Method of tagging artificial intelligence / machine learning output for positioning

Abstract

Systems, methods, apparatuses, and computer program products for reporting AI / ML- based positioning output with a tag information on the input of an AI / ML model. One method may include receiving, by a UE, positioning information comprising at least one DL PRS; performing, by the UE, at least one measurement of the at least one DL PRS; and transmitting, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an AI model input or an AI model output.

Description

METHOD OF TAGGING ARTIFICIAL INTELLIGENCE / MACHINE LEARNINGOUTPUT FOR POSITIONINGTECHNICAL FIELD

[0001] Some example embodiments may generally relate to mobile or wireless telecommunication systems, such as 3rdGeneration Partnership Project (3GPP) Long Term Evolution (LTE), 5thgeneration (5G) radio access technology (RAT), new radio (NR) access technology, 6thgeneration (6G), and / or other communications systems. For example, certain example embodiments may relate to systems and / or methods for reporting artificial intelligence / machine learning (AIZML)-based positioning output with a tag information on the input of an AI / ML model.BACKGROUND

[0002] Examples of mobile or wireless telecommunication systems may include radio frequency (RF) 5G RAT, the Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), LTE Evolved UTRAN (E-UTRAN), LTE- Advanced (LTE-A), LTE-A Pro, NR access technology, and / or MulteFire Alliance. 5G wireless systems refer to the next generation (NG) of radio systems and network architecture. A 5G system is typically built on a 5G NR, but a 5G (or NG) network may also be built on E- UTRA radio. It is expected that NR can support service categories such as enhanced mobile broadband (eMBB), ultra-reliable low-latency-communication (URLLC), and massive machine-type communication (mMTC). NR is expected to deliver extreme broadband, ultra- robust, low-latency connectivity, and massive networking to support the Internet of Things (loT). The next generation radio access network (NG-RAN) represents the radio access network (RAN) for 5G, which may provide radio access for NR, LTE, and LTE-A. It is noted that the nodes in 5G providing radio access functionality to a user equipment (e.g., similar to the Node B in UTRAN or the Evolved Node B (eNB) in LTE) may be referred to as next-generation Node B (gNB) when built on NR radio, and may be referred to as next-generation eNB (NG- eNB) when built on E-UTRA radio.SUMMARY

[0003] In accordance with some example embodiments, a method may include receiving, by a user equipment, positioning information comprising at least one downlink positioning reference signal. The method may further include performing, by the user equipment, at least onemeasurement of the at least one downlink positioning reference signal. The method may further include transmitting, by the user equipment, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

[0004] In accordance with certain example embodiments, an apparatus may include means for receiving positioning information comprising at least one downlink positioning reference signal. The apparatus may further include means for performing at least one measurement of the at least one downlink positioning reference signal. The apparatus may further include means for transmitting, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

[0005] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include receiving positioning information comprising at least one downlink positioning reference signal. The method may further include performing at least one measurement of the at least one downlink positioning reference signal. The method may further include transmitting, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

[0006] In accordance with some example embodiments, a computer program product may perform a method. The method may include receiving positioning information comprising at least one downlink positioning reference signal. The method may further include performing at least one measurement of the at least one downlink positioning reference signal. The method may further include transmitting, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

[0007] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to receive positioning information comprising at least one downlink positioning reference signal. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to perform at least one measurement of the at least one downlink positioning reference signal. The at leastone memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

[0008] In accordance with various example embodiments, an apparatus may include receiving circuitry configured to perform receiving positioning information comprising at least one downlink positioning reference signal. The apparatus may further include performing circuitry configured to perform performing at least one measurement of the at least one downlink positioning reference signal. The apparatus may further include transmitting circuitry configured to perform transmitting, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

[0009] In accordance with some example embodiments, a method may include transmitting, by a location management function, to a user equipment, positioning information comprising at least one downlink positioning reference signal. The method may further include receiving, by the location management function, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output. The method may further include adjusting, by the location management function, an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment. The method may further include transmitting, by the location management function, a feedback message to the user equipment configured to cause the user equipment to use other tag information.

[0010] In accordance with certain example embodiments, an apparatus may include means for transmitting, to a user equipment, positioning information comprising at least one downlink positioning reference signal. The apparatus may further include means for receiving, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output. The apparatus may further include means for adjusting an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment. The apparatus may further include means for transmitting a feedback message to the user equipment configured to cause the user equipment to use other tag information.

[0011] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include transmitting, to a user equipment, positioning information comprising at least one downlink positioning reference signal. The method may further include receiving, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output. The method may further include adjusting an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment. The method may further include transmitting a feedback message to the user equipment configured to cause the user equipment to use other tag information.

[0012] In accordance with some example embodiments, a computer program product may perform a method. The method may include transmitting, to a user equipment, positioning information comprising at least one downlink positioning reference signal. The method may further include receiving, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output. The method may further include adjusting an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment. The method may further include transmitting a feedback message to the user equipment configured to cause the user equipment to use other tag information.

[0013] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to transmit, to a user equipment, positioning information comprising at least one downlink positioning reference signal. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to receive, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to adjust an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag informationreceived from the user equipment. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit a feedback message to the user equipment configured to cause the user equipment to use other tag information.

[0014] In accordance with various example embodiments, an apparatus may include transmitting circuitry configured to perform transmitting, to a user equipment, positioning information comprising at least one downlink positioning reference signal. The apparatus may further include receiving circuitry configured to perform receiving, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output. The apparatus may further include adjusting circuitry configured to perform adjusting an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment. The apparatus may further include transmitting circuitry configured to perform transmitting a feedback message to the user equipment configured to cause the user equipment to use other tag information.BRIEF DESCRIPTION OF THE DRAWINGS

[0015] For a proper understanding of example embodiments, reference should be made to the accompanying drawings, wherein:

[0016] FIG. 1 illustrates an AI / ML model according to various example embodiments;

[0017] FIG. 2 illustrates an example of a signaling diagram according to certain example embodiments;

[0018] FIG. 3 illustrates an example of a flow diagram of a method according to various example embodiments;

[0019] FIG. 4 illustrates an example of a flow diagram of a method according to various example embodiments;

[0020] FIG. 5 illustrates an example of various network devices according to some example embodiments; and

[0021] FIG. 6 illustrates an example of a 5G network and system architecture according to certain example embodiments.DETAILED DESCRIPTION

[0022] It will be readily understood that the components of certain example embodiments, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of some example embodiments of systems, methods, apparatuses, and computer program products for reporting AI / ML-based positioning output with a tag information on the input of an AI / ML model is not intended to limit the scope of certain example embodiments, but is instead representative of selected example embodiments.

[0023] For UE-side model inference (e.g. , UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning; UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning) where an AI / ML model is located on the UE side, the input dataset may be internally available at the UE. For instance, in UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning, the DL time, phase and angle-based measurements such as channel impulse response (OR), power delay profile (PDP), delay profile (DP), and reference signal time difference (RSTD) may be used as input of AI / ML functionalities running on the UE side.

[0024] Once the inference is performed by using the AI / ML model, the output of the AI / ML model may be the location coordinates of the UE e.g., UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning) or other intermediate positioning measurement e.g., UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning). The output of the AI / ML model may be used by another entity (e.g., LMF) or another application using the coordination information of the UE. However, the output of the inference based on an AI / ML model does not represent any accuracy of the output, or it may be difficult to guarantee the performance of the AI / ML-based inference. Therefore, such an uncertainty may be detrimental to the operation and performance of another network entity or application.

[0025] Certain example embodiments described herein may have various benefits and / or advantages to overcome the disadvantages described above. For example, certain example embodiments may improve the positioning accuracy by using an AI / ML model and functionality. Specifically, assistance information (e.g., tag information) may be configured to improve the accuracy of the AI / ML model output, and / or evaluate the quality of the output of AIML-based inference. Thus, certain example embodiments discussed below are directed to improvements in computer-related technology.

[0026] Positioning accuracy can be enhanced in AI / ML use cases, including direct AI / ML positioning (e.g., AI / ML model output: UE location; fingerprinting based on channelobservation as the input of AI / ML model) and AI / ML assisted positioning (e.g., AI / ML model output: new measurement and / or enhancement of existing measurement; line of sight (LOS) / non-line of sight (NLOS) identification, timing and / or angle of measurement, likelihood of measurement). For example, AI / ML could include any of UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning; UE-assisted / location management function (LMF)-based positioning with UE-side model, AI / ML assisted positioning; UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning; NG-RAN node assisted positioning with NE-side model, AI / ML assisted positioning; and NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning. A one-sided model whose inference is performed entirely at the UE or at the network may be prioritized.

[0027] For UE-side model inferences (e.g., UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning; UE-assisted / LMF-based positioning with UE- side model, AI / ML assisted positioning), input data may be internally available at the UE, where the inference process is performed. For NE-side model inferences, input data may be internally available at the NE; in this case, the UE may also generate the necessary input data while the termination point for this input data lies within the NE, where the inference process is performed. For LMF-side model inferences, the UE or NE may generate the necessary input data while the termination point for this input data lies within the LMF where the inference process is performed.

[0028] For direct AI / ML positioning (e.g., UE-assisted / LMF-based positioning with LMF- side model, direct AI / ML positioning; NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning), type of measurements as model inference input may consider performance impact and associated signalling overhead (e.g., potential new measurements (e.g., CIR / PDP); existing measurements (e.g., reference signal received power (RSRP) / reference signal received path power (RSRPP) / RSTD)).

[0029] For AI / ML assisted positioning with UE-assisted / LMF-based positioning with UE- side model, AI / ML assisted positioning and NG-RAN node assisted positioning with NE- side model, AI / ML assisted positioning, measurement reports may carry model outputs to the LMF (e.g., new measurement report (e.g., time of arrival (To A), path phase); existing measurement report (e.g., RSTD, LOS / NLOS indicator, RSRPP); and enhancements of existing measurement report (e.g., soft information / high resolution of RSTD)).

[0030] Various types of model inference output (e.g., timing estimation, LOS / NLOS indicator) may be identified as candidates providing performance benefits. The report toLMF may be derived based on and / or differ from the model inference output. Furthermore, assistance signaling and procedure may facilitate model inferences for both UE-side and network-side model (e.g. , reference signal (RS) configurations).

[0031] Model inference input may include new and / or existing measurements. UE may perform measurement as model inference input for UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning, UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning, and UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning; and the transmission reception point (TRP) may perform measurement as model inference input for NG-RAN node assisted positioning with NE-side model, AI / ML assisted positioning and NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning.

[0032] Report of measurements as model inference input may be provided to the LMF for LMF-side model (e.g., UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning; NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning). Assistance signalling and procedures may facilitate model inferences for both UE-side and network-side models.

[0033] For AI / ML assisted positioning, new measurement reports and / or potential enhancements of existing measurement report as model output to LMF for UE-assisted (e.g. , UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning) and NG-RAN node assisted positioning (e.g., NG-RAN node assisted positioning with NE-side model, AI / ML assisted positioning).

[0034] For AI / ML-based positioning, FIG. 1 illustrates an example of an AI / ML model structure with a set of inputs and another set of outputs. The input of the AI / ML model may include datasets such as positioning-related measurements (e.g., RSTD measurements). Similarly, the output of the AI / ML model may include information configured to identify the location of a UE. For example, the output of the AI / ML model may be the coordinates of the UE in AI / ML-based direct positioning.

[0035] For UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning, the AI / ML model may be located at the UE. For example, the UE may collect data as an input of the AI / ML model. The input data can be the downlink (DL) measurements (e.g., RSTD). The inference function using the AI / ML model may be performed by the UE, and the output of the inference based on AI / ML model may be the coordinates of the UE.

[0036] In UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning, the AI / ML model may be located at the UE. For example, the UE may use theAI / ML model having the received signal (e.g., positioning reference signal (PRS)) as inputs. The output of the AI / ML model may then be the inferred measurements as an output. The output measurement for UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning may be intermediate features, such as ToA, path phase, existing measurement report (e.g., RSTD, LOS / NLOS indicator, RSRP), and enhancements of measurement reports (e.g., soft information / high resolution of RSTD). The output may then be sent from the UE to the LMF. Consequently, based on the reported measurements, the LMF may determine the position of the UE.

[0037] For the model input used in evaluations of AI / ML based positioning, if time-domain OR or PDP is used as model input in the evaluation, the input dimension NTRP * NpOrt * Nt may be reported, where NTRP is the number of TRPs, Nport is the number of transmit / receive antenna port pairs, and Nt is the number of consecutive time domain samples. If N’t (N’t < Nt) samples with the strongest power are selected as the model input, with remaining (Nt - N’t) time domain samples set to zero, then value N’t in addition to Nt may be reported. Timing info for the N’t samples may also be provided as model input. For evaluations, sampling periods may be reported.

[0038] For selecting N’t from Nt (i.e., sub-sampling), the subset of the consecutive or non- consecutive time-domain samples may be selected and used as the input of AI / ML functionalities. For evaluation of AI / ML based positioning, when time domain samples are used as model input and sub-sampling is applied, the selection of N't measurements may be based on the strongest power. When sub-sampling is applied, the N't measurement may not be consecutive in time. Training and testing datasets may use the same measurement selection method (e.g., strongest power). However, other selection methodologies for N't measurements may be used.

[0039] As used throughout this description, “Al model” may refer to and be interchangeable with any of: ML model, AIML model, AI / ML model, ML / Al model, or any other term that means Al and / or ML functionalities.

[0040] FIG. 2 illustrates an example of a signaling diagram 200 depicting for reporting AI / ML- based positioning output with a tag information on the input of an AI / ML model. UE 220 may be similar to UE 520, and NE 230 and LMF 240 may be similar to NE 510, as illustrated in FIG. 5, according to certain example embodiments.

[0041] At operation 201 , LMF 240 may configure UE 220 to initiate AI / ML positioning using a UE-side model.

[0042] At operation 202, LMF 240 may transmit to UE 220 DL positioning information, including TRPs and their associated TRP Rx / Tx TEGs.

[0043] At operation 203, LMF 240 may transmit to UE 220 DL PRS.

[0044] At operation 204, UE 220 may perform DL measurements.

[0045] At operation 205, information acquired from the measurements may be used as an input of the AI / ML model for positioning inferences to determine location coordinate information of UE 220.

[0046] At operation 206, UE 220 may transmit to NE 230 and / or LMF 240 an output of the AI / ML-based inference with tag information. In certain example embodiments, the tag information may indicate a number of measurement samples used as input of the AI / ML model (e.g., the number of samples can be 1, 4, 8, or 16). If the input includes measurements based on a specific value of the sample number, the value may be attached to the output. The number of measurement samples may performance; for example, if UE 220 is experiencing a bad channel condition, a high number of the samples may improve the quality of input value, and subsequently improve the positioning accuracy of the output. In another example, if UE 220 has a high mobility with a dynamic channel condition, a small number of samples may be sufficient to capture an instantaneous response from the channel. Thus, the output with a small number of samples may improve the accuracy of the output.

[0047] In certain example embodiments, the tag information may indicate a number of TRPs configured for the performing the at least one measurement as the Al model input. For example, the at least one positioning measurement may include at least one of: ToA, RSRP, RSTD, user equipment receive-transmit time difference (UE Rx-Tx time difference), or RSRPP.

[0048] In some example embodiments, the tag information on the radio port may be configured to detect or measure the targeting signal e.g., PRS).

[0049] In various example embodiments, the tag information may include a number of TRPs used to generate the DL measurements as an input of the AI / ML model. Specifically, the number of TRPs may be 8 or 16. If the DL measurements are collected by observing a certain number of TRPs, the number of TRPs may be attached to the output. For example, UE 220 may be configured to obtain DL positioning measurements from 64 TRPs, but UE 220 may only select 8 of these 64 TRPs based on a certain criterion. UE 220 may be configured to use a different number of TRPs, and provide a set of results for various number of TRPs.

[0050] In certain example embodiments, when sub-sampling is applied for model inputs, measurements may be selected that include consecutive or non-consecutive samples basedon the channel conditions; therefore, the tag information may include a flag with the output measurements to indicate consecutive or non-consecutive samples used as model inputs.

[0051] In some example embodiments, the tag information may include at least one of a number, configuration, composition, or selection of the subsamples; an indication of whether any arbitrary number is added to the subsamples to make the AI / ML input dimension (z.e., size) consistent; an indication of whether the zero padding used to make the AI / ML input dimension (z.e., size) consistent, wherein sub-sampling is applied; an indication of whether UE 220 is configured to use a configured sub-sampling method of NE 230 to determine the inputs of AI / ML functionalities; and / or a determination of UE 220 of whether the configured sub-sampling method of NE 230 is suitable for the radio condition. For example, if UE 220 detects that radio condition is degraded, UE 220 may want to use a larger number of subsamples than the configuration, and / or UE 220 may prefer to use a configuration of consecutive sub-samples over the configuration with non-consecutive sub-samples.

[0052] In various example embodiments, the information on Rx and / or Tx TEG(s) of the DL measurements used as an input of the AI / ML model. For example, the number of TEGs (e.g., information on how many different TEGs is associated with the DL measurements) may be added to the output. Alternatively, the full information on TEGs e.g., information including TEG index and the number of DL measurement associated with each TEG) may also be attached. As an input of the AI / ML model, UE 220 may be requested by LMF 240 to use specific TRP Tx TEGs. For example, the request may be to use the same TRP Tx TEGs across 64 TRPs. If 8 TRPs are associated with a same TRP Tx TEG, UE 220 may select these TRPs and TRP Tx TEGs. For example, a TRP Rx TEG may be associated with one or more measurements, which have the Rx timing error difference within a certain margin. A TRP Tx TEG may be associated with one or more DL PRSs which have the same Tx timing error within a certain margin. For example, the timing error may be caused by a delay from a radio frequency (RF) circuit to an antenna or an antenna element.

[0053] In certain example embodiments, the tag information may include an initial assumption / decision of a location estimation. For example, UE location estimation algorithms may need an initial assumption of the target estimation location, and its accuracy may also affect the output. As an input value, UE 220 may be requested to use a specific data on the initial assumption.

[0054] At operation 207, LMF 240 may consider the tag information received from UE 220 to evaluate the accuracy / preciseness of the output reported by UE 220, and may adjust an AI / ML positioning configuration based on the received output.

[0055] At operation 208, if LMF 240 expects that a different set of input data could improve the accuracy / performance of the AI / ML-based positioning functionalities of UE 220, LMF 240 may transmit a feedback message to UE 220. In certain example embodiments, the feedback message may be transmitted directly to UE 220. In some example embodiments, NE 230 may be used as a relay node; for example, the feedback message may be transmitted from LMF 240 to NE 230, which may then transmit the feedback message to UE 220. In various example embodiments, the feedback message may be configured to cause UE 220 to use other tag information to improve positioning functionalities of the user equipment.

[0056] At operation 209, based upon the feedback from LMF 240, UE 220 may use the feedback information as an additional input to the AI / ML model to calibrate / fine-tune the output.

[0057] At operation 210, UE 220 may transmit the output with an updated tag information to LMF 240.

[0058] FIG. 3 illustrates an example of a flow diagram of a method 300 that may be performed by a UE, such as UE 520 illustrated in FIG. 5, according to various example embodiments.

[0059] At step 301, the method may include receiving, by a UE, positioning information including at least one DL PRS.

[0060] At step 302, the method may further include performing, by the UE, at least one measurement of the at least one DL PRS. For example, the at least one measurement may include at least one positioning measurement. Additionally or alternatively, the at least one positioning measurement may include at least one of: ToA, RSRP, RSTD, UE Rx-Tx time difference, or RSRPP.

[0061] At step 303, the method may further include transmitting, by the UE, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an Al model input or an Al model output. The positioning inference information may be transmitted to a NE or LMF, which may be similar to NE 510 illustrated in FIG. 5. For example, the tag information may indicate TEG information associated with the positioning inference information and / or a location estimate associated with the positioning inference information.

[0062] The tag information may indicate at least one of: a number of measurement samples, consecutive samples, non-consecutive samples, or associated measurements used as the Al model input. Additionally or alternatively, the tag information may indicate a radio port or an antenna port configured to perform at least one of: detecting or measuring a target signal.For example, the target signal may include at least one of: the DL PRS or a sensing signal. Additionally or alternatively, the tag information may indicates a number of transmission reception points configured to perform the at least one measurement as the Al model input.

[0063] In certain example embodiments, the method may further include receiving, by the UE, feedback from the NE configured to cause the UE to use other tag information; modifying, by the UE, the positioning inference information based on the feedback; and transmitting, by the UE, the modified positioning inference information to the NE.

[0064] FIG. 4 illustrates an example of a flow diagram of a method 400 that may be performed by a NE or LMF, such as NE 510 illustrated in FIG. 5, according to various example embodiments.

[0065] At step 401 , the method may include transmitting, to a UE, such as UE 520 illustrated in FIG. 5, positioning information including at least one DL PRS. In various example embodiments, the positioning inference information may be transmitted to the UE via a NE.

[0066] At step 402, the method may include receiving, from the UE, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an Al model input or an Al model output. In certain example embodiments, the tag information may indicate TEG information associated with the positioning inference information. In various example embodiments, the tag information may indicate a location estimate associated with the positioning inference information.

[0067] In some example embodiments, the at least one measurement may include at least one positioning measurement. For example, the at least one positioning measurement may include at least one of: ToA, RSRP, RSTD, UE Rx-Tx time difference, or RSRPP.

[0068] In certain example embodiments, the tag information may indicate at least one of: a number of measurement samples, consecutive samples, non-consecutive samples, or associated measurements used as the Al model input.

[0069] In some example embodiments, the tag information may indicate a radio port or an antenna port configured to perform at least one of: detecting a target signal or measuring the target signal. For example, the target signal may include at least one of: the DL PRS or a sensing signal.

[0070] In various example embodiments, the tag information may indicate a number of transmission reception points configured to perform the at least one measurement as the Al model input.

[0071] At step 403, the method may include adjusting an Al positioning configuration based on the at least one of positioning inference information or tag information received from the UE.

[0072] At step 404, the method may further include transmitting a feedback message to the UE configured to cause the UE to use other tag information.

[0073] In certain example embodiments, the method may further include receiving modified positioning inference information from the UE.

[0074] FIG. 5 illustrates an example of a system according to certain example embodiments. In one example embodiment, a system may include multiple devices, such as, for example, NE 510 and / or UE 520.

[0075] NE 510 may be one or more of a base station (e.g., 3GUMTS NodeB, 4G LTE Evolved NodeB, or 5G NR Next Generation NodeB), a serving gateway, a server, and / or any other access node or combination thereof.

[0076] NE 510 may further include at least one gNB -centralized unit (CU), which may be associated with at least one gNB -distributed unit (DU). The at least one gNB-CU and the at least one gNB-DU may be in communication via at least one Fl interface, at least one Xn-C interface, and / or at least one NG interface via a 5thgeneration core (5GC).

[0077] UE 520 may include one or more of a mobile device, such as a mobile phone, smart phone, personal digital assistant (PDA), tablet, or portable media player, digital camera, pocket video camera, video game console, navigation unit, such as a global positioning system (GPS) device, desktop or laptop computer, single-location device, such as a sensor or smart meter, or any combination thereof. Furthermore, NE 510 and / or UE 520 may be one or more of a citizens broadband radio service device (CBSD).

[0078] NE 510 and / or UE 520 may include at least one processor, respectively indicated as 511 and 521. Processors 511 and 521 may be embodied by any computational or data processing device, such as a central processing unit (CPU), application specific integrated circuit (ASIC), or comparable device. The processors may be implemented as a single controller, or a plurality of controllers or processors.

[0079] At least one memory may be provided in one or more of the devices, as indicated at 512 and 522. The memory may be fixed or removable. The memory may include computer program instructions or computer code contained therein. Memories 512 and 522 may independently be any suitable storage device, such as a non-transitory computer-readable medium. The term “non-transitory,” as used herein, may correspond to a limitation of the medium itself (z.e., tangible, not a signal) as opposed to a limitation on data storagepersistency (e.g., random access memory (RAM) vs. read-only memory (ROM)). A hard disk drive (HDD), random access memory (RAM), flash memory, or other suitable memory may be used. The memories may be combined on a single integrated circuit as the processor, or may be separate from the one or more processors. Furthermore, the computer program instructions stored in the memory, and which may be processed by the processors, may be any suitable form of computer program code, for example, a compiled or interpreted computer program written in any suitable programming language.

[0080] Processors 511 and 521, memories 512 and 522, and any subset thereof, may be configured to provide means corresponding to the various blocks of FIGs. 1-4. Although not shown, the devices may also include positioning hardware, such as GPS or micro electrical mechanical system (MEMS) hardware, which may be used to determine a location of the device. Other sensors are also permitted, and may be configured to determine location, elevation, velocity, orientation, and so forth, such as barometers, compasses, and the like.

[0081] As shown in FIG. 5, transceivers 513 and 523 may be provided, and one or more devices may also include at least one antenna, respectively illustrated as 514 and 524. The device may have many antennas, such as an array of antennas configured for multiple input multiple output (MIMO) communications, or multiple antennas for multiple RATs. Other configurations of these devices, for example, may be provided. Transceivers 513 and 523 may be a transmitter, a receiver, both a transmitter and a receiver, or a unit or device that may be configured both for transmission and reception.

[0082] The memory and the computer program instructions may be configured, with the processor for the particular device, to cause a hardware apparatus, such as UE, to perform any of the processes described above (z.e., FIGs. 1-4). Therefore, in certain example embodiments, a non-transitory computer-readable medium may be encoded with computer instructions that, when executed in hardware, perform a process such as one of the processes described herein. Alternatively, certain example embodiments may be performed entirely in hardware.

[0083] In certain example embodiments, an apparatus may include circuitry configured to perform any of the processes or functions illustrated in FIGs. 1-4. As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry), (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, andmemory (ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions), and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g. , firmware) for operation, but the software may not be present when it is not needed for operation. This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0084] FIG. 5 illustrates an example of a 5G network and system architecture according to certain example embodiments. Shown are multiple network functions that may be implemented as software operating as part of a network device or dedicated hardware, as a network device itself or dedicated hardware, or as a virtual function operating as a network device or dedicated hardware. The NE and UE illustrated in FIG. 5 may be similar to NE 510 and UE 520, respectively. The user plane function (UPF) may provide services such as intra-RAT and inter- RAT mobility, routing and forwarding of data packets, inspection of packets, user plane quality of service (QoS) processing, buffering of downlink packets, and / or triggering of downlink data notifications. The application function (AF) may primarily interface with the core network to facilitate application usage of traffic routing and interact with the policy framework.

[0085] According to certain example embodiments, processors 511 and 521, and memories 512 and 522, may be included in or may form a part of processing circuitry or control circuitry. In addition, in some example embodiments, transceivers 513 and 523 may be included in or may form a part of transceiving circuitry.

[0086] In some example embodiments, an apparatus e.g., NE 510 and / or UE 520) may include means for performing a method, a process, or any of the variants discussed herein. Examples of the means may include one or more processors, memory, controllers, transmitters, receivers, and / or computer program code for causing the performance of the operations.

[0087] In various example embodiments, apparatus 520 may be controlled by memory 522 and processor 521 to receive positioning information including at least one DL PRS; perform at least one measurement of the at least one DL PRS; and transmit, based at least partiallyon the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an Al model input or an Al model output.

[0088] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for receiving positioning information including at least one DL PRS; means for performing at least one measurement of the at least one DL PRS; and means for transmitting, based at least partially on the at least one measurement, at least one of positioning inference information or tag information associated with at least one of an Al model input or an Al model output.

[0089] In various example embodiments, apparatus 510 may be controlled by memory 512 and processor 511 to transmit, to a user equipment, positioning information comprising at least one DL PRS; receive, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an Al model input or an Al model output; adjust an Al positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment; and transmit a feedback message to the user equipment configured to cause the user equipment to use other tag information.

[0090] Certain example embodiments may be directed to an apparatus that includes means for transmitting, to a user equipment, positioning information comprising at least one DL PRS; means for receiving, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an Al model input or an Al model output; means for adjusting an Al positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment; and means for transmitting a feedback message to the user equipment configured to cause the user equipment to use other tag information.

[0091] The features, structures, or characteristics of example embodiments described throughout this specification may be combined in any suitable manner in one or more example embodiments. For example, the usage of the phrases “various embodiments,” “certain embodiments,” “some embodiments,” or other similar language throughout this specification refers to the fact that a particular feature, structure, or characteristic described in connection with an example embodiment may be included in at least one example embodiment. Thus, appearances of the phrases “in various embodiments,” “in certain embodiments,” “in some embodiments,” or other similar language throughout this specification does not necessarily allrefer to the same group of example embodiments, and the described features, structures, or characteristics may be combined in any suitable manner in one or more example embodiments.

[0092] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or,” mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0093] Additionally, if desired, the different functions or procedures discussed above may be performed in a different order and / or concurrently with each other. Furthermore, if desired, one or more of the described functions or procedures may be optional or may be combined. As such, the description above should be considered as illustrative of the principles and teachings of certain example embodiments, and not in limitation thereof.

[0094] One having ordinary skill in the art will readily understand that the example embodiments discussed above may be practiced with procedures in a different order, and / or with hardware elements in configurations which are different than those which are disclosed. Therefore, although some embodiments have been described based upon these example embodiments, it would be apparent to those of skill in the art that certain modifications, variations, and alternative constructions would be apparent, while remaining within the spirit and scope of the example embodiments.

[0095] Partial Glossary

[0096] 3GPP Third Generation Partnership Project

[0097] 5G fifth generation

[0098] 5GC fifth generation core

[0099] 6G sixth generation

[0100] AF application function

[0101] AI / ML artificial intelligence / machine learning

[0102] ASIC application specific integrated circuit

[0103] CBSD citizens broadband radio service device

[0104] CIR channel impulse response

[0105] CPU central processing unit

[0106] CU centralized unit

[0107] DL downlink

[0108] DP delay profile

[0109] DU distributed unit

[0110] eMBB enhanced mobile broadband

[0111] eNB evolved node B

[0112] gNB next generation node B

[0113] GPS global positioning system

[0114] HDD hard disk drive

[0115] loT internet of things

[0116] LMF location management function

[0117] LOS line of sight

[0118] LTE long-term evolution

[0119] LTE-A long-term evolution advanced

[0120] MEMS micro electrical mechanical system

[0121] MIMO multiple input multiple output

[0122] mMTC massive machine type communication

[0123] NE network entity

[0124] NG next generation

[0125] NG-eNB next generation evolved node B

[0126] NG-RAN next generation radio access network

[0127] NLOS non-line of sight

[0128] NR new radio

[0129] PDA personal digital assistance

[0130] PDP power delay profrle

[0131] PRS positioning reference signal

[0132] QoS quality of service

[0133] RAM random access memory

[0134] RAN radio access network

[0135] RAT radio access technology

[0136] RF radio frequency

[0137] ROM read-only memory

[0138] RS reference signal

[0139] RSRP reference signal received power

[0140] RSRPP reference signal received path power

[0141] RSTD reference signal time difference

[0142] TEG timing error group

[0143] TOA time of arrival

[0144] TRP transmission reception point

[0145] Tx transmission

[0146] UE user equipment

[0147] UMTS universal mobile telecommunications system

[0148] UPF user plane function

[0149] URLLC ultra-reliable and low-latency communication

[0150] UTRAN universal mobile telecommunications system terrestrial radio access network

[0151] WLAN wireless local area network

Claims

WE CLAIM:

1. A method comprising : receiving, by a user equipment, positioning information comprising at least one downlink positioning reference signal; performing, by the user equipment, at least one measurement of the at least one downlink positioning reference signal; and transmitting, by the user equipment, based at least partially on the at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

2. The method of claim 1, wherein the positioning inference information is transmitted to a network entity or location management function.

3. The method of claim 1 or 2, wherein the tag information indicates at least one of: a number of measurement samples, consecutive samples, non-consecutive samples, or associated measurements used as the artificial intelligence model input.

4. The method of any one of claims 1-3, wherein the tag information indicates a radio port or an antenna port configured to perform at least one of: detecting a target signal or measuring the target signal.

5. The method of claim 4, wherein the target signal comprises at least one of: the downlink positioning reference signal or a sensing signal.

6. The method of any one of claims 1-5, wherein the tag information indicates a number of transmission reception points configured to perform the at least one measurement as the artificial intelligence model input.

7. The method of any one of claims 1-6, wherein the at least one measurement comprises at least one positioning measurement.

8. The method of claim 7, wherein the at least one positioning measurement comprises at least one of: time of arrival, reference signal received power, reference signal timedifference, user equipment receive-transmit time difference, or reference signal received path power.

9. The method of any one of claims 1-8, further comprising: receiving, by the user equipment, feedback from the network entity configured to cause the user equipment to use other tag information; modifying, by the user equipment, the positioning inference information based on the feedback; and transmitting, by the user equipment, the modified positioning inference information to the network entity.

10. The method of any one of claims 1-9, wherein the tag information indicates timing error group information associated with the positioning inference information.

11. The method of any one of claims 1-10, wherein the tag information indicates a location estimate associated with the positioning inference information.

12. A method comprising: transmitting, by a location management function, to a user equipment, positioning information comprising at least one downlink positioning reference signal; receiving, by the location management function, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output; adjusting, by the location management function, an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment; and transmitting, by the location management function, a feedback message to the user equipment configured to cause the user equipment to use other tag information.

13. The method of claim 12, wherein the positioning inference information is transmitted to the user equipment via a network entity.

14. The method of claim 12 or 13, wherein the tag information indicates at least oneof: a number of measurement samples, consecutive samples, non-consecutive samples, or associated measurements used as the artificial intelligence model input.

15. The method of any one of claims 12-14, wherein the tag information indicates a radio port or an antenna port configured to perform at least one of: detecting a target signal or measuring the target signal.

16. The method of claim 15, wherein the target signal comprises at least one of: the downlink positioning reference signal or a sensing signal.

17. The method of any one of claims 12-16, wherein the tag information indicates a number of transmission reception points configured to perform the at least one measurement as the artificial intelligence model input.

18. The method of any one of claims 12-17, wherein the at least one measurement comprises at least one positioning measurement.

19. The method of claim 18, wherein the at least one positioning measurement comprises at least one of: time of arrival, reference signal received power, reference signal time difference, user equipment receive-transmit time difference, or reference signal received path power.

20. The method of any one of claims 12-19, further comprising: receiving, by the location management function, modified positioning inference information from the user equipment.

21. The method of any one of claims 12-20, wherein the tag information indicates timing error group information associated with the positioning inference information.

22. The method of any one of claims 12-21, wherein the tag information indicates a location estimate associated with the positioning inference information.

23. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:receive positioning information comprising at least one downlink positioning reference signal; perform at least one measurement of the at least one downlink positioning reference signal; and transmit, based at least partially on the at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

24. The apparatus of claim 23, wherein the positioning inference information is transmitted to a network entity or location management function.

25. The apparatus of claim 23 or 24, wherein the tag information indicates at least one of: a number of measurement samples, consecutive samples, non-consecutive samples, or associated measurements used as the artificial intelligence model input.

26. The apparatus of any one of claims 23-25, wherein the tag information indicates a radio port or an antenna port configured to perform at least one of: detecting a target signal or measuring the target signal.

27. The apparatus of claim 26, wherein the target signal comprises at least one of: the downlink positioning reference signal or a sensing signal.

28. The apparatus of any one of claims 23-27, wherein the tag information indicates a number of transmission reception points configured to perform the at least one measurement as the artificial intelligence model input.

29. The apparatus of any one of claims 23-28, wherein the at least one measurement comprises at least one positioning measurement.

30. The apparatus of claim 29, wherein the at least one positioning measurement comprises at least one of: time of arrival, reference signal received power, reference signal time difference, user equipment receive-transmit time difference, or reference signal received path power.

31. The apparatus of any one of claims 23-30, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at leastto: receive feedback from the network entity configured to cause the user equipment to use other tag information; modify the positioning inference information based on the feedback; and transmit the modified positioning inference information to the network entity.

32. The apparatus of any one of claims 23-31, wherein the tag information indicates timing error group information associated with the positioning inference information.

33. The apparatus of any one of claims 23-32, wherein the tag information indicates a location estimate associated with the positioning inference information.

34. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit to a user equipment, positioning information comprising at least one downlink positioning reference signal; receive, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output; adjust an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment; and transmit a feedback message to the user equipment configured to cause the user equipment to use other tag information.

35. The apparatus of claim 34, wherein the positioning inference information is transmitted to the user equipment via a network entity.

36. The apparatus of claim 34 or 35, wherein the tag information indicates at least one of: a number of measurement samples, consecutive samples, non-consecutive samples, or associated measurements used as the artificial intelligence model input.

37. The apparatus of any one of claims 34-36, wherein the tag information indicatesa radio port or an antenna port configured to perform at least one of: detecting a target signal or measuring the target signal.

38. The apparatus of claim 37, wherein the target signal comprises at least one of: the downlink positioning reference signal or a sensing signal.

39. The apparatus of any one of claims 34-38, wherein the tag information indicates a number of transmission reception points configured to perform the at least one measurement as the artificial intelligence model input.

40. The apparatus of any one of claims 34-39, wherein the at least one measurement comprises at least one positioning measurement.

41. The apparatus of claim 40, wherein the at least one positioning measurement comprises at least one of: time of arrival, reference signal received power, reference signal time difference, user equipment receive-transmit time difference, or reference signal received path power.

42. The apparatus of any one of claims 34-41, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive modified positioning inference information from the user equipment.

43. The apparatus of any one of claims 34-42, wherein the tag information indicates timing error group information associated with the positioning inference information.

44. The apparatus of any one of claims 34-43, wherein the tag information indicates a location estimate associated with the positioning inference information.

45. An apparatus comprising: means for receiving positioning information comprising at least one downlink positioning reference signal; means for performing at least one measurement of the at least one downlink positioning reference signal; andmeans for transmitting, based at least partially on the at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output.

46. An apparatus comprising: means for transmitting, to a user equipment, positioning information comprising at least one downlink positioning reference signal; means for receiving, from the user equipment, based at least partially on at least one measurement, at least one of: positioning inference information or tag information associated with at least one of an artificial intelligence model input or an artificial intelligence model output; means for adjusting an artificial intelligence positioning configuration based on the at least one of positioning inference information or tag information received from the user equipment; and means for transmitting a feedback message to the user equipment configured to cause the user equipment to use other tag information.

47. A non-transitory computer readable medium comprising program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method according to any one of claims 1-22.

48. A computer program comprising instructions, which, when executed by an apparatus, cause the apparatus to perform the method of any one of claims 1-22.

Images