110 may perform a positioning operation to obtain a second UE position estimate.

[0199] 22 shows another method 1800 by a network node 1112 for improved UE positioning, according to an embodiment. In the illustrated embodiment, the method includes a generating step at 1802, a providing step at 1804, a determining step at 1806, and an executing step 1808. For example, based on at least one wireless signal received on an uplink channel from the UE, the network node 1112 generates at least one positioning-related report associated with at least one ML model at step 1802. At step 1804, the network node 1112 provides the at least one positioning-related report to a position generation entity. At step 1806, the network node 1112 determines whether feedback has been received from the position generation entity. At step 1808, the network node 1112 performs at least one action based on whether feedback has been received from the position generation entity.

[0200] 23 shows another exemplary method 1900 by a network node 1112 operating as a position generating entity for improved UE-assisted positioning, according to an embodiment. In the illustrated embodiment, the method includes a receiving step at 1902, a determining step at 1904, and a transmitting step at 1906. For example, at step 1902, the network node 1112 may receive at least one positioning-related report generated based on at least one downlink wireless signal from a network node operating as a position-related report generating entity. The network node 1112 may determine a position of the UE at step 1904. At step 1906, the network node 1112 may transmit feedback to the network node operating as the position-related report generating entity. The feedback indicates at least one of the position of the UE 1110 and quality of the at least one positioning-related report.

[0201] 24 illustrates a method 2000 by a first network node 1110 for improved UE positioning, according to an embodiment. As shown, the method includes, in step 2002, generating at least one positioning-related report associated with at least one ML model. In step 2004, the network node 1110 transmits the at least one positioning-related report to a second network node 1110 acting as a position generating entity. In step 2006, the network node 1110 receives feedback from the second network node indicating a quality level of the at least one positioning-related report. In step 2008, the network node 1110 performs at least one action based on the feedback indicating a quality level of the at least one positioning-related report.

[0202] In a particular embodiment, if feedback is not received from the position generating entity within a period of time, performing the at least one action includes discarding data associated with the at least one wireless signal received on the uplink channel.

[0203] In certain embodiments, performing the at least one action includes at least one of generating or compiling new training data based on feedback received from the position generation entity and transmitting the new training data to a positioning-related training data collection entity.

[0204] In a particular embodiment, the feedback includes an indication of good quality of the at least one positioning-related report, and performing the at least one action includes continuing to use the at least one model for determining the location of the UE 1112 and / or generating the positioning-related report based on the indication of good quality of the at least one positioning-related report.

[0205] In a particular embodiment, the feedback indicates poor quality of the at least one positioning-related report, and performing the at least one action includes generating at least one new training sample based on at least one of the at least one wireless signal received on the uplink, data associated with the at least one wireless signal, and the at least one target positioning-related report label. The network node 1110 adds the at least one new training sample to the training data set.

[0206] In certain embodiments, performing the at least one action includes deactivating at least one ML model used for determining the location of the UE and / or generating the at least one positioning-related report based on poor quality of the at least one positioning-related report.

[0207] In a further particular embodiment, performing the at least one action includes updating at least one ML model used for determining the location of the UE and / or generating the at least one positioning-related report based on poor quality of the at least one positioning-related report.

[0208] In a particular embodiment, generating the at least one positioning-related report includes receiving, from the UE, at least one value associated with at least one measurement performed by the UE based on the wireless signals, wherein the at least one positioning-related report includes the at least one value associated with the at least one performed measurement.

[0209] In a further particular embodiment, the at least one value includes at least one of a UL SRS-RSRP value, a UL SRS-RSRPP value, a ToA estimate or value, a TDoA value, a UL AoA, a gNB Rx-Tx time difference value, and a received time value.

[0210] In certain embodiments, the at least one positioning related report includes a UE position estimate, a timestamp associated with at least one measurement and / or at least one value, a cell ID, a TRP ID, SSB information, spatial direction information, DL-PRS configuration information, LoS information, NLoS information, and a quality estimate associated with at least one measurement performed on a wireless signal received on an uplink channel.

[0211] In a particular embodiment, providing the at least one positioning-related report to the position generation entity includes transmitting the at least one positioning-related report to a second network node acting as an LMF.

[0212] In particular embodiments, the network node 1110 inputs at least one wireless signal to at least one ML model and receives a location estimate of the UE from the at least one ML model.

[0213] In a particular embodiment, the network node 1110 performs pre-processing to transform at least one wireless signal into an input for at least one ML model. The network node 1110 inputs the transformed input to the at least one ML model and receives a position estimate for the UE from the at least one ML model.

[0214] In a particular embodiment, the at least one position estimate includes at least one ToA estimate.

[0215] In a particular embodiment, the at least one wireless signal includes at least one SRS.

[0216] In certain embodiments, the first network node comprises a base station, a gNodeB, a TRP, or a reception point.

[0217] 25 shows a method 2100 by a second network node 1110 operating as a position generating entity for improved assisted positioning, according to an embodiment. In the illustrated embodiment, the method begins at step 2102, where the second network node 1110 receives, from a first network node 1110 operating as a position-related report generating entity, a first set of positioning-related reports generated based on at least one wireless signal transmitted on a downlink channel. Based on the first set of positioning-related reports, the second network node 1110 determines, in step 2104, a position of the UE 1112. In step 2106, the second network node 1110 transmits feedback to the first network node operating as a position-related report generating entity, the feedback indicating the quality of the at least one positioning-related report.

[0218] In particular embodiments, when determining the location of the UE, the second network node 1110 performs a positioning operation to obtain a first UE location estimate based on the first set of positioning-related reports. Based on the respective suitability scores for each positioning-related report in the first set of positioning-related reports, the second network node 1110 identifies a second set of positioning-related reports having suitability scores that are better than a suitability threshold and a third set of positioning-related reports having suitability scores that are less than the suitability threshold. The second network node 1110 sends a notification to the first network node that the third set of positioning reports is associated with a suitability score that is less than the suitability threshold.

[0219] In a particular embodiment, the second set of positioning-related reports is a first subset of the first set of positioning-related reports, and the third set of positioning-related reports is a subset of the first set of positioning-related reports.

[0220] In a particular embodiment, based on the distance between the location of the UE and the known location of the TRP, the second network node 1110 obtains at least one new target positioning-related report label for at least one positioning-related report in the third set of positioning-related reports. The second network node 1110 transmits the at least one new target positioning-related report label to the first network node 1110.

[0221] In a particular embodiment, when obtaining at least one new target positioning-related report label for at least one positioning-related report in the third set of positioning-related reports, the second network node 1110 calculates the at least one new target positioning-related report label based on at least one of the speed of the wireless signal, the UE timing error-related estimate, and the time difference of arrival between two TRPs.

[0222] In a particular embodiment, the second network node 1110 compares the location of the UE determined by the second network node with an estimated location of the UE provided in the first set of positioning-related reports, and determines a quality of the first set of positioning-related reports based on the comparison of the location of the UE determined by the second network node with the estimated location of the UE provided in the first set of positioning-related reports.

[0223] In a further particular embodiment, the feedback includes an indication of good quality of at least one positioning related report if the estimated location of the UE provided in the first set of positioning related reports is less than or equal to a threshold distance from the location of the UE determined by the second network node.

[0224] In a particular embodiment, the feedback includes an indication of poor quality of at least one positioning-related report if the estimated location of the UE provided in the first set of positioning-related reports is greater than a threshold distance from the location of the UE determined by the second network node.

[0225] In certain embodiments, the first set of positioning-related reports includes at least one value associated with at least one measurement performed by the UE based on at least one wireless signal, the at least one value including at least one of a DL RSTD value, a DL PRS-RSRP value, a DL PRS-RSRPP value, a ToA estimate or value, a UE Rx-Tx time difference value, and a transmission time value.

[0226] In certain embodiments, the first set of positioning related reports includes a UE position estimate, a timestamp associated with at least one measurement and / or at least one value, a cell ID, a TRP ID, SSB information, spatial direction information, DL-PRS configuration information, LoS information, NLoS information, and a quality estimate associated with at least one measurement performed on a wireless signal received on a downlink channel.

[0227] In a particular embodiment, the at least one position estimate includes at least one ToA estimate.

[0228] In certain embodiments, the at least one wireless signal includes at least one PRS associated with at least one TRP.

[0229] In a particular embodiment, the second network node acting as the position generating entity is an LMF.

[0230] In a particular embodiment, the first network node acting as the location-related report generating entity is a gNodeB or a TRP.

[0231] While the computing devices (e.g., UEs, network nodes, hosts) described herein may include combinations of the illustrated hardware components, other embodiments may include computing devices with different combinations of components. It should be understood that the computing devices may include any suitable combination of hardware and / or software required to perform the tasks, features, functions, and methods disclosed herein. The determining, calculating, obtaining, or similar operations described herein may be performed by processing circuitry, which may process information by, for example, transforming the obtained information into other information, comparing the obtained or transformed information with information stored at a network node, and / or performing one or more operations based on the obtained or transformed information, and making a decision as a result of that processing. Moreover, while components are depicted as a single box located within a larger box or nested within multiple boxes, in reality, the computing device may include multiple different physical components that make up the illustrated single component, and functionality may be partitioned among the separate components. For example, a communication interface may be configured to include any of the components described herein, and the functionality of those components may be partitioned between the processing circuitry and the communication interface. In other examples, the computationally less intensive functions of any of these components may be implemented in software or firmware, and the computationally intensive functions may be implemented in hardware.

[0232] In some embodiments, some or all of the functionality described herein may be provided by a processing circuit executing instructions stored in a memory, which in some embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by a processing circuit, such as in a hardwired manner, without executing instructions stored on a separate or discrete device-readable storage medium. In any of these specific embodiments, the processing circuit can be configured to perform the described functionality regardless of whether it executes instructions stored on a non-transitory computer-readable storage medium. Benefits provided by such functionality are not limited to just the processing circuit or other components of the computing device, but are enjoyed by the computing device as a whole and / or by end users and wireless networks in general.

[0233] Example embodiment <Example of Group A Implementation> Example Embodiment A1. A method by a user equipment (UE) for improved UE positioning, the method including any of the user equipment steps, features, or functions described above, either alone or in combination with other steps, features, or functions described above. Example Embodiment A2. The method of any preceding embodiment, further comprising one or more additional user equipment steps, features, or functions described above. Example Embodiment A3. The method of any of the preceding embodiments, further comprising providing user data and transferring the user data to the host computer via transmission to the network node.

[0234] <Example of Group B Implementation> Example Embodiment B1. A method performed by a network node for improved UE positioning, comprising any of the steps, features or functions of the network node described above, either alone or in combination with the steps, features or functions described above. Example Embodiment B2. The method of any preceding embodiment, further comprising one or more additional network node steps, features, or functions as described above. Example Embodiment B3. The method of any preceding embodiment, further comprising obtaining user data and transferring the user data to a host or user device. The method according to any of the preceding embodiments.

[0235] <Example of Group C Implementation> Example Embodiment C1. A method by a UE for improved UE positioning, comprising: performing a positioning operation to obtain a first UE position estimate based on a first set of positioning-related reports (step 1); determining a suitability score for each positioning-related report included in the first set of positioning-related reports (step 2); identifying a second set of positioning-related reports and a third set of positioning-related reports based on the suitability score for each positioning-related report included in the first set of positioning-related reports (step 3); and performing a positioning operation to obtain a second UE position estimate based on the second set of positioning-related reports (step 4).

[0236] Example Embodiment C2. The method of example embodiment C1, wherein the second set of positioning-related reports overlaps with the first set of positioning-related reports.

[0237] Example Embodiment C3. The method of example embodiment C1, wherein the second set of positioning-related reports completely overlaps with the first set of positioning-related reports.

[0238] Example Embodiment C4. The method of any of Examples C1 to C3, wherein the third set of positioning related reports does not overlap with the second set of positioning related reports.

[0239] Example Embodiment C5. The method of any of Examples C1 to C3, wherein the third set of positioning-related reports is an empty set.

[0240] Example Embodiment C5b. The method of Example Embodiment C5, comprising transmitting to a network node or another UE acting as a positioning-related report generating entity at least one of: an all-clear signal; an indication that the third set of positioning-related reports is an empty set; an indication that none of the positioning-related reports in the first set of positioning-related reports have been executed; and an indication that none of the positioning-related reports in the first set of positioning-related reports have a suitability score below a threshold.

[0241] Example Embodiment C6. The method of any of Examples C1 to C5b, wherein identifying a second set of positioning-related reports based on the relevance scores includes, for each positioning-related report in the first set of positioning-related reports, comparing an associated relevance score to a relevance threshold, and selecting any positioning-related reports having a relevance score greater than (or greater than or equal to) the relevance threshold.

[0242] Example Embodiment C7. The method of Example Embodiment C6, wherein the second suitability threshold is determined based on at least one of: a distribution of suitability scores for the first set of positioning-related reports, the radio environment, the performance of the positioning algorithm, the type of model or algorithm used to generate the first set of positioning-related reports, and the number of iterations used to obtain the final UE position estimate.

[0243] Example Embodiment C8. The method of any one of example embodiment examples C1 to C5, wherein identifying a second set of positioning-related reports based on the suitability scores includes determining a ranking of each positioning-related report in the first set of positioning-related reports based on the respective suitability scores, the ranking of each positioning-related report indicating a level of suitability of the positioning-related report with the first UE position estimate.

[0244] Example Embodiment C9. The method of Example Embodiment C8, including selecting, based on ranking, N positioning-related reports from the first set of positioning-related reports that are least compatible with the first UE position estimate, and excluding the N least compatible positioning-related reports from the second set of positioning-related reports.

[0245] Example Embodiment C10. The method of Example Embodiment C8, comprising: selecting, based on ranking, M positioning-related reports from the first set of positioning-related reports that are most compatible with the first UE position estimate; and including the M most compatible positioning-related reports in a second set of positioning-related reports.

[0246] Example Embodiment C11. The method of any of Examples C9 to C10, wherein N and / or M are determined based on at least one of the configuration and / or performance and / or type of model or algorithm used to generate the first set of positioning-related reports and the radio environment.

[0247] Example Embodiment C12. The method of any of Examples C6 to C11, comprising: determining a quality level of each one of the first set of positioning-related reports or the second set of positioning-related reports; comparing the quality level of each one of the first set of positioning-related reports or the second set of positioning-related reports with a quality threshold; removing positioning-related reports having a quality level lower than the quality threshold from the second set of positioning-related reports; and / or adding positioning-related reports having a quality level higher than the quality threshold to a third set of positioning-related reports.

[0248] Example Embodiment C12. The method of any of Example Embodiments C1 to C5, wherein identifying the second set of positioning-related reports and the third set of positioning-related reports includes performing one of: for each positioning-related report in the first set of positioning-related reports, comparing an associated relevance score to a relevance threshold; selecting, for the second set of positioning-related reports, positioning-related reports having a relevance score greater than or equal to the first relevance threshold; selecting for the second set of positioning-related reports any positioning-related reports having a relevance score greater than or equal to the first relevance threshold and any positioning-related reports having a relevance score less than the first relevance threshold; and selecting for the second set of positioning-related reports any positioning-related reports having a relevance score greater than the first relevance threshold and any positioning-related reports having a relevance score less than the first relevance threshold for the third set of positioning-related reports.

[0249] Example Embodiment C14. The method of Example Embodiment C13, wherein the suitability threshold is determined based on at least one of the distribution of suitability scores for the first set of positioning-related reports, the radio environment, the performance of the positioning algorithm, the type of model or algorithm used to generate the first set of positioning-related reports, and the number of iterations used to obtain the final UE position estimate.

[0250] Example Embodiment C15. The method of any of Example Embodiments C1 to C5, wherein identifying the second set of positioning-related reports and the third set of positioning-related reports includes determining a ranking for each positioning-related report in the first set of positioning-related reports based on a respective suitability score, wherein the ranking of each positioning-related report indicates a level of suitability of the positioning-related report with the first UE position estimate; and performing at least one of: selecting, based on the ranking, N positioning-related reports from the first set of positioning-related reports that are least compatible with the first UE position estimate and including the N least compatible positioning-related reports from the second set of positioning-related reports in the positioning-related reports of the third set of positioning-related reports; and selecting, based on the ranking, M positioning-related reports from the first set of positioning-related reports that are most compatible with the first UE position estimate and including the M most compatible positioning-related reports with the first UE position estimate in the positioning-related reports of the second set of positioning-related reports.

[0251] Example Embodiment C16. The method of Example Embodiment C15, wherein N and / or M are determined based on at least one of the configuration and / or performance and / or type of model or algorithm used to generate the first set of positioning-related reports and the wireless environment.

[0252] Example Embodiment C17. The method of any of Example Embodiments C1 through C16, including outputting a second UE position estimate.

[0253] Example Embodiment C18. The method of any of Example Embodiments C1 to C16, including determining that the second set of positioning-related reports is smaller than the first set of positioning-related reports; and outputting a second UE position estimate based on the second set of positioning-related reports being smaller than the first set of positioning-related reports.

[0254] Example Embodiment C19. The method of any of Example Embodiments C1 to C16, including determining that the second set of positioning related reports is less than a minimum number of positioning related reports, and outputting a first UE position estimate based on the second set of positioning related reports being less than the minimum number of positioning related reports.

[0255] Example Embodiment C20. The method of example embodiment C19, including determining a minimum number of positioning-related reports based on the types of the first set of positioning-related reports.

[0256] Example Embodiment C21. The method of example embodiment C20, wherein the first set of types of positioning related reports is associated with 2D positioning or 3D positioning.

[0257] Example Embodiment C22. The method of any of Example Embodiments C1 to C16, comprising: determining that the second set of positioning related reports is not smaller than the first set of positioning related reports; replacing the first set of positioning related reports with the second set of positioning related reports based on the second set of positioning related reports being not smaller than the first set of positioning related reports; repeating steps 1-4 until the first set of positioning related reports is smaller than the previous set of positioning related reports; and outputting a final UE position estimate based on a positioning operation performed on the final set of positioning related reports.

[0258] Example Embodiment C23. The method of any of Examples C1 to C21, comprising: obtaining at least one new target positioning-related report label for at least one positioning-related report in a third set of positioning-related reports based on a distance between the second UE position estimate or the final UE position estimate and a known position of the TRP; and transmitting the at least one new target positioning-related report label to a network node or another UE acting as a positioning-related training data collection entity.

[0259] Example Embodiment C24. The method of any of Examples C1 to C21, comprising generating at least one new or updated positioning-related report for at least one positioning-related report in a third set of positioning-related reports based on a distance between the second UE position estimate or the final UE position estimate and a known position of the TRP, and transmitting the at least one new or updated positioning-related report to a network node or another UE acting as a positioning-related training data collection entity.

[0260] Example Embodiment C25. The method of any of Examples C1 to C24, comprising sending to a network node or another UE acting as a positioning-related report generating entity at least one of: an indication that at least one of the positioning-related reports in the first set of positioning-related reports is under-performing; and an indication that at least one of the positioning-related reports in the first set of positioning-related reports has a suitability score below a threshold.

[0261] Example Embodiment C26. The method of any of Example Embodiments C1 to C25, wherein performing a positioning operation to obtain a first UE position estimate and / or a second UE position estimate includes using trilateration.

[0262] Example Embodiment C27. The method of any of Examples C1 to C26, wherein performing a positioning operation to obtain a first UE position estimate and / or a second UE position estimate is based on at least one of one or more ToAs, one or more TDoAs, one or more loss functions, and one or more estimated timing errors and / or jitter.

[0263] Example Embodiment C28. The method of any of Example Embodiments C1 to C27, wherein the suitability score of each positioning related report in the first set of positioning related reports is determined as a function of the first UE position estimate and the known location of at least one network node.

[0264] Example Embodiment C29. The method of any of Example Embodiments C1 to C28, including transmitting the second UE position estimate and / or the final UE position estimate to a network node.

[0265] Example Embodiment C30. The method of any of Example Embodiments C1 to C29, wherein the first set of positioning related reports includes at least one value associated with at least one NLoS between the UE and at least one TRP.

[0266] Example Embodiment C31. The method of any of Example Embodiments C1 to C30, wherein the first set of positioning related reports includes at least one value associated with at least one LoS between the UE and at least one TRP.

[0267] Example Embodiment C32. The method of any of Examples C1 to C31, further comprising providing user data and forwarding the user data to the host via transmission to the network node.

[0268] Example Embodiment C33. A user equipment comprising processing circuitry configured to perform any of the methods of example embodiments C1-C32.

[0269] Example Embodiment C34. A user equipment configured or adapted to perform any of the methods of example embodiments C1 to C32.

[0270] Example Embodiment C35. A wireless device comprising processing circuitry configured to perform any of the methods of example embodiments C1 through C32.

[0271] Example Embodiment C36. A computer program comprising instructions which, when executed on a computer, perform any of the methods of Examples C1 to C32.

[0272] Example Embodiment C37. A computer program product comprising a computer program, the computer program comprising instructions for performing any of the methods of Examples C1 to C32 when the computer program is run on a computer.

[0273] Example Embodiment C38. A non-transitory computer-readable medium having stored thereon instructions that, when executed by a computer, perform any of the methods of Examples C1 through C32.

[0274] <Example of Group D Implementation> Example Embodiment D1. A method by a network node for improved UE positioning, comprising: performing a positioning operation to obtain a first UE position estimate based on a first set of positioning-related reports (step 1); determining a suitability score for each positioning-related report included in the first set of positioning-related reports (step 2); identifying a second set of positioning-related reports and a third set of positioning-related reports based on the suitability score for each positioning-related report included in the first set of positioning-related reports (step 3); and performing a positioning operation to obtain a second UE position estimate based on the second set of positioning-related reports (step 4).

[0275] Example Embodiment D2. The method of example embodiment D1, including obtaining a first set of positioning-related reports from a plurality of other network nodes.

[0276] Example Embodiment D3. The method of Example Embodiment D2, wherein the plurality of other network nodes includes at least one base station and / or at least one TRP.

[0277] Example Embodiment D4. The method of example embodiment D1, including obtaining a first set of positioning-related reports from the UE.

[0278] Example Embodiment D5. The method of any of Examples D1-D4, wherein the second set of positioning related reports overlaps with the first set of positioning related reports.

[0279] Example Embodiment D6. The method of any of Examples D1-D4, wherein the second set of positioning related reports completely overlaps with the first set of positioning related reports.

[0280] Example Embodiment D7. The method of any of Example Embodiments D1 through D6, wherein the third set of positioning related reports does not overlap with the second set of positioning related reports.

[0281] Example Embodiment D8. The method of any of Example Embodiments D1 through D6, wherein the third set of positioning-related reports is an empty set.

[0282] Example Embodiment D9. The method of Example Embodiment D8, including transmitting to a network node or another UE acting as a positioning-related report generating entity at least one of: an all-clear signal; an indication that the third set of positioning-related reports is an empty set; an indication that none of the positioning-related reports in the first set of positioning-related reports have been executed; and an indication that none of the positioning-related reports in the first set of positioning-related reports have a suitability score below a threshold.

[0283] Example Embodiment D10. The method of any of Examples D1 to D9, wherein identifying a second set of positioning-related reports based on the suitability scores includes, for each positioning-related report in the first set of positioning-related reports, comparing the associated suitability score to a suitability threshold, and selecting any positioning-related reports having a suitability score greater than (or greater than or equal to) the suitability threshold.

[0284] Example Embodiment D11. The method of Example Embodiment D10, wherein the second suitability threshold is determined based on at least one of: a distribution of suitability scores for the first set of positioning-related reports, the radio environment, the performance of the positioning algorithm, the type of model or algorithm used to generate the first set of positioning-related reports, and the number of iterations used to obtain the final UE position estimate.

[0285] Example Embodiment D12. The method of any one of example embodiments D1 to D9, including any one of example embodiments D1 to D5, wherein identifying a second set of positioning-related reports based on the suitability scores includes determining a ranking of each positioning-related report in the first set of positioning-related reports based on the respective suitability scores, the ranking of each positioning-related report indicating a level of suitability of the positioning-related report with the first UE position estimate.

[0286] Example Embodiment D13. The method of Example Embodiment D12, including selecting, based on ranking, N positioning-related reports from the first set of positioning-related reports that are least compatible with the first UE position estimate, and excluding the N least compatible positioning-related reports from the second set of positioning-related reports.

[0287] Example Embodiment D14. The method of Example Embodiment D12, comprising: selecting, based on ranking, M positioning-related reports from the first set of positioning-related reports that are most compatible with the first UE position estimate; and including the M most compatible positioning-related reports in a second set of positioning-related reports.

[0288] Example Embodiment D15. The method of any of Examples D13 to D14, wherein N and / or M are determined based on at least one of the configuration and / or performance and / or type of model or algorithm used to generate the first set of positioning-related reports and the radio environment.

[0289] Example embodiment D16. A method of any of examples D10 to D15, comprising determining a quality level of each one of the first set of positioning-related reports or the second set of positioning-related reports, comparing the quality level of each one of the first set of positioning-related reports or the second set of positioning-related reports with a quality threshold, removing positioning-related reports having a quality level lower than the quality threshold from the second set of positioning-related reports, and / or adding positioning-related reports having a quality level higher than the quality threshold to a third set of positioning-related reports.

[0290] Example Embodiment D17. The method of any of Example Embodiments D1 to D9, wherein identifying the second set of positioning-related reports and the third set of positioning-related reports includes performing one of the following: for each positioning-related report in the first set of positioning-related reports, comparing an associated relevance score to a relevance threshold; selecting, for the second set of positioning-related reports, positioning-related reports having a relevance score that is greater than or equal to the first relevance threshold; selecting any positioning-related reports having a relevance score that is greater than or equal to the first relevance threshold for the second set of positioning-related reports and any positioning-related reports having a relevance score that is less than the first relevance threshold for the third set of positioning-related reports; and selecting any positioning-related reports having a relevance score greater than the first relevance threshold for the second set of positioning-related reports and any positioning-related reports having a relevance score that is less than or equal to the first relevance threshold for the third set of positioning-related reports.

[0291] Example Embodiment D18. The method of Example Embodiment D17, wherein the suitability threshold is determined based on at least one of the distribution of suitability scores for the first set of positioning-related reports, the radio environment, the performance of the positioning algorithm, the type of model or algorithm used to generate the first set of positioning-related reports, and the number of iterations used to obtain the final UE position estimate.

[0292] Example Embodiment D19. The method of any of Examples D1 to D9, wherein identifying the second set of positioning-related reports and the third set of positioning-related reports includes determining a ranking for each positioning-related report in the first set of positioning-related reports based on a respective suitability score, wherein the ranking of each positioning-related report indicates a level of suitability of the positioning-related report with the first UE position estimate; and performing at least one of: selecting, based on the ranking, N positioning-related reports from the first set of positioning-related reports that are least compatible with the first UE position estimate and including the N least compatible positioning-related reports from the second set of positioning-related reports in the positioning-related reports of the third set of positioning-related reports; and selecting, based on the ranking, M positioning-related reports from the first set of positioning-related reports that are most compatible with the first UE position estimate and including the M most compatible positioning-related reports with the first UE position estimate in the positioning-related reports of the second set of positioning-related reports.

[0293] Example Embodiment D20. The method of Example Embodiment D19, wherein N and / or M are determined based on at least one of the configuration and / or performance and / or type of model or algorithm used to generate the first set of positioning-related reports and the wireless environment.

[0294] Example Embodiment D21. The method of any of Example Embodiments D1-D20, including outputting a second UE position estimate.

[0295] Example Embodiment D22. The method of any of Examples D1 to D20, including determining that the second set of positioning-related reports is smaller than the first set of positioning-related reports, and outputting a second UE position estimate based on the second set of positioning-related reports being smaller than the first set of positioning-related reports.

[0296] Example Embodiment D23. The method of any of Examples D1 to D20, including determining that the second set of positioning-related reports is less than a minimum number of positioning-related reports, and outputting a first UE position estimate based on the second set of positioning-related reports being less than the minimum number of positioning-related reports.

[0297] Example Embodiment D24. The method of Example Embodiment D23, including determining a minimum number of positioning-related reports based on the types of the first set of positioning-related reports.

[0298] Example Embodiment D25. The method of example embodiment D24, wherein the first set of types of positioning related reports is associated with 2D positioning or 3D positioning.

[0299] Example Embodiment D26. The method of any of Example Embodiments D1 to D20, comprising: determining that the second set of positioning related reports is not smaller than the first set of positioning related reports; replacing the first set of positioning related reports with the second set of positioning related reports based on the second set of positioning related reports being not smaller than the first set of positioning related reports; repeating steps 1-4 until the first set of positioning related reports is smaller than the previous set of positioning related reports; and outputting a final UE position estimate based on a positioning operation performed on the final set of positioning related reports.

[0300] Example Embodiment D27. The method of any of Examples D1 to D26, comprising: obtaining at least one new target positioning-related report label for at least one positioning-related report in a third set of positioning-related reports based on a distance between the second UE position estimate or the final UE position estimate and the known position of the TRP; and transmitting the at least one new target positioning-related report label to a network node or another UE acting as a positioning-related training data collection entity.

[0301] Example Embodiment D28. The method of any of Examples D1 to D26, comprising generating at least one new or updated positioning-related report for at least one positioning-related report in a third set of positioning-related reports based on a distance between the second UE position estimate or the final UE position estimate and a known position of the TRP, and transmitting the at least one new or updated positioning-related report to a network node or another UE acting as a positioning-related training data collection entity.

[0302] Example embodiment D29. The method of any of example embodiments D1 to D28, comprising sending to a network node or another UE acting as a positioning-related report generating entity at least one of: an indication that at least one of the positioning-related reports in the first set of positioning-related reports is under-performing; and an indication that at least one of the positioning-related reports in the first set of positioning-related reports has a suitability score below a threshold.

[0303] Example Embodiment D30. The method of any of Example Embodiments D1 to D29, wherein performing a positioning operation to obtain a first UE position estimate and / or a second UE position estimate includes using trilateration.

[0304] Example Embodiment D31. The method of any of Examples D1 to D30, wherein performing a positioning operation to obtain a first UE position estimate and / or a second UE position estimate is based on at least one of one or more ToAs, one or more TDoAs, one or more loss functions, and one or more estimated timing errors and / or jitter.

[0305] Example Embodiment D32. The method of any of Examples D1 to D31, wherein the suitability score of each positioning related report in the first set of positioning related reports is determined as a function of the first UE position estimate and the known location of at least one network node.

[0306] Example Embodiment D33. The method of any of Example Embodiments D1-D32, including transmitting the second UE position estimate and / or the final UE position estimate to another network node.

[0307] Example Embodiment D34. The method of any of Example Embodiments D1-D33, including transmitting the second UE position estimate and / or the final UE position estimate to the UE.

[0308] Example Embodiment D35. The method of any of Examples D1 to D34, wherein the first set of positioning-related reports includes at least one value associated with at least one NLoS between the UE and at least one TRP.

[0309] Example Embodiment D36. The method of any of Example Embodiments D1 to D35, wherein the first set of positioning related reports includes at least one value associated with at least one LoS between the UE and at least one TRP.

[0310] Example Embodiment D37. The method of any of Example Embodiments D1 through D36, wherein the network node acts as an LMF.

[0311] Example Embodiment D38. The method of any of Example Embodiments D1 to D37, further comprising obtaining user data and transferring the user data to the host or user device.

[0312] Example Embodiment D39. A network node comprising processing circuitry configured to perform any of the methods of example embodiments D1 through D38.

[0313] Example Embodiment D40. A network node configured to perform any of the methods of example embodiments D1 to D38.

[0314] Example Embodiment D41. A computer program comprising instructions which, when executed on a computer, perform any of the methods of Examples D1 to D38.

[0315] Example Embodiment D42. A computer program product comprising a computer program, the computer program comprising instructions for performing any of the methods of Examples D1 to D38 when the computer program is run on a computer.

[0316] Example Embodiment D43. A non-transitory computer-readable medium having stored thereon instructions that, when executed by a computer, perform any of the methods of Examples D1 through D38.

[0317] <Example of Group E Implementation> Example Embodiment E1. A method by a network node for improved UE positioning, the method comprising: generating at least one positioning-related report associated with at least one ML model based on at least one radio signal received on an uplink channel from the UE; providing the at least one positioning-related report to a position generation entity; determining whether feedback is received from the position generation entity; and performing at least one action based on whether feedback is received from the position generation entity.

[0318] Example Embodiment E2. The method of Example Embodiment E1, wherein performing at least one action if no feedback is received from the position generation entity within a period of time includes at least one of: discarding at least one wireless signal received on an uplink channel; and discarding data associated with at least one wireless signal received on an uplink channel.

[0319] Example Embodiment E3. The method of Example Embodiment E1, wherein performing at least one action if feedback is received from the position generation entity includes at least one of: generating or compiling new training data based on the feedback received from the position generation entity; and transmitting the new training data to a positioning-related training data collection entity.

[0320] Example Embodiment E4. The method of example embodiment E3, wherein the feedback includes an indication of good quality of at least one positioning-related report.

[0321] Example Embodiment E5. The method of Example Embodiment E4, including continuing to use the ML model to determine the location of the UE and / or for generating the positioning-related report based on good quality of at least one positioning-related report.

[0322] Example Embodiment E6. The method of Example Embodiment E3, wherein when the feedback indicates underperformance of at least one positioning-related report, performing at least one action includes combining at least one wireless signal received on the uplink, and / or pre-processed data associated with the at least one wireless signal, and / or at least one target positioning-related report label to generate at least one new training sample, and adding the at least one new training sample to the training dataset.

[0323] Example Embodiment E7. The method of example embodiment E6, wherein the feedback includes an indication of poor quality of at least one positioning-related report.

[0324] Example Embodiment E8. The method of Example Embodiment E7, including deactivating an ML model used to determine the location of the UE and / or for generating the positioning-related report based on poor quality of at least one positioning-related report.

[0325] Example Embodiment E9. The method of Example Embodiment E7, including updating an ML model used to determine the location of the UE and / or for generating the positioning-related report based on poor quality of at least one positioning-related report.

[0326] Example Embodiment E10. The method of any of Example Embodiments E1 to E9, wherein generating at least one positioning-related report based on at least one wireless signal includes performing at least one measurement based on wireless signals received on an uplink channel, and the at least one positioning-related report includes at least one value associated with the at least one performed measurement.

[0327] Example Embodiment E11. The method of any of Example Embodiments E1 to E10, wherein the at least one value includes at least one of a UL RSTD value, a UL SRS-RSRP value, a UL SRS-RSRPP value, a ToA estimate or value, a UL TDoA value, a UL angle of arrival, a gNB Rx-Tx time difference value, and a reception time value.

[0328] Example Embodiment E12. The method of any of Example Embodiments E1 to E11, wherein at least one positioning-related report includes a UE position estimate, a timestamp associated with at least one measurement and / or at least one value, a cell ID, a TRP ID, SSB information, spatial direction information, UL-SRS configuration information, LoS information, NLoS information, and a quality estimate associated with at least one measurement performed on a wireless signal received on an uplink channel.

[0329] Example Embodiment E13. The method of any of Example Embodiments E1 to E12, wherein providing at least one positioning-related report to the position generation entity includes transmitting at least one positioning-related report to a second network node acting as an LMF.

[0330] Example Embodiment E14. The method of any of Example Embodiments E1 to E12, wherein the position generation entity is located in a network node, and the position generation entity operates to determine the position of the UE based on at least one positioning-related report.

[0331] Example Embodiment E15. The method of any of Example Embodiments E1 to E14, wherein feedback is received from a position generation entity, the feedback including a position of the UE determined based on at least one positioning-related report.

[0332] Example Embodiment E16. The method of any of Example Embodiments E1 to E15, comprising inputting at least one wireless signal to an ML model and receiving a position estimate of the UE from the ML model.

[0333] Example Embodiment E17. The method of any of Example Embodiments E1 to E15, comprising: performing pre-processing to convert at least one wireless signal received on an uplink channel into an input for an ML model; inputting the converted input into the ML model; and receiving a position estimate of the UE from the ML model.

[0334] Example Embodiment E18. The method of any of Example Embodiments E16-E17, wherein the at least one position estimate includes at least one ToA estimate.

[0335] Example Embodiment E19. The method of any of Examples E1 to E18, wherein the at least one wireless signal includes at least one SRS.

[0336] Example Embodiment E20. The method of any of Example Embodiments E1 to E19, wherein the at least one wireless signal includes a plurality of SRSs, each SRS being associated with a respective one of a plurality of TRPs.

[0337] Example Embodiment E21. The method of any of Example Embodiments E1 to E20, wherein the network node includes a base station, a gNB, a TRP, or a reception point.

[0338] Example Embodiment E22. The method of any of Example Embodiments E1-E21, further comprising providing user data and forwarding the user data to the host via transmission to the network node.

[0339] Example Embodiment E23. A user equipment comprising processing circuitry configured to perform any of the methods of example embodiments E1-E22.

[0340] Example Embodiment E24. A user equipment configured or adapted to perform any of the methods of example embodiments E1 to E22.

[0341] Example Embodiment E25. A wireless device comprising processing circuitry configured to perform any of the methods of example embodiments E1-E22.

[0342] Example Embodiment E26. A computer program comprising instructions which, when executed on a computer, perform any of the methods of Example Embodiments E1 to E22.

[0343] Example Embodiment E27. A computer program product comprising a computer program, the computer program comprising instructions for performing any of the methods of example embodiments E1 to E22 when the computer program is run on a computer.

[0344] Example Embodiment E28. A non-transitory computer-readable medium having stored thereon instructions that, when executed by a computer, perform any of the methods of Example Embodiments E1-E22.

[0345] <Example of Group F Implementation> Example Embodiment F1. A method by a network node acting as a position generating entity for improved UE-assisted positioning, the method comprising: receiving, from the network node acting as a position related report generating entity, at least one positioning related report generated based on at least one downlink radio signal; determining a position of the UE based on the at least one positioning related report; and transmitting feedback to the network node acting as the position related report generating entity, the feedback indicating at least one of the position of the UE and a quality of the at least one positioning related report.

[0346] Example Embodiment F2. The method of Example Embodiment F1, including comparing the determined location of the UE with an estimated location of the UE provided in at least one positioning-related report, and determining a quality of the at least one positioning-related report based on the comparing step.

[0347] Example Embodiment F3. The method of Example Embodiment F2, wherein the feedback includes an indication of good quality of the at least one positioning-related report if the estimated location of the UE is within a threshold distance from the determined location of the UE.

[0348] Example Embodiment F4. The method of Example Embodiment F2, wherein if the estimated location of the UE is more than a threshold distance from the determined location of the UE, the feedback includes an indication of poor quality of at least one positioning-related report.

[0349] Example Embodiment F5. The method of any of Examples F1 to F4, wherein the at least one value includes at least one of a DL RSTD value, a DL PRS-RSRP value, a DL PRS-RSRPP value, a ToA estimate or value, a UE Rx-Tx time difference value, and a transmit time value.

[0350] Example Embodiment F6. The method of any of Examples F1 to F5, wherein the at least one positioning-related report includes a UE position estimate, a timestamp associated with at least one measurement and / or at least one value, a cell ID, a TRP ID, SSB information, spatial direction information, DL-PRS configuration information, LoS information, NLoS information, and a quality estimate associated with at least one measurement performed on a wireless signal received on a downlink channel.

[0351] Example Embodiment F7. The method of any of Examples F1 through F6, wherein the at least one position estimate includes at least one ToA estimate.

[0352] Example Embodiment F8. The method of any of Examples F1 through F7, wherein the at least one wireless signal includes at least one PRS associated with at least one TRP.

[0353] Example Embodiment F9. The method of any of Examples F1 to F8, wherein the at least one wireless signal includes a plurality of PRSs, each PRS being associated with a respective one of a plurality of TRPs.

[0354] Example Embodiment F10. The method of any of Examples F1 to F9, wherein the network node acting as the location generating entity is an LMF.

[0355] Example Embodiment F11. The method of any of Example Embodiments F1 to F10, wherein the network node acting as the location-related report generating entity is a gNB or a TRP.

[0356] Example Embodiment F12. The method of any of Examples F1 to F11, further comprising obtaining user data and transferring the user data to a host or user device.

[0357] Example Embodiment F13. A network node comprising processing circuitry configured to perform any of the methods of example embodiments F1 to E12.

[0358] Example Embodiment F14. A network node configured to perform any of the methods of example embodiments F1 to E12.

[0359] Example Embodiment F15. A computer program comprising instructions which, when executed on a computer, perform any of the methods of Examples F1 to E12.

[0360] Example Embodiment F16. A computer program product including a computer program, the computer program including instructions for performing any of the methods of Examples F1 to F12 when the computer program is run on a computer.

[0361] Example Embodiment F17. A non-transitory computer-readable medium having stored thereon instructions that, when executed by a computer, perform any of the methods of Example Embodiments F1-F12.

[0362] <Example of Group G Implementation> Example Embodiment G1. A user equipment (UE) for improved UE positioning, the UE comprising: a processing circuit configured to perform any of the steps of any of the embodiments of groups A and C; and a power supply circuit configured to provide power to the processing circuit.

[0363] Example Embodiment G2. A network node for improved UE positioning, the network node comprising: processing circuitry configured to perform any of the steps of any of the embodiments of groups B, D, E, and F; and power supply circuitry configured to provide power to the processing circuitry.

[0364] Example Embodiment G3. A user equipment (UE) for improved UE positioning, the UE comprising: an antenna configured to transmit and receive radio signals; a radio front-end circuit coupled to the antenna and the processing circuit and configured to condition signals communicated between the antenna and the processing circuit; a processing circuit configured to perform any of the steps of any of the example embodiments of Groups A and C; an input interface coupled to the processing circuit and configured to enable input of information to the UE to be processed by the processing circuit; an output interface coupled to the processing circuit and configured to output information from the UE that has been processed by the processing circuit; and a battery coupled to the processing circuit and configured to provide power to the UE.

[0365] Example Embodiment G4. A host configured to operate in a communication system to provide over-the-top (OTT) services, the host comprising: processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a cellular network for transmission to a user equipment (UE), the UE comprising a communications interface and processing circuitry, the communications interface and processing circuitry of the UE configured to perform any of the steps of any of the example embodiments of groups A and C to receive user data from the host.

[0366] Example Embodiment G5. The host of any preceding example embodiment, wherein the cellular network further includes a network node configured to communicate with the UE to transmit user data from the host to the UE.

[0367] Example Embodiment G6. A host of the two example embodiments described above, wherein the processing circuitry of the host is configured to execute a host application to thereby provide user data, and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0368] Example Embodiment G7. A method implemented by a host operating in a communication system further including a network node and user equipment (UE), the method including providing user data for the UE and initiating a transmission carrying the user data to the UE via a cellular network including the network node, the UE receiving the user data from the host by performing any of the operations of any of the embodiments of Group A.

[0369] Example Embodiment G8. The method of any preceding example embodiment, further comprising receiving user data from the UE by executing, at the host, a host application associated with the client application running on the UE.

[0370] Example Embodiment G9. The method of any preceding example embodiment, further comprising sending, at the host, input data to a client application executing on the UE, wherein the input data is provided by executing the host application and the user data is provided by the client application in response to the input data from the host application.

[0371] Example Embodiment G10. A host configured to operate in a communication system to provide over-the-top (OTT) services, the host comprising processing circuitry configured to provide user data and a network interface configured to initiate transmission of the user data to a cellular network for transmission to a user equipment (UE), the UE comprising a communications interface and processing circuitry, the communications interface and processing circuitry of the UE being configured to transmit the user data to the host by performing any of the steps of any of the example embodiments of groups A and C.

[0372] Example Embodiment G11. The host of any preceding example embodiment, wherein the cellular network further includes a network node configured to communicate with the UE to transmit user data from the UE to the host.

[0373] Example Embodiment G12. A host of the two example embodiments described above, wherein the processing circuitry of the host is configured to execute a host application to thereby provide user data, and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0374] Example Embodiment G13. A method implemented by a host operating in a communication system further including a network node and user equipment (UE), the method including receiving, at the host, user data transmitted by the UE to the host via the network node, and the UE transmitting the user data to the host by performing any of the steps of any of the example embodiments of groups A and C.

[0375] Example Embodiment G14. The method of any preceding example embodiment, further comprising receiving user data from the UE by executing, at the host, a host application associated with the client application executing on the UE.

[0376] Example Embodiment G15. The method of any preceding example embodiment, further comprising sending, at the host, input data to a client application executing on the UE, wherein the input data is provided by executing the host application and the user data is provided by the client application in response to the input data from the host application.

[0377] Example Embodiment G16. A host configured to operate in a communication system to provide over-the-top (OTT) services, the host comprising processing circuitry configured to provide user data and a network interface configured to initiate transmission of the user data to a cellular network for transmission to a user equipment (UE), the network node having the communication interface and processing circuitry, the processing circuitry of the network node configured to transmit the user data from the host to the UE by performing any of the operations of any of the example embodiments of groups B, D, E, and F.

[0378] Example Embodiment G17. The host of the example embodiment described above, wherein processing circuitry of the host is configured to execute a host application that provides user data, and the UE includes processing circuitry configured to receive transmissions of the user data from the host by executing a client application associated with the host application.

[0379] Example Embodiment G18. A method implemented in a host configured to operate in a communication system further including a network node and user equipment (UE), the method including: providing user data for the UE; and initiating a transmission carrying the user data to the UE via a cellular network including the network node, wherein the network node transmits the user data from the host to the UE by performing any of the operations of any of the example embodiments of groups B, D, E, and F.

[0380] Example Embodiment G19. The method of any preceding example embodiment, further comprising, at the network node, transmitting user data provided by the host for the UE.

[0381] Example Embodiment G20. The method of the two example embodiments described above, wherein the user data is provided at the host by executing a host application that interacts with a client application running on the UE, and the client application is associated with the host application.

[0382] Example Embodiment G21. A communications system configured to provide over-the-top services, the communications system including a host, the host comprising processing circuitry configured to provide user data for user equipment (UE), the user data being associated with the over-the-top services, and a network interface configured to initiate transmission of the user data to a cellular network node for transmission to the UE, the network node having a communications interface and processing circuitry, the processing circuitry of the network node being configured to transmit the user data from the host to the UE by performing any of the operations of any of the example embodiments of groups B, D, E, and F.

[0383] Example Embodiment G22. The communication system of any preceding example embodiment, further comprising a network node and / or user equipment.

[0384] Example Embodiment G23. A host configured to operate in a communication system to provide over-the-top (OTT) services, the host comprising: processing circuitry configured to initiate reception of user data; and a network interface configured to receive the user data from a network node in a cellular network, the network node having a communication interface and processing circuitry, the processing circuitry of the network node configured to receive the user data from a user equipment (UE) for the host by performing any of the operations of any of the example embodiments of groups B, D, E, and F.

[0385] Example Embodiment G24. A host of the two example embodiments, wherein the processing circuitry of the host is configured to provide user data by executing a host application, the host application is configured to interact with a client application running on the UE, and the client application is associated with the host application.

[0386] Example Embodiment G25. The host of any of the preceding two example embodiments, wherein initiating reception of user data includes requesting the user data.

[0387] Example Embodiment G26. A method implemented by a host configured to operate in a communication system further including a network node and a user equipment (UE), the method including initiating, at the host, reception of user data from the UE, the user data originating from a transmission received by the network node from the UE, the network node receiving the user data from the UE for the host by performing any of the steps of any of the example embodiments of groups B, D, E, and F.

[0388] Example Embodiment G27. The method of any preceding example embodiment, further comprising, at the network node, transmitting the received user data to the host.

Claims

1. A method (2000) for improving UE positioning by a first network node (1110), the method comprising: generating at least one positioning-related report associated with at least one ML (machine learning) model (2002); transmitting (2004) said at least one positioning-related report to a second network node (1110, 502) acting as a position generating entity; receiving feedback from the second network node indicating a quality level of the at least one positioning-related report (2006); performing at least one action based on the feedback indicating the quality level of the at least one positioning-related report (2008); A method comprising:

2. 2. The method of claim 1, wherein if the feedback is not received from the position generation entity within a period of time, performing the at least one action comprises discarding data associated with at least one wireless signal received on the uplink channel.

3. 2. The method of claim 1, wherein performing the at least one action comprises: generating or compiling new training data based on the feedback received from the position generation entity; transmitting the new training data to a positioning-related training data collection entity; The method includes at least one of:

4. 4. The method of claim 3, the feedback includes an indication of good quality of the at least one positioning-related report; performing the at least one action includes continuing to use the at least one model for determining a position of a UE (User Equipment) and / or generating a positioning-related report based on the indication of good quality of the at least one positioning-related report.

5. 4. The method of claim 3, the feedback indicating poor quality of the at least one positioning-related report; Performing the at least one action includes: generating at least one new training sample based on at least one of the at least one wireless signal received on the uplink, data associated with the at least one wireless signal, and at least one target positioning-related report label; adding the at least one new training sample to a training dataset; and A method comprising:

6. 6. The method of claim 5, wherein performing the at least one action comprises: based on the poor quality of the at least one positioning-related report, invalidating the at least one ML model used for determining the UE's position and / or generating the at least one positioning-related report.

7. 6. The method of claim 5, wherein performing the at least one action comprises: updating the at least one ML model used for determining the location of the UE and / or generating the at least one positioning-related report based on the poor quality of the at least one positioning-related report.

8. 8. The method of claim 1, wherein generating the at least one positioning-related report comprises: receiving from the UE at least one value associated with at least one measurement performed by the UE based on the radio signal; The method, wherein the at least one positioning related report includes the at least one value associated with the at least one measurement performed.

9. 9. The method of claim 8, wherein the at least one value is: UL SRS-RSRP (Uplink-Sounding Reference Signal-Reference Signal Received Power) value, UL SRS-RSRPP (Uplink-Sounding Reference Signal-Reference Signal Received Path Power) value, ToA (time of arrival) estimate or value, UL TDoA (Uplink Time Difference of Arrival) value, UL AoA (Uplink Angle of Arrival), gNB Rx-Tx (gNodeB receive-transmit) time difference value, and Received time value, The method includes at least one of:

10. 10. The method of claim 1, wherein the at least one positioning related report comprises: UE position estimate, a timestamp associated with at least one measurement and / or at least one value; Cell ID (cell identifier), TRP ID (Transmitting / Receiving Point Identifier), SSB (Synchronization Signal Block) information, spatial direction information, DL-PRS (downlink positioning reference signal) setting information, LoS (line of sight) information, NLoS (non-line-of-sight) information, and a quality estimate associated with at least one measurement performed on the wireless signal received on the uplink channel; The method includes at least one of:

11. 11. The method of claim 1, wherein providing the at least one positioning related report to the location generation entity comprises sending at least one positioning related report to a second network node acting as a Location Management Function (LMF).

12. 12. The method of claim 1, comprising inputting the at least one radio signal to the at least one ML model; and receiving a position estimate of the UE from the at least one ML model.

13. 12. The method according to any one of claims 1 to 11, performing pre-processing to convert said at least one radio signal into an input to said at least one ML model; inputting the transformed input into the at least one ML model; receiving a location estimate of the UE from the at least one ML model; A method comprising:

14. 14. The method of claim 12 or 13, wherein at least one said position estimate comprises at least one ToA (Time of Arrival) estimate.

15. 15. The method according to any one of claims 1 to 14, wherein the at least one radio signal comprises at least one SRS.

16. 16. The method of any one of claims 1 to 15, wherein the first network node comprises a base station, a gNodeB, a TRP (Transmission / Reception Point), or a reception point.

17. 1. A method (2100) for improving assisted positioning by a second network node (1110, 502) acting as a position generating entity, the method comprising: receiving (2102) from a first network node (1110, 506) operating as a positioning-related report generating entity a first set of positioning-related reports generated based on at least one wireless signal transmitted on a downlink channel; determining (2104) a location of a UE (User Equipment) (1112) based on the first set of positioning-related reports; sending (2106) feedback to the first network node acting as the positioning-related report generating entity, the feedback indicating a quality of the at least one positioning-related report; A method comprising:

18. 18. The method of claim 17, wherein determining the location of the UE comprises: performing a positioning operation to obtain a first UE position estimate based on the first set of positioning-related reports; based on a respective relevance score for each positioning-related report in the first set of positioning-related reports; a second set of positioning-related reports having a relevance score better than a relevance threshold; a third set of positioning-related reports having a relevance score not better than the relevance threshold; and sending a notification to the first network node that the third set is associated with a fitness score that is not better than the fitness threshold; A method comprising:

19. 20. The method of claim 18, the second set of positioning-related reports is a first subset of the first set of positioning-related reports; A method, wherein the third set of positioning related reports is a first subset of the first set of positioning related reports.

20. 19. The method of claim 17 or 18, obtaining at least one new target positioning-related report label for at least one positioning-related report in the third set of positioning-related reports based on a distance between the location of the UE and a known location of a TRP (Transmission / Reception Point); transmitting the at least one new target positioning related report label to the first network node; A method comprising:

21. 21. The method of claim 20, wherein obtaining the at least one new target positioning-related report label for the at least one positioning-related report in the third set of positioning-related reports comprises: the speed of the wireless signal; UE timing error related estimates, and the time difference of arrival between two TRPs, and calculating based on at least one of:

22. 22. The method of any one of claims 17 to 21, comprising: comparing the location of the UE determined by the second network node with an estimated location of the UE provided in the first set of positioning related reports; determining the quality of the first set of positioning-related reports based on the comparison between the location of the UE determined by the second network node and the estimated location provided in the first set of positioning-related reports; A method comprising:

23. 23. The method of claim 22, wherein if the estimated location of the UE provided in the first set of positioning-related reports is less than or equal to a threshold distance from the location of the UE determined by the second network node, the feedback comprises an indication of good quality of the at least one positioning-related report.

24. 23. The method of claim 22, wherein if the estimated location of the UE provided in the first set of positioning-related reports is more than a threshold distance from the location of the UE determined by the second network node, the feedback includes an indication of poor quality of the at least one positioning-related report.

25. 25. The method of any one of claims 1 to 24, the first set of positioning-related reports includes at least one value associated with at least one measurement performed by the UE based on the at least one radio signal; The at least one value is DL RSTD (Downlink Reference Signal Time Difference) value, DL PRS-RSRP (Downlink Positioning Reference Signal-Reference Signal Received Power) value, DL PRS-RSRPP (Downlink Positioning Reference Signal-Reference Signal Received Path Power) value, ToA (time of arrival) estimate or value, UE Rx-Tx (UE receiver-transmitter) time difference value, and Send time value, The method includes at least one of:

26. 26. The method of any one of claims 17 to 25, wherein the first set of positioning related reports comprises: UE position estimate, a timestamp associated with at least one measurement and / or at least one value; Cell ID (cell identifier), TRP ID (Transmitting / Receiving Point Identifier), SSB (Synchronization Signal Block) information, spatial direction information, DL-PRS (downlink positioning reference signal) setting information, LoS (line of sight) information, NLoS (non-line-of-sight) information, and a quality estimate associated with at least one measurement performed on the wireless signal received on the downlink channel; The method includes at least one of:

27. 27. The method of claim 26, wherein the at least one location estimate includes at least one ToA (Time of Arrival) estimate.

28. 28. The method of any one of claims 17 to 27, wherein the at least one radio signal comprises at least one PRS (Positioning Reference Signal) associated with at least one TRP (Transmission / Reception Point).

29. 29. The method of any one of claims 17 to 28, wherein the second network node acting as a location generation entity is a Location Management Function (LMF).

30. 30. The method according to any one of claims 17 to 29, wherein the first network node acting as the positioning-related report generating entity is a gNodeB or a TRP (Transmission / Reception Point).

31. A first network node (1110, 506) for improving UE positioning, said first network node comprising: generating at least one positioning-related report associated with at least one ML (machine learning) model; transmitting said at least one positioning related report to a second network node (1110, 502) acting as a position generating entity; receiving feedback from the second network node indicating a quality level of the at least one positioning-related report; performing at least one action based on the feedback indicating the quality level of the at least one positioning-related report; a first network node configured to:

32. A first network node according to claim 31, configured to perform the method according to any one of claims 2 to 16.

33. a second network node (1110, 502) acting as a position generating entity for improving the assisted positioning, said second network node comprising: receiving, from a first network node (1110, 506) operating as a positioning-related report generating entity, a first set of positioning-related reports generated based on at least one radio signal transmitted on a downlink channel; determining a location of a UE (User Equipment) (1112) based on said first set of positioning-related reports; sending feedback to the first network node acting as the positioning-related report generating entity, the feedback indicating a quality of the at least one positioning-related report; a second network node configured to:

34. A second network node according to claim 31, configured to perform the method according to any one of claims 18 to 30.

Images