Positioning frame including enhanced support for AI / ML

Abstract

A user equipment (100) of a wireless communication system according to an embodiment is provided. The user equipment (100) is configured to determine and / or receive information about the suitability of the machine learning model. And / or the user equipment (100) is configured to determine and / or receive information that the user equipment (100) is located in the machine learning assistance area.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication systems or networks, and more particularly, to an apparatus and method for providing a modified OFDM frame structure. Background Art

[0002] FIG. 18 is a schematic diagram of an example of a terrestrial wireless network 100, as shown in FIG. 18(a), including a core network and one or more radio access networks RAN1, RAN2, ...RAN N (RAN = Radio Access Network). FIG. 18(b) shows a radio access network RAN. n Schematic diagram of an example of a 5G network, which may include one or more base stations gNB1 to gNB5 (gNB = next generation Node B), each base station serving a specific area around the base station schematically represented by the corresponding cells 1061 to 1065. The base station is arranged to provide services to users within the cell. One or more base stations can serve users in licensed and / or unlicensed frequency bands. The term base station BS refers to a gNB in ​​a 5G network, an eNB in ​​UMTS / LTE / LTE-A / LTE-A Pro, or simply a BS in other mobile communication standards. Users can be fixed devices or mobile devices. The wireless communication system can also be accessed by mobile or fixed IoT (Internet of Things) devices connected to the base station or the user. Mobile devices or IoT devices can include physical devices, ground vehicles (such as robots or cars), aircraft (such as manned or unmanned aerial vehicles, UAVs (the latter also called drones)), buildings and other items or devices, in which electronic devices, software, sensors, actuators, etc. are embedded, as well as network connections that enable these devices to collect and exchange data on existing network infrastructure. Figure 18(b) shows an exemplary view of five cells, however, the RAN n More or fewer such cells may be included, and the RAN nIt is also possible to include only one base station. Figure 18(b) shows two users UE1 and UE2 (UE = user equipment), also referred to as user equipment UE, which are located in cell 1062 and served by base station gNB2. Another user UE3 served by base station gNB4 is shown in cell 1064. Arrows 1081, 1082 and 1083 schematically represent uplink / downlink connections for sending data from users UE1, UE2 and UE3 to base stations gNB2, gNB4, or for sending data from base stations gNB2, gNB4 to users UE1, UE2, UE3. This can be achieved in a licensed band or an unlicensed band. In addition, Figure 18(b) shows two IoT devices 1101 and 1102 in cell 1064, which can be fixed or mobile devices. IoT device 1101 accesses the wireless communication system via base station gNB4 to receive and send data, as schematically represented by arrow 1121. As schematically indicated by arrow 1122, the IoT device 1102 accesses the wireless communication system via the user UE3. The corresponding base stations gNB1 to gNB5 can be connected to the core network 102, for example, via the S1 interface, via the corresponding backhaul links 1141 to 1145, which is schematically indicated by the arrow pointing to "core" in Figure 18(b). The core network 102 can be connected to one or more external networks. The external network can be the Internet or a private network, such as an intranet or any other type of campus network, such as a private WiFi or a 4G or 5G mobile communication system. In addition, some or all of the corresponding base stations gNB1 to gNB5 can be connected to each other via corresponding backhaul links 1161 to 1165, for example, via the S1 or X2 interface or XN interface in NR (New Radio), as shown by the arrow pointing to "gNBs" in Figure 18(b). The sidelink channel allows direct communication between UEs, also known as device-to-device, D2D (device-to-device) communication. The sidelink interface in 3GPP (3rd Generation Partnership Project) is named PC5 (Short Range Communication 5).

[0003] For data transmission, a physical resource grid may be used. The physical resource grid may include a set of resource units to which various physical channels and physical signals are mapped. For example, physical channels may include physical downlink, uplink and sidelink shared channels PDSCH (Physical Downlink Shared Channel), PUSCH (Physical Uplink Shared Channel) and PSSCH (Physical Sidelink Shared Channel) carrying user-specific data (also referred to as downlink, uplink, sidelink payload data), physical broadcast channels PBCH (Physical Broadcast Channel) carrying, for example, a master information block MIB and one or more system information blocks SIB, one or more sidelink information blocks SLIB (if supported), physical downlink, uplink and sidelink control channels PDCCH (Physical Downlink Control Channel), PUCCH (Physical Uplink Control Channel), PSCCH (Physical Sidelink Control Channel) carrying downlink control information DCI, uplink control information UCI and sidelink control information SCI, and physical sidelink feedback channels PSFCH (Physical Sidelink Feedback Channel) carrying PC5 feedback responses. Note that the sidelink interface may support level 2 SCI (voice call item). This refers to a first control region comprising some portion of the SCI, and optionally a second control region comprising a second portion of the control information.

[0004] For the uplink, the physical channels may also include a physical random access channel PRACH (packet random access channel) or RACH (random access channel), which the UE uses to access the network once it is synchronized and obtains the MIB and SIB. Physical signals may include reference signals or symbols RS, synchronization signals, etc. The resource grid may include frames or radio frames with a specific duration in the time domain and a given bandwidth in the frequency domain. The frame may have a specific number of subframes of a predetermined length (e.g. 1ms). Depending on the length of the cyclic prefix CP, each subframe may include one or more time slots of 12 or 14 OFDM symbols (OFDM = Orthogonal Frequency Division Multiplexing). The frame may also include a smaller number of OFDM symbols, for example when utilizing a shortened transmission time interval, sTTI (slot or subslot transmission time interval) or a mini-slot / non-slot based frame structure comprising only a few OFDM symbols.

[0005] The wireless communication system may be any single tone or multi-carrier system using frequency division multiplexing, such as orthogonal frequency division multiplexing OFDM or orthogonal frequency division multiple access OFDMA (Orthogonal Frequency Division Multiple Access), or any other IFFT-based signal (IFFT=Inverse Fast Fourier Transform) with or without CP, such as DFT-s-OFDM (DFT=Discrete Fourier Transform). Other waveforms may be used, such as non-orthogonal waveforms for multiple access, such as filter bank multi-carrier FBMC, generalized frequency division multiplexing GFDM or universal filtering multi-carrier UFMC. The wireless communication system may operate, for example, according to the LTE-Advanced pro standard, the 5G or NR new radio standard or the NR-U new radio unlicensed standard.

[0006] The wireless network or communication system shown in Figure 18 can be a heterogeneous network with different overlapping networks, for example, a macrocell network, each macrocell including macro base stations (such as base stations gNB1 to gNB5) and a small cell base station network (not shown in Figure 18, such as femto or pico base stations). In addition to the above-mentioned terrestrial wireless networks, there are also non-terrestrial wireless communication networks NTN, including space-borne transceivers such as satellites and / or airborne transceivers such as unmanned aircraft systems. The non-terrestrial wireless communication network or system can operate in a similar manner to the terrestrial system described above with reference to Figure 18, for example according to the LTE-Advanced Pro standard or the 5G or NR new radio standard.

[0007] In a mobile communication network, for example, in a network as described above with reference to FIG. 18 , such as an LTE or 5G / NR network, there may be UEs that communicate directly with each other through one or more side link SL channels, for example using a PC5 / PC3 interface or WiFi direct connection. UEs that communicate directly with each other through side links may include vehicles that communicate directly with other vehicles (V2V communication), vehicles that communicate with other entities of a wireless communication network (e.g., roadside units RSU or roadside entities such as traffic lights, traffic signs, or pedestrians) (V2X communication). Depending on the specific network configuration, the RSU may have the functionality of a BS or a UE. Other UEs may not be vehicle-related UEs and may include any of the above-mentioned devices. These devices may also communicate directly with each other (D2D communication) using SL channels.

[0008] In a wireless communication network, as shown in Figure 18, it may be necessary to locate a UE with a certain accuracy, for example, to determine the position of the UE in a cell. Several positioning methods are known, such as satellite-based positioning methods, such as autonomous and assisted global navigation satellite systems A-GNSS (such as GPS), mobile radio cellular positioning methods (such as observed time difference of arrival OTDOA and enhanced cell ID E-CID or a combination thereof).

[0009] High accuracy positioning is usually based on line of sight (LOS) signals, where the first signal arrives in time of flight (ToF) based on distance and the speed of light relative to the transmission time. Position can be determined by transmitting or receiving signals from a TRP (transmit and receive point) using a known location (anchor point for positioning) and trilateration and / or triangulation or other positioning algorithms.

[0010] There may be areas in the network where the UE may not have a sufficient number of anchors, e.g., TRPs with known positions that are reachable under LOS conditions. As a result, the accuracy of the estimate of the corresponding UE position may deteriorate. A brute force solution is to increase the number of TRPs (densification of TRPs) such that the UE can always find a minimum number of TRPs with at least LOS conditions for a given positioning method. However, this approach is not scalable and cannot adapt to changes in the environment. Of course, in some cases, it may not be possible to reach sufficient TRPs, either under LOS or NLOS conditions, and the position accuracy may be further degraded.

[0011] Methods based on detailed analysis of the received signal (mainly the channel impulse response (CIR) with or without angular information) may also work under NLOS conditions, but these methods require detailed environmental information. One example is ray tracing-based methods to predict CIR characteristics under NLOS conditions. Another example is to measure the characteristics of the received signal (signal strength, CIR, angle of arrival (AoA) information, etc. or a subset thereof) during a "training phase" and store them as fingerprints.

[0012] Both examples may be affected by changes in the environment, which may require updating the data captured during the training phase or generated by other methods.

[0013] 3GPP's Rel-16 introduced different UL and DL positioning methods to support timing and angle-based solutions for 5G positioning. In Rel-17, in addition to the introduction of RSRP measurements, accuracy enhancements also focused on LOS and NLOS classification and additional path reporting. However, NR positioning solutions depend on LOS conditions, while NR positioning solutions in NLOS are left for Rel-18 discussion, as most of these methods are AI / ML related or AI / ML enabled. Summary of the invention

[0014] It would be advantageous if improved concepts for positioning in wireless communication systems could be provided.

[0015] A user equipment of a wireless communication system according to an embodiment is provided. The user equipment is configured to determine and / or receive information about the applicability of a machine learning model. And / or, the user equipment is configured to determine and / or receive information that the user equipment is located in a machine learning auxiliary area.

[0016] Furthermore, a user equipment of a wireless communication system according to an embodiment is provided. The user equipment is configured to determine, based on the time reference information, whether it shall act as a time anchor unit, for example as a time anchor or as a time PRU or as a PRU.

[0017] In addition, a user equipment of a wireless communication system according to an embodiment is provided. The user equipment is configured to obtain information about its location and / or obtain distance information (e.g., ranging information) between the user equipment and another entity of the wireless communication system (e.g., another user equipment). The information is obtained by receiving information from another user equipment acting as a time anchor unit (e.g., a time anchor or a time PRU or PRU), for example, via a direct communication link or indirectly through a network, wherein the information received from the time anchor unit includes the location of the time anchor unit and / or one or more measurements performed by the time anchor unit on a signal sent by the user equipment, or wherein the information contains a location reference signal. In addition, the information is obtained by performing one or more measurements on one or more received signals and / or by sending derived information derived from the measurements of the wireless communication system to a network entity (e.g., to an LMF or NWDAF).

[0018] In addition, a user equipment of a wireless communication system according to an embodiment is provided. The user equipment (e.g., a UL-TDOA device) is configured to support an entity of the wireless communication system (e.g., a network entity) to obtain information about the location of the user equipment and / or obtain information about the distance between the user equipment and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information) by sending one or more reference signals to another user equipment acting as a time anchor unit (e.g., a time anchor or time PRU or PRU), for example, via a direct communication link or indirectly through a network, so as to allow the time anchor to perform one or more measurements on the one or more reference signals and / or report one or more measurements to the entity of the wireless communication system.

[0019] In addition, a user equipment of a wireless communication system according to an embodiment is provided. The user equipment is configured to determine, for example, by using RAT-independent techniques and / or by using RAT-dependent techniques and / or by using time anchor points, or is configured to receive information about its location and / or information about the distance between the user equipment and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information). In addition, the user equipment is configured to use the information about its location and / or the information about the distance to assist in generating training data for a machine learning model for positioning, for example, for machine learning with relevant labels.

[0020] In addition, a user equipment of a wireless communication system according to an embodiment is provided. The user equipment is configured to send information about one or more attributes of RF channel characteristics between the user equipment and another entity of the wireless communication system and / or an indicator of the probability of the existence of a direct path ("line of sight" path) and / or information about the characteristics of one or more RF channel propagation paths that are not associated with the direct path, wherein the other entity of the wireless communication system is a base station or another user equipment of the wireless communication system. In addition, the user equipment is configured to report information about one or more channel impulse responses to the other entity or another entity of the wireless communication system.

[0021] In addition, a user equipment of a wireless communication system is provided. The user equipment is configured to receive measurement and / or transmission characteristic information.

[0022] In addition, a user equipment of a wireless communication system according to an embodiment is provided. The user equipment is configured to receive one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system from a network entity of the wireless communication system. In addition, the user equipment is configured to receive measurement and / or transmission characteristic information including a set of one or more parameters from the network entity of the wireless communication system. In addition, the user equipment is configured to use one or more PRS configurations and use the measurement and / or transmission characteristic information to determine its position and / or information about the distance between the user equipment and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information).

[0023] In addition, a network entity of a wireless communication system according to an embodiment is provided. The network entity is configured to send time reference information to a user equipment of the wireless communication system to enable the user equipment to determine whether it can act as a time anchor unit, for example as a time anchor or as a time PRU or as a PRU. If the user equipment has determined that it will act as a time anchor unit, the network entity is configured to receive information about its location and / or about one or more measurement and / or location reference signals from the user equipment; and / or information about the distance between the user equipment and another entity of the wireless communication system (for example, another user equipment) (for example, ranging information).

[0024] Furthermore, a network entity of a wireless communication system according to an embodiment is provided. The network entity is configured to receive, from a user equipment of the wireless communication system, information about one or more line-of-sight links, for example defined by an RF channel (the RF channel comprising a direct path with a delay according to the distance), or information about one or more attributes or one or more characteristics of one or more RF channels between the network entities, or information that there is no line-of-sight link to another entity of the wireless communication system (for example to another network entity).

[0025] In addition, a network entity of a wireless communication system according to an embodiment is provided. If a user equipment of the wireless communication system is to act as a time anchor unit, the network entity is configured to receive information about one or more measurements from the user equipment, such as one or more measurements performed on a location reference signal sent by the device. In addition, the network entity is configured to use the information about the location of the user equipment and use the information about the one or more measurements to determine the location of the device and / or determine the distance between the user equipment and the device.

[0026] In addition, a network entity of a wireless communication system according to an embodiment is provided. The network entity is configured to send measurement and / or transmission characteristic information, such as ACS information (association and calibration point information), to a user equipment of the wireless communication system, wherein the measurement and / or transmission characteristic information is associated with one or more TRPs and is also associated with a geographical area.

[0027] In addition, a network entity of a wireless communication system according to an embodiment is provided. The network entity is configured to send one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system to a user equipment of the wireless communication system. The network entity is configured to send measurement and / or transmission characteristic information, such as ACS information (association and calibration point information), including a set of one or more parameters to the user equipment of the wireless communication system, for example, wherein the measurement and / or transmission characteristic information includes information about the relationship between the ACS-ID and the auxiliary data, for example, wherein the auxiliary data includes the PRS configuration.

[0028] Furthermore, a wireless communication system is provided, comprising one or more user equipments (100) as described above according to the embodiments, and one or more network entities as described above.

[0029] In addition, a wireless communication system according to an embodiment is provided. The wireless communication system includes at least two entities, each of which is a user equipment or a network entity, wherein the at least two entities include a first entity and a second entity. The first entity is configured to determine whether it will act as a time anchor unit, such as a time anchor or as a time PRU or as a PRU, based on time reference information. The second network entity is configured to perform one or more measurements and is configured to provide one or more reports derived from the one or more measurements to another network entity (e.g., an LMF or an NWDAF) to train a model (e.g., a neural network) or capture characteristics of one or more RF signals received in an area.

[0030] In addition, a wireless communication system according to an embodiment is provided. At least one of the multiple entities is configured to use one or more measurements of one or more user equipments of the wireless communication system to perform one or more comparisons. In addition, at least one of the multiple entities is configured to perform unsupervised learning of similar attributes or characteristics, such as one or more channel impulse responses or one or more parameters thereof. At least one of the multiple entities is configured to perform supervised learning using one or more time anchors of the wireless communication system. In addition, at least one of the multiple entities is configured to perform supervised learning to map similar attributes or characteristics (such as channel impulse responses or parameters thereof) to corresponding reference information, such as speed and / or orientation and / or acceleration and / or position and / or distance. At least one of the multiple entities is configured to train or collect ML models using a combination of supervised (e.g., with output labels) and unsupervised (e.g., without output labels) methods. In addition, at least one of the multiple entities is configured to use labels obtained from one or more time anchors to provide real-world dimensions to the trained model, wherein the labels allow the learned representations to be converted (e.g., scaled and rotated) to real-world dimensions.

[0031] In addition, a method for a wireless communication system according to an embodiment is provided. The method includes determining by a user equipment of the wireless communication system and / or receiving by the user equipment information about the applicability of the machine learning model. And / or, the method includes determining by a user equipment of the wireless communication system and / or receiving by the user equipment information that the user equipment is located in a machine learning assistance area.

[0032] Furthermore, a method for a wireless communication system according to an embodiment is provided. The method comprises determining, based on time reference information, whether a user equipment of the wireless communication system is to act as a time anchor unit, for example as a time anchor or as a time PRU or as a PRU.

[0033] In addition, a method for a wireless communication system according to an embodiment is provided. The method includes obtaining, by a user equipment of the wireless communication system, information about its location and / or obtaining information about the distance between the user equipment and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information). The information is obtained by receiving information from another user equipment acting as a time anchor unit (e.g., a time anchor or a time PRU or a PRU), for example, via a direct communication link or indirectly through a network, wherein the information received from the time anchor unit includes the location of the time anchor unit and / or one or more measurements performed by the time anchor unit on a signal sent by the user equipment, or wherein the information contains a location reference signal. In addition, information is obtained by performing one or more measurements on one or more received signals and / or by sending derived information derived from the measurements of the wireless communication system to a network entity (e.g., to an LMF or NWDAF).

[0034] In addition, a method for a wireless communication system according to an embodiment is provided. The method includes sending one or more reference signals by a user equipment of the wireless communication system to another user equipment acting as a time anchor unit (e.g., a time anchor or time PRU or PRU), for example, via a direct communication link or indirectly through a network, to support an entity of the wireless communication system (e.g., a network entity) to obtain information about the location of the user equipment and / or obtain information about the distance between the user equipment and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information), so as to allow the time anchor point to perform one or more measurements on the one or more reference signals and / or report one or more measurements to the entity of the wireless communication system.

[0035] In addition, a method for a wireless communication system according to an embodiment is provided. The method includes determining, for example, by using RAT-independent techniques and / or by using RAT-dependent techniques and / or by using time anchor points, or receiving by a user equipment of the wireless communication system, information about the location of the user equipment and / or information about the distance between the user equipment and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information), and using the information about its location or the information about the distance by the user equipment to assist in generating training data for a machine learning model, such as for machine learning with relevant labels. For example, the machine learning model is located on the LMF or NWDAF of the wireless communication system.

[0036] In addition, a method for a wireless communication system according to an embodiment is provided. The method includes sending, by a user equipment of the wireless communication system, information about one or more attributes of RF channel characteristics between the user equipment and another entity of the wireless communication system and / or an indicator of the probability of the existence of a direct path ("line of sight" path) and / or information about characteristics of one or more RF channel propagation paths that are not associated with the direct path, wherein the other entity of the wireless communication system is a base station or another user equipment of the wireless communication system. The method includes reporting, by the user equipment, information about one or more channel impulse responses to the other entity or another entity of the wireless communication system.

[0037] Furthermore, a method for a wireless communication system according to an embodiment is provided, wherein the method comprises receiving measurement and / or transmission characteristic information by a user equipment.

[0038] In addition, a method for a wireless communication system is provided. The method includes receiving, by a user equipment, one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system from a network entity of the wireless communication system. In addition, the method includes receiving, by the user equipment, measurement and / or transmission characteristic information including a set of one or more parameters from the network entity of the wireless communication system. In addition, the method includes determining, by the user equipment, its location and / or information about the distance between the user equipment and another entity of the wireless communication system (e.g., another user equipment) using the one or more PRS configurations and using the measurement and / or transmission characteristic information. (e.g., ranging information).

[0039] Furthermore, a computer program according to the embodiment is provided for implementing one of the above methods when a computer or a signal processor executes the computer program.

[0040] Some embodiments may, for example, define methods for managing related neural networks, methods for continuous updating, and related signaling. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Hereinafter, embodiments of the present invention will be described in more detail with reference to the accompanying drawings, in which:

[0042] Figure 1 A user equipment and network entities of a wireless communication system according to an embodiment are shown.

[0043] Figure 2 An overview of some concepts according to certain embodiments is presented.

[0044] Figure 3 An example of NLOS positioning is shown.

[0045] Figure 4Components of a 3GPP network in a non-roaming scenario suitable for positioning are shown.

[0046] Figure 5 An example process of determining UE location at LMF based on an ML model according to an implementation scheme is shown.

[0047] Figure 6 An example of obtaining training features based on ML on the network side is shown.

[0048] Figure 7 An example stage 2 of UE-based positioning based on an ML model and network-provided assistance data is shown.

[0049] Figure 8 Association and calibration points are shown according to an embodiment.

[0050] Fig. 9 Shown according to Figure 8 Example of ACS information for an implementation of a scenario.

[0051] Fig.10 Details of potential pre-processing steps according to an embodiment are shown.

[0052] Fig.11 A scheme of a specific model identification process according to an embodiment is shown.

[0053] Fig.12 An exemplary scheme of a continuous model identification process according to an embodiment is shown.

[0054] Fig.13 An exemplary scheme of our proposed supervised learning process according to an implementation scheme is shown.

[0055] Fig.14 A scheme of an unsupervised learning process according to an embodiment is shown.

[0056] Fig.15 A global perspective of the continuous learning process according to an embodiment is shown.

[0057] Fig.16 A processing scheme for a continuous iterative learning process according to an embodiment is shown.

[0058] Fig.17 An abstract scheme of a model identification process according to an embodiment is shown.

[0059] FIG. 18 shows a schematic diagram of an example of a terrestrial wireless network.

[0060] Fig.19 An example of a computer system on which the units or modules and method steps described according to the method of the present invention can be executed is shown. DETAILED DESCRIPTION

[0061] Figure 1 A user equipment 100 of a wireless communication system according to an embodiment is shown.

[0062] The user device 100 is configured to determine and / or receive information regarding the suitability of a machine learning model.

[0063] And / or, the user device 100 is configured to determine and / or receive information that the user device 100 is located in a machine learning assisted area.

[0064] also, Figure 1 A network entity 200 of a wireless communication system is shown.

[0065] Specific details of the machine learning model and / or machine learning auxiliary area will be provided later in the description, for example, see Figures 11 to 17 and the corresponding parts in the description relating to these figures.

[0066] Additionally, some implementation schemes related to machine learning models and / or machine learning auxiliary areas will now be provided.

[0067] According to an embodiment, the user equipment 100 may for example be a sensor unit and / or wherein the user equipment 100 may for example have sensor unit capabilities.

[0068] In one embodiment, the user equipment 100 may be configured, for example, to receive information from a network entity 200 of the wireless communication system that the user equipment 100 is located in a machine learning assisted area.

[0069] According to one embodiment, the user equipment 100 may, for example, be configured to receive information from a network node of a wireless communication system, the information comprising information about at least one of the following:

[0070] - no AI / ML support is provided for the region where the user device 100 is located,

[0071] - the model for the user's region is still in the training phase and the model is requesting further data for model training,

[0072] - the model is partially trained and position estimation, separation estimation or distance estimation and / or measurement signal classification may be required to further determine the availability of ML / AI support,

[0073] - The model also covers the NLOS region and is able to determine the position or distance in the NLOS region,

[0074] - the model is usable but may be less accurate, for example due to changes in the environment,

[0075] - an operating mode, such as requiring an update of the operating mode due to reduced confidence and / or such as an update phase operating mode and / or a high confidence operating mode such as in a NLOS area.

[0076] In one embodiment, the user equipment 100 may be configured, for example, to perform one or more measurements by measuring one or more reference signals. The user equipment 100 may be configured, for example, to determine whether the user equipment 100 is located in a machine learning assisted area by receiving an indication from a network entity 200 of the wireless communication system and / or by receiving auxiliary data required to identify the machine learning assisted area from the network entity 200 of the wireless communication system. And / or, the user equipment 100 may be configured, for example, to identify the machine learning assisted area by analyzing one or more measurements. And / or, the user equipment 100 may be configured, for example, to transmit information about one or more measurements to an entity of the wireless communication system, and obtain the information about whether the user equipment (100) is located in the machine learning assisted area from the entity or from another entity of the wireless communication system as a response to transmitting the information about one or more measurements.

[0077] According to one embodiment, the user equipment 100 may, for example, be configured to measure one or more reference signals, which are one or more downlink reference signals and / or through one or more sidelink reference signals and / or one or more uplink reference signals.

[0078] In one embodiment, the one or more downlink reference signals are one or more of PSS, SSS, CSI-RS and DL-PRS, and / or the one or more uplink reference signals are one or more UL-PRS and / or one or more SRS.

[0079] According to one embodiment, the user device 100 may be configured to receive one or more thresholds, for example. The user device 100 may be configured to compare one or more measurements with one or more thresholds, for example, to determine whether the user device 100 is located in a machine learning assisted area.

[0080] In one embodiment, the one or more thresholds include at least one of an RSRP threshold and an SNR threshold. Based on the RSRP threshold and / or the SNR threshold, the user equipment 100 may, for example, be configured to trigger activation or deactivation of the machine learning model.

[0081] According to one embodiment, the user equipment 100 may, for example, be configured to perform one or more of the following measurements:

[0082] - RSRP (Reference Signal Received Power) on one or more downlink reference signals,

[0083] - RSRPP (Reference Signal Received Path Power) on one or more downlink reference signals,

[0084] -RSTD,

[0085] -AoD,

[0086] -AoA,

[0087] -RxTx time difference.

[0088] The user equipment 100 may, for example, be configured to report information about the one or more measurements to a network entity 200 of the wireless communication system.

[0089] In one embodiment, the user device 100 may be configured, for example, to use a machine learning model or parameters of a machine learning model to determine its location and / or determine a distance between the user device 100 and another entity of the wireless communication system (e.g., another user device 100), such as ranging information.

[0090] According to one embodiment, the user equipment 100 may, for example, be configured to receive parameters of a machine learning model or a machine learning model from a network entity 200 of the wireless communication system.

[0091] In one embodiment, the machine learning model represents a machine learning model selected from a set of machine learning models (e.g., from a global machine learning model library).

[0092] According to one embodiment, the user device 100 may, for example, be configured to select a machine learning model from a set of machine learning models (e.g., from a global machine learning model library).

[0093] In one embodiment, the user device 100 may, for example, be configured to receive a description or configuration comprising the set of machine learning models.

[0094] According to one embodiment, the set of machine learning models may, for example, include multiple machine learning models, each of the multiple machine learning models is a machine learning model for a specific zone (e.g., a specific area).

[0095] In one embodiment, the user device 100 may, for example, be configured to select a machine learning model from the set of machine learning models based on one or more measurements.

[0096] According to one embodiment, the result of the one or more measurements depends on the location of the user equipment 100 .

[0097] In one embodiment, the user device 100 may be configured to deploy the machine learning model or a portion thereof, or a parameter of the machine learning model or a portion thereof to other user devices, for example. And / or, the user device 100 may be configured to update the machine learning model or a portion thereof, or a parameter of the machine learning model or a portion thereof, during the interference phase, for example. And / or, the user device 100 may be configured to update the machine learning model or a portion thereof, or a parameter of the machine learning model or a portion thereof, in a global library, for example.

[0098] According to one embodiment, during training of the machine learning model, the user device 100 may, for example, be configured to monitor the output of the machine learning model.

[0099] In one embodiment, the user device 100 may, for example, be configured to train a pre-trained model to obtain a trained model.

[0100] According to one embodiment, the input to the machine learning model may be, for example, at least one of the following:

[0101] - one or more channel impulse responses,

[0102] - at least one TOA,

[0103] - at least one AOA,

[0104] - at least one AOD,

[0105] - at least one TOT,

[0106] - At least one TDOA.

[0107] In one embodiment, the user equipment 100 may be configured, for example, to receive update information about the machine learning model or the parameters of the machine learning model from the network entity 200 of the wireless communication system. The user equipment 100 may be configured, for example, to update the machine learning model or the parameters of the machine learning model using the update information.

[0108] According to one embodiment, the user device 100 may, for example, be configured to receive training data from another user device 100. The user device 100 may, for example, be configured to train and / or retrain and / or calibrate the machine learning model using the training data.

[0109] In one embodiment, if the user equipment 100 is located in a machine learning assistance area, the user equipment 100 may, for example, be configured to receive assistance data from a network entity 200 of the wireless communication system.

[0110] According to one embodiment, if the user equipment 100 is located in a machine learning assistance area, the user equipment 100 may be configured, for example, to receive information that the assistance data is available from a network entity 200 of the wireless communication system.

[0111] In one embodiment, the user device 100 may be configured to receive one or more of the following machine learning model parameters as auxiliary data, for example:

[0112] - a machine learning model, e.g. a type of model,

[0113] - the structure of the model, such as the type and / or number of layers and their structural dependencies,

[0114] - one or more features of the machine learning model, such as input data,

[0115] - one or more coefficients describing a machine learning model and / or a part thereof,

[0116] - additional auxiliary data when making measurements,

[0117] - Information for triggering the user equipment 100 to provide additional measurements (eg as a sensor unit).

[0118] According to one embodiment, the user equipment 100 may, for example, be configured to receive information from a network node of the wireless communication system, the information comprising information requesting additional information from the user equipment 100. For example, the additional information may include information correlating measurements of one positioning session with measurements of another positioning session and / or consistency between measurements, for example. The user equipment 100 may, for example, be configured to transmit the additional information.

[0119] Furthermore, a user equipment 100 of a wireless communication system according to an embodiment is provided. The user equipment 100 is configured to determine whether it shall act as a time anchor unit, for example as a time anchor or as a time PRU or as a PRU, according to the time reference information.

[0120] According to one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the user equipment 100 displays information about its location, or another entity of the wireless communication system (e.g., the network entity 200) may, for example, include information about the location of the user equipment 100 and / or may, for example, include information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100) (e.g., ranging information).

[0121] In one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the user equipment 100 can, for example, be configured to transmit one or more reference signals to another user equipment 100 of the wireless communication system, and / or can, for example, be configured to receive one or more reference signals from other user equipment 100, such as for determining location information about the location of the other user equipment 100, and / or for determining information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100) (e.g., ranging information).

[0122] According to one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the user equipment 100 can, for example, be configured to report information about its location and / or information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100) (e.g., ranging information) in the same positioning session; and information about one or more measurements of a reference signal.

[0123] In one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the user equipment can, for example, be configured to receive a location reference signal from an entity of the wireless communication system, and / or the user equipment 100 can, for example, be configured to transmit a location reference signal to an entity, which is a network entity 200 of the wireless communication system or another user equipment 100.

[0124] According to one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the network entity 200 of the wireless communication system is able to determine the location of a device of the wireless communication system and / or determine the distance between the user equipment 100 and the device, for example, by receiving a report from the user equipment 100 regarding one or more measurements (e.g., one or more measurements performed on location reference signals sent by other devices in the wireless communication system).

[0125] In one embodiment, the user equipment 100 may for example be configured to receive a time reference information message from a network entity 200 of the wireless communication system or from another user equipment 100 of the wireless communication device. The time reference information message may for example comprise time reference information.

[0126] According to one embodiment, the user equipment 100 may access the time reference information without receiving the time reference information within a message.

[0127] In one embodiment, the user equipment 100 may, for example, be configured to determine and / or assist in determining the location of another user equipment 100 of the wireless communication system.

[0128] According to one embodiment, the time reference information may for example include one or more conditional criteria. The user equipment 100 may for example be configured to decide whether it will act as a time anchor unit by determining whether the user equipment 100 satisfies at least one conditional criterion among the one or more conditional criteria.

[0129] In one embodiment, the one or more conditional criteria include one or more of the following:

[0130] - an indication of the absolute or relative accuracy of positioning,

[0131] - Certainty,

[0132] - location quality,

[0133] - the protection level, which could be, for example, a statistical upper limit on the positioning error,

[0134] - An integrity flag, which may for example be an indication whether the protection level is greater than an alarm limit.

[0135] According to one embodiment, the one or more conditional criteria include capability signaling that provides one or more of the following information:

[0136] - azimuth,

[0137] -direction,

[0138] -speed,

[0139] - acceleration,

[0140] -A motion state within a motion model, such as a state in stationary, pedestrian, vehicle traffic, or highway traffic.

[0141] In one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the user equipment 100 can, for example, be configured to use PRU capability signaling to provide information that it will act as a time anchor point unit to one of the network entities of the wireless communication system or one of the user equipments (100).

[0142] According to one embodiment, if the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to report its position to an entity of the wireless communication system and / or report one or more measurements and / or transmit a position reference signal and / or receive a position reference signal from an entity of the wireless communication system in the same positioning session, and / or report distance information, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment (100).

[0143] In one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the user equipment 100 may, for example, be configured to provide information of a machine learning model for positioning to one of the entities of the wireless communication system.

[0144] According to one embodiment, if the user equipment 100 has determined that it will act as a time anchor point unit, the user equipment 100 can, for example, be configured to provide ACS information to an entity of the wireless communication system, for example, information about one or more characteristics of one or more transmission channels of the wireless communication system, and / or provide information about the validity of the ACS information for a specific area.

[0145] In one embodiment, if the user equipment 100 has determined that it will not act as a time anchor unit, the user equipment 100 may, for example, be configured to avoid reporting its position to an entity of the wireless communication system, and / or may, for example, be configured to report to an entity of the wireless communication system that it will not act as a time anchor unit. And / or, if the user equipment 100 has determined that it will no longer act as a time anchor unit, the user equipment 100 may, for example, be configured to avoid reporting its position to an entity of the wireless communication system, and / or may, for example, be configured to report to an entity of the wireless communication system that it will no longer act as a time anchor unit.

[0146] According to one embodiment, the user equipment 100 is capable of, for example, sending information about its location and / or is capable of, for example, sending information about the distance between the user equipment 100 and another entity of the wireless communication system (for example, another user equipment 100) (for example, ranging information).

[0147] In one embodiment, the user equipment 100 may, for example, be configured to inform the network of its capability to become a time anchor point unit.

[0148] According to one embodiment, if one or more predefined conditions are met, the user equipment 100 can, for example, be configured to notify the network that the conditions for the UE to act as a PRU are met, and / or the user equipment 100 can, for example, be configured to start sending measurements to a network entity 200 of the wireless communication system or another user equipment 100, for example, so that the user equipment 100 acts as a time anchor point or PRU.

[0149] In one embodiment, the user equipment 100 may, for example, be configured to obtain its position using a first positioning method (e.g., GNSS and / or iGPS and / or a RAT-dependent positioning method) and / or using reference information (e.g., O&M), and may, for example, be configured to provide reference measurements to a network entity 200 of the wireless communication system and / or another user equipment 100 and / or send a signal for collecting reference measurements, for example, to satisfy conditions for becoming a PRU.

[0150] According to an embodiment, the user equipment 100 may, for example, be configured to receive a request from a network entity 200 of the wireless communication system to act as a time anchor point unit for another device.

[0151] In one embodiment, the user equipment 100 may, for example, be configured to perform RTT measurements.

[0152] According to an embodiment, the user equipment 100 may, for example, be configured to perform one or more measurements on one or more side links together with one or more other user equipments 100 of the wireless communication system.

[0153] In one embodiment, one or more measurements are used to measure a side link distance and / or provide direction information between the user equipment (100) and another user equipment to be located.

[0154] According to one embodiment, the user equipment 100 may, for example, be configured to determine the distance and / or direction using a RAT-independent technique, and may, for example, be configured to notify a network entity 200 or another device of the wireless communication system that the ranging and / or direction information is obtained using a RAT-independent technique.

[0155] In one embodiment, the user equipment 100 may be configured to adopt one or more of the following ranging techniques as RAT-independent techniques:

[0156] -UWB,

[0157] - LiDAR,

[0158] -radar,

[0159] - WLAN-based ranging.

[0160] In addition, a user equipment 100 of a wireless communication system according to an embodiment is provided. The user equipment 100 is configured to obtain information about its location and / or obtain information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100) (e.g., ranging information). The information is obtained by receiving information from another user equipment 100 acting as a time anchor unit (e.g., a time anchor or a time PRU or PRU), for example, via a direct communication link or indirectly through a network, wherein the information received from the time anchor unit includes the location of the time anchor unit and / or one or more measurements performed by the time anchor unit on a signal sent by the user equipment 100, or wherein the information includes a location reference signal. In addition, the information is obtained by performing one or more measurements on one or more received signals and / or by transmitting derived information derived from the measurements of the wireless communication system to a network entity 200 (e.g., to an LMF or NWDAF).

[0161] According to one embodiment, the user equipment 100 may be configured to determine its own location, for example, by employing user equipment-based OTDOA, and / or may be configured to report its location to a network entity 200 of the wireless communication system, for example. The user equipment 100 may be configured to perform and / or report one or more measurements on one or more received signals as one or more downlink signals.

[0162] In addition, a user equipment 100 of a wireless communication system according to an embodiment is provided. The user equipment 100 (for example, a UL-TDOA device) is configured to support an entity of the wireless communication system (for example, a network entity 200) by sending one or more reference signals to another user equipment 100 acting as a time anchor unit (for example, a time anchor or a time PRU or a PRU) via a direct communication link or indirectly through a network, so as to obtain information about the location of the user equipment 100 and / or obtain information about the distance between the user equipment 100 and another entity of the wireless communication system (for example, another user equipment 100) (for example, ranging information), so as to allow the time anchor to perform one or more measurements on the one or more reference signals and / or report one or more measurements to the entity of the wireless communication system.

[0163] In addition, a user equipment 100 of a wireless communication system according to an embodiment is provided. The user equipment 100 is configured to determine, for example by using RAT-independent techniques and / or by using RAT-dependent techniques and / or by using time anchor points, or is configured to receive information about its location and / or information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100) (e.g., ranging information). In addition, the user equipment 100 is configured to use the information about its location and / or the information about the distance to assist in generating training data for a machine learning model for positioning, for example, for machine learning with relevant labels.

[0164] For example, the machine learning model may be located, for example, on the LMF or NWDAF of a wireless communication system.

[0165] According to one embodiment, the user equipment 100 may, for example, be configured to employ information about one or more channel impulse responses to assist in generating training data for a machine learning model.

[0166] In one embodiment, the user equipment 100 may be configured, for example, to send information about one or more channel impulse responses and information about its location and / or information about the distance to an entity of the wireless communication system (e.g., the network entity 200) to assist in generating training data for a machine learning model.

[0167] Furthermore, a user equipment 100 of a wireless communication system according to the embodiment is provided.

[0168] The user equipment 100 is configured to send information about one or more properties of RF channel characteristics between the user equipment 100 and another entity of the wireless communication system and / or an indicator of the probability that a direct path ("line-of-sight" path) exists and / or information about characteristics of one or more RF channel propagation paths that are not associated with the direct path, wherein the other entity of the wireless communication system is a base station or another user equipment 100 of the wireless communication system.

[0169] Furthermore, the user equipment 100 is configured to report information about one or more channel impulse responses to said other entity or another entity of the wireless communication system.

[0170] According to one embodiment, the user equipment 100 may, for example, be configured to report one or more signal characteristics of at least one received reference signal to a network entity 200 of the wireless communication system, the at least one received reference signal comprising at least one of the following information:

[0171] - Signal strength,

[0172] -LOS / NLOS probability,

[0173] - information about one or more received beams,

[0174] - the similarity of two or more (e.g. consecutive) beams,

[0175] - one or more channel impulse response parameters,

[0176] - similarity of two or more (e.g. consecutive) channel impulse responses,

[0177] - one or more estimates of range and / or bearing,

[0178] - Motion curves,

[0179] - Signal classification, e.g. depending on confidence information.

[0180] In one embodiment, the user equipment 100 may, for example, be configured to measure DL reference signals during the execution of or supporting DL-TDOA and / or Multi-RTT and / or DL-AoD methods.

[0181] According to one embodiment, if the number of TRPs with LOS conditions is insufficient, the user equipment 100 may, for example, be configured to indicate to the network entity 200 of the wireless communication system that the number of TRPs with LOS conditions is insufficient.

[0182] In one embodiment, the user equipment 100 may be configured, for example, to receive information from an entity of the wireless communication system, to communicate with another user equipment 100 acting as a time anchor unit (e.g., a time anchor or time PRU or PRU) to obtain information about its location, and / or to obtain information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100) (e.g., ranging information).

[0183] According to an embodiment, the user equipment 100 may be, for example, a sensor unit and / or wherein the user equipment 100 has sensor unit capabilities.

[0184] In one embodiment, the other user equipment 100 acting as a time anchor point unit may be, for example, the user equipment 100 described above.

[0185] According to one embodiment, the user equipment 100 may, for example, be configured to receive and process information about one or more available time anchor point units.

[0186] In one embodiment, the user equipment 100 may be configured, for example, to send a PRS signal synchronized with the network entity 200 of the wireless communication system to another entity of the wireless communication system, for example, to transmit a sidelink PRS to another user equipment 100 .

[0187] According to an embodiment, the user equipment 100 may, for example, be configured to measure the arrival time of the SRS signal relative to a network clock of the wireless communication system.

[0188] In one embodiment, the user equipment 100 may be configured, for example, as the user equipment 100 described above.

[0189] According to one embodiment, the user equipment 100 may be configured, for example, to receive a machine learning model or parameters of a machine learning model from a network entity 200 of the wireless communication system. The user equipment 100 may be configured, for example, to use the machine learning model or parameters of the machine learning model to determine its location, and / or wherein the user equipment 100 may be configured, for example, to determine a distance (e.g., ranging information) between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100).

[0190] In one embodiment, the user equipment 100 may be configured, for example, to receive update information about the machine learning model or the parameters of the machine learning model from the network entity 200 of the wireless communication system. The user equipment 100 may be configured, for example, to update the machine learning model or the parameters of the machine learning model using the update information.

[0191] According to one embodiment, the user device 100 may, for example, be configured to receive training data from another user device 100. The user device 100 may, for example, be configured to train and / or retrain and / or calibrate the machine learning model using the training data.

[0192] In one embodiment, the user equipment 100 may, for example, be configured to report its position and / or report one or more measurements and / or transmit a location reference signal to another user equipment of the wireless communication system via a side link and / or receive a location reference signal from another user equipment of the wireless communication system, and / or report information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information).

[0193] According to one embodiment, the user equipment 100 may, for example, be configured to send training data to a network entity 200 of a wireless communication system to train and / or retrain and / or calibrate a machine learning model.

[0194] In one embodiment, the user equipment 100 may, for example, be configured to transmit training data to another user equipment of the wireless communication system to train and / or retrain and / or calibrate the machine learning model.

[0195] In addition, a user equipment 100 of a wireless communication system is provided.

[0196] The user equipment 100 is configured to receive measurement and / or transmission characteristic information.

[0197] According to an embodiment, the user equipment 100 may, for example, include and / or implement a measurement device and may, for example, be configured to receive measurement and / or transmission characteristic information, which enables the measurement device to identify one or more measurement characteristics.

[0198] In one embodiment, the user equipment 100 may, for example, include and / or implement a transmission device and may, for example, be configured to transmit a PRS, which enables the network to identify and / or generate training data for model calibration.

[0199] According to one embodiment, the measurement and / or transmission characteristic information may, for example, be associated with one or more TRPs and may, for example, also be associated with a geographical area.

[0200] In one embodiment, the measurement and / or transmission characteristic information may be, for example, ACS information (Correlation and Calibration Point Information).

[0201] According to one embodiment, ACS information may be associated with one or more TRPs, for example, and may also be associated with a geographic region, for example.

[0202] In one embodiment, the user equipment 100 may be configured, for example, to determine, with respect to the measurement and / or transmission characteristic information, whether the measurement and / or transmission characteristic information is valid for the area where the user equipment 100 is located.

[0203] According to an embodiment, the user equipment 100 may, for example, be configured to make and / or report one or more measurements of one or more reference signals based on the measurements and / or the transmission characteristic information.

[0204] In one embodiment, the user equipment 100 may be configured to receive measurements and / or transmission characteristic information including power information about a power level for a given path, for example, where the power information is absolute or relative to one or more resources or multiple paths within a resource or within a measurement. The user equipment 100 may be configured to use the information to detect the indicated path and / or determine its location and / or report measurements related to the detected path; and / or determine information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information).

[0205] According to one embodiment, the user equipment 100 may, for example, be configured to use measurement and / or transmission characteristic information to set a detection method or a detection threshold to derive ToA and / or RSRPP and / or AoA.

[0206] In one embodiment, the measurement and / or transmission characteristic information may, for example, include at least one indication of a delay and / or direction of a non-LOS path.

[0207] According to one embodiment, the measurement and / or transmission characteristic information may, for example, include at least one indication on a plurality of beams detectable in a region (eg, an ACS region).

[0208] In one embodiment, the plurality of beams are associated with one or more expected channel conditions, the one or more expected channel conditions comprising one or more of the following:

[0209] - soft or hard indication of LOS or NLOS condition per beam,

[0210] - Expected power level per beam, e.g. RSRPP and / or RSRP.

[0211] According to one embodiment, the plurality of beams are associated with indicative antenna radiation information provided to the user equipment 100 of a main lobe, a null lobe, or a side lobe.

[0212] In one embodiment, the user equipment 100 may, for example, be configured to receive information about two or more antennas of the same TRP of the wireless communication system and / or two or more antennas of the same user equipment 100 of the wireless communication system.

[0213] Furthermore, a user equipment 100 of a wireless communication system according to the embodiment is provided.

[0214] The user equipment 100 is configured to receive one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system from a network entity 200 of the wireless communication system.

[0215] Furthermore, the user equipment 100 is configured to receive measurement and / or transmission characteristic information including a set of one or more parameters from a network entity 200 of the wireless communication system.

[0216] In addition, the user equipment 100 is configured to use one or more PRS configurations and use measurement and / or transmission characteristic information to determine its location and / or information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment) (e.g., ranging information).

[0217] According to an embodiment, the user equipment 100 may, for example, include and / or implement a measurement device and may, for example, be configured to receive measurement and / or transmission characteristic information, which enables the measurement device to identify one or more measurement characteristics.

[0218] In one embodiment, the measurement and / or transmission characteristic information may be, for example, ACS information (Correlation and Calibration Point Information).

[0219] According to an embodiment, the user equipment 100 may, for example, be configured to select a part of the measurement and / or transmission characteristic information as a subset of the measurement and / or transmission characteristic information.

[0220] In one embodiment, the user equipment 100 can, for example, be configured to select a subset of measurement and / or transmission characteristic information based on information received from a network entity 200 of the wireless communication system and / or based on information derived from a side link and / or based on information derived from an uplink reference signal, and / or based on mobility type or speed information or direction information or pressure information.

[0221] According to one embodiment, the user equipment 100 may be configured to receive a first part of the measurement and / or transmission characteristic information. The user equipment 100 may be configured to receive a second part of the measurement and / or transmission characteristic information after the first part, wherein the second part may include more detailed information than the first part.

[0222] In one embodiment, the measurement and / or transmission characteristic information may, for example, include one or more of the following:

[0223] - one or more delay paths for LOS and / or multipath components,

[0224] - one or more directional paths for LOS and / or multipath components,

[0225] - power / amplitude information of one or more directional and delay paths associated with one resource or with one path per resource,

[0226] - the expected LOS delay and amplitude of the multipath components, such as the maximum peak expected for a given resource,

[0227] - Window configuration indicating the expected delay or direction of LOS or multipath to be applied to the measurement or to be reported,

[0228] - Window configuration indicating expected delays or directions of LOS or multipath that should not be measured or reported,

[0229] - a validity area with information about the validity, wherein the information may be a soft value or a hard value,

[0230] - correlation of the measurement and / or transmission characteristic information in a given area with the number of times the measurement and / or transmission characteristic information is required or expected to be updated,

[0231] - Indications from the measuring unit.

[0232] According to an embodiment, the user equipment 100 may be, for example, a sensor unit and / or wherein the user equipment 100 has sensor unit capabilities.

[0233] In addition, a network entity 200 of a wireless communication system according to an embodiment is provided. The network entity 200 is configured to send time reference information to a user equipment 100 of the wireless communication system to enable the user equipment 100 to determine whether it can act as a time anchor unit, such as as a time anchor or as a time PRU or as a PRU. If the user equipment 100 has determined that it will act as a time anchor unit, the network entity 200 is configured to receive information about its location and / or about one or more measurement and / or location reference signals from the user equipment 100; and / or information about the distance between the user equipment 100 and another entity of the wireless communication system (e.g., another user equipment 100) (e.g., ranging information).

[0234] Furthermore, a network entity 200 of a wireless communication system according to an embodiment is provided. The network entity 200 is configured to receive, from a user equipment 100 of the wireless communication system, information about one or more line-of-sight links, for example defined by an RF channel (the RF channel comprising a direct path with a delay according to the distance), or information about one or more properties or one or more characteristics of one or more RF channels between network entities, or information about the absence of a line-of-sight link with another entity, for example with another network entity (200) of the wireless communication system.

[0235] According to one embodiment, the network entity 200 may, for example, be configured to send information that the user equipment 100 of the wireless communication system is located in a machine learning assisted area.

[0236] In one embodiment, the network entity 200 may, for example, be configured to store one or more identifiers of a user device 100 of the wireless communication system that is entering the machine learning assistance area. For example, the network entity 200 may be configured to delete the identifier of the user device 100 that leaves the machine learning assistance area. In addition, the network entity 200 or another entity of the wireless communication system may, for example, be configured to obtain an identifier of at least one user device 100 located in the machine learning assistance area to initiate the process of training a machine learning model and / or updating a machine learning model.

[0237] According to one embodiment, the network entity 200 may, for example, be configured to transmit a machine learning model or parameters of a machine learning model to the user equipment 100 .

[0238] In one embodiment, the network entity 200 may, for example, be configured to receive training data from the user equipment 100. For example, the network entity 200 may be configured to train and / or retrain and / or calibrate the machine learning model using the training data.

[0239] Furthermore, a network entity 200 of a wireless communication system according to an embodiment is provided. If a user equipment 100 of the wireless communication system is to act as a time anchor unit, the network entity 200 is configured to receive information about one or more measurements from the user equipment 100, such as one or more measurements performed on a location reference signal sent by the device. Furthermore, the network entity 200 is configured to use the information about the location of the user equipment 100 and use the information about the one or more measurements to determine the location of the device and / or determine the distance between the user equipment 100 and the device.

[0240] In addition, a network entity 200 of a wireless communication system according to an embodiment is provided. The network entity 200 is configured to send measurement and / or transmission characteristic information, such as ACS information (association and calibration point information), to a user equipment 100 of the wireless communication system, wherein the measurement and / or transmission characteristic information is associated with one or more TRPs and is also associated with a geographical area.

[0241] Furthermore, a network entity 200 of a wireless communication system according to an embodiment is provided. The network entity 200 is configured to send one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system to a user equipment 100 of the wireless communication system. The network entity 200 is configured to send measurement and / or transmission characteristic information, such as ACS information (association and calibration point information), including a set of one or more parameters to the user equipment 100 of the wireless communication system, for example, wherein the measurement and / or transmission characteristic information includes information about a relationship between an ACS-ID and assistance data, for example, wherein the assistance data includes the PRS configuration.

[0242] According to one embodiment, the NW entity may be, for example, any of the following:

[0243] -NWDAF,

[0244] -LMF,

[0245] -NRF,

[0246] -NEF,

[0247] -NG-RAN,

[0248] -AMF,

[0249] -GMLC,

[0250] -UDM.

[0251] Furthermore, a wireless communication system is provided, comprising one or more user equipments (100) as described above according to the embodiments, and one or more network entities as described above.

[0252] In addition, a wireless communication system according to an embodiment is provided. The wireless communication system includes at least two entities, wherein each of the at least two entities is a user equipment 100 or a network entity 200, wherein the at least two entities include a first entity and a second entity. The first entity is configured to determine whether it will act as a time anchor unit, such as a time anchor or as a time PRU or as a PRU, based on time reference information. The second network entity 200 is configured to perform one or more measurements and is configured to provide one or more reports derived from the one or more measurements to another network entity 200 (e.g., to an LMF or NWDAF) to train a model (e.g., a neural network) or to capture characteristics of one or more RF signals received in an area.

[0253] According to one embodiment, the first entity (e.g., a time anchor point) may, for example, be configured to send to the second entity and / or may, for example, be configured to receive one or more reference signals as information from the second entity. The second entity may, for example, be configured to use the information to determine its location; and / or determine information about the distance between the second entity and another entity (e.g., another user equipment) of the wireless communication system (e.g., ranging information).

[0254] In one embodiment, the first entity (e.g., a time anchor point) may, for example, be configured to provide information about one or more measurements performed on the received one or more reference signals, and / or may, for example, be configured to report characteristics of the received one or more reference signals as information to the second entity. For example, the second entity may be configured to employ the information to determine its position relative to the first entity; and / or determine a distance between the second entity and the first entity (e.g., ranging information).

[0255] According to one embodiment, the first entity may be, for example, the user equipment 100 as described above, and the second entity may be, for example, the network entity 200 as described above. Alternatively, the second entity may be, for example, the user equipment 100 as described above, and the first entity may be, for example, the network entity 200 as described above.

[0256] In addition, a wireless communication system according to an embodiment is provided. At least one of the multiple entities is configured to use one or more measurements of one or more user devices (100) of the wireless communication system to perform one or more comparisons. In addition, at least one of the multiple entities is configured to perform unsupervised learning of similar attributes or characteristics, such as one or more channel impulse responses or one or more parameters thereof. At least one of the multiple entities is configured to use one or more time anchors of the wireless communication system for supervised learning. In addition, at least one of the multiple entities is configured to perform supervised learning to map similar attributes or characteristics to corresponding reference information, such as mapping the channel impulse response or its parameters to speed and / or direction and / or acceleration and / or position and / or distance. At least one of the multiple entities is configured to train or collect ML models using a combination of supervised learning (e.g., with output labels) and unsupervised learning (e.g., without output labels). In addition, at least one of the multiple entities is configured to use labels obtained from one or more time anchors to provide real-world dimensions to the trained model, wherein the labels allow the learned representations to be transformed (e.g., scaled and rotated) to real-world dimensions.

[0257] According to an embodiment, the plurality of entities may, for example, include the user equipment 100 as described above and the network entity 200 as described above.

[0258] Hereinafter, specific embodiments of the present invention are described.

[0259] Figure 2 An overview of some concepts according to certain embodiments is presented.

[0260] For example, an implementation may include utilizing measurements made by the UE and network entities to understand the environment and utilizing the learned information to improve UE position estimates based on LMF (UE-assisted and TRP-assisted) or UE-based mode.

[0261] The goal of this solution is to provide complementary information to the positioning algorithm as a reference for position calculation. This can make the signals sent to or received from the TRP useful for positioning under NLOS conditions. Examples include (1) virtual TRP and (2) CIR and directional characteristics.

[0262] Regarding "virtual TRP", a wall, ceiling or other object can act as a "mirror" for the signal. If the location of the mirror is known, the positioning algorithm can use the signal reflected from the mirror.

[0263] Regarding "CIR and directional characteristics", even if the location of the reflecting object is not identified, the CIR can include information that can be used when the bounce characteristics at a certain location can be determined by a trained model without necessarily knowing the location of the virtual TRP. Especially if multiple TRPs are used, the combination of CIR and / or directional information can provide a unique (local) fingerprint for each location.

[0264] In order to be able to use such information, a correlation between the measured data and the location must be established. For example, AI / ML-based positioning technology can use this correlation to train a neural network.

[0265] Without limiting the approach to AI / ML based positioning techniques, AI / ML based solutions require a training phase. Training can be divided into initial training and continuous updating of the neural network (“model”) or any other (parameterized) function approximator used for positioning applications.

[0266] The proposed solution may for example include:

[0267] - Initial training during the (first) deployment of the system can be applied first. Different initial training methods can be used. One example is a robot scanning the environment.

[0268] -Continuously update the neural network by identifying temporally available anchor points.

[0269] - Identify "Virtual TRPs".

[0270] -Exchange information with devices in the same area.

[0271] An example scenario is described below.

[0272] We consider Figure 3In the example scenario in , the goal is to locate UE2 under harsh NLOS conditions. In this scenario, we have multiple UEs at different locations, resulting in different channel conditions relative to the TRP: UE1, UE3 and UE4 have a sufficient number of LOS links, and UE2 partially blocks the TRP, making it possible to communicate with other UEs. Three examples of other UEs are given:

[0273] - UE1 may not support direct communication with other UEs.

[0274] -UE3 may support distance measurements to other UEs. However, the UE may be close to TRP2 and may provide no or little gain to UE2's position calculation.

[0275] -UE4 might be a good fit as a time anchor.

[0276] If a time anchor point is available, UE2 can determine its location and can capture the relevant CIR characteristics as a "fingerprint". Any multipath component can be used as a fingerprint. However, it should be noted that some CIR components may be more susceptible to environmental changes than others.

[0277] As an example, we highlight a reflective object (e.g. a wall) at a fixed location as a "virtual TRP". If the location of the reflective object is known, it can be identified as a "virtual TRP" and the CIR resulting from the reflection of this object can also be predicted for other UE locations. In some cases, further information about the characteristics of the virtual TRP, such as the size of the object (e.g. length of the wall), reflective characteristics (e.g. type of surface), may be relevant to further infer the usability of the virtual TRP.

[0278] Figure 3 An example of NLOS positioning is shown.

[0279] For example, in the sample scene we used a "Time Anchor" and a "(Time) Sensor" with the following properties:

[0280] If UE2 is in a position where it cannot determine its position with sufficient accuracy due to lack of available LOS signals, the UE (UE4 in this example) can become a "time anchor" that supports positioning other UEs (UE2 in this example).

[0281] If the UE2 can be positioned with the support of a "time anchor point", the UE can act as a "sensor" measuring the characteristics of the received signal and make the data available as training data for ML-based schemes (neural networks or other implementations of the "fingerprint" concept). The measurements (=input data for the machine learning model="features") together with the positions ("labels") form a set of training data.

[0282] In principle, any UE with a known location (either by RAT-dependent or RAT-independent methods) can serve as a sensor for model training. But training is often specifically needed in situations where other positioning methods fail. Therefore, in critical scenarios, the introduction of a “time anchor” increases the probability that the UE’s location can also be determined by the UE itself (UE-based positioning) or by the network.

[0283] If the position of the time anchor point cannot be estimated with sufficient accuracy for RTT or TDOA and / or angle-based positioning techniques, the time anchor point can perform the same measurements as the "sensor UE" (UE2 in this example) and can provide information about the characteristics of the received signal. This information can be provided to other UEs and compared with data measured by other UEs to identify commonalities.

[0284] Especially if several time anchor points (at different locations around the "sensor UE") provide measurements, the position of the sensor UE can be estimated by a method that can interpolate between the measurements performed for different locations.

[0285] In summary, the goal of the present invention is to enable a device (UE or other network entity) to act as a sensor, at least in time, to provide training data for AI / ML-based positioning methods. This helps to set up and / or fine-tune and / or check the effectiveness of the AI / ML-based positioning method model.

[0286] In the following, solution details of a specific implementation will be presented. First, solution elements that play a basic role in achieving the above process will be introduced.

[0287] Now, a description of concepts according to some embodiments is provided.

[0288] First, the initial training (first setup of the model) according to the embodiment is described.

[0289] At least three approaches are considered for initial training:

[0290] - Training is performed by a device whose position is determined by other techniques. For example, a robot measures the relationship between position and channel characteristics.

[0291] - If the setup also supports a positioning solution without neural networks, training of the model can be performed by this approach to determine the positions ("labels") of the devices for training purposes. Positioning methods that rely on LOS links may not be able to provide labels for all positions. Therefore, in a first step, training is performed on areas with a sufficient number of LOS links and the positions can be calculated using traditional positioning algorithms. This can also be used to build a "partially trained model" (= a model trained only for part of the area = a model trained for areas where the LMF or UE is able to calculate the position without the support of an AI / ML model). At this stage, additional information associated with the position is captured in order to perform positioning in case the LOS link is lost.

[0292] - Initial training is performed using data generated offline in simulation. Simulations can take into account known environmental information or simulations from tools such as ray tracing. Initial training can be performed using data generated by simulation.

[0293] These approaches can be used in combination, for example, performing a first pre-training step using data generated in simulation and measuring support for fine-tuning of the model.

[0294] Generally, the initial training is left to the NW to perform. In one aspect, the NW can provide initial training data to a device such as a UE or TRP, which can use this data to train its model.

[0295] Model updating using "time anchor points" according to an embodiment is now described.

[0296] For initial training, we assume that the training devices are able to determine their absolute or relative position by methods that are not available to the devices used in the operational phase. In principle, every device with a known position can provide input data for training. However, for areas where the model needs to be updated due to changes in the environment, the devices may no longer be able to determine their position. Therefore, especially for areas that need to be updated, the devices may not be able to locate themselves. Finding other temporally available devices with known positions ("temporal anchors") may solve this problem. If a device is able to determine its position, it is able to report an association between position and measurement data.

[0297] - Every device (stationary or mobile) with a known position can serve as an anchor for positioning.

[0298] - The device may, for example, provide position quality or uncertainty information, or meet positioning accuracy conditions to be used as an anchor.

[0299] - The first device may perform distance and / or angle measurements on the second device.

[0300] - If the location of the first device is known and the second device cannot detect a sufficient number of anchors using a fixed TRP, it can use the first device as a temporal anchor point.

[0301] A complementary method for identifying "virtual anchors" is now described.

[0302] For example, the characteristics of the virtual anchor can be

[0303] -The signal is sent or received by a TRP with a known location.

[0304] -The direct link between the TRP and the UE is blocked or very weak.

[0305] -The signal is received via a reflector.

[0306] -The position of the reflector may be known or unknown.

[0307] -The reflection point is not fixed and may depend on the TRP and the location of the UE. This may be due to the angle of incidence equals angle of departure effect, so the reflection point depends on the location of the device.

[0308] CIR can include two types of multipath components:

[0309] - Multipath components associated with the known location of a reflector (single bounce) or multiple reflectors (N bounces)

[0310] - Other multipath components.

[0311] If the multipath components in the measured CIR can be associated with the known positions of reflectors, the CIR characteristics at other locations can be predicted. Furthermore, even the position of the reflector can be taken into account to calculate the distance. In this case, the measured ToA of the multipath components provides similar information as the ToA measured for the components received from the TRP via the direct path. Therefore, these signals are associated with a "virtual TRP". The virtual TRP can help reduce the number of TRPs required, or a TRP that is not received in LOS conditions can still be useful.

[0312] In an implementation scheme, we believe that during the training phase with sufficient LOS links, complementary virtual anchors can be identified. If the number of LOS links is no longer sufficient due to changes in the environment, "virtual anchors" may help calculate the position. UE, TRP and other nodes can also represent nodes of a graph with confidence values ​​for each location; virtual nodes can be generated (adversarially) between nodes with high confidence; such virtual nodes can be used to resolve connections between nodes with low confidence; such a graph can be embedded in a neural network or a function approximator; such a graph can also contain time information; such a graph can also be embedded in a neural network; so that the function approximator learns the dynamics (time dependency) of the environment in its manifold.

[0313] Now, the association with neighbors according to an embodiment is described. In particular, UEs in the same ACS or similar ACS characteristics are described.

[0314] In the following, we describe the association with neighbors mainly for DL ​​signals. The same concept can also be applied to uplink. In this case, the UE sends the signal and the network evaluates the signal.

[0315] If the UE measures the DL reference signal and the association with the location is known, the UE can determine its location, or the measurement can be reported to the network for position calculation in the network. The following types of problems may occur:

[0316] Due to changes in circumstances, the association may no longer be valid.

[0317] The UE (or network) has no reference data for this location (eg, this location was not captured during the training phase).

[0318] To address these issues, a UE may exchange information (directly or via the network) with other UEs in the same area.

[0319] Using fingerprints of UEs with known locations that are located in the same area as a UE with unknown location may help estimate the location or improve the accuracy of the location estimate.

[0320] In a first step, for example, measurements of other UEs with known locations that are close to a UE with unknown location may be identified.

[0321] By comparing the measurement characteristics of a first UE with an unknown location with measurements of other UEs with known locations, the location of the first UE may be estimated.

[0322] For model monitoring, UEs with known locations (e.g., ground truth labels) can provide measurements or trigger transmissions to the model management entity or LCM. The LCM or model inference training / entity will use the measurements to validate the ML models of UEs in the vicinity of the reported transmission measurements.

[0323] The input data for model training can include information derived from geometry (position of TRPs, position of walls, etc.) and data captured through measurements (ACS orientation and / or latency information). Changes in the environment can be caused by changes in the position of objects (moving objects such as machines, furniture, cars, or people). For example, the model can identify the remaining elements ("measurements") in the input data that are not affected by the changes, or it can be continuously updated by using information derived from temporal anchors.

[0324] Thus, in one aspect, the NW identifies one or more UEs in the ML support area. In UE assisted mode, the NW configures a report configuration for measurements on DL and / or UL reference signals for the UE or / and TRP. The report configuration is associated with one or more DL resources and / or UL resources and includes direction and / or delay information for additional paths identified by each resource. In an optional step, the NW may trigger one or more UEs to perform and report sidelink measurements. The NW uses the measurement report to identify the relative position or / and absolute position of at least one UE relative to other UEs.

[0325] Now, an overview of the 5G architecture according to the implementation scheme is provided.

[0326] Figure 4 Some important components of a 3GPP network in a non-roaming scenario suitable for positioning are shown. A service-based interface representation of the network is shown here, where each component of the 5GS announces its interface via a common signaling bus. The 5GS contains more components than described here, which are omitted only for the purpose of describing the functionality. The NG-RAN node can host one or more transmission and reception points (TRPs), where the TRP can receive SRS sent by the UE and / or send downlink PRS, etc. At least one NG-RAN node acts as a serving gNB for the UE. The UE registers with the Access and Mobility Function (AMF) located in the core network. Signaling between the UE and the AMF is routed through the NG-RAN node.

[0327] LMF is the Location Management Function (LMF) that coordinates the location functions. Among others, it interacts with the UE and NG-RAN nodes to calculate the location of the UE. To do this, it receives a request to locate the UE from the UE (Mobile Originated Location Request (MO-LR)), from the AMF (Network Induced Location Request - NI-LR), or from another application function or external client (also known as Mobile Terminated Location Request (MT-LR)). To calculate the location, the LMF may obtain the UE capabilities and may interact with one or more nodes in the RAN network or the core network to calculate the location and pass the location to the network client.

[0328] The Network Data Analysis Function (NWDAF) is a function that implements the Nnwdaf interface. This is an example node that, in some deployments, can process data to train models and / or calculate locations based on data (or features) provided by the LMF. Alternatively, in some deployments, the calculation of the model can be done in the LMF itself. Similarly, the trained model can be stored in any of the network nodes, LMF, NWDAF, NEF, NRF, or UDM. NEF exposes network functions to other network functions or external functions or clients. NRM is used to process the stored data, which can be stored in the NRM itself or in a dedicated function that stores data, called UDM.

[0329] NWDAF and / or LMF can read and / or store data into one or more components. Generally speaking, LMF is used to provide a mechanism for collecting data that can be further processed by itself or provided to NWDAF for further processing. This applies to training data, validation data, and test data.

[0330] The model is trained at one of the network entities, either at the LMF or the NWDAF, or partly at the LMF and partly at the NWDAF. We distinguish four types of training:

[0331] 1. The methods used for (initial) training are not defined by the framework, and many methods are vendor or operator specific.

[0332] 2. The network supports (initial) training using other methods to generate "labels". In the case of positioning, the LMF or UE (for UE-based positioning) can calculate the position and provide it to the training entity.

[0333] 3. Fine-tuning of the model: The initially trained model may already be good enough to provide valid output (in the case of location and / or other data such as speed or direction of travel). But further training data may improve performance.

[0334] 4. Update the model incrementally to capture changes in the environment or for further fine-tuning.

[0335] The model training status can be different for each region and can be associated with the ACS data.

[0336] The trained model can be obtained by querying the NWDAF function and / or NRF and / or NEF and / or UDM.

[0337] Determine UE location on the NW side (UE assisted / NG-RAN assisted mode).

[0338] In the following, a first variant is described, where the ML model is trained at NWDAF:

[0339] ● The model can be trained at NWDAF using measurements provided by LMF. LMF can provide:

[0340] ○ Certain information (e.g. list of nearby cells, list of ACS, list of information about the environment)

[0341] and / or

[0342] ○ One or more measurements made by the UE and / or LMF

[0343] ●Or

[0344] ○LMF queries NWDAF for locations and provides features for training the model.

[0345] ○LMF returns location parameters (such as position, speed, time, etc.) to the UE.

[0346] ●Or

[0347] ○LMF provides the parameters of the trained model applicable to a specific region to the LMF. The LMF can indicate the region to the NWDAF.

[0348] In the following, a second variant is presented, where the ML model is trained at the LMF:

[0349] UE location is determined at the UE side (UE-based mode)

[0350] The ML model is trained on the NW side using measured and / or simulated data from one or more UEs. For a given set of data, one or more models can be trained on the NW side. Depending on the UE capabilities, the network may generate and provide one or more models. UE capabilities are related to the following:

[0351] ○Measurements that the UE can provide

[0352] ○ RAT-dependent and RAT-independent technologies supported by the UE

[0353] ○ Frequency band

[0354] Bandwidth

[0355] The ML model is provided to the UE based on the UE capabilities.

[0356] The UE calculates the position using the provided assistance data, the obtained side information and UE measurements.

[0357] Determine UE location on the NW side (UE assisted / NG-RAN assisted mode).

[0358] The ML model is trained on the NW side using measured and / or simulated data from one or more UEs. For a given set of data, one or more models can be trained on the NW side.

[0359] Depending on the UE capabilities, the network may generate and provide one or more models. UE capabilities are related to the following:

[0360] ○Measurements that the UE can provide

[0361] ○ RAT-dependent and RAT-independent technologies supported by the UE

[0362] ○ Frequency band

[0363] Bandwidth

[0364] The LMF obtains measurements from one or more positioning sessions configured by the UE and uses these data to train the model.

[0365] About the process, Figure 5 An example Phase 2 process for determining UE location at the LMF based on an ML model according to an implementation scheme is shown.

[0366] Figure 6 An example stage 2 of obtaining training features based on ML on the network side is shown.

[0367] Figure 7 An example stage 2 of UE-based positioning based on an ML model and network-provided assistance data is shown.

[0368] Next, the features for training the model obtained on the network side according to the implementation scheme are described.

[0369] The machine learning model may be trained on the network side in at least one network node. The LMF shall configure at least one UE and / or at least one NG-RAN node to report measurements of certain signals that they are configured to measure. In addition, the LMF may configure the UE and / or the NG-RAN node to report at least one side information. In addition, the LMF may request the UE to report its known or calculated location and / or determine the location on the NW side using at least one measurement obtained by the NG-RAN node and / or the UE. The LMF may combine the information together so that the combined information forms a feature set of a single training example for training the machine learning model.

[0370] One way to identify a UE from a group of UEs in a network is to identify the UE based on its location. If a UE is known to be located within a machine learning assisted positioning area, the LMF can configure such a UE to provide training samples. Alternatively, some UEs may be deployed at fixed locations, such as by a network operator. These UEs may serve the function of a position reference unit (PRU). Known information about the location of the PRU can be used together with measurements made by the PRU and / or measurements of reference signals sent by the PRU on the NG-RAN network side to generate training data for supervised learning. In other examples, the PRU location can be used to generate calibration data and / or provide further auxiliary data. A specific example is that in the case of a channel map, there may be several UEs whose locations are unknown, and if they are close together, these UEs may look similar in features to the PRU. In this case, information about the known reliable location information of such PRUs can be used to recover the physical size of the channel map.

[0371] In order to obtain such a training example, according to a variant, the LMF may configure at least two positioning sessions for the UE. In one of the positioning sessions, the UE is configured to report at least one measurement on at least one DL-RS that it is configured to measure. In the second positioning session, the UE may report at least one measurement about at least one DL-RS that it is configured to measure and / or at least report the position of the UE. The UE position may be obtained using at least one of the UE-based positioning methods. According to this variant, in at least one of the ProvideLocationInformation messages in the positioning session, the UE may report at least one of the following:

[0372] - The source of the UE position, where the source may indicate which positioning method, RAT-dependent technology or RAT-independent technology, the UE uses to determine the UE position, or it may indicate that the UE position is reported using a static configuration, e.g. during network provisioning, where the UE position of a stationary UE may be stored in the UE's memory or obtained from a database.

[0373] - Quality and / or reliability of the UE estimate. This could be the accuracy of the UE measurements, or an integrity parameter such as the protection level, or an integrity flag (e.g. a flag 0 / 1 indicating if the protection level is greater than an alarm limit), or a combination thereof.

[0374] Alternatively, the LMF may configure at least two positioning sessions for the UE, in at least one positioning session, the UE may be configured to report at least one measurement made by the UE on at least one DL-RS that the UE is configured to report. Using at least the measurements reported by the NG-RAN node, the LMF may at least calculate the UE position obtained by the NG-RAN assisted method. In addition, the LMF may synchronize the measurements and side information reported by the UE, and / or the measurements and / or side information reported by the NG-RAN node and / or the UE position determined by the network to form features for training the network.

[0375] According to a second variant, the LMF may configure the UE to report the set of measurements and side information in a single message in order to form a single training example for training the network.

[0376] The model can be trained on the LMF side or at the NWDAF node.

[0377] If the model is trained at the NWDAF node, LMF can configure the NWDAF node to train the model by specifying configuration parameters, which include at least one of the following:

[0378] 1. The type of model trained (e.g. CNN, etc.)

[0379] 2. Number of layers in the network

[0380] 3. Number of nodes in each layer

[0381] 4. Number of features used for training

[0382] Alternatively, the LMF may query the NWDAF, and the LMF may also query the NWDAF node for the characteristics that the LMF is expected to report.

[0383] According to a variation in which the LMF obtains the trained model from the second NW element, the LMF may obtain the trained model by querying the NWDAF or the NRF.

[0384] Next, the determination of the location of the UE on the network side according to the implementation scheme is described.

[0385] If the trained model is deployed on the NWDAF side, the LMF may send a request to the NWDAF node, where the request contains at least one measurement and / or at least one measurement from the UE and / or at least one measurement from the NW and / or at least one side information. The NWDAF may use these features to determine the UE location and return the location to the LMF. The returned LCS information may include at least one of the following:

[0386] 1.UE location

[0387] 2.UE speed

[0388] 3. Accuracy of Information

[0389] 4. Reliability information related to position estimation

[0390] Alternatively, the LMF may obtain the trained model and / or its configuration by querying the NWDAF function or NRF. The query may optionally include at least one of the UE capabilities supported by the UE. Once the model is obtained on the network, the LMF may use these features to estimate the location of the UE using the trained model.

[0391] To provide features to the ML model to compute the position, LMF can perform the following steps:

[0392] According to a first variant, the LMF may configure one or more positioning sessions for the UE, wherein the LMF may obtain measurements corresponding to positioning methods such as DL-TDOA, DL-AoD, multi-RTT. If multiple positioning sessions are used, the LMF may synchronize information from different positioning sessions to obtain a set of features required by the trained model.

[0393] According to a second variant, the LMF may configure a specific message to the UE, instructing the UE to report a specific set of features or a set of measurements required to obtain the features required by the trained model.

[0394] The above feature set should be provided to the trained model, and the trained model should give an estimate of the UE location.

[0395] The following describes determining the location of the UE at the UE side.

[0396] To determine based on the UE's location, the NW entity (e.g., LMF) may provide the UE with a trained model corresponding to the ML assisted area in which the UE finds itself. The LMF may utilize the UE location reported by the UE and / or measurements reported by the UE and / or NG-RAN nodes and / or information about the UE's connection to the network (e.g., serving cell, TA, etc.) to determine that the UE is within such an ML assisted area. Alternatively, the UE may have determined that the UE has entered an ML assisted area and requested NW assistance.

[0397] The UE may (optionally) send UE capabilities to the LMF using the ProvideCapability message, either proactively or in response to a "RequestCapability" message.

[0398] The UE may send a RequestAssistanceData message, where the RequestAssistanceData message either indicates the ML assistance area or simply indicates that the UE has requested an ML model to calculate the UE position.

[0399] The NW can provide the model using ProvideSassistanceData, where the model parameters are transmitted. Alternatively, the model can be transmitted via broadcast. Alternatively, the NW can indicate the source from where the UE can obtain the model. The source can be the URL of a repository where the ML model is stored.

[0400] The UE can obtain side information from the network, perform measurements to obtain the features required by the model to calculate the location, and determine the location.

[0401] The UE may optionally report the determined location using the ProvideLocationInformation message. The UE may explicitly indicate to the LMF that the reported location has been obtained using ML methods, or the NW may infer this information from the context of the positioning session in which the message has been obtained. If ProvideLocationInformation is transmitted as part of a supplementary service, an indication that positioning was obtained using ML methods may be provided.

[0402] The solution according to the embodiment may, for example, include one or more of the parts set out below.

[0403] It should be noted that the solution parts are applicable to different operation modes, unless it is explicitly stated in the description that the solution is only applicable to UE-assisted, UE-based, TRP-assisted, LMF-assisted or LMF-based.

[0404] First, the time anchor points are described.

[0405] The 3GPP standard defines a PRU (Position Reference Unit), which is a device with a known location. The PRU can be used for calibration purposes (e.g., determining TRD (Transmit-Receive Delay)) of positioning algorithms based on UL-TDOA, OTDOA or RTT using fixed anchors. There may be different PRU types, and some are already defined by the 5G standard:

[0406] ● PRU similar to gNB

[0407] ●PRU is used as an anchor for DL-based positioning. In this case, the PRU can send DL-PRS synchronized with the network and can be regarded as a simplified TRP for the gNB.

[0408] ●PRU is the unit of measurement for UL signals and can be equivalent to LMU for UL-TDOA signals. In this case, the LMU must also be fully synchronized with the network.

[0409] ● If the PRU is not sufficiently synchronized for UL or DL-TDOA positioning methods, the PRU may still be suitable for RTT measurements. Also in this case, the PRU can be a simplified gNB.

[0410] UE type PRU

[0411] ● If used for downlink: PRU provides measurements for DL-PRS signal

[0412] ●If used for uplink: PRU transmits SRS

[0413] ●UE type PRU for SL-based ranging:

[0414] The device can measure the distance to other UEs using the sidelink signals.

[0415] It should be noted that the PRU can support different operation modes. The PRU can operate as a PRU for SL-based ranging and as a PRU for network-based positioning. In the context of the present invention, we mainly consider a "time anchor point", which can be a UE that supports UL and / or DL-based positioning and communicates with other UEs via a side link. But the time anchor point can also be implemented by a time-available gNB-type PRU. The time anchor point can report its position to the network and / or other UEs and can send and / or receive (and process) position reference signals to other UEs.

[0416] Another example of a temporal anchor point can be a mobile terminal (e.g., a drone). After the network is deployed, for example, a drone can be used as a temporal anchor point. In this case, the model can be informed that additional anchors are available for a limited time, and an update of the model training can be triggered.

[0417] Instead of the ranging technology defined by 3GPP, the time anchor point can also support other ranging or positioning technologies.

[0418] In the following, possible characteristics according to some embodiments are described.

[0419] In one embodiment, the UE is receiving a configuration message from a NW entity (such as an LMF) or a second device (such as a UE or a gNB), which configuration message includes conditional information, wherein if the UE satisfies the condition, the UE can act as a time anchor point or time PRU or PRU.

[0420] In an alternative embodiment, a UE is pre-configured or known to the UE with condition information, wherein if the UE satisfies the condition, the UE can act as a time anchor point or a time PRU or a PRU.

[0421] In a related embodiment, the condition information includes one or more of the following:

[0422] -Indication of absolute or relative positioning accuracy

[0423] - Certainty

[0424] - Location quality

[0425] - Protection level

[0426] -Integrity flag (1 bit signaling)

[0427] In a related embodiment, the UE may indicate that it meets the condition based on PRU capability signaling.

[0428] In a related embodiment, whenever the UE becomes a temporal PRU, the UE reports its location information and measurements within the same positioning session.

[0429] In a related embodiment, the NW uses measurements and information from the temporal RPU to maintain the ML model or obtain a score of model effectiveness.

[0430] In some examples, the measurements may include ACS information derived from the ACS or a check on the validity of the ACS.

[0431] In a related embodiment, the UE shall refrain from reporting its position when the condition is no longer met or / and indicate that the condition is no longer associated with the positioning session or one or more measurements or one or more timestamps.

[0432] A time anchor is a device that has a known location and is able to perform measurements on signals received from other devices and / or send RSs to other devices for relative ranging purposes.

[0433] Any UE with a known location can serve as a time anchor point (subject to capabilities).

[0434] The UE may inform the network of the capability to become a time anchor point.

[0435] The network may request the UE to act as a time anchor for another device.

[0436] The network may provide the UE with information about available time anchor points.

[0437] The time anchor point may be a UE supporting sidelink ranging.

[0438] The time anchor point may be a device capable of sending a DL-PRS signal synchronized with the network and the associated AD.

[0439] The time anchor point may be a device capable of measuring the ToA on the SRS-pos signal relative to the network clock (synchronized with the network).

[0440] A time anchor point may be a device that is capable of performing RTT measurements with neighboring devices.

[0441] In a related embodiment, the time anchor point performs sidelink-based measurements on one or more target UEs. The measurements may be related to sidelink distance and / or direction information between the time anchor point and the UE to be located.

[0442] Sidelink ranging may be the subject of 3GPP standard Rel. 18. In addition to sidelink-based ranging, other ranging technologies, such as UWB, LiDAR, radar, and other ranging methods based on RF signals (e.g., WLAN-based technologies) may also be applicable.

[0443] The time sensor is described below.

[0444] Each device with a known location and the ability to perform and report measurements on received signals can act as a sensor for neural network training or generating a "fingerprint." The location ("tag") together with the sensor or the measurements performed by the network on the signals emitted by the sensor form a set of training data.

[0445] We distinguish different types of sensors:

[0446] "Specialized sensors" can be used for the initial setup of the network. For example, a robot determines its position through a technical solution independent of the RAT and provides many position measurement data to train the model.

[0447] “Monitoring sensors”: Devices located in fixed locations — known or unknown — that detect changes in the environment and can trigger the need to update the model.

[0448] “UE type sensor”: If training is limited to areas where RAT-dependent techniques are sufficient, the UE may act as a sensor by determining position using RAT-dependent techniques (such as RTT- or TDOA-based methods) and providing measurements to the training entity to build a model of positioning methods that are complementary to or independent of TDOA or RTT techniques.

[0449] "Temporal sensor": Similar to UE type sensors, measurements and positions are provided together to the training network. If the position can be calculated with the support of only temporally available information (e.g., signals received from or measured by a temporal anchor point), the sensor becomes a "temporal sensor".

[0450] In the following, identification of a "NLOS region" - "region status identification" according to some embodiments is described.

[0451] The approach (choice of algorithm or model chosen) may depend on the region. A local region can be divided into different sub-regions:

[0452] "LOS region": In the LOS region, the number of LOS links is sufficient and positioning may be mainly based on the LOS links.

[0453] “Partial NLOS region”: LOS links are available, but not in sufficient quantity for reliable positioning.

[0454] “Critical NLOS region”: Most signals are received under NLOS conditions.

[0455] The status of a region may change (temporarily or permanently) to account for changes in the environment or temporary blockage of links due to moving obstacles. A LOS region may become a "partial NLOS region" if some links are blocked, or a "partial NLOS region" may become a "critical NLOS region" if more LOS links are blocked.

[0456] Assuming that parts of the CIR do not change when the state of a region changes, it is feasible to maintain a trained model if sometimes a region enters a "LOS state" and during the LOS state the position can be calculated and training data provided to the model.

[0457] In another example, region state identification must determine the number of required time anchor points sufficient to compute a reliable position. If the number of available time anchor points is sufficient and the position can be computed with sufficient accuracy, a model update can be triggered.

[0458] Possible characteristics may include, for example:

[0459] The UE reports the signal characteristics of each received reference signal to the network, including at least one of the following information:

[0460] Signal strength

[0461] ○LOS / NLOS probability

[0462] ○ Information about the received beam

[0463] ○CIR parameters, such as estimated K factor

[0464] ○And so on.

[0465] ●UE uses UE-based OTDOA as the primary positioning method. The UE may indicate to the network that the number of TRPs is insufficient.

[0466] The machine learning assisted region is described below.

[0467] Information about the presence of ML assisted areas may be indicated to the UE by the network. This may be done via broadcast posSib or other means. Alternatively, when the UE enters an ML assisted area, the UE may receive unicast, multicast or broadcast signaling to inform of the presence of these areas.

[0468] For each region, the AD can include an ML-assisted status, which is one of the following states:

[0469] ●AI / ML is not supported in this region

[0470] ●The model for this region is still in the training phase. The model is requesting further data for model training.

[0471] ● Model partially trained. Position estimation and / or measured signal classification may be required to further determine the availability of ML / AI support. For example, the model was trained using LOS data, but the trained model captures enough information for temporal blocking of one or more links. The model may not have been trained for NLOS regions. The model seeks further input data to cover NLOS regions.

[0472] The model also covers the NLOS regions and is able to determine the location of the NLOS regions.

[0473] For each region, the model state may change if the environment changes. For example, one could consider further refining the model state definition to define the level of inconsistency of the most recent measurements received from that region. This could be defined, for example, by the model accuracy level.

[0474] The UE may also infer that it has entered the ML assistance region by means of measurements performed on certain DL signals (e.g., PSS, SSS, CSI-RS, DL-PRS, etc.) and / or sidelink reference signals and / or uplink reference signals (e.g., UL-PRS).

[0475] A network entity (e.g., LMF or NG-RAN node) may provide a configuration to the UE, instructing the UE to perform measurements on certain reference signals. The UE may be configured to report such measurements and / or analyze the measurements to determine whether the UE has entered an ML assisted area. The UE may also be provided with a threshold to compare the measurements with the threshold to determine whether the UE has entered such an ML assisted area. If the UE determines that it has entered an ML assisted area, it may send a signal to the NW.

[0476] A network entity (e.g., LMF or NG-RAN node) may determine that the UE has entered an ML assisted area. The LMF may determine this information using at least one information:

[0477] 1. Measurements reported by the NG-RAN node, which may include one or more of the following: RSRP of the uplink reference signal, TA used by the UE, AoA, RToA, RxTxTimeDiff (the time difference between the reception of the UL signal and the transmission time of the downlink reference signal)

[0478] 2. Logical information, as information about the serving cell (primary cell and / or secondary cell)

[0479] 3. The measurements reported by the UE may include one or more of the following: RSRP, RSTD, AoD, TA, RxTxTimeDiff (the time difference between the reception time of the UL signal and the transmission time of the downlink reference signal) on the downlink reference signal

[0480] The LMF may indicate to the UE that it has entered the ML assistance area. In addition, the LMF may indicate the availability of additional assistance data available to the UE. In addition, the LMF may additionally (and / or optionally) signal the UE to report additional measurements and / or additional information.

[0481] Additional assistance data applicable to the ML region may include any of the following:

[0482] i.ML model parameters include at least one of the following:

[0483] a.ML Model

[0484] b. Characteristics of ML models

[0485] c. Coefficients describing an ML model and / or a part of it.

[0486] d. Other auxiliary data in the measurement, such as

[0487] ii. Other information that needs to be reported may be

[0488] a. Information that associates measurements from one positioning session to another

[0489] b. Consistency between measurements

[0490] In the following, the definition and use of ACS according to embodiments are provided.

[0491] With respect to ACS definitions, according to one aspect, a positioning system includes one or more Association and Calibration Points (ACS), which refers to a geographic area associated with information related to channel characteristics managed in the point. Figure 8 An example of an ACS implementation is shown, the ACS has an identifier ID and is associated with 2 resources from TRP-A and one resource from TRP-B. In some examples, the ID is implicitly derived from ACS characteristics such as absolute, relative position, distance or direction information. It should be noted that the association is not limited to beam direction, but can also be related to transmission characteristics or / and receiver assumptions.

[0492] Regarding the effective area of ​​ACS, in related aspects, Figure 8 It is also shown that ACS information is valid within a given area and partially valid or invalid outside of that area. This may be related to the validity of ACS information at different altitudes, for example, or to indications of area changes and the expected relevance of required channel information (such as V-TRP). Using the number of required ACSs in a positioning area is related to the trade-off between signaling complexity, information availability, and required granularity. The NW may identify the validity information of each ACS and the number of ACS information required based on context-related information and / or ML model performance.

[0493] With respect to calibration usage, the ACS usage within the solution supports several aspects: In one option, the usage associated with the provided calibration tag enables the measurement device to identify the required measurement characteristics or receiver assumptions to estimate one or more measurements at the measurement device. In one example, a UE performing DL or / and UL measurements in (UE-assisted and UE-based modes) or TRP uses the ACS information to set the detection method or thresholds to derive ToA, RSRPP or AoA. The ACS information in this example may be related to the expected reception level of the LOS path relative to a later and potentially stronger multipath path. Here, it should be particularly noted that the usage associated with the provided calibration tag enables the measurement device to identify the measurement characteristics of one or more measurements at the measurement device. For example, this may be related to the monitoring usage described above.

[0494] Regarding the use of association, in the second option, the ACS provides association information to help the UE or TRP report additional path and direction information. In one example, the UE or TRP is able to report a configurable number of paths, and the number of identified paths or directions exceeds the number of configured paths. Therefore, in this example, the ACS can provide guidance to the UE or TRP to associate the measurement paths and / or directions with the ACS information and identify the information required for the measurement report.

[0495] In a related implementation, the ACS information is associated with one or more resources from one or more antennas corresponding to one or more transmitters or receivers. Thus, the ACS information can provide information from multiple antennas of the same TRP or UE and / or between different TRPs or UEs.

[0496] Figure 8 and Fig. 9 Two implementations of ACS information according to an embodiment are shown, in the first implementation, multipath information and optionally amplitude information for each path are provided. In the second implementation, paths are provided within a time window to obtain the expected certainty of these paths, and amplitude information is optionally provided. Obviously, the ACS only includes a subset of information compared to the measured CIR.

[0497] Specifically, Figure 8 Association and calibration points are shown according to an embodiment.

[0498] Fig. 9 Shown according to Figure 8 Example of ACS information for an implementation of a scenario.

[0499] Regarding UE-based ACS, in one aspect, the solution proposes a method for providing ACS information to a UE in a UE-based mode, wherein the UE is configured to receive one or more PRS configurations for one or more antennas of one or more transmitting devices from a NW, and; receive a set of parameters including information about at least one ACS from a NW entity; wherein the UE will use the information to determine its position.

[0500] This information can be point locations defined by ground truth labels and ACS valid areas.

[0501] With regard to UE-based and UE-assisted ACS identification, in related aspects, the solution provides a method for identifying relevant ACS information in a positioning area. For UE-based, the NW needs to identify a subset of ACSs relevant to the UE from a set of ACSs supported in the positioning area. To this end, there are several options that can be applied individually or in combination with each other. In one option, the NW can utilize the reported UE position and uncertainty, or derive the UE position based on reported measurements and identify the ACS area. In the second option, sidelink information can be used for the second UE to identify the area; these sidelink information can be reported from the second UE (for example, a time PRU) or reported by the device itself, or inferred by the NW based on reported measurements. In the third option, the NW can utilize UL reference signals reported from one or more TRPs and use these measurements of the ML model to extract similarities and identify relevant ACS subsets. In the fourth option, the UE can provide information about the type of motion or speed information to identify the number of ACSs predicted on one or more potential orbits. Alternatively, for the last option, the UE can request multiple ACS information from the NW for calculating its position or reporting measurements.

[0502] With respect to ACS multi-level information, in another related aspect, the provided ACS information can be provided in a multi-level approach. That is, in a first stage, coarse ACS information is provided, wherein refinement or granularity of the ACS information occurs in subsequent stages based on measurements, matching with outputs of a previous stage, or changes in conditions.

[0503] Regarding ACS information, an ACS includes one or more of the following associated with one or more resources or resource sets:

[0504] - One or more delay paths for LOS and / or multipath components

[0505] - One or more directional paths for LOS and / or multipath components

[0506] - Power / amplitude information for one or more directions and delay paths associated with a resource or with one path per resource

[0507] - Expected LOS delays and amplitudes of multipath components, such as the maximum peak expected for a given resource

[0508] - Window configuration indicating the expected delay or direction of LOS or multipath that should be measured or reported

[0509] - Window configuration indicating expected delays or directions of LOS or multipath that should not be measured or reported

[0510] - A validity area with information about the validity, where the information can be a soft value or a hard value

[0511] - Relevance of ACS information for a given area to the number of updates required or expected

[0512] - an indication from the measurement unit of the applicability of the received ACS information on the received measurements and / or configured measurement reports

[0513] The following is an overview of the processes associated with model maintenance.

[0514] The lifecycle management of a model includes at least the following phases / states:

[0515] ● Initial training during the deployment phase:

[0516] The scope of the initial training is to build a model that can estimate the position with full or reduced accuracy at least for some parts of the network or to assist other localization techniques.

[0517] ○For network-based localization, the trained model is part of the network

[0518] ○ For UE-based positioning, the trained model must be deployed to the UEs in the network. This can be done by the network operator or the equipment vendor. Different models may be required for different regions.

[0519] ○ For UE-assisted positioning, parts of the model (e.g., area type identification) can be deployed to the UE

[0520] ●Fine-tuning of the model:

[0521] Using information from UEs deployed in the network (e.g. IoT devices), the model can be fed with additional training data and updated accordingly.

[0522] ○ Provide additional training data for “LOS regions” to prepare the network for changes in the environment (e.g.: LOS regions become NLOS regions)

[0523] ○ Use time anchors or information from UEs in the same ACS to provide additional training data for NLOS regions

[0524] ●Incremental updates of the model as the environment changes:

[0525] ○Continuously update the model, similar to the fine-tuning phase

[0526] ○ Identify the model status for each ACS (“Valid”, “Updating / Limited Accuracy”, “Invalid”)

[0527] ● Detect invalid model and enter "full" retraining (= new initial training):

[0528] If incremental updates fail, a full retraining may be necessary.

[0529] Possible processes may, for example, include one or more or all of the following elements:

[0530] ACS information:

[0531] ○ The network can capture and manage the relevant AD for each ACS

[0532] ○ The UE can request ACS information related to its current location from the network

[0533] ● In another embodiment, the ACS data may include (or define) information used as input data for training

[0534] ● The UE can first determine a rough location to identify relevant ACS information

[0535] ○ACS information can be used to

[0536] ■Identify “area status” (LOS / NLOS area)

[0537] ■ Check the consistency of the measured data with the characteristics provided by the ACS information

[0538] ■Search for UE in the same ACS

[0539] ○UE can request available time anchor points associated with ACS from the network

[0540] ○UE can request activation time anchor from the network

[0541] ● The UE may perform measurements and may report ACS related data to the network. The network may use these measurements to update ACS information or as input data for model training updates.

[0542] • Depending on the type of ACS area (LOS or NLOS), the UE or the network can select an appropriate positioning method, or the ACS information is an additional input to a (generic) positioning method.

[0543] ●ACS information can also control the portion of the CIR reported to the LMF.

[0544] o CIR can include different types of multipath clusters. The reporting method (delay and amplitude only, or delay and complex CIR, or delay, amplitude and phase) can depend on the type of cluster

[0545] ■At least for LOS paths / clusters, full reporting (complex value or phase) is assumed

[0546] ■For virtual TRP, additional information may be provided at this stage

[0547] ■For other clusters, simplified (latency and amplitude only) reporting may be sufficient.

[0548] Based on this, the following process according to the implementation scheme is provided:

[0549] 1) Initial training:

[0550] - Initial training using simulation data (LOS area training)

[0551] - Identify areas that require "NLOS model initialization"

[0552] -Statistics of deployed IoT devices

[0553] - "Robot" scanning area that requires model initialization

[0554] - Uncertainty estimates of the initial model (the one trained on simulation vs. real-world characteristics) show low confidence in environments with different / changing characteristics, e.g., a model trained on LOS returns low confidence values ​​in an environment with NLOS

[0555] -Optionally via: "NLOS area triggered initialization"

[0556] - Start the drone

[0557] -Optional: Robot scanning other areas

[0558] -(Location) Model uncertainty measure; confidence varies with known to unknown data, i.e., there is a deviation between training data and inference data

[0559] 2a) “Operational Phase”, Network-Based Positioning

[0560] - Identify the area status

[0561] - Case 1: From NLOS to LOS

[0562] - Update fingerprint using LOS positioning

[0563] - Case 2: From LOS to NLOS

[0564] -Search for time anchors

[0565] - If a temporal anchor is available (and of sufficient quality), update the model

[0566] - If no time anchor is available: check model state (last update still valid?)

[0567] -Different model status for each ACS

[0568] - Reports estimated position and model status

[0569] - Case 3: Receiving status remains unchanged

[0570] - Identify relevant ACS

[0571] - Check the model status of the ACS model

[0572] - If an update is suggested, search for a time anchor

[0573] - If a temporal anchor is available, update the model

[0574] 2b) Operation phase, based on UE positioning

[0575] a) New UE: Copy the model to the UE

[0576] b) UE has received the model

[0577] i) Identify the ACS region

[0578] ii) Check the model status of the relevant ACS (request model status from the network)

[0579] iii) Request model updates when necessary

[0580] iv) If no model update is available

[0581] ● Check the positioning accuracy estimate

[0582] ●Notify the network of required updates when necessary.

[0583] In the following, a training phase according to some embodiments is described, which may be similarly or analogously applicable to, for example, LMF, UE and TRP procedures. It should be noted that, for example, one or more or all of the following may be implemented:

[0584] Black box global model

[0585] ○ Pre-training on known configurations with appropriate channel characteristics

[0586] ○ Pre-training can be based on simulated or real-world data or a mixture of them

[0587] ○ “User” may not know the description of the parameter

[0588] ○ Global models can be deployed to participants for localization

[0589] ○ A global model can be deployed and calibrated with local models

[0590] This local model combines the output of the global model and calibrates its parameters to the local environment or configuration.

[0591] This local model can also replace part of the global model for calibration

[0592] ○ Partial or compressed versions of the global model can be deployed for local calibration

[0593] ○ The global model can also just listen to information and implicitly learn configuration and features

[0594] ■This model can be reconstructed or embedded in the global or local environment

[0595] ■This local model can generate data to update the global model

[0596] ○ Participants can record and learn local models without reference when measuring similarities between individual measurements

[0597] ■This similarity can depend on side information such as time, speed, distance, orientation, absolute position, other sensor information such as camera / visual inertial odometry, GNSS, IMU, etc.

[0598] ■ The local model can interpret its manifold to identify, for example, walls or other potential temporal anchors

[0599] Transparent

[0600] ○ Potential architectures where global or local models can be deployed to participants

[0601] ■This architecture can also provide structure and pre-trained parameters

[0602] ■This architecture can provide requirements for local or global models

[0603] ■ This architecture or component can be replaced or retrained

[0604] ●Combination

[0605] ○ Some parts of the global graph can be black boxes, and other parts can be transparent

[0606] ●Supervised training

[0607] ○ Pre-training can be performed on simulation, real-world data, or a mixture thereof; measurements and corresponding reference values, i.e., locations, are available;

[0608] ○ Calibration can be performed on simulation, real-world data, or a mixture of these; the error between the estimate and the reference participant can be used as the calibration value;

[0609] Unsupervised training

[0610] ○ Pre-training may be performed on simulation, real-world data, or a mixture thereof; a reference may not be available; similarity estimates such as the Jensen Shannon divergence, Wasserstein divergence, or Kullback Leibler divergence between measurements may be available;

[0611] ○ Calibration can be performed on simulated or real-world data, or a mixture thereof; again, a reference may not be available;

[0612] ○ Scaling and rotation of the manifold can be performed with few similarity measures and combined as local or global Figure 1 Some side information, such as distance, direction, and location

[0613] Semi-supervised training

[0614] ○ Pre-training can be similar to unsupervised training, with few references available for (semi-)supervised calibration of the model

[0615] ○ For example, a black-box model pre-trained in simulation can be calibrated on a small amount of representative real-world data with reference information

[0616] ■ The reference information can be, for example, a virtual time anchor point with high confidence

[0617] …

[0618] In the following, model deployment / monitoring according to an embodiment is described:

[0619] ○Model validity and correlation with reference models

[0620] ○Model performance score

[0621] ○Monitoring reference point or PRU information

[0622] -Black box deployment

[0623] ○Cascade deployment

[0624] ○ Use continuous model to fine-tune / adapt to target (site / device)

[0625] -Transparent deployment

[0626] ○ Deploy only parts of the network (layers / weights) to fine-tune / calibrate the network specific to a site or device - compression

[0627] ○ Models can be compressed (e.g., from 32 bits to 8 bits) to reduce network traffic and cost; the accuracy of the model remains unchanged.

[0628] ○ Models can be compressed in a global library or locally.

[0629] Fig.10Details of potential pre-processing steps according to an embodiment are shown. It should be noted that non-linear N / LOS classification, quantification or uncertainty estimation may also be part of the potential pre-processing scheme.

[0630] Fig.11 A scheme of a specific model identification process according to an implementation scheme is shown. Based on the "process", a specific local model can be selected from the global model pool relative to the description or configuration. All or part of the pre-deployed "local" model can be redeployed to other UEs again, or updated during the inference phase, or updated to the global library.

[0631] Fig.12 An exemplary scheme of a continuous "model identification" process according to an embodiment is shown. The model identifies the lack of known information, which may appear as known information / data gaps in the training phase, leading to high uncertainty in the inference / real-time phase. Potential inputs can be, for example, (a set of) channel impulse responses or their descriptive parameters, such as TOA, AOA, AOD, TOT, TDOA..., side information (see Fig.12 ). Potential outputs could be, for example, positions, their derivations, probabilities / variances (uncertainties), side information. This involves monitoring the outputs of the trained model.

[0632] Fig.13 An exemplary scheme of our proposed supervised learning process according to an implementation scheme is shown. The reference known information can be absolute or relative "spatial" information, which can contribute to the localization task as exogenous information. The absolute known information can be the position; the relative information can be the side information. Potential inputs: (a set of) channel impulse responses or their descriptive parameters, such as TOA, AOA, AOD, TOT, TDOA..., side information (see Fig.13 ). Potential outputs could be, for example: location, its derivation, probability / variance (uncertainty), side information.

[0633] Fig.14 A scheme of an unsupervised learning process according to an implementation scheme is shown. The process exploits similarities that are defined by side information such as distance, speed, time, etc. or absolute spatial information such as time anchors, ACS, etc. Virtual scale / rotation variants will be converted into real-world scale and rotation variants with side information. From there, downstream localization or classification tasks can be performed. Potential inputs can be, for example, channel impulse responses (tuples or triplets of sets) or their descriptive parameters such as TOA, AOA, AOD, TOT, TDOA, ..., side information (see Fig.14 ; allows real-world scaling and translation of the manifold); internal similarity of these tuples, triplets: potential outputs can be: similarity measures; implicit locations, clustering, interpretable disentanglement of manifolds, classification.

[0634] Fig.15 A global view of the continuous learning process according to an embodiment is shown. It should be noted that one or more time anchors or ACDs may be included in each step. Potential inputs may be, for example, (a set of) channel impulse responses or their descriptive parameters, such as TOA, AOA, AOD, TOT, TDOA, ..., side information (see Fig.15 ). Potential outputs could be, for example, position, derived information such as velocity, distance, acceleration, direction, probability / variance (uncertainty), side information.

[0635] Fig.16 The processing scheme of the continuous iterative learning pipeline according to the implementation scheme is shown. The observation unit scans and steers the beam management unit to identify, observe and track the evolution of the time anchor points and the ACS, thereby iteratively updating the observation unit using the spatial information provided by these units. The uncertainty and error estimation component provides additional confidence measures to analyze the information gain of each iteration and improve the observation process. Potential inputs can be, for example, (a set of) channel impulse responses or their descriptive parameters, such as TOA, AOA, AOD, TOT, TDOA..., side information (see Fig.16 ), state, reward, possible actions. Potential outputs can be, for example, position, derived information such as speed, distance, acceleration, orientation, probability / variance (uncertainty), side information.

[0636] Fig.17 An abstract scheme of a model identification process according to an embodiment is shown.

[0637] Although some aspects of the described concepts are described in the context of an apparatus, it is clear that these aspects also represent a description of the corresponding method, where a block or device corresponds to a method step or a feature of a method step. Similarly, aspects described in the context of a method step also represent a description of a corresponding block or item or feature of a corresponding apparatus.

[0638] The various elements and features of the present invention can be implemented in hardware using analog and / or digital circuits, in software, by executing one or more general or special processor instructions, or as a combination of hardware and software. For example, embodiments of the present invention can be implemented in the environment of a computer system or another processing system. Fig.19An example of a computer system 600 is shown. The units or modules and the steps of the methods performed by the units can be executed on one or more computer systems 600. The computer system 600 includes one or more processors 602, such as a dedicated or general-purpose digital signal processor. The processor 602 is connected to a communication infrastructure 604, such as a bus or a network. The computer system 600 includes a main memory 606, such as a random access memory RAM, and an auxiliary memory 608, such as a hard drive and / or a removable storage drive. The auxiliary memory 608 can allow computer programs or other instructions to be loaded into the computer system 600. The computer system 600 can also include a communication interface 610 to allow software and data to be transmitted between the computer system 600 and external devices. Communication can be carried out in the form of electronic, electromagnetic, optical or other signals that can be processed by the communication interface. Communication can use wires or cables, optical fibers, telephone lines, cellular phone links, RF links and other communication channels 612.

[0639] The terms "computer program medium" and "computer readable medium" generally refer to tangible storage media, such as a removable storage unit or a hard disk installed in a hard drive. These computer program products are means for providing software to the computer system 600. Computer programs, also referred to as computer control logic, are stored in the main memory 606 and / or the secondary memory 608. The computer program may also be received via the communication interface 610. When the computer program is executed, the computer system 600 is able to implement the present invention. In particular, when executed, the computer program enables the processor 602 to implement the process of the present invention, such as any method described herein. Therefore, such a computer program may represent a controller of the computer system 600. In the case of implementing the present disclosure using software, the software may be stored in a computer program product and loaded into the computer system 600 using a removable storage drive, an interface (such as the communication interface 610).

[0640] The implementation in hardware or software may be performed using a digital storage medium, such as cloud storage, floppy disk, DVD, Blu-ray, CD, ROM, PROM, EPROM, EEPROM or flash memory, on which electronically readable control signals are stored, which cooperate or can cooperate with a programmable computer system to perform the corresponding method. Therefore, the digital storage medium can be computer readable.

[0641] Some embodiments according to the invention comprise a data carrier having electronically readable control signals, which are capable of cooperating with a programmable computer system, such that one of the methods described herein is performed.

[0642] Generally, the embodiments of the present invention can be realized as a computer program product with a program code, wherein the program code is used to perform one of the methods when the computer program product runs on a computer. The program code can be stored on a machine-readable carrier, for example.

[0643] Other embodiments comprise the computer program for performing one of the methods described herein, stored on a machine readable carrier. In other words, therefore, one embodiment of the inventive method is a computer program having a program code for performing one of the methods described herein when it runs on a computer.

[0644] Therefore, another embodiment of the method of the present invention is a data carrier or a digital storage medium, or a computer readable medium, on which is recorded a computer program for performing one of the methods described herein. Therefore, another embodiment of the method of the present invention is a data stream or a signal sequence representing a computer program for performing one of the methods described herein. The data stream or signal sequence can be configured, for example, to be transmitted via a data communication connection (e.g., via the Internet). Another embodiment includes a processing device, such as a computer or a programmable logic device, which is configured or adapted to perform one of the methods described herein. Another embodiment includes a computer having a computer program for performing one of the methods described herein installed thereon.

[0645] In some embodiments, a programmable logic device (e.g., a field programmable gate array) can be used to perform some or all of the functions of the methods described herein. In some embodiments, a field programmable gate array can be coordinated with a microprocessor to perform one of the methods described herein. Typically, these methods are preferably performed by any hardware device.

[0646] The above embodiments are only used to illustrate the principles of the present invention. It should be understood that modifications and variations of the arrangements and details described herein will be apparent to other persons skilled in the art. Therefore, it is intended that the scope of the patent claims to be filed be limited only, and not limited by the specific details set forth herein by describing and explaining the embodiments.

[0647] abbreviation

[0648]

[0649]

[0650]

[0651]

Claims

1. A user equipment (100) of a wireless communication system, wherein the user device (100) is configured to determine and / or receive information about the suitability of the machine learning model, and / or The user device (100) is configured to determine and / or receive information that the user device (100) is located in a machine learning assisted area.

2. The user equipment (100) according to claim 1, The user equipment (100) is a sensor unit and / or the user equipment (100) has sensor unit capabilities.

3. The user equipment (100) according to claim 1 or 2, The user equipment (100) is configured to receive information from a network entity (200) of the wireless communication system that the user equipment (100) is located in a machine learning assisted area.

4. The user equipment (100) according to any one of the preceding claims, The user equipment (100) is configured to receive information from a network node of the wireless communication system, wherein the information includes at least one of the following: The region where the user device (100) is located does not provide AI / ML support, The model in the area where the user is located is still in the training phase and the model is requesting more data for model training. The model is partially trained and position estimation or interval estimation or distance estimation and / or measurement signal classification may be required to further determine the availability of ML / AI support. The model also covers NLOS regions and is able to determine position or distance in NLOS regions. The model is usable but may be less accurate, for example due to changes in the environment. Operation mode, such as the need to update the operation mode due to reduced confidence and / or such as updating the phase operation mode and / or a high confidence operation mode such as in a NLOS area.

5. The user equipment (100) according to any one of the preceding claims, wherein the user equipment (100) is configured to perform one or more measurements by measuring one or more reference signals, and wherein the user equipment (100) is configured to determine whether the user equipment (100) is located in a machine learning assisted area by receiving an indication from a network entity (200) of the wireless communication system and / or receiving auxiliary data required to identify a machine learning assisted area from a network entity (200) of the wireless communication system; and / or wherein the user device (100) is configured to identify the machine learning assisted region by analyzing the one or more measurements; and / or The user equipment (100) is configured to transmit information about the one or more measurements to an entity of the wireless communication system, and obtain information about whether the user equipment (100) is located in a machine learning assisted area from the entity or from another entity of the wireless communication system in response to transmitting the information about the one or more measurements.

6. The user equipment (100) according to claim 5, The user equipment (100) is configured to measure the one or more reference signals, which are one or more downlink reference signals, and / or through one or more sidelink reference signals and / or one or more uplink reference signals.

7. The user equipment (100) according to claim 6, The one or more downlink reference signals are one or more of PSS, SSS, CSI-RS and DL-PRS, and / or the one or more uplink reference signals are one or more UL-PRS and / or one or more SRS.

8. The user equipment (100) according to any one of the preceding claims, wherein the user equipment (100) is configured to receive one or more threshold values, and The user device (100) is configured to compare the one or more measurements with the one or more thresholds to determine whether the user device (100) is located in a machine learning assisted area.

9. The user equipment (100) according to claim 8, wherein the one or more thresholds include at least one of an RSRP threshold and an SNR threshold, in, Based on the RSRP threshold and / or the SNR threshold, the user equipment (100) is configured to trigger activation or deactivation of the machine learning model.

10. The user equipment (100) according to any one of the preceding claims, The user equipment (100) is configured to perform one or more of the following measurements: RSRP (reference signal received power) of one or more downlink reference signals, RSRPP (reference signal received path power) of one or more downlink reference signals, RSTD, AoD, AoA, RxTx time difference, And wherein the user equipment (100) is configured to report information about the one or more measurements to a network entity (200) of the wireless communication system.

11. The user equipment (100) according to any one of the preceding claims, in, The user equipment (100) is configured to determine its location and / or determine the distance between the user equipment (100) and another entity of the wireless communication system, such as another user equipment (100), using the machine learning model or parameters of the machine learning model, such as ranging information.

12. The user equipment (100) according to claim 11, The user equipment (100) is configured to receive the machine learning model or parameters of the machine learning model from a network entity (200) of the wireless communication system.

13. The user equipment (100) according to claim 12, The machine learning model represents a machine learning model selected from a group of machine learning models, for example, selected from a global machine learning model library.

14. The user equipment (100) according to any one of the preceding claims, The user device (100) is configured to select the machine learning model from a group of machine learning models, for example, from a global machine learning model library.

15. The user equipment (100) according to claim 13 or 14, The user device (100) is configured to receive a description or configuration comprising the set of machine learning models.

16. The user equipment (100) according to any one of claims 13 to 15, The set of machine learning models includes multiple machine learning models, wherein each of the multiple machine learning models is a machine learning model for a specific area, for example, for a specific area.

17. The user equipment (100) according to any one of claims 13 to 16, The user device (100) is configured to select the machine learning model from the set of machine learning models based on one or more measurements.

18. The user equipment (100) according to claim 17, The result of the one or more measurements depends on the location of the user equipment (100).

19. The user equipment (100) according to any one of claims 11 to 18, wherein the user device (100) is configured to deploy the machine learning model or a portion thereof, or a parameter of the machine learning model or a portion thereof, to other user devices, and / or wherein the user equipment (100) is configured to update the machine learning model or a part thereof during the interference phase, or to update a parameter of the machine learning model or a part thereof, and / or The user device (100) is configured to update the machine learning model or a part thereof, or a parameter of the machine learning model or a part thereof, in a global library.

20. The user equipment (100) according to any one of claims 11 to 19, in, During training of the machine learning model, the user device (100) is configured to monitor an output of the machine learning model.

21. The user equipment (100) according to claim 20, The user equipment (100) is configured to train a pre-trained model to obtain a trained model.

22. The user equipment (100) according to any one of claims 11 to 21, The input to the machine learning model is at least one of the following: one or more channel impulse responses, At least one TOA, At least one AOA, At least one AOD, At least one TOT, At least one TDOA.

23. The user equipment (100) according to any one of claims 11 to 22, wherein the user equipment (100) is configured to receive update information about the machine learning model or a parameter of the machine learning model from a network entity (200) of the wireless communication system, and The user device (100) is configured to use the update information to update the machine learning model or parameters of the machine learning model.

24. The user equipment (100) according to any one of claims 11 to 23, wherein the user device (100) is configured to receive training data from another user device (100), and The user device (100) is configured to train and / or retrain and / or calibrate the machine learning model using the training data.

25. The user equipment (100) according to any one of the preceding claims, Wherein if the user equipment (100) is located in a machine learning assisted area, the user equipment (100) is configured to receive auxiliary data from a network entity (200) of the wireless communication system.

26. The user equipment (100) according to claim 25, Wherein if the user equipment (100) is located in a machine learning assisted area, the user equipment (100) is configured to receive information that the auxiliary data is available from a network entity (200) of the wireless communication system.

27. The user equipment (100) according to claim 25 or 26, The user equipment (100) is configured to receive one or more of the following machine learning model parameters as the auxiliary data: Machine learning models, such as a type of model, the structure of the model, such as the type and / or number of layers and their structural dependencies, One or more features of a machine learning model, such as input data, one or more coefficients describing a machine learning model and / or a part thereof, Additional auxiliary data for making measurements, Information for triggering the user equipment (100) to provide additional measurements, for example as a sensor unit.

28. The user equipment (100) according to any one of the preceding claims, The user equipment (100) is configured to receive information from a network node of the wireless communication system, wherein the information comprises a request for the user equipment (100) to provide additional information. wherein the additional information comprises, for example, information relating measurements of one positioning session to measurements of another positioning session and / or, for example, consistency between measurements, and The user equipment (100) is configured to transmit the additional information.

29. A user equipment (100) of a wireless communication system, The user equipment (100) is configured to determine whether it will act as a time anchor unit, such as as a time anchor or as a time PRU or as a PRU, based on the time reference information.

30. The user equipment (100) according to claim 29, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) displays its location information, or another entity of the wireless communication system, such as a network entity (200), includes location information about the user equipment (100) and / or includes distance information, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment (100).

31. The user equipment (100) according to claim 29 or 30, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to transmit one or more reference signals to another user equipment (100) of the wireless communication system, and / or is configured to receive one or more reference signals from the other user equipment (100), for example for determining location information about the location of the other user equipment (100), and / or for determining distance information between the user equipment (100) and another entity of the wireless communication system, for example another user equipment (100), such as ranging information.

32. The user equipment (100) according to any one of claims 29 to 31, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to report in the same positioning session: information about its location, and / or information about the distance between the user equipment (100) and another entity of the wireless communication system, such as another user equipment (100), such as ranging information; and One or more measurements of a reference signal.

33. The user equipment (100) according to any one of claims 29 to 32, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to receive a location reference signal from an entity of the wireless communication system and / or the user equipment (100) is configured to transmit a location reference signal to the entity, the entity being a network entity (200) of the wireless communication system or another user equipment (100).

34. The user equipment (100) according to any one of claims 29 to 33, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the network entity (200) of the wireless communication system is able to determine the location of a device of the wireless communication system and / or determine the distance between the user equipment (100) and the device by receiving a report on one or more measurements from the user equipment (100), such as one or more measurements performed on a location reference signal transmitted by other devices in the wireless communication system.

35. The user equipment (100) according to any one of claims 29 to 34, wherein the user equipment (100) is configured to receive a time reference information message from a network entity (200) of the wireless communication system or from another user equipment (100) of the wireless communication system, The time reference information message includes the time reference information.

36. The user equipment (100) according to any one of claims 29 to 34, The user equipment (100) can access the time reference information without receiving the time reference information in a message.

37. The user equipment (100) according to any one of claims 29 to 36, The user equipment (100) is configured to determine and / or assist in determining the location of another user equipment (100) of the wireless communication system.

38. The user equipment (100) according to any one of claims 29 to 37, wherein the time reference information includes one or more conditional criteria, The user equipment (100) is configured to decide whether it will act as a time anchor point unit by determining whether the user equipment (100) satisfies at least one conditional criterion among the one or more conditional criteria.

39. The user equipment (100) according to claim 38, The one or more conditional criteria include one or more of the following: An indication of the absolute or relative accuracy of positioning, Certainty, Location quality, The protection level, which is the statistical upper limit of the positioning error, An integrity flag which is an indication of whether the protection level is greater than the alarm limit.

40. The user equipment (100) according to claim 38 or 39, The one or more conditional criteria include capability signaling for providing one or more of the following information: Azimuth, direction, speed, Acceleration, A state of motion in a motion model, such as stationary, pedestrian, vehicle traffic, or highway traffic.

41. The user equipment (100) according to any one of claims 29 to 40, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to provide information that it will act as a time anchor point unit to one of the network entities of the wireless communication system or one of the user equipments (100) using PRU capability signaling.

42. The user equipment (100) according to any one of claims 29 to 41, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to report its position to an entity of the wireless communication system and / or report one or more measurements and / or transmit a position reference signal and / or receive a position reference signal from an entity of the wireless communication system in the same positioning session, and / or report distance information, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment (100).

43. The user equipment (100) according to any one of claims 29 to 42, in, If the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to provide information of a machine learning model for positioning to one of the entities of the wireless communication system.

44. The user equipment (100) according to any one of claims 29 to 43, Wherein if the user equipment (100) has determined that it will act as a time anchor point unit, the user equipment (100) is configured to provide ACS information to an entity of the wireless communication system, for example, information about one or more characteristics of one or more transmission channels of the wireless communication system, and / or provide information about the validity of ACS information for a specific area.

45. The user equipment (100) according to any one of claims 29 to 44, in, If the user equipment (100) has determined that it will not act as a time anchor unit, the user equipment (100) is configured to avoid reporting its position to an entity of the wireless communication system and / or is configured to report to an entity of the wireless communication system that it will not act as a time anchor unit; and / or Wherein, if the user equipment (100) has determined that it will no longer act as a time anchor point unit, the user equipment (100) is configured to avoid reporting its location to an entity of the wireless communication system, and / or is configured to report to an entity of the wireless communication system that it will no longer act as a time anchor point unit.

46. ​​The user equipment (100) according to any one of claims 29 to 45, The user equipment (100) is capable of transmitting information about its location and / or is capable of transmitting information about the distance between the user equipment (100) and another entity of the wireless communication system, such as another user equipment, such as ranging information.

47. The user equipment (100) according to any one of claims 29 to 46, The user equipment (100) is configured to inform the network that it has the capability to become a time anchor unit.

48. The user equipment (100) according to any one of claims 29 to 47, Wherein if one or more predefined conditions are met, the user equipment (100) is configured to notify the network that the UE meets the conditions for acting as a PRU, and / or the user equipment (100) is configured to start sending measurements to a network entity (200) or another user equipment of the wireless communication system, for example, so that the user equipment (100) acts as a time anchor point or PRU.

49. The user equipment (100) according to any one of claims 29 to 48, The user equipment (100) is configured to obtain its position using a first positioning method, such as GNSS and / or iGPS and / or a positioning method dependent on RAT, and / or use reference information, such as O&M, and is configured to provide reference measurements and / or transmit signals for collecting reference measurements to a network entity (200) of the wireless communication system and / or another user equipment, for example, in order to meet the conditions for becoming a PRU.

50. The user equipment (100) according to any one of claims 29 to 49, The user equipment (100) is configured to receive a request, for example from a network entity (200) of the wireless communication system, to serve as a time anchor point unit for another device.

51. The user equipment (100) according to any one of claims 29 to 50, The user equipment (100) is configured to perform RTT measurement.

52. The user equipment (100) according to any one of claims 29 to 51, The user equipment (100) is configured to perform one or more measurements on one or more side links together with one or more other user equipments of the wireless communication system.

53. The user equipment (100) according to claim 52, The one or more measurements are used to measure the side link distance between the user equipment (100) and another user equipment to be located and / or to provide direction information.

54. The user equipment (100) according to any one of claims 29 to 53, The user equipment (100) is configured to determine the distance and / or direction using a RAT-independent technique, and is configured to notify a network entity (200) or another device of the wireless communication system that the ranging and / or direction information is obtained using a RAT-independent technique.

55. The user equipment (100) according to claim 54, The user equipment (100) is configured to use one or more of the following ranging technologies as the RAT-independent technology: UWB, LiDAR, radar, WLAN-based ranging.

56. A user equipment (100) of a wireless communication system, The user equipment (100) is configured to obtain information about its location and / or obtain information about the distance between the user equipment (100) and another entity of the wireless communication system, such as another user equipment, such as ranging information. by receiving information from another user equipment acting as a time anchor point unit, such as a time anchor point or a time PRU or a PRU, e.g. via a direct communication link or indirectly through a network, wherein the information received from the time anchor point unit comprises a location of the time anchor point unit and / or one or more measurements performed by the time anchor point unit on a signal transmitted by the user equipment (100), or wherein the information comprises a location reference signal, and By performing one or more measurements on one or more received signals and / or by transmitting derived information derived from said measurements of said wireless communication system to a network entity (200), such as to a LMF or NWDAF.

57. The user equipment (100) according to claim 56, wherein the user equipment (100) is configured to determine its own location, for example by adopting user equipment-based OTDOA, and / or is configured to report its location to a network entity (200) of the wireless communication system, Wherein the user equipment (100) is configured to perform and / or report one or more measurements on the one or more received signals as one or more downlink signals.

58. A user equipment (100) of a wireless communication system, The user equipment (100), for example a UL-TDOA device, is configured to support an entity of the wireless communication system, for example a network entity (200), in the following manner to obtain location information about the user equipment (100) and / or obtain distance information, for example ranging information, between the user equipment (100) and another entity of the wireless communication system, for example another user equipment, By sending one or more reference signals to another user equipment acting as a time anchor unit, such as a time anchor or a time PRU or a PRU, for example via a direct communication link or indirectly through a network, to allow the time anchor to make one or more measurements on the one or more reference signals and / or report one or more measurements to the entity of the wireless communication system.

59. A user equipment (100) of a wireless communication system, wherein the user equipment (100) is configured to determine, for example by using a RAT-independent technique and / or by using a RAT-dependent technique and / or by using a time anchor point, or is configured to receive, location information thereof and / or distance information, for example ranging information, between the user equipment (100) and another entity of the wireless communication system, for example another user equipment, and The user device (100) is configured to use the location information and / or the distance information thereof to assist in generating training data for a machine learning model for positioning, such as for machine learning with relevant labels, For example, the machine learning model is located on the LMF or NWDAF of the wireless communication system.

60. The user equipment (100) according to claim 59, The user equipment (100) is configured to use information about one or more channel impulse responses to assist in generating training data for the machine learning model.

61. The user equipment (100) according to claim 60, The user equipment (100) is configured to transmit information about the one or more channel impulse responses and their location information and / or the distance information to an entity of the wireless communication system, such as a network entity (200), to assist in generating training data for the machine learning model.

62. A user equipment (100) of a wireless communication system, wherein the user equipment (100) is configured to transmit one or more property information about the characteristics of an RF channel between the user equipment (100) and another entity of the wireless communication system and / or to transmit an indicator about the probability of the existence of a direct path ("line of sight" path) and / or characteristic information about one or more RF channel propagation paths not associated with the direct path, wherein the other entity of the wireless communication system is a base station or another user equipment of the wireless communication system, The user equipment (100) is configured to report information about one or more channel impulse responses to the other entity or another entity of the wireless communication system.

63. The user equipment (100) according to any one of claims 56 to 62, The user equipment (100) is configured to report one or more signal characteristics of at least one received reference signal to a network entity (200) of the wireless communication system, wherein the at least one received reference signal comprises at least one of the following information: Signal strength, LOS / NLOS probability, information about one or more received beams, The similarity of two or more, e.g. consecutive, beams, one or more channel impulse response parameters, similarity of two or more, e.g. consecutive, channel impulse responses, one or more estimates of distance and / or direction, Motion curve, Signal classification, for example, depends on confidence information.

64. The user equipment (100) according to any one of claims 56 to 63, The user equipment (100) is configured to measure DL reference signals during the execution of or supporting DL-TDOA and / or multi-RTT and / or DL-AoD methods.

65. The user equipment (100) according to any one of claims 56 to 64, in, If the number of TRPs with LOS conditions is insufficient, the user equipment (100) is configured to indicate to a network entity (200) of the wireless communication system that the number of TRPs with LOS conditions is insufficient.

66. The user equipment (100) according to any one of claims 56 to 65, The user equipment (100) is configured to receive information from an entity of the wireless communication system to communicate with another user equipment acting as a time anchor unit, such as a time anchor or a time PRU or a PRU, to obtain information about its location, and / or to obtain information about the distance between the user equipment (100) and another entity of the wireless communication system, such as another user equipment, such as ranging information.

67. The user equipment (100) according to any one of claims 56 to 66, The user equipment (100) is a sensor unit and / or the user equipment (100) has sensor unit capabilities.

68. The user equipment (100) according to any one of claims 56 to 67, The other user equipment acting as a time anchor point unit is a user equipment (100) according to any one of claims 18 to 44.

69. The user equipment (100) according to any one of claims 56 to 68, The user equipment (100) is configured to receive and process information about one or more available time anchor point units.

70. The user equipment (100) according to any one of claims 56 to 69, The user equipment (100) is configured to transmit a PRS signal synchronized with a network entity (200) of the wireless communication system to another entity of the wireless communication system, for example, to transmit a side link PRS to another user equipment.

71. The user equipment (100) according to any one of claims 56 to 70, The user equipment (100) is configured to measure the arrival time of the SRS signal relative to the network clock of the wireless communication system.

72. The user equipment (100) according to any one of claims 1 to 28, The user equipment (100) is configured as a user equipment (100) according to any one of claims 29 to 71.

73. The user equipment (100) according to any one of claims 29 to 71, wherein the user equipment (100) is configured to receive a machine learning model or parameters of the machine learning model from a network entity (200) of the wireless communication system, and The user equipment (100) is configured to determine its location using the machine learning model or parameters of the machine learning model, and / or the user equipment (100) is configured to determine a distance, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment.

74. The user equipment (100) according to claim 73, wherein the user equipment (100) is configured to receive update information about the machine learning model or a parameter of the machine learning model from a network entity (200) of the wireless communication system, and The user device (100) is configured to use the update information to update the machine learning model or parameters of the machine learning model.

75. The user equipment (100) according to claim 73 or 74, wherein the user device (100) is configured to receive training data from another user device, and The user device (100) is configured to train and / or retrain and / or calibrate the machine learning model using the training data.

76. The user equipment (100) according to any of the preceding claims, The user equipment (100) is configured to report its position and / or report one or more measurements and / or transmit a position reference signal to another user equipment of the wireless communication system via a side link and / or receive a position reference signal from another user equipment of the wireless communication system, and / or report distance information, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment.

77. The user equipment (100) according to any of the preceding claims, The user equipment (100) is configured to send training data to a network entity (200) of the wireless communication system to train and / or retrain and / or calibrate a machine learning model.

78. The user equipment (100) according to any of the preceding claims, The user equipment (100) is configured to transmit training data to another user equipment of the wireless communication system to train and / or retrain and / or calibrate the machine learning model.

79. A user equipment (100) of a wireless communication system, The user equipment (100) is configured to receive measurement and / or transmission characteristic information.

80. The user equipment (100) according to claim 79, The user equipment (100) comprises and / or implements a measurement device and is configured to receive measurement and / or transmission characteristic information, which enables the measurement device to identify one or more measurement characteristics.

81. The user equipment (100) according to claim 79, The user equipment (100) includes and / or implements a transmission device and is configured to transmit a PRS, which enables the network to identify and / or generate training data for model calibration.

82. The user equipment (100) according to any one of claims 79 to 81, The measurement and / or transmission characteristic information is associated with one or more TRPs and is also associated with a geographic area.

83. The user equipment (100) according to any one of claims 79 to 81, The measurement and / or transmission characteristic information is ACS information (correlation and calibration point information).

84. The user equipment (100) according to claim 83, The ACS information is associated with one or more TRPs and is also associated with a geographical area.

85. The user equipment (100) according to any one of claims 79 to 84, The user equipment (100) is configured to determine, based on the measurement and / or transmission characteristic information, whether the measurement and / or transmission characteristic information is valid for the area where the user equipment (100) is located.

86. The user equipment (100) according to any one of claims 79 to 85, The user equipment (100) is configured to perform and / or report one or more measurements of one or more reference signals based on the measurement and / or transmission characteristic information.

87. The user equipment (100) according to any one of claims 79 to 86, wherein the user equipment (100) is configured to receive the measurements and / or transmission characteristic information including power information about a power level of a given path, for example, wherein the power information is absolute or relative to one or more resources or multiple paths within a resource or within a measurement, The user equipment (100) is configured to use the information to detect the indicated path and / or determine its position and / or report measurements related to the detected path; and / or determine information about the distance between the user equipment (100) and another entity of the wireless communication system, such as another user equipment, such as ranging information.

88. The user equipment (100) according to any one of claims 79 to 87, The user equipment (100) is configured to use the measurement and / or transmission characteristic information to set a detection method or a detection threshold to derive ToA and / or RSRPP and / or AoA.

89. The user equipment (100) according to any one of claims 79 to 88, Wherein the measurement and / or transmission characteristic information comprises at least one indication of a delay and / or a direction of a non-LOS path.

90. The user equipment (100) according to any one of claims 79 to 89, The measurement and / or transmission characteristic information comprises at least one indication on a plurality of beams detectable in an area, such as an ACS area.

91. The user equipment (100) according to claim 90, The plurality of beams are associated with one or more expected channel conditions, the one or more expected channel conditions comprising one or more of the following: Soft or hard indication of LOS or NLOS conditions per beam, The expected power level per beam, e.g. RSRPP and / or RSRP.

92. The user equipment (100) according to claim 90 or 91, The plurality of beams are associated with indicative antenna radiation information of a main lobe, a null lobe or a side lobe provided to the user equipment (100).

93. The user equipment (100) according to any of the preceding claims, The user equipment (100) is configured to receive information about two or more antennas of the same TRP of the wireless communication system and / or information about two or more antennas of the same user equipment of the wireless communication system.

94. A user equipment (100) of a wireless communication system, wherein the user equipment (100) is configured to receive one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system from a network entity (200) of the wireless communication system, wherein the user equipment (100) is configured to receive measurement and / or transmission characteristic information including a set of one or more parameters from a network entity (200) of the wireless communication system, and The user equipment (100) is configured to use the one or more PRS configurations and use the measurement and / or transmission characteristic information to determine its location and / or distance information, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment.

95. The user equipment (100) according to claim 94, The user equipment (100) comprises and / or implements a measurement device and is configured to receive measurement and / or transmission characteristic information, which enables the measurement device to identify one or more measurement characteristics.

96. The user equipment (100) according to claim 94 or 95, The measurement and / or transmission characteristic information is ACS information (correlation and calibration point information).

97. The user equipment (100) according to any one of claims 79 to 96, The user equipment (100) is configured to select a part of the measurement and / or transmission characteristic information as a subset of the measurement and / or transmission characteristic information.

98. The user equipment (100) according to claim 97, The user equipment (100) is configured to select a subset of the measurement and / or transmission characteristic information based on information received from a network entity (200) of the wireless communication system and / or based on information derived from a side link and / or based on information derived from an uplink reference signal and / or based on movement type or speed information or direction information or pressure information.

99. The user equipment (100) according to any one of claims 79 to 98, wherein the user equipment (100) is configured to receive a first portion of the measurement and / or transmission characteristic information, and The user equipment (100) is configured to receive a second part of the measurement and / or transmission characteristic information after the first part, wherein the second part comprises more detailed information than the first part.

100. The user equipment (100) according to any one of claims 79 to 99, The measurement and / or transmission characteristic information includes one or more of the following: one or more delay paths for LOS and / or multipath components, one or more directional paths for LOS and / or multipath components, power / amplitude information for one or more directional and delay paths associated with a resource or with one path per resource, The expected LOS delay and amplitude of the multipath components, such as the maximum peak value expected for a given resource, Window configuration, indicating the expected delay or direction of LOS or multipath to be applied to the measurement or to be reported, Window configuration, indicating expected delays or directions of LOS or multipath that should not be measured or reported, a validity area with information about the validity, wherein the information may be a soft value or a hard value, correlation of the measurement and / or transmission characteristic information in a given area with the number of times the measurement and / or transmission characteristic information is required or expected to be updated, Instructions from the measuring unit.

101. The user equipment (100) according to any one of claims 79 to 100, The user equipment (100) is a sensor unit and / or the user equipment (100) has sensor unit capabilities.

102. The user equipment (100) according to any one of claims 79 to 101, The user equipment (100) is configured as a user equipment (100) according to any one of claims 1 to 78.

103. A network entity (200) of a wireless communication system, wherein the network entity (200) is configured to transmit time reference information to a user equipment (100) of the wireless communication system so as to enable the user equipment (100) to determine whether it can act as a time anchor unit, for example as a time anchor or as a time PRU or as a PRU, Wherein, if the user equipment (100) has determined that it will act as a time anchor point unit, the network entity (200) is configured to receive from the user equipment (100) information about its location and / or about one or more measurement and / or location reference signals; and / or information about the distance between the user equipment (100) and another entity of the wireless communication system, such as another user equipment, such as ranging information.

104. A network entity (200) of a wireless communication system, The network entity (200) is configured to receive, from a user equipment (100) of the wireless communication system, information about one or more line-of-sight links, e.g. defined by an RF channel as a direct path comprising a delay according to distance, or one or more properties or one or more characteristics of one or more RF channels between network entities, or information about the absence of a line-of-sight link with another entity, e.g. another network entity (200) of the wireless communication system.

105. A network entity (200) of a wireless communication system, The network entity (200) is configured to transmit information that the user equipment (100) of the wireless communication system is located in a machine learning assisted area.

106. The network entity (200) according to claim 105, wherein the network entity (200) is configured to store one or more identifiers of user equipment (100) of the wireless communication system that is entering a machine learning assisted area, wherein the network entity (200) is configured to delete an identifier of the user equipment (100) that leaves the machine learning assisted area, The network entity (200) or another entity of the wireless communication system is configured to obtain an identifier of at least one user device (100) located within the machine learning auxiliary area to initiate a process of training a machine learning model and / or updating a machine learning model.

107. The network entity (200) according to claim 106, The network entity (200) is configured to transmit the machine learning model or parameters of the machine learning model to the user equipment (100).

108. The network entity (200) according to claim 106 or 107, wherein the network entity (200) is configured to receive training data from the user equipment (100), and The network entity (200) is configured to train and / or retrain and / or calibrate a machine learning model using the training data.

109. A network entity (200) of a wireless communication system, in, If a user equipment (100) of a wireless communication system is to act as a time anchor unit, then The network entity (200) is configured to receive information about one or more measurements from the user equipment (100), such as one or more measurements performed on a location reference signal sent by the device, and The network entity (200) is configured to use location information about the user equipment (100) and to use information about one or more measurements to determine the location of the device and / or to determine a distance between the user equipment (100) and the device.

110. A network entity (200) of a wireless communication system, The network entity (200) is configured to send measurement and / or transmission characteristic information, such as ACS information (association and calibration point information), to a user equipment (100) of the wireless communication system, wherein the measurement and / or transmission characteristic information is associated with one or more TRPs and is also associated with a geographical area.

111. A network entity (200) of a wireless communication system, wherein the network entity (200) is configured to send one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system to a user equipment (100) of the wireless communication system, and The network entity (200) is configured to send measurement and / or transmission characteristic information, such as ACS information (association and calibration point information), to a user equipment (100) of the wireless communication system, wherein the ACS information includes a set of one or more parameters, for example, wherein the measurement and / or transmission characteristic information includes information about a relationship between an ACS-ID and auxiliary data, for example, wherein the auxiliary data includes a PRS configuration.

112. The network entity (200) according to any one of claims 103 to 111, Wherein the NW entity is any of the following: NWDAF, LMF, NRF, NEF, NG-RAN, AMF, GMLC, UDM.

113. A wireless communication system, comprising: One or more user equipment (100) according to any one of claims 1 to 102, and One or more network entities according to any one of claims 103 to 112.

114. A wireless communication system, wherein the wireless communication system comprises at least two entities, wherein each of the at least two entities is a user equipment (100) or a network entity (200), wherein the at least two entities comprise a first entity and a second entity, wherein the first entity is configured to determine, based on the time reference information, whether it will act as a time anchor point unit, for example as a time anchor point or as a time PRU or as a PRU, The second network entity (200) is configured to perform one or more measurements and to provide one or more reports derived from the one or more measurements to another network entity (200), such as to an LMF or NWDAF, to train a model, such as a neural network, or to capture characteristics of one or more RF signals received in an area.

115. The wireless communication system according to claim 114, wherein the first entity, such as a time anchor point, is configured to send to the second entity and / or is configured to receive one or more reference signals as information from the second entity, and The second entity is configured to use the information to determine its position; and / or determine distance information, such as ranging information, between the second entity and another entity of the wireless communication system, such as another user equipment.

116. The wireless communication system according to claim 114 or 115, wherein the first entity, e.g. a time anchor point, is configured to provide information about one or more measurements performed on the received one or more reference signals and / or is configured to report characteristics of the received one or more reference signals as information to the second entity, and The second entity is configured to use the information to determine its position relative to the first entity; and / or determine the distance between the second entity and the first entity, such as ranging information.

117. A wireless communication system according to any one of claims 112 to 116, wherein the first entity is a user equipment (100) according to any one of claims 1 to 102, and the second entity is a network entity (200) according to any one of claims 103 to 112, or The second entity is a user equipment (100) according to any one of claims 1 to 102, and the first entity is a network entity (200) according to any one of claims 103 to 112.

118. A wireless communication system comprising a plurality of entities, wherein at least one of the plurality of entities is configured to perform one or more comparisons using one or more measurements of one or more user equipment (100) of the wireless communication system, wherein at least one of the plurality of entities is configured to perform unsupervised learning of similar attributes or characteristics, such as one or more channel impulse responses or one or more parameters thereof, wherein at least one of the plurality of entities is configured to employ one or more time anchor points of the wireless communication system for supervised learning, wherein at least one of the plurality of entities is configured to perform supervised learning to map similar attributes or characteristics to corresponding reference information, such as mapping a channel impulse response or a parameter thereof to a speed and / or a direction and / or an acceleration and / or a position and / or a distance, wherein at least one of the plurality of entities is configured to train or collect ML models using a combination of supervised learning, e.g., with output labels, and unsupervised learning, e.g., without output labels, At least one of the plurality of entities is configured to employ labels obtained from one or more temporal anchor points to provide real-world dimensions to a training model, wherein the labels allow transformations, such as scaling and rotation, to transform learned representations into real-world dimensions.

119. The wireless communication system according to claim 118, The plurality of entities include a user equipment (100) according to any one of claims 1 to 102 and a network entity (200) according to any one of claims 103 to 112.

120. A method for a wireless communication system, The method comprises determining, by a user equipment (100) of the wireless communication system and / or receiving, by the user equipment (100), information about the suitability of a machine learning model, and / or The method comprises determining by a user equipment (100) of the wireless communication system and / or receiving by the user equipment (100) information that the user equipment (100) is located in a machine learning assisted area.

121. A method for a wireless communication system, The method comprises determining, based on the time reference information, whether a user equipment (100) of the wireless communication system is to act as a time anchor unit, for example as a time anchor or as a time PRU or as a PRU.

122. A method for a wireless communication system, The method comprises obtaining, by a user equipment (100) of the wireless communication system, information about its location and / or obtaining information about a distance between the user equipment (110) and another entity of the wireless communication system, such as another user equipment (120), such as ranging information, in the following manner: by receiving information from another user equipment acting as a time anchor point unit, such as a time anchor point or a time PRU or a PRU, e.g. via a direct communication link or indirectly through a network, wherein the information received from the time anchor point unit comprises a location of the time anchor point unit and / or one or more measurements performed by the time anchor point unit on a signal sent by the user equipment (100), or wherein the information contains a location reference signal, and By performing one or more measurements on one or more received signals and / or by sending derived information derived from said measurements of said wireless communication system to a network entity (200), such as to a LMF or NWDAF.

123. A method for a wireless communication system, The method comprises supporting an entity of the wireless communication system, such as a network entity (200), by a user equipment (100) of the wireless communication system in the following manner to obtain location information about the user equipment (100) and / or obtain distance information, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment, By sending one or more reference signals to another user equipment acting as a time anchor unit, such as a time anchor or time PRU or PRU, for example via a direct communication link or indirectly through a network, to allow the time anchor to make one or more measurements on the one or more reference signals and / or report one or more measurements to the entity of the wireless communication system.

124. A method for a wireless communication system, The method comprises determining, for example by using a RAT-independent technique and / or by using a RAT-dependent technique and / or by using a time anchor point, or receiving by a user equipment (100) of the wireless communication system, location information about the user equipment (100) and / or distance information between the user equipment (100) and another entity of the wireless communication system, for example another user equipment, such as ranging information, and The user device (100) uses the location information and / or the distance information to assist in generating training data for a machine learning model, for example, for machine learning with relevant labels. For example, the machine learning model is located on the LMF or NWDAF of the wireless communication system.

125. A method for a wireless communication system, The method comprises transmitting, by a user equipment (100) of the wireless communication system, information on one or more properties of RF channel characteristics between the user equipment (100) and another entity of the wireless communication system and / or an indicator on the probability of the existence of a direct path ("line of sight" path) and / or information on characteristics of one or more RF channel propagation paths not associated with the direct path, wherein the other entity of the wireless communication system is a base station or another user equipment of the wireless communication system, The method comprises reporting, by the user equipment (100), information about one or more channel impulse responses to the other entity or another entity of the wireless communication system.

126. A method for a wireless communication system, The method comprises receiving, by a user equipment (100), measurement and / or transmission characteristic information.

127. A method for a wireless communication system, The method comprises receiving, by a user equipment (100) from a network entity (200) of the wireless communication system, one or more PRS configurations for one or more antennas of one or more transmitting devices of the wireless communication system, The method comprises receiving, by the user equipment (100) from a network entity (200) of the wireless communication system, measurement and / or transmission characteristic information comprising a set of one or more parameters, and The method comprises the user equipment (100) using the one or more PRS configurations and using the measurement and / or transmission characteristic information to determine its position and / or distance information, such as ranging information, between the user equipment (100) and another entity of the wireless communication system, such as another user equipment.

128. A computer program for implementing the method according to any one of claims 120 to 127 when the computer program is executed by a computer or a signal processor.

Images