Line-of-sight artificial intelligence / machine learning inferencing using sample-based measurements

Abstract

Systems and methods for line-of-sight (LoS) artificial intelligence (AI) / machine learning (ML) inferencing using sample-based measurements are disclosed herein. An operator entity (e.g., a user equipment (UE), or a base station) of a wireless communication system generates one or more LoS / non-line-of-sight (nLoS) inference(s) by applying one or more sample-based measurements to an AI / ML model. These inference(s) are then reported to a location function (e.g., a location management function (LMF)) of the wireless communication system. LoS / nLoS inferences may be generated using first-in-time samples for a first path (in which case an indication of the (number of) the first-in-time samples is also sent), using a (single) first-in-time sample, using a strongest sample, and / or one using one or more selected sample(s) (in which case corresponding indexes for the one or more selected samples are then also indicated to the LMF). In some embodiments, probabilistic indications may be used as such LoS / nLoS inference(s).

Description

LINE-OF- SIGHT ARTIFICIAL INTELLIGENCE / MACHINE LEARNINGINFERENCING USING SAMPLE-BASED MEASUREMENTSTECHNICAL FIELD

[0001] This application relates generally to wireless communication systems, including wireless communication systems using line-of-sight (LoS) artificial intelligence (AI) / machine learning (ML) inferencing.BACKGROUND

[0002] Wireless mobile communication technology uses various standards and protocols to transmit data between a base station and a wireless communication device. Wireless communication system standards and protocols can include, for example, 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard for Wireless Local Area Networks (WLAN) (commonly known to industry groups as Wi-Fi®).

[0003] As contemplated by the 3 GPP, different wireless communication systems' standards and protocols can use various radio access networks (RANs) for communicating between a base station of the RAN (which may also sometimes be referred to generally as a RAN node, a network node, or simply a node) and a wireless communication device known as a user equipment (UE). 3GPP RANs can include, for example, Global System for Mobile communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE) RAN (GERAN), Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next-Generation Radio Access Network (NG-RAN).

[0004] Each RAN may use one or more radio access technologies (RATs) to perform communication between the base station and the UE. For example, the GERAN implements GSM and / or EDGE RAT, the UTRAN implements Universal Mobile Telecommunication System (UMTS) RAT or other 3GPP RAT, the E-UTRAN implements LTE RAT (sometimes simply referred to as LTE), and NG-RAN implements NR RAT (sometimes referred to herein as 5G RAT, 5G NR RAT, or simply NR). In certain deployments, the E-UTRAN may also implement NR RAT. In certain deployments, NG-RAN may also implement LTE RAT.1P68964WO1 4929-0472-1490\l

[0005] A base station used by a RAN may correspond to that RAN. One example of an E-UTRAN base station is an Evolved Universal Terrestrial Radio Access Network (E- UTRAN) Node B (also commonly denoted as evolved Node B, enhanced Node B, eNodeB, or eNB). One example of an NG-RAN base station is a next generation Node B (also sometimes referred to as a g Node B or gNB).

[0006] A RAN provides its communication services with external entities through its connection to a core network (CN). For example, E-UTRAN may utilize an Evolved Packet Core (EPC) while NG-RAN may utilize a 5G Core Network (5GC).BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0007] To easily identify the discussion of any particular element or act, the most significant digit or digits in a reference number refer to the figure number in which that element is first introduced.

[0008] FIG. 1 illustrates a diagram of a wireless communication system that includes a UE that communicates with a first TRP, a second TRP, and a third TRP.

[0009] FIG. 2 illustrates a diagram showing a path-based measurement mechanism used by a receiver.

[0010] FIG. 3 illustrates a diagram showing Nt' samples taken of a reference signal as received at a receiver.

[0011] FIG. 4 illustrates a diagram showing Nt' samples taken of a reference signal as received at a receiver.

[0012] FIG. 5 illustrates a diagram showing Nt' samples taken of a reference signal as received at a receiver.

[0013] FIG. 6 illustrates a diagram showing Nt' samples taken of a reference signal as received at a receiver.

[0014] FIG. 7 illustrates a diagram showing Nt' samples taken of a reference signal as received as a receiver.

[0015] FIG. 8 illustrates a method of a UE of a wireless communication system, according to embodiments discussed herein.

[0016] FIG. 9 illustrates a method of a base station of a wireless communication system, according to embodiments discussed herein.2P68964WO1 4929-0472-1490\l

[0017] FIG. 10 illustrates a method of a UE of a wireless communication system, according to embodiments discussed herein.

[0018] FIG. 11 illustrates a method of a base station of a wireless communication system, according to embodiments discussed herein.

[0019] FIG. 12 illustrates a method of a UE of a wireless communication system, according to embodiments discussed herein.

[0020] FIG. 13 illustrates a method of a base station of a wireless communication system, according to embodiments discussed herein.

[0021] FIG. 14 illustrates a method of a UE of a wireless communication system, according to embodiments discussed herein.

[0022] FIG. 15 illustrates a method of a base station of a wireless communication system, according to embodiments discussed herein.

[0023] FIG. 16 illustrates a method of a UE of a wireless communication system, according to embodiments discussed herein.

[0024] FIG. 17 illustrates a method of a base station of a wireless communication system, according to embodiments discussed herein.

[0025] FIG. 18 illustrates a method of a UE of a wireless communication system, according to embodiments discussed herein.

[0026] FIG. 19 illustrates a method of a base station of a wireless communication system, according to embodiments discussed herein.

[0027] FIG. 20 illustrates a method of a UE of a wireless communication system, according to embodiments discussed herein.

[0028] FIG. 21 illustrates a method of a base station of a wireless communication system, according to embodiments discussed herein.DETAILED DESCRIPTION

[0029] Various embodiments are described with regard to a UE. However, reference to a UE is merely provided for illustrative purposes. The example embodiments may be utilized with any electronic component that may establish a connection to a network and is configured with the hardware, software, and / or firmware to exchange information and data with the network. Therefore, the UE as described herein is used to represent any appropriate electronic component.3P68964WO1 4929-0472-1490\l

[0030] In some wireless communication systems, a sample-based measurement (e.g., of a reference signal) may be composed of Nt' samples of an estimated channel response in time domain. Corresponding to such cases, the timing information for the Nt' samples may correspond to / be reported with a timing granularity Z, where T= 2kx Tc, where k represents a timing reporting granularity factor, and where Tc represents a basic time unit for the wireless communication system (for example, in an NR-based wireless communication system, Tc may be equal to 0.509 nanoseconds). A reported measurement (e.g., a reported power measurement) may then be understood to correspond to the measurements for the reported Nt' samples.

[0031] Note that in some cases, values for one or more of Nt' and / or k can be signaled. Further, it may be that the timing information for the Nt' samples is defined relative to a reference time.

[0032] Various mechanisms for determining values for Nt' and / or k may be contemplated. Corresponding mechanisms for signaling these values may be contemplated. In some cases, it may be beneficial to introduce a particular mechanism for selecting a value of Nt' samples within the wireless communication system.

[0033] In some wireless communication systems, it may be understood that a “pathbased measurement” refers to a type of measurement that may be used by existing wireless communication systems (e.g., (up to) NR release 18 specifications). It will correspondingly be understood that the measurement reporting discussed in terms of the existing wireless communication system relates to these path-based measurements. Corresponding to such cases, potential enhancements with respect to the number of reported paths may be considered.

[0034] With respect to various wireless communication systems, representative sub-use cases for the use case of machine learning (ML) / artificial intelligence (Al)-based positioning may be considered. These sub-use cases include direct AI / ML positioning, including cases for AI / ML model output of UE location and / or fingerprinting based on a channel observation as the input of an AI / ML model.

[0035] These sub-use cases further include AI / ML assisted positioning including the use of AI / ML model output of new measurement(s) and / or enhancement(s) of existing measurement, such as line-of-sight (LoS) / non-line-of-sight (nLoS) (LoS / nLoS) identifications / indications, a timing of a measurement, an angle of a measurement, and / or a likelihood / probability associated with the measurement.4P68964WO1 4929-0472-1490\l

[0036] Various cases as AI / ML assisted positioning considered according to the subuse cases as described may therefore be considered:• Case 1 : UE-based positioning with a UE-sided AI / ML model, using either direct AI / ML or AI / ML assisted positioning;• Case 2a: UE-assisted / location management function (LMF)-based positioning with a UE-sided model, using AI / ML assisted positioning;• Case 2b: UE-assisted / LMF-based positioning with an LMF-sided model, using direct AI / ML positioning;• Case 3a: NG-RAN-node (e.g., base-station)-assisted positioning with a basestation-sided model, using AI / ML assisted positioning; and• Case 3b: NG-RAN-node (e.g., base-station)-assisted positioning with an LMF- side model, using direct AI / ML positioning.

[0037] Also note that in various wireless communication systems, the use of one-sided AI / ML models where inferencing is performed entirely at a UE or at the network (e.g., as opposed to two-sided AI / ML models that are distributed across the UE and the network) may be prioritized.

[0038] Embodiments herein relate to LoS / nLoS indications for AI / ML assisted positioning sub-cases according to Case 2a and Case 3a as described above. It may be that corresponding to such embodiments, one or more LoS / nLoS indications is generated by an AI / ML model. Note that, as used herein, an LoS / nLoS identification / indication as generated / output by an AI / ML model may also be referred to as an LoS / nLoS inference.

[0039] FIG. 1 illustrates a diagram 100 of a wireless communication system that includes a UE 102 that communicates with a first transmission reception point (TRP) 104, a second TRP 106, and a third TRP 108.

[0040] Discussion herein may relate that a measurement of a reference signal as performed at a UE is on a per-resource basis. In such cases, it should be understood that in the case that there are multiple TRPs performing transmission, each TRP sends a different reference signal resource. Accordingly, a per-resource based transmission within the diagram 100 means that, for example, the UE 102 measures a first reference signal resource sent by the first TRP 104, a second reference signal resource from the second TRP 106, and a third reference signal resource from the third TRP 108.

[0041] Discussion herein may relate that a measurement of a reference signal as performed at a UE is on a per-TRP basis. In such cases, it should be understood that in5P68964WO1 4929-0472-1490\lthe case that there are multiple TRPs performing transmission, each TRP sends a same reference signal resource but that is uniquely differentiated in some way at each TRP (e.g., using an index within the reference signal resource). Thus, a per-TRP based measurement within the diagram 100 means that, for example, the UE 102 measures a reference signal resource as sent by the first TRP 104 according to a first index representing the first TRP 104, measures the (same) reference signal resource as sent by the second TRP 106 according to a second index representing the second TRP 106, and measures the (same) reference signal resource as sent by the third TRP 108 according to a third index representing the third TRP 108.Wireless Communication Systems Using Path-Based Measurements

[0042] Concepts related to path-based-measurements as used in various wireless communication systems are now described.

[0043] In some wireless communication systems using path-based measurements, an nr-DL-PRS-FirstPathRSRP-Result field may be used (e.g., for configuration purposes). This field specifies an NR downlink (DL) positioning reference signal (DL-PRS) reference signal received path power (a DL PRS-RSRPP) of a first detected path in time. The corresponding measured quantity may be mapped according to an existing definition for such mapping.

[0044] In some wireless communication systems using path-based measurements, an nr-los-nlos-Indicator field may be used. This field specifies a target device's best estimate of an LoS or nLoS of one of a UE receive (Rx)-transmit (Tx) time difference measurement, a reference signal receive power (RSRP) measurement, or a reference signal received path power (RSRPP) of a first path measurement of a TRP or resource. Note that in cases where a requested type or granularity in nr-los-nlos-Indicator Request is not possible, the target device may instead provide a different type and granularity for an estimated LOS-NLOS-Indicator.

[0045] In some wireless communication systems using path-based measurements, an nr-AdditionalPathListExt field is used. This field may provide up to eight additional detected path timing values for a TRP or resource, relative to the path timing used for determining an nr-UE-RxTxTimeDiff value. In cases where this field is requested but is not included, it is understood that the UE did not detect any additional path timing values. If this field is present, the field nr-AdditionalPathList may be absent.6P68964WO1 4929-0472-1490\l

[0046] In some wireless communication systems using path-based measurements, a UE may be requested, subject to a UE capability, to report LoS / nLoS indicator(s) via higher layer parameter nr-los-nlos-IndicatorRequest . The UE can report LoS / NLoS indicator(s) via higher layer parameter nr-los-nlos-Indicator that are associated with, for example, DL reference signal time difference (RSTD) measurements, DL positioning reference signal (PRS)-RSRP measurements, DL PRS-RSRPP measurements, and / or UE Rx-Tx time difference measurements. The UE may report LoS / nLoS indicator(s) via a higher layer parameter nr-los-nlos-Indicator associated with each dl-PRS-ID item in a measurement report. For the LoS / nLoS indicator(s) associated with DL RSTD, the UE may report one indicator associated with the dl-PRS-ID indicated by higher layer parameter dl-PRS-Referencelnfo and one indicator associated with the dl-PRS-ID of the DL RSTD measurement. A UE may be provided with LoS / nLoS indicator(s) via a higher layer parameter nr-los-nlos-Indicator , and it may be associated with each DL PRS resource of each configured dl-PRS-ID or may be associated with each configured dl- PRS-ID. In some cases, the values of the higher layer parameter LOS-NLOS-Indicator may be soft values (0, 0.1, ..., 0.9, 1) or hard values (0, 1) with the values corresponding to the likelihood of LoS, with a value of 1 corresponding to LoS and a value of 0 corresponding to nLoS.

[0047] Note that in path-based measurement cases, an LoS / nLoS indicator may be understood to apply to a first-in-time path of a received signal.

[0048] FIG. 2 illustrates a diagram 200 showing a path-based measurement mechanism used by a receiver. It should be preliminarily noted that concepts corresponding to the diagram 200 are applicable with respect to any receiver entity within a wireless communication system (e.g., a UE, a base station, etc.).

[0049] The diagram 200 illustrates that a first-in-time path 202 and a second-in-time path 204 of a reference signal received at the receiver. The receiver identifies the first- in-time path 202 based on the first set of measurements 206 of the reference signal as received at the receiver and the second-in-time path 204 based on a second set of measurements 208 of the reference signal as received at the receiver.

[0050] The receiver identifies the first-in-time path 202 and the second-in-time path 204 independently of any time-based grid (e.g., for sampling) known to the receiver. Accordingly, the illustrated interval 210 between the first-in-time path 202 and the7P68964WO1 4929-0472-1490\lsecond-in-time path 204 is not (necessarily) aligned to any such time-based grid that is used for sampling.

[0051] Note that with respect to path-based measurements, the exact definition of a path (and thus a path's corresponding timing) may be up to a particular implementation at the receiver.Embodiments for Wireless Communication Systems Using Sample-Based Measurements

[0052] It will be understood that when sample-based measurement is used, one path (e.g., the first-in-time path) can correspond to one or more than one of the measurement samples.

[0053] FIG. 3 illustrates a diagram 300 showing a sample-based measurement mechanism used by a receiver. It should be preliminarily noted that concepts corresponding to the diagram 300 are applicable with respect to any receiver entity within a wireless communication system (e.g., a UE, a base station, etc.).

[0054] FIG. 3 illustrates diagram 300 showing Nt' samples (the first sample 302a through the tenth sample 302j ) taken of a reference signal as received at the receiver. As illustrated, the receiver may be capable of identifying groupings of one or more samples that are relatively stronger than other nearby samples (e.g., capable of identifying that the second sample 302b, the third sample 302c and the fourth sample 302d are stronger than the first sample 302a and the fifth sample 302e, and / or that the seventh sample 302g, the eighth sample 302h, and the ninth sample 302i are stronger than the sixth sample 302f and the tenth sample 302j ). The receiver may understand that such groupings of samples correspond to a first set of measurements 304 and a second set of measurements 306 of the received reference signal.

[0055] Note that the samples of the diagram 300 have a finer granularity than the paths of the diagram 200. For this reason, the use of the samples as an input to the AI / ML model may allow an entity using the samples to make LoS / nLoS determinations to be more relatively accurate then cases where path-based measurements are used to make LoS / nLoS determinations (e.g., because there is more / more granular information).

[0056] Embodiments herein relate various methods of generating and reporting LoS / nLoS indications in the context of sample-based measurement and reporting (e.g., as opposed to path-based measurement and reporting).8P68964WO1 4929-0472-1490\l

[0057] Various embodiments discussed herein relate to the use of an explicit mapping of samples to a first-in-time path and for which an LoS / nLoS indication is made. In some such cases, an indication of the mapping is also reported.

[0058] Various embodiments discussed herein relate to the use of an LoS / nLoS indicator for a first-in-time sample (e.g., on a per-TRP or per-resource basis).

[0059] Various embodiments discussed herein relate to the use of an LoS / nLoS indicator for a particular sample or samples (e.g., on a per-TRP or per-resource basis). In some such cases, it may be that sample index(es) are also reported.

[0060] Various embodiments discussed herein may relate to various measurement types (including, for example, time of arrival (ToA) measurement types).

[0061] It will be understood that, with respect to AI / ML model input, the use of a sample-based input may invoke differing performance and feedback overhead tradeoffs as compared to cases of path-based input to an AI / ML model.

[0062] Embodiments described herein relate to AI / ML models for assisted positioning sub cases, including mechanisms for using LoS / nLoS information as the output of the AI / ML model in such cases.

[0063] Various embodiments for AI / ML-based assisted positioning using either a UE- sided AI / ML model or a base-station-sided AI / ML model where sample-based measurement input is provided to the AI / ML model and where one or more LoS / nLoS indicator(s) generated by the AI / ML model are reported are contemplated.Corresponding to such cases, a report may occur via a higher layer parameter (e.g., an nr-los-nlos-indicator-ai parameter). Further, such an LoS / nLoS indicator may be associated with (e.g., each of one or more of) a DL RSTD measurement, a DL PRS- RSRP measurement, a DL-PRS-RSRPP measurement, a UE Rx-Tx time difference measurement, and / or a ToA measurement. Various scenarios for such embodiments are now discussed.

[0064] In first scenarios for the use of AI / ML models using sample-based input to generate and report one or more LoS / nLoS indicators, an explicit mapping of measurement samples belonging to a first-in-time path may be used. This explicit mapping may be signaled to another entity of the wireless communication system (e.g., to an LMF) for location determination purposes.9P68964WO1 4929-0472-1490\l

[0065] Within these first scenarios, the LoS / nLoS indicator may be a hard value (e.g., 0, 1) that indicates an inferenced LoS / nLoS determination for the samples of the first-in- time path in a binary fashion (e.g., where a value of 1 corresponds to LoS and a value of 0 corresponds to nLoS). In other cases within these first scenarios, the LoS / nLoS indicator may be a soft / probabilistic value (e.g., 0, 0.1, ..., 0.9, 1) that corresponds to a likelihood / probability of LoS or of nLoS of the samples of the first-in-time path (e.g., where a value of 1 corresponds to LoS and a value of 0 corresponds to nLoS, or vice- versa). It may be that the use of such a probabilistic value for an LoS / nLoS indicator may be according to a specification for the wireless communication system (and thus no separate signaling other than the value is necessary).

[0066] In some cases, this signaling / reporting further indicates an index Nt_l ’ that corresponds to a number of first-in-time measurement samples that are determined to belong to the first-in-time path of a reference signal. It will be understood that Nt_l ’ is a sub-set of the Nt’ (the total set of samples of the sample-based measurement). Thus, per an indication or mapping of Nt_l it is understood that all samples in Nt' within the range [0, Nt_l ’] are samples of the first-in-time path.

[0067] Note that in such cases, each sample has a granularity of 2fex Tc.

[0068] In these first scenarios, for cases of UE-assisted / LMF -based positioning using a UE-sided AI / ML model for AI / ML assisted positioning, the LoS / nLoS indicator and the mapping may be reported from UE to LMF. Further, in cases of NG-RAN-node (e.g., base-station)-assisted positioning using a base-station-sided AI / ML model for AI / ML assisted positioning, the LoS / nLoS indicator and the mapping may be reported from the base station to the LMF.

[0069] FIG. 4 illustrates a diagram 400 showing Nt' samples (the first sample 402a through the tenth sample 402j) taken of a reference signal as received at a receiver (e.g., a UE or a base station of the wireless communication system that receives the reference signal). Note that in some cases this receiver entity is also an operator entity that operates the AI / ML model for generating an LoS / nLoS indicator and related information. However, in cases where the operator entity is not the receiver entity, these samples are then provided to the operator entity (e.g., as in a case where the UE is the receiver entity, but the base station is the operator entity).

[0070] In some cases, based on its analysis of the samples, the operator entity identifies that a first set of measurements 404 of the reference signal corresponds to a first-in-time10P68964WO1 4929-0472-1490\lpath of the reference signal and that a second set of measurements 406 corresponds to a second-in-time path of the reference signal. The operator entity further identifies that the first-five-in-time measurement samples 408 of the reference signal (the first sample 402a, the second sample 402b, the third sample 402c, the fourth sample 402d, and the fifth sample 402e) correspond to the determined first-in-time path.

[0071] The first-five-in-time measurement samples 408 are then provided to the AI / ML model of the operator entity and an LoS / nLoS indicator corresponding to the first-five- in-time measurement samples 408 is generated.

[0072] In alternative cases, the AI / ML model at the operator entity is configured to itself identify samples that are in the first-in-time path. In such cases, the entire set of Nt' samples (the first sample 402a through the tenth sample 402j) is provided to the AI / ML model. The AI / ML model then provides an indication of the value of Nt' l that provides a mapping to the first-five-in-time measurement samples 408 and the LoS / nLoS indicator corresponding to the first-five-in-time measurement samples 408.

[0073] In the case of a UE-sided AI / ML model (UE as operator entity), the UE provides the generated LoS / nLoS indicator for the first-in-time path and a value of Nt_l ’ = 4 to the RAN (e.g., a base station). The RAN then passes this information to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0074] In the case of a base-station-sided AI / ML model (base station as operator entity), the base station provides the generated LoS / nLoS indicator for the first-in-time path and a value of Nt_l ’ = 4 to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0075] Note that the signaling of the value of Nt_l ’ to the LMF identifies, to the LMF, which first-in-time samples of the Nt' samples were used to generate the LoS / nLoS indicator. For example, the value of Nt_l ’ = 4 as discussed here in relation to FIG. 4 communicates to the LMF that the first-five-in-time measurement samples 408 were used to generate the LoS / nLoS indicator (assuming that the Nt' samples are indexed starting at value 0).

[0076] Note that the reference signal measurements as discussed here for these first scenarios and in cases where the UE is the receiving entity may be performed on a per- TRP basis or on a per-resource basis, as is explained elsewhere herein.

[0077] In second scenarios for the use of AI / ML models using sample-based input to generate and report one or more LoS / nLoS indicators, an LoS / nLoS indicator generated11P68964WO1 4929-0472-1490\lby an operator entity (e.g., the base station, the UE) specifies an AI / ML model -generated estimate of the LoS or nLoS of a single sample.

[0078] In some cases according to the second scenarios, the single sample for which the LoS / nLoS indicator is indicated may be a first-in-time sample of the total number of samples Nt'. Accordingly, once the first-in-time sample is identified by a receiver, it is applied to an AI / ML model at the operator entity for generating the LoS / nLoS indicator.

[0079] In some cases according to the second scenarios, the single sample for which the LoS / nLoS indicator is indicated may be a strongest sample of the total number of samples Nt'. Accordingly, once the strongest sample is identified by a receiver, it is applied to an AI / ML model at the operator entity for generating the LoS / nLoS indicator.

[0080] Within the second scenarios, the LoS / nLoS indicator may be a hard value (e.g., 0, 1) that indicates an inferenced LoS / nLoS determination for the sample in a binary fashion (e.g., where a value of 1 corresponds to LoS and a value of 0 corresponds to nLoS). In other cases within the second scenarios, the LoS / nLoS indicator may be a soft / probabilistic value (e.g., 0, 0.1, ..., 0.9, 1) that corresponds to a likelihood / probability of LoS or of nLoS of the sample (e.g., where a value of 1 corresponds to LoS and a value of 0 corresponds to nLoS, or vice-versa). It may be that the use of such a probabilistic value for an LoS / nLoS indicator may be according to a specification for the wireless communication system (and thus no separate signaling other than the value is necessary).

[0081] In the third scenarios, for cases of UE-assisted / LMF -based positioning using a UE-sided AI / ML model for AI / ML assisted positioning, the first-in-time or strongest (as the case may be) sample may be identified by the UE, and the corresponding LoS / nLoS indicator may be provided from the UE to LMF. Further, in cases of NG-RAN-node (e.g., base-station)-assisted positioning using a base-station-sided AI / ML model for AI / ML assisted positioning, the first-in-time or strongest (as the case may be) sample may be identified by the base station, and the corresponding LoS / nLoS indicator may be provided from the base station to the LMF.

[0082] FIG. 5 illustrates a diagram 500 showing Nt' samples (the first sample 502a through the tenth sample 502j ) taken of a reference signal as received at a receiver (e.g., a UE or a base station of the wireless communication system that receives the reference signal). Note that in some cases this receiver entity is also an operator entity that operates the AI / ML model for generating an LoS / nLoS indicator and related information.12P68964WO1 4929-0472-1490\lHowever, in cases where the operator entity is not the receiver entity, these samples are then provided to the operator entity (e.g., as in a case where the UE is the receiver entity, but the base station is the operator entity).

[0083] In some cases of the second scenarios, based on its analysis of the samples, the operator entity identifies a first sample 502a as a first-in-time sample 504. The first sample 502a is then accordingly applied with an AI / ML model, which generates an LoS / nLoS indicator corresponding to the first sample 502a.

[0084] In some cases of the second scenarios, based on its analysis of the samples, the operator entity identifies a third sample 502c as a strongest sample 506. The third sample 502c is then accordingly applied with an AI / ML model, which generates an LoS / nLoS indicator corresponding to the third sample 502c.

[0085] In the case of a UE-sided AI / ML model (UE as operator entity), the UE provides the generated LoS / nLoS indicator for the first-in-time sample 504 or the strongest sample 506 (as the case may be) to the RAN (e.g., a base station). The RAN then passes this information to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0086] In the case of a base-station-sided AI / ML model (base station as operator entity), the base station provides the generated LoS / nLoS indicator for the first-in-time sample 504 or the strongest sample 506 (as the case may be) to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0087] Note that the reference signal measurements as discussed here for these second scenarios and in cases where the UE is the receiver entity may be performed on a per- TRP basis or on a per-resource basis, as is explained elsewhere herein.

[0088] In the third scenarios for the use of AI / ML models using sample-based input to report one or more LoS / nLoS indicators, each of one or more LoS / nLoS indicator(s) generated by a device (e.g., the base station, the UE) specifies an AI / ML modelgenerated estimate of the LoS or nLoS for each of one or more samples, and index(es) corresponding to these selected sample(s) are also signaled.

[0089] Within the third scenarios, the LoS / nLoS indicator for each selected sample may be a hard value (e.g., 0, 1) that indicates an inferenced LoS / nLoS determination in a binary fashion for each selected sample (e.g., where a value of 1 corresponds to LoS and a value of 0 corresponds to nLoS). In other cases within the first scenarios, the LoS / nLoS indicator for each selected sample may be a soft / probabilistic value (e.g., 0, 0.1, ..., 0.9,13P68964WO1 4929-0472-1490\l1) that corresponds to a likelihood / probability of LoS or of nLoS of the sample (e.g., where a value of 1 corresponds to LoS and a value of 0 corresponds to nLoS, or vice- versa). It may be that the use of such a probabilistic value for an LoS / nLoS indicator may be according to a specification for the wireless communication system (and thus no separate signaling other than the value is necessary).

[0090] In the third scenarios, for cases of UE-assisted / LMF -based positioning using a UE-sided AI / ML model for AI / ML assisted positioning, the selected sample(s) may be identified by the UE, and the index(es) of the selected samples may be provided from the UE to LMF along with any corresponding LoS / nLoS indicator(s). Further, in cases of NG-RAN-node (e.g., base-station)-assisted positioning using a base-station-sided AI / ML model for AI / ML assisted positioning, the selected sample(s) may be identified by the base station, and the index(es) of the selected samples may be provided from the base station to the LMF.

[0091] FIG. 6 illustrates a diagram 600 showing Nt' samples (the first sample 602a through the tenth sample 602j) taken of a reference signal as received at a receiver (e.g., a UE or a base station of the wireless communication system that receives the reference signal). Note that in some cases this receiver entity is also an operator entity that operates the AI / ML model for generating an LoS / nLoS indicator and related information. However, in cases where the operator entity is not the receiver entity, these samples are then provided to the operator entity (e.g., as in a case where the UE is the receiver entity, but the base station is the operator entity).

[0092] In some corresponding cases of the second scenarios, based on its analysis of the samples, the operator entity identifies a third sample 602c as a selected sample 604. The third sample 602c is then accordingly applied at an AI / ML model, which generates an LoS / nLoS indicator corresponding to the third sample 602c.

[0093] In alternative cases, the AI / ML model at the operator entity is configured to itself identify a sample for use. In such cases, the entire set of Nt' samples (the first sample 602a through the tenth sample 602j) is provided to the AI / ML model. The AI / ML model then provides an identification (e.g., a sample index) of the third sample 602c as the selected sample 604 and a LoS / nLoS indicator corresponding to the third sample 602c.

[0094] In the case of a UE-sided AI / ML model (UE as operator entity), the UE provides the generated LoS / nLoS indicator for the selected sample 604 and a corresponding index14P68964WO1 4929-0472-1490\l(the index of the third sample 602c used as the selected sample 604) to the RAN (e.g., a base station). The RAN then passes this information to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0095] In the case of a base-station-sided AI / ML model (base station as operator entity), the base station provides the generated LoS / nLoS indicator for the selected sample 604 and a corresponding index (the index of the third sample 602c used as the selected sample 604) to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0096] FIG. 7 illustrates a diagram 700 showing Nt' samples (the first sample 702a through the tenth sample 702j) taken of a reference signal as received as a receiver (e.g., a UE or a base station of the wireless communication system that receives the reference signal). Note that in some cases, this receiver entity is also an operator entity that operates the AI / ML model for generating an LoS / nLoS indicator and related information. However, in cases where the operator entity is not the receiver entity, these samples are then provided to the operator entity (e.g., as in a case where the UE is the receiver entity, but the base station is the operator entity).

[0097] In some corresponding cases of the third scenarios, based on its analysis of the samples, the operator entity identifies each of the second sample 702b, the third sample 702c, and the fourth sample 702d as selected samples 704. The second sample 702b is then applied at an AI / ML model, which generates a first LoS / nLoS indicator corresponding to the second sample 702b. The third sample 702c is also applied at the AI / ML model, which generates a second LoS / nLoS indicator corresponding to the third sample 702c. The fourth sample 702d is also applied at the AI / ML model, which generates a second LoS / nLoS indicator corresponding to the fourth sample 702d.

[0098] In alternative cases, the AI / ML model at the operator entity is configured to itself identify multiple samples for use. In such cases, the entire set of Nt' samples (the first sample 702a through the tenth sample 702j) is provided to the AI / ML model. The AI / ML model then provides identifications (e.g., sample indexes) each of the second sample 702b, the third sample 702c, and the fourth sample 702d as the selected samples 704 and LoS / nLoS indicators corresponding to each of the second sample 702b, the third sample 702c, and the fourth sample 702d.

[0099] In the case of a UE-sided AI / ML model for generating LoS / nLoS indicators (UE as operator entity), the UE provides the generated LoS / nLoS indicators for the selected15P68964WO1 4929-0472-1490\lsamples 704 and corresponding indexes (the indexes of the second sample 702b, the third sample 702c, and the fourth sample 702d used as the selected samples 704) to the RAN (e.g., a base station). The RAN then passes this information to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0100] In the case of a base-station-sided AI / ML model for generating LoS / nLoS indicators (base station as operator entity), the base station provides the generated LoS / nLoS indicators for the selected samples 704 and corresponding indexes (the indexes of the second sample 702b, the third sample 702c, and the fourth sample 702d used as the selected samples 704) to the LMF in the CN. Note that the Nt' samples may also be passed to the LMF in this reporting.

[0101] Note that the reference signal measurements as discussed here for the third scenarios and in the cases where the UE is the measurement entity may be performed on a per-TRP basis or on a per-resource basis, as is explained elsewhere herein.Embodiments for Measurement Types

[0102] The various scenarios described herein with respect to LoS / nLoS indicators use may be applied with respect to the taking of various different types of measurements. Available measurement types useable with such scenarios include, but are not limited to, DL RSTD measurements, DL PRS-RSRP measurements, DL-PRS-RSRPP measurements, UE Rx-Tx time difference measurements, and / or To A measurements.

[0103] For use cases for LoS / nLoS indicator use as described herein, it may be that a particular type of measurement to use to generate the LoS / nLoS indicator is communicated to the receiver entity and / or the operator entity via a higher layer parameter (e.g., an nr-los-nlos-indicator-ai parameter). It will thus be understood that such a higher layer parameter may be used to indicate any of DL RSTD measurement, DL PRS-RSRP measurement, DL-PRS-RSRPP measurement, ToA measurement (including DL ToA and / or uplink (UL) ToA measurement), and / or UE Rx-Tx time difference measurement.

[0104] In cases corresponding to the use of DL ToA for measuring a reference signal, it may be understood that a DL ToA is defined / understood as a received timing from a transmission point z, defined as TsubframeRxt, which is the time when the UE receives a first-in-time sample of one subframe from TRP i.16P68964WO1 4929-0472-1490\lAdditional Discussion of Example Embodiments

[0105] FIG. 8 illustrates a method 800 of a UE of a wireless communication system, according to embodiments discussed herein. The method 800 includes sampling 802 a reference signal received from a network using Nt' samples. The method 800 further includes determining 804 that first-in-time Nt'_l samples of the Nt' samples are of a first-in-time path of the reference signal. The method 800 further includes applying 806 the first-in-time Nt'_l samples at an AI / ML model to generate an LoS / nLoS inference for the first-in-time path. The method 800 further includes sending 808, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in- time path and Nt' l.

[0106] In some embodiments of the method 800, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an LoS path.

[0107] In some embodiments of the method 800, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an LoS path.

[0108] In some embodiments of the method 800, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an nLoS path.

[0109] In some embodiments of the method 800, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an nLoS path.

[0110] In some embodiments of the method 800, the reference signal indicates a TRP of the network by which it is transmitted.[OHl] FIG. 9 illustrates a method 900 of a base station of a wireless communication system, according to embodiments discussed herein. The method 900 includes sampling 902 a reference signal received from a UE at a TRP of the base station using Nt' samples. The method 900 further includes determining 904 that first-in-time Nt'_l samples of the Nt' samples are of a first-in-time path of the reference signal. The method 900 further includes applying 906 the first-in-time Nt'_l samples at an AI / ML model to generate an LoS / nLoS inference for the first-in-time path. The method 900 further includes sending 908, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time path and Nt' l .

[0112] In some embodiments of the method 900, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an LoS path.17P68964WO1 4929-0472-1490\l

[0113] In some embodiments of the method 900, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an LoS path.

[0114] In some embodiments of the method 900, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an nLoS path.

[0115] In some embodiments of the method 900, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an nLoS path.

[0116] In some embodiments of the method 900, the reference signal indicates the TRP.

[0117] FIG. 10 illustrates a method 1000 of a UE of a wireless communication system, according to embodiments discussed herein. The method 1000 includes sampling 1002 a reference signal received from a network using Nt' samples. The method 1000 further includes applying 1004 a first-in-time sample of the Nt' samples at an AI / ML model to generate an LoS / nLoS inference for the first-in-time sample. The method 1000 further includes sending 1006, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time sample.

[0118] In some embodiments of the method 1000, the LoS / nLoS inference for the first- in-time sample comprises an indication that the first-in-time sample is of an LoS path.

[0119] In some embodiments of the method 1000, the LoS / nLoS inference for the first- in-time sample comprises a probability that the first-in-time sample is of an LoS path.

[0120] In some embodiments of the method 1000, the LoS / nLoS inference for the first- in-time sample comprises an indication that the first-in-time sample is of an nLoS path.

[0121] In some embodiments of the method 1000, the LoS / nLoS inference for the first- in-time sample comprises a probability that the first-in-time sample is of an nLoS path.

[0122] In some embodiments of the method 1000, the reference signal indicates a TRP of the network by which it is transmitted.

[0123] FIG. 11 illustrates a method 1100 of a base station of a wireless communication system, according to embodiments discussed herein. The method 1100 includes sampling 1102 a reference signal received from a UE at a TRP of the base station using Nt' samples. The method 1100 further includes applying 1104 a first-in-time sample of the Nt' samples at an AI / ML model to generate an LoS / nLoS inference for the first-in-time sample. The method 1100 further includes sending 1106, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time sample.18P68964WO1 4929-0472-1490\l

[0124] In some embodiments of the method 1100, the LoS / nLoS inference for the first- in-time sample comprises an indication that the first-in-time sample is of an LoS path.

[0125] In some embodiments of the method 1100, the LoS / nLoS inference for the first- in-time sample comprises a probability that the first-in-time sample is of an LoS path.

[0126] In some embodiments of the method 1100, the LoS / nLoS inference for the first- in-time sample comprises an indication that the first-in-time sample is of an nLoS path.

[0127] In some embodiments of the method 1100, the LoS / nLoS inference for the first- in-time sample comprises a probability that the first-in-time sample is of an nLoS path.

[0128] In some embodiments of the method 1100, the reference signal indicates the TRP.

[0129] FIG. 12 illustrates a method 1200 of a UE of a wireless communication system, according to embodiments discussed herein. The method 1200 includes sampling 1202 a reference signal received from a network using Nt' samples. The method 1200 further includes identifying 1204 a strongest sample of the Nt' samples. The method 1200 further includes applying 1206 the strongest sample of the Nt' samples at an AI / ML model to generate an LoS / nLoS inference for the strongest sample. The method 1200 further includes sending 1208, to a location function of the wireless communication system, the LoS / nLoS inference for the strongest sample.

[0130] In some embodiments of the method 1200, the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an LoS path.

[0131] In some embodiments of the method 1200, the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an LoS path.

[0132] In some embodiments of the method 1200, the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an nLoS path.

[0133] In some embodiments of the method 1200, the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an nLoS path.

[0134] In some embodiments of the method 1200, the reference signal indicates a transmission reception point (TRP) of the network by which it is transmitted.

[0135] FIG. 13 illustrates a method 1300 of a base station of a wireless communication system, according to embodiments discussed herein. The method 1300 includes sampling 1302 a reference signal received from a UE at a TRP of the base station using Nt' samples. The method 1300 further includes identifying 1304 a strongest sample of the19P68964WO1 4929-0472-1490\lNt' samples. The method 1300 further includes applying 1306 the strongest sample of the Nt' samples at an AI / ML model to generate an LoS / nLoS inference for the strongest sample. The method 1300 further includes sending 1308, to a location function of the wireless communication system, the LoS / nLoS inference for the strongest sample.

[0136] In some embodiments of the method 1300, the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an LoS path.

[0137] In some embodiments of the method 1300, the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an LoS path.

[0138] In some embodiments of the method 1300, the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an nLoS path.

[0139] In some embodiments of the method 1300, the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an nLoS path.

[0140] In some embodiments of the method 1300, the reference signal indicates the TRP.

[0141] FIG. 14 illustrates a method 1400 of a UE of a wireless communication system, according to embodiments discussed herein. The method 1400 includes sampling 1402 a reference signal received from a network using Nt' samples. The method 1400 further includes applying 1404 each of one or more selected samples of the Nt' samples at an AI / ML model to generate one or more LoS / nLoS inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples. The method 1400 further includes sending 1406 to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

[0142] In some embodiments, the method 1400 further includes selecting the one or more selected samples based on a determination that the one or more selected samples are of a first path of the reference signal.

[0143] In some embodiments of the method 1400, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.20P68964WO1 4929-0472-1490\l

[0144] In some embodiments of the method 1400, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.

[0145] In some embodiments of the method 1400, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.

[0146] In some embodiments of the method 1400, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

[0147] In some embodiments of the method 1400, the reference signal indicates a TRP of the network by which it is transmitted.

[0148] FIG. 15 illustrates a method 1500 of a base station of a wireless communication system, according to embodiments discussed herein. The method 1500 includes sampling 1502 a reference signal received from a UE at a TRP of the base station using Nt' samples. The method 1500 further includes applying 1504 each of one or more selected samples of the Nt' samples at an AI / ML model to generate one or more LoS / nLoS inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples. The method 1500 further includes sending 1506, to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

[0149] In some embodiments, the method 1500 further includes selecting the one or more selected samples based on a determination that the one or more selected samples are of a first path of the reference signal.

[0150] In some embodiments of the method 1500, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.

[0151] In some embodiments of the method 1500, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.21P68964WO1 4929-0472-1490\l

[0152] In some embodiments of the method 1500, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.

[0153] In some embodiments of the method 1500, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

[0154] In some embodiments of the method 1500, the reference signal indicates the TRP.

[0155] FIG. 16 illustrates a method 1600 of a UE of a wireless communication system, according to embodiments discussed herein. The method 1600 includes sampling 1602 a reference signal received from a network using Nt' samples. The method 1600 further includes applying 1604 the Nt' samples at an AI / ML model to determine that first-in-time Nt'_l samples of the Nt' samples are of a first-in-time path of the reference signal and to generate a LoS / nLoS inference for the first-in-time path. The method 1600 further includes sending 1606, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time path and Nt' l.

[0156] In some embodiments of the method 1600, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an LoS path.

[0157] In some embodiments of the method 1600, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an LoS path.

[0158] In some embodiments of the method 1600, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an nLoS path.

[0159] In some embodiments of the method 1600, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an nLoS path.

[0160] In some embodiments of the method 1600, the reference signal indicates a TRP of the network by which it is transmitted.

[0161] FIG. 17 illustrates a method 1700 of a base station of a wireless communication system, according to embodiments discussed herein. The method 1700 includes sampling 1702 a reference signal received from a UE at a TRP of the base station using Nt' samples. The method 1700 further includes applying 1704 the Nt' samples at an AI / ML model to determine that first-in-time Nt'_l samples of the Nt' samples are of a first-in- time path of the reference signal and to generate a LoS / nLoS inference for the first-in-22P68964WO1 4929-0472-1490\ltime path. The method 1700 further includes sending 1706, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time path and Nt' 1.

[0162] In some embodiments of the method 1700, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an LoS path.

[0163] In some embodiments of the method 1700, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an LoS path.

[0164] In some embodiments of the method 1700, the LoS / nLoS inference for the first- in-time path comprises an indication that the first-in-time path is an nLoS path.

[0165] In some embodiments of the method 1700, the LoS / nLoS inference for the first- in-time path comprises a probability that the first-in-time path is an nLoS path.

[0166] In some embodiments of the method 1700, the reference signal indicates the TRP.

[0167] FIG. 18 illustrates a method 1800 of a UE, according to embodiments discussed herein. The method 1800 includes sampling 1802 a reference signal received from a network using Nt' samples. The method 1800 further includes applying 1804 the Nt' samples at an AI / ML model to identify one or more selected samples of the Nt' samples and to generate one or more LoS / nLoS inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples. The method 1800 further includes sending 1806, method 1800 sends, to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

[0168] In some embodiments of the method 1800, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.

[0169] In some embodiments of the method 1800, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.

[0170] In some embodiments of the method 1800, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.23P68964WO1 4929-0472-1490\l

[0171] In some embodiments of the method 1800, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

[0172] In some embodiments of the method 1800, the reference signal indicates a TRP of the network by which it is transmitted.

[0173] FIG. 19 illustrates a method 1900 of a base station of a wireless communication system, according to embodiments discussed herein. The method 1900 includes sampling 1902 a reference signal received from a UE at a TRP of the base station using Nt' samples. The method 1900 further includes applying 1904 the Nt' samples at an AI / ML model to identify one or more selected samples of the Nt' samples and to generate one or more LoS / nLoS inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples. The method 1900 further includes sending 1906, to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

[0174] In some embodiments of the method 1900, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.

[0175] In some embodiments of the method 1900, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.

[0176] In some embodiments of the method 1900, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

[0177] In some embodiments of the method 1900, a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.

[0178] In some embodiments of the method 1900, the reference signal indicates the TRP.

[0179] FIG. 20 illustrates an example architecture of a wireless communication system 2000, according to embodiments disclosed herein. The following description is provided for an example wireless communication system 2000 that operates in conjunction with24P68964WO1 4929-0472-1490\lthe LTE system standards and / or 5G or NR system standards as provided by 3 GPP technical specifications.

[0180] As shown by FIG. 20, the wireless communication system 2000 includes UE 2002 and UE 2004 (although any number of UEs may be used). In this example, the UE 2002 and the UE 2004 are illustrated as smartphones (e.g., handheld touchscreen mobile computing devices connectable to one or more cellular networks), but may also comprise any mobile or non-mobile computing device configured for wireless communication.

[0181] The UE 2002 and UE 2004 may be configured to communicatively couple with a RAN 2006. In embodiments, the RAN 2006 may be NG-RAN, E-UTRAN, etc. The UE 2002 and UE 2004 utilize connections (or channels) (shown as connection 2008 and connection 2010, respectively) with the RAN 2006, each of which comprises a physical communications interface. The RAN 2006 can include one or more base stations (such as base station 2012 and base station 2014) that enable the connection 2008 and connection 2010.

[0182] In this example, the connection 2008 and connection 2010 are air interfaces to enable such communicative coupling, and may be consistent with RAT(s) used by the RAN 2006, such as, for example, an LTE and / or NR.

[0183] In some embodiments, the UE 2002 and UE 2004 may also directly exchange communication data via a sidelink interface 2016. The UE 2004 is shown to be configured to access an access point (shown as AP 2018) via connection 2020. By way of example, the connection 2020 can comprise a local wireless connection, such as a connection consistent with any IEEE 802.11 protocol, wherein the AP 2018 may comprise a Wi-Fi® router. In this example, the AP 2018 may be connected to another network (for example, the Internet) without going through a CN 2024.

[0184] In embodiments, the UE 2002 and UE 2004 can be configured to communicate using orthogonal frequency division multiplexing (OFDM) communication signals with each other or with the base station 2012 and / or the base station 2014 over a multicarrier communication channel in accordance with various communication techniques, such as, but not limited to, an orthogonal frequency division multiple access (OFDMA) communication technique (e.g., for downlink communications) or a single carrier frequency division multiple access (SC-FDMA) communication technique (e.g., for uplink and ProSe or sidelink communications), although the scope of the embodiments is25P68964WO1 4929-0472-1490\lnot limited in this respect. The OFDM signals can comprise a plurality of orthogonal subcarriers.

[0185] In some embodiments, all or parts of the base station 2012 or base station 2014 may be implemented as one or more software entities running on server computers as part of a virtual network. In addition, or in other embodiments, the base station 2012 or base station 2014 may be configured to communicate with one another via interface 2022. In embodiments where the wireless communication system 2000 is an LTE system (e.g., when the CN 2024 is an EPC), the interface 2022 may be an X2 interface. The X2 interface may be defined between two or more base stations (e.g., two or more eNBs and the like) that connect to an EPC, and / or between two eNBs connecting to the EPC. In embodiments where the wireless communication system 2000 is an NR system (e.g., when CN 2024 is a 5GC), the interface 2022 may be an Xn interface. The Xn interface is defined between two or more base stations (e.g., two or more gNBs and the like) that connect to 5GC, between a base station 2012 (e.g., a gNB) connecting to 5GC and an eNB, and / or between two eNBs connecting to 5GC (e.g., CN 2024).

[0186] The RAN 2006 is shown to be communicatively coupled to the CN 2024. The CN 2024 may comprise one or more network elements 2026, which are configured to offer various data and telecommunications services to customers / subscribers (e.g., users of UE 2002 and UE 2004) who are connected to the CN 2024 via the RAN 2006. The components of the CN 2024 may be implemented in one physical device or separate physical devices including components to read and execute instructions from a machine- readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium).

[0187] In embodiments, the CN 2024 may be an EPC, and the RAN 2006 may be connected with the CN 2024 via an SI interface 2028. In embodiments, the SI interface 2028 may be split into two parts, an SI user plane (Sl-U) interface, which carries traffic data between the base station 2012 or base station 2014 and a serving gateway (S-GW), and the SI -MME interface, which is a signaling interface between the base station 2012 or base station 2014 and mobility management entities (MMEs).

[0188] In embodiments, the CN 2024 may be a 5GC, and the RAN 2006 may be connected with the CN 2024 via an NG interface 2028. In embodiments, the NG interface 2028 may be split into two parts, an NG user plane (NG-U) interface, which carries traffic data between the base station 2012 or base station 2014 and a user plane26P68964WO1 4929-0472-1490\lfunction (UPF), and the SI control plane (NG-C) interface, which is a signaling interface between the base station 2012 or base station 2014 and access and mobility management functions (AMFs).

[0189] Generally, an application server 2030 may be an element offering applications that use internet protocol (IP) bearer resources with the CN 2024 (e.g., packet switched data services). The application server 2030 can also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc.) for the UE 2002 and UE 2004 via the CN 2024. The application server 2030 may communicate with the CN 2024 through an IP communications interface 2032.

[0190] FIG. 21 illustrates a system 2100 for performing signaling 2134 between a wireless device 2102 and a network device 2118, according to embodiments disclosed herein. The system 2100 may be a portion of a wireless communications system as herein described. The wireless device 2102 may be, for example, a UE of a wireless communication system. The network device 2118 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.

[0191] The wireless device 2102 may include one or more processor(s) 2104. The processor(s) 2104 may execute instructions such that various operations of the wireless device 2102 are performed, as described herein. The processor(s) 2104 may include one or more baseband processors implemented using, for example, a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a controller, a field programmable gate array (FPGA) device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0192] The wireless device 2102 may include a memory 2106. The memory 2106 may be a non-transitory computer-readable storage medium that stores instructions 2108 (which may include, for example, the instructions being executed by the processor(s) 2104). The instructions 2108 may also be referred to as program code or a computer program. The memory 2106 may also store data used by, and results computed by, the processor(s) 2104.

[0193] The wireless device 2102 may include one or more transceiver(s) 2110 that may include radio frequency (RF) transmitter circuitry and / or receiver circuitry that use the antenna(s) 2112 of the wireless device 2102 to facilitate signaling (e.g., the signaling27P68964WO1 4929-0472-1490\l2134) to and / or from the wireless device 2102 with other devices (e.g., the network device 2118) according to corresponding RATs.

[0194] The wireless device 2102 may include one or more antenna(s) 2112 (e.g., one, two, four, or more). For embodiments with multiple antenna(s) 2112, the wireless device 2102 may leverage the spatial diversity of such multiple antenna(s) 2112 to send and / or receive multiple different data streams on the same time and frequency resources. This behavior may be referred to as, for example, multiple input multiple output (MIMO) behavior (referring to the multiple antennas used at each of a transmitting device and a receiving device that enable this aspect). MIMO transmissions by the wireless device 2102 may be accomplished according to precoding (or digital beamforming) that is applied at the wireless device 2102 that multiplexes the data streams across the antenna(s) 2112 according to known or assumed channel characteristics such that each data stream is received with an appropriate signal strength relative to other streams and at a desired location in the spatial domain (e.g., the location of a receiver associated with that data stream). Certain embodiments may use single user MIMO (SU-MIMO) methods (where the data streams are all directed to a single receiver) and / or multi user MIMO (MU-MIMO) methods (where individual data streams may be directed to individual (different) receivers in different locations in the spatial domain).

[0195] In certain embodiments having multiple antennas, the wireless device 2102 may implement analog beamforming techniques, whereby phases of the signals sent by the antenna(s) 2112 are relatively adjusted such that the (joint) transmission of the antenna(s) 2112 can be directed (this is sometimes referred to as beam steering).

[0196] The wireless device 2102 may include one or more interface(s) 2114. The interface(s) 2114 may be used to provide input to or output from the wireless device 2102. For example, a wireless device 2102 that is a UE may include interface(s) 2114 such as microphones, speakers, a touchscreen, buttons, and the like in order to allow for input and / or output to the UE by a user of the UE. Other interfaces of such a UE may be made up of transmitters, receivers, and other circuitry (e.g., other than the transceiver(s) 2110 / antenna(s) 2112 already described) that allow for communication between the UE and other devices and may operate according to known protocols (e.g., Wi-Fi®, Bluetooth®, and the like).

[0197] The wireless device 2102 may include a sampling module 2116. The sampling module 2116 may be implemented via hardware, software, or combinations thereof. For28P68964WO1 4929-0472-1490\lexample, the sampling module 2116 may be implemented as a processor, circuit, and / or instructions 2108 stored in the memory 2106 and executed by the processor(s) 2104. In some examples, the sampling module 2116 may be integrated within the processor(s) 2104 and / or the transceiver(s) 2110. For example, the sampling module 2116 may be implemented by a combination of software components (e.g., executed by a DSP or a general processor) and hardware components (e.g., logic gates and circuitry) within the processor(s) 2104 or the transceiver(s) 2110.

[0198] The sampling module 2116 may be used for various aspects of the present disclosure, for example, aspects of any of FIG. 8, FIG. 10, FIG. 12, FIG. 14, FIG. 16, and or FIG. 18. The sampling module 2116 may configure the wireless device 2102 to generate and / or report one or more LoS / nLoS inference(s) (e.g., a LoS / nLoS inference base on first-in-time samples for a first path, an LoS / nLoS inference for a first-in-time sample, an LoS / nLoS inference for a strongest sample, and / or one or more LoS / nLoS inference(s) for one or more selected sample(s)) and any applicable related information in the manner described herein.

[0199] The network device 2118 may include one or more processor(s) 2120. The processor(s) 2120 may execute instructions such that various operations of the network device 2118 are performed, as described herein. The processor(s) 2120 may include one or more baseband processors implemented using, for example, a CPU, a DSP, an ASIC, a controller, an FPGA device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0200] The network device 2118 may include a memory 2122. The memory 2122 may be a non-transitory computer-readable storage medium that stores instructions 2124 (which may include, for example, the instructions being executed by the processor(s) 2120). The instructions 2124 may also be referred to as program code or a computer program. The memory 2122 may also store data used by, and results computed by, the processor(s) 2120.

[0201] The network device 2118 may include one or more transceiver(s) 2126 that may include RF transmitter circuitry and / or receiver circuitry that use the antenna(s) 2128 of the network device 2118 to facilitate signaling (e.g., the signaling 2134) to and / or from the network device 2118 with other devices (e.g., the wireless device 2102) according to corresponding RATs.29P68964WO1 4929-0472-1490\l

[0202] The network device 2118 may include one or more antenna(s) 2128 (e.g., one, two, four, or more). In embodiments having multiple antenna(s) 2128, the network device 2118 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc., as has been described.

[0203] The network device 2118 may include one or more interface(s) 2130. The interface(s) 2130 may be used to provide input to or output from the network device 2118. For example, a network device 2118 that is a base station may include interface(s) 2130 made up of transmitters, receivers, and other circuitry (e.g., other than the transceiver(s) 2126 / antenna(s) 2128 already described) that enables the base station to communicate with other equipment in a core network, and / or that enables the base station to communicate with external networks, computers, databases, and the like for purposes of operations, administration, and maintenance of the base station or other equipment operably connected thereto.

[0204] The network device 2118 may include a sampling module 2132. The sampling module 2132 may be implemented via hardware, software, or combinations thereof. For example, the sampling module 2132 may be implemented as a processor, circuit, and / or instructions 2124 stored in the memory 2122 and executed by the processor(s) 2120. In some examples, the sampling module 2132 may be integrated within the processor(s) 2120 and / or the transceiver(s) 2126. For example, the sampling module 2132 may be implemented by a combination of software components (e.g., executed by a DSP or a general processor) and hardware components (e.g., logic gates and circuitry) within the processor(s) 2120 or the transceiver(s) 2126.

[0205] The sampling module 2132 may be used for various aspects of the present disclosure, for example, aspects of any of FIG. 9, FIG. 11, FIG. 13, FIG. 15, FIG. 17, and / or FIG. 19. The sampling module 2132 may configure the network device 2118 to generate and / or report one or more LoS / nLoS inference(s) (e.g., a LoS / nLoS inference base on first-in-time samples for a first path, an LoS / nLoS inference for a first-in-time sample, an LoS / nLoS inference for a strongest sample, and / or one or more LoS / nLoS inference(s) for one or more selected sample(s)) and any applicable related information in the manner described herein.

[0206] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any one or more of the method 800, the method 1000, the method 1200, the method 1400, the method 1600, and the method 1800. This30P68964WO1 4929-0472-1490\lapparatus may be, for example, an apparatus of a UE (such as a wireless device 2102 that is a UE, as described herein).

[0207] Embodiments contemplated herein include one or more non-transitory computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform one or more elements of any one or more of the method 800, the method 1000, the method 1200, the method 1400, the method 1600, and the method 1800. This non- transitory computer-readable media may be, for example, a memory of a UE (such as a memory 2106 of a wireless device 2102 that is a UE, as described herein).

[0208] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of any one or more of the method 800, the method 1000, the method 1200, the method 1400, the method 1600, and the method 1800. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 2102 that is a UE, as described herein).

[0209] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of any one or more of the method 800, the method 1000, the method 1200, the method 1400, the method 1600, and the method 1800. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 2102 that is a UE, as described herein).

[0210] Embodiments contemplated herein include a signal as described in or related to one or more elements of any one or more of the method 800, the method 1000, the method 1200, the method 1400, the method 1600, and the method 1800.

[0211] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processor is to cause the processor to carry out one or more elements of any one or more of the method 800, the method 1000, the method 1200, the method 1400, the method 1600, and the method 1800. The processor may be a processor of a UE (such as a processor(s) 2104 of a wireless device 2102 that is a UE, as described herein). These instructions may be, for example, located in the processor and / or on a memory of the UE (such as a memory 2106 of a wireless device 2102 that is a UE, as described herein).31P68964WO1 4929-0472-1490\l

[0212] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any one or more of the method 900, the method 1100, the method 1300, the method 1500, the method 1700, and the method 1900. This apparatus may be, for example, an apparatus of a base station (such as a network device 2118 that is a base station, as described herein).

[0213] Embodiments contemplated herein include one or more non-transitory computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform one or more elements of any one or more of the method 900, the method 1100, the method 1300, the method 1500, the method 1700, and the method 1900. This non- transitory computer-readable media may be, for example, a memory of a base station (such as a memory 2122 of a network device 2118 that is a base station, as described herein).

[0214] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of any one or more of the method 900, the method 1100, the method 1300, the method 1500, the method 1700, and the method 1900. This apparatus may be, for example, an apparatus of a base station (such as a network device 2118 that is a base station, as described herein).

[0215] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of any one or more of the method 900, the method 1100, the method 1300, the method 1500, the method 1700, and the method 1900. This apparatus may be, for example, an apparatus of a base station (such as a network device 2118 that is a base station, as described herein).

[0216] Embodiments contemplated herein include a signal as described in or related to one or more elements of any one or more of the method 900, the method 1100, the method 1300, the method 1500, the method 1700, and the method 1900.

[0217] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processing element is to cause the processing element to carry out one or more elements of any one or more of the method 900, the method 1100, the method 1300, the method 1500, the method 1700, and the method 1900. The processor may be a processor of a32P68964WO1 4929-0472-1490\lbase station (such as a processor(s) 2120 of a network device 2118 that is a base station, as described herein). These instructions may be, for example, located in the processor and / or on a memory of the base station (such as a memory 2122 of a network device 2118 that is a base station, as described herein).

[0218] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, and / or methods as set forth herein. For example, a baseband processor as described herein in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein. For another example, circuitry associated with a UE, base station, network element, etc. as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein.

[0219] Any of the above described embodiments may be combined with any other embodiment (or combination of embodiments), unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.

[0220] Embodiments and implementations of the systems and methods described herein may include various operations, which may be embodied in machine-executable instructions to be executed by a computer system. A computer system may include one or more general-purpose or special-purpose computers (or other electronic devices). The computer system may include hardware components that include specific logic for performing the operations or may include a combination of hardware, software, and / or firmware.

[0221] It should be recognized that the systems described herein include descriptions of specific embodiments. These embodiments can be combined into single systems, partially combined into other systems, split into multiple systems or divided or combined in other ways. In addition, it is contemplated that parameters, attributes, aspects, etc. of one embodiment can be used in another embodiment. The parameters, attributes, aspects, etc. are merely described in one or more embodiments for clarity, and it is recognized that the parameters, attributes, aspects, etc. can be combined with or substituted for33P68964WO1 4929-0472-1490\lparameters, attributes, aspects, etc. of another embodiment unless specifically disclaimed herein.

[0222] It is well understood that the use of personally identifiable information should follow privacy policies and practices that are generally recognized as meeting or exceeding industry or governmental requirements for maintaining the privacy of users. In particular, personally identifiable information data should be managed and handled so as to minimize risks of unintentional or unauthorized access or use, and the nature of authorized use should be clearly indicated to users.

[0223] Although the foregoing has been described in some detail for purposes of clarity, it will be apparent that certain changes and modifications may be made without departing from the principles thereof. It should be noted that there are many alternative ways of implementing both the processes and apparatuses described herein. Accordingly, the present embodiments are to be considered illustrative and not restrictive, and the description is not to be limited to the details given herein, but may be modified within the scope and equivalents of the appended claims.34P68964WO1 4929-0472-1490\l

Claims

CLAIMS1. A method of a user equipment (UE) of a wireless communication system, comprising: sampling a reference signal received from a network using Nt' samples; determining that first-in-time Nt'_l samples of the Nt' samples are of a first-in- time path of the reference signal; applying the first-in-time Nt'_l samples at an artificial intelligence (AI) / machine learning (ML) model to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the first-in-time path; and sending, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time path and Nt' l.

2. The method of claim 1, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an LoS path.

3. The method of claim 1, wherein the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an LoS path.

4. The method of claim 1, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an nLoS path.

5. The method of claim 1, wherein the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an nLoS path.

6. The method of claim 1, wherein the reference signal indicates a transmission reception point (TRP) of the network by which it is transmitted.

7. A method of a base station of a wireless communication system, comprising: sampling a reference signal received from a user equipment (UE) at a transmission reception point (TRP) of the base station using Nt' samples; determining that first-in-time Nt'_l samples of the Nt' samples are of a first-in- time path of the reference signal; applying the first-in-time Nt'_l samples at an artificial intelligence (AI) / machine learning (ML) model to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the first-in-time path; and35P68964WO1 4929-0472-1490Usending, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time path and Nt' l.

8. The method of claim 7, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an LoS path.

9. The method of claim 7, wherein the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an LoS path.

10. The method of claim 7, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an nLoS path.

11. The method of claim 7, wherein the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an nLoS path.

12. The method of claim 7, wherein the reference signal indicates the TRP.

13. A method of a user equipment (UE) of a wireless communication system, comprising: sampling a reference signal received from a network using Nt' samples; applying a first-in-time sample of the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the first-in-time sample; and sending, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time sample.

14. The method of claim 13, wherein the LoS / nLoS inference for the first-in-time sample comprises an indication that the first-in-time sample is of an LoS path.

15. The method of claim 13, wherein the LoS / nLoS inference for the first-in-time sample comprises a probability that the first-in-time sample is of an LoS path.

16. The method of claim 13, wherein the LoS / nLoS inference for the first-in-time sample comprises an indication that the first-in-time sample is of an nLoS path.

17. The method of claim 13, wherein the LoS / nLoS inference for the first-in-time sample comprises a probability that the first-in-time sample is of an nLoS path.36P68964WO1 4929-0472-1490\l18. The method of claim 13, wherein the reference signal indicates a transmission reception point (TRP) of the network by which it is transmitted.

19. A method of a base station of a wireless communication system, comprising: sampling a reference signal received from a user equipment (UE) at a transmission reception point (TRP) of the base station using Nt' samples; applying a first-in-time sample of the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the first-in-time sample; and sending, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time sample.

20. The method of claim 19, wherein the LoS / nLoS inference for the first-in-time sample comprises an indication that the first-in-time sample is of an LoS path.

21. The method of claim 19, wherein the LoS / nLoS inference for the first-in-time sample comprises a probability that the first-in-time sample is of an LoS path.

22. The method of claim 19, wherein the LoS / nLoS inference for the first-in-time sample comprises an indication that the first-in-time sample is of an nLoS path.

23. The method of claim 19, wherein the LoS / nLoS inference for the first-in-time sample comprises a probability that the first-in-time sample is of an nLoS path.

24. The method of claim 19, wherein the reference signal indicates the TRP.

25. A method of a user equipment (UE) of a wireless communication system, comprising: sampling a reference signal received from a network using Nt' samples; identifying a strongest sample of the Nt' samples; applying the strongest sample of the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the strongest sample; and sending, to a location function of the wireless communication system, the LoS / nLoS inference for the strongest sample.37P68964WO1 4929-0472-1490\l26. The method of claim 25, wherein the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an LoS path.

27. The method of claim 25, wherein the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an LoS path.

28. The method of claim 25, wherein the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an nLoS path.

29. The method of claim 25, wherein the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an nLoS path.

30. The method of claim 25, wherein the reference signal indicates a transmission reception point (TRP) of the network by which it is transmitted.

31. A method of a base station of a wireless communication system, comprising: sampling a reference signal received from a user equipment (UE) at a transmission reception point (TRP) of the base station using Nt' samples; identifying a strongest sample of the Nt' samples; applying the strongest sample of the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the strongest sample; and sending, to a location function of the wireless communication system, the LoS / nLoS inference for the strongest sample.

32. The method of claim 31, wherein the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an LoS path.

33. The method of claim 31, wherein the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an LoS path.

34. The method of claim 31, wherein the LoS / nLoS inference for the strongest sample comprises an indication that the strongest sample is of an nLoS path.

35. The method of claim 31, wherein the LoS / nLoS inference for the strongest sample comprises a probability that the strongest sample is of an nLoS path.

36. The method of claim 31, wherein the reference signal indicates the TRP.38P68964WO1 4929-0472-1490\l37. A method of a user equipment (UE) of a wireless communication system, comprising: sampling a reference signal received from a network using Nt' samples; applying each of one or more selected samples of the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to generate one or more line-of-sight (LoS) / non-line-of-sight (nLoS) inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples; and sending, to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

38. The method of claim 37, further comprising selecting the one or more selected samples based on a determination that the one or more selected samples are of a first path of the reference signal.

39. The method of claim 37, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.

40. The method of claim 37, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.

41. The method of claim 37, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.

42. The method of claim 37, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

43. The method of claim 37, wherein the reference signal indicates a transmission reception point (TRP) of the network by which it is transmitted.39P68964WO1 4929-0472-1490\l44. A method of a base station of a wireless communication system, comprising: sampling a reference signal received from a user equipment (UE) at a transmission reception point (TRP) of the base station using Nt' samples; applying each of one or more selected samples of the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to generate one or more line-of-sight (LoS) / non-line-of-sight (nLoS) inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples; and sending, to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

45. The method of claim 44, further comprising selecting the one or more selected samples based on a determination that the one or more selected samples are of a first path of the reference signal.

46. The method of claim 44, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.

47. The method of claim 44, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.

48. The method of claim 44, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.

49. The method of claim 44, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

50. The method of claim 44, wherein the reference signal indicates the TRP.

51. A method of a user equipment (UE) of a wireless communication system, comprising: sampling a reference signal received from a network using Nt' samples;40P68964WO1 4929-0472-1490\lapplying the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to determine that first-in-time Nt'_l samples of the Nt' samples are of a first-in- time path of the reference signal and to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the first-in-time path; and sending, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time path and Nt' l.

52. The method of claim 51, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an LoS path.

53. The method of claim 51, wherein the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an LoS path.

54. The method of claim 51, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an nLoS path.

55. The method of claim 51, the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an nLoS path.

56. The method of claim 51, wherein the reference signal indicates a transmission reception point (TRP) of the network by which it is transmitted.

57. A method of a base station of a wireless communication system, comprising: sampling a reference signal received from a user equipment (UE) at a transmission reception point (TRP) of the base station using Nt' samples; applying the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to determine that first-in-time Nt'_l samples of the Nt' samples are of a first-in- time path of the reference signal and to generate a line-of-sight (LoS) / non-line-of-sight (nLoS) inference for the first-in-time path; and sending, to a location function of the wireless communication system, the LoS / nLoS inference for the first-in-time path and Nt' l.

58. The method of claim 57, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an LoS path.

59. The method of claim 57, wherein the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an LoS path.41P68964WO1 4929-0472-1490\l60. The method of claim 57, wherein the LoS / nLoS inference for the first-in-time path comprises an indication that the first-in-time path is an nLoS path.

61. The method of claim 57, wherein the LoS / nLoS inference for the first-in-time path comprises a probability that the first-in-time path is an nLoS path.

62. The method of claim 57, wherein the reference signal indicates the TRP.

63. A method of a user equipment (UE) of a wireless communication system, comprising: sampling a reference signal received from a network using Nt' samples; applying the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to identify one or more selected samples of the Nt' samples and to generate one or more line-of-sight (LoS) / non-line-of-sight (nLoS) inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples; and sending, to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

64. The method of claim 63, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.

65. The method of claim 63, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.

66. The method of claim 63, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.

67. The method of claim 63, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

68. The method of claim 63, wherein the reference signal indicates a transmission reception point (TRP) of the network by which it is transmitted.42P68964WO1 4929-0472-1490\l69. A method of a base station of a wireless communication system, comprising: sampling a reference signal received from a user equipment (UE) at a transmission reception point (TRP) of the base station using Nt' samples; applying the Nt' samples at an artificial intelligence (AI) / machine learning (ML) model to identify one or more selected samples of the Nt' samples and to generate one or more line-of-sight (LoS) / non-line-of-sight (nLoS) inferences, each of the one or more LoS / nLoS inferences corresponding to one of the one or more selected samples; and sending, to a location function of the wireless communication system, the one or more LoS / nLoS inferences and one or more sample indexes, each of the one or more sample indexes identifying one of the one or more selected samples.

70. The method of claim 69, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an LoS path.

71. The method of claim 69, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an LoS path.

72. The method of claim 69, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises a probability that a corresponding sample of the one or more selected samples is of an nLoS path.

73. The method of claim 69, wherein a first LoS / nLoS inference of the one or more LoS / nLoS inferences comprises an indication that a corresponding sample of the one or more selected samples is of an nLoS path.

74. The method of claim 69, wherein the reference signal indicates the TRP.

75. An apparatus comprising means to perform the method of any of claim 1 to claim 74.

76. A computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform the method of any of claim 1 to claim 74.

77. An apparatus comprising logic, modules, or circuitry to perform the method of any of claim 1 to claim 74.43P68964WO1 4929-0472-1490\l78. A baseband processor for a user equipment (UE) that is configured to cause the UE to perform one or more elements of any one of claim 1 to claim 6, claim 13 to claim 18, claim 25 to claim 30, claim 37 to claim 43, claim 51 to claim 56, and claim 63 to claim 68.

79. A baseband processor for a base station that is configured to cause the base station to perform one or more elements of any one of claim 7 to claim 12, claim 19 to claim 24, claim 31 to claim 36, claim 44 to claim 50, claim 57 to claim 62, and claim 69 to claim 74.44P68964WO1 4929-0472-1490\l

Images