AIML-based positioning for a wireless communication network supporting generalization of AIML based positioning

Abstract

A UE receives a configuration to perform AIML-based positioning measurements which includes at least TRP-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups include TRP(s), and the configuration includes one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group. The UE selects, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on RSs received from individual ones of the multiple TRP groups. The UE determines positioning measurements to be reported to the network at least based on the selected AIML functionality, and reports the determined positioning measurements. A network element sends the configuration to the UE and receives the positioning measurements.

Description

AIML-Based Positioning for a Wireless Communication Network Supporting Generalization of AIML Based PositioningRELATED APPLICATION

[0001] This application claims priority to US provisional Application No. 63 / 694966 filed September 16, 2024, which is incorporated herein by reference in its entirety.TECHNICAL FIELD

[0002] Examples of embodiments herein relate generally to wireless communication networks and, more specifically, relate to positioning that uses AIML (artificial intelligence, machine learning, also AL / ML) to determine position of a user equipment within the wireless communications network.BACKGROUND

[0003] In wireless communication networks such as modern cellular networks, precise user location estimation is crucial for various applications such as emergency services, navigation systems, and smart cities. Traditional methods like Global Positioning System (GPS) and cell ID (identification)-based positioning have limitations, and the increasing demand for accurate location information has led to the development of artificial intelligence / machine learning (AI / ML) based position estimation techniques.

[0004] Challenges for traditional position estimation techniques include the following. There is often non-line-of-sight (NLOS) propagation, where signals are affected by obstacles like buildings, trees, and hills, making it difficult to accurately estimate user positions. Multipath fading is another issue, where signals can arrive at the receiver via multiple paths, causing signal distortion and interference. There is limited sensor data, where cellular networks typically rely on sensor data from a limited number of base stations, which may not be sufficient for accurate position estimation.

[0005] AI / ML-based position estimation techniques address these issues and include the following. Machine Learning (ML) based techniques utilize ML algorithms to learn patterns in sensor data and improve positioning accuracy. Supervised learning is used to train models using labeled data (known user locations) to predict positions, and unsupervised learning clusters sensor data based on similarity to infer user positions without labels. Deep Neural Networks (DNNs) leverage DNN architectures to process sensor data and estimateuser positions. Bayesian inference uses Bayesian networks to model the uncertainty in position estimation and incorporate prior knowledge. Reinforcement learning techniques may be used to optimize positioning algorithms by iteratively updating the estimates based on feedback.

[0006] Advantages of AL / ML-based position estimation techniques include the following. AI / ML-based techniques can provide more precise user location estimates than traditional methods. These techniques can adapt to changing environmental conditions and sensor noise. AI / ML models can efficiently process large amounts of sensor data, making them suitable for large-scale cellular networks. AI / ML-based position estimation techniques have the potential to improve cellular network positioning, offering improved accuracy, robustness, and scalability.

[0007] While AI / ML-based position estimation techniques have benefits, the amount of data these may need to analyze can get to be substantial. For instance, data from up to 64 TRPs (transmission-reception points) may be used for position estimation, and even considering small combinations of the 64 TRPS for position estimate yields huge amounts of data and corresponding processing.BRIEF SUMMARY

[0008] This section is intended to include examples and is not intended to be limiting.

[0009] In an exemplary embodiment, a method is disclosed that includes receiving, at a user equipment from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, by the user equipment at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining, by the user equipment, positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting, by the user equipment, the determined positioning measurements.

[0010] An additional exemplary embodiment includes a computer program, comprising instructions for performing the method of the previous paragraph, when the computer program is run on an apparatus. The computer program according to this paragraph, wherein the computer program is a computer program product comprising a computer- readable medium bearing the instructions embodied therein for use with the apparatus. Another example is the computer program according to this paragraph, wherein the program is directly loadable into an internal memory of the apparatus.

[0011] An exemplary apparatus includes one or more processors and one or more memories storing instructions that, when executed by the one or more processors, cause the apparatus at least to perform: receiving, from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting the determined positioning measurements.

[0012] An exemplary computer program product includes a computer-readable storage medium bearing instructions that, when executed by an apparatus, cause the apparatus to perform at least the following: receiving, from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting the determined positioning measurements.

[0013] In another exemplary embodiment, an apparatus comprises means for: receiving, from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting the determined positioning measurements.

[0014] In an exemplary embodiment, a method is disclosed that includes sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

[0015] An additional exemplary embodiment includes a computer program, comprising instructions for performing the method of the previous paragraph, when the computer program is run on an apparatus. The computer program according to this paragraph, wherein the computer program is a computer program product comprising a computer- readable medium bearing the instructions embodied therein for use with the apparatus. Another example is the computer program according to this paragraph, wherein the program is directly loadable into an internal memory of the apparatus.

[0016] An exemplary apparatus includes one or more processors and one or more memories storing instructions that, when executed by the one or more processors, cause the apparatus at least to perform: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs,and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

[0017] An exemplary computer program product includes a computer-readable storage medium bearing instructions that, when executed by an apparatus, cause the apparatus to perform at least the following: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

[0018] In another exemplary embodiment, an apparatus comprises means for: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmissionreception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings use reference numerals, where the same reference numerals may be used to refer to like parts throughout, but parts having the same reference numeral can differ in operation and components. In the attached drawings:

[0020] FIG. 1 is a signaling diagram used to explain a method of generalization of AIML based positioning;

[0021] FIGS. 2 A and 2B show an illustrative example of functionality associations for TRP groups and corresponding configurations used as the UE starts in cell #1 (FIG. 2 A) and moves to cell #2 (FIG. 2B);

[0022] FIG. 3 is a block diagram of an example of a proposed UE behavior for the method of FIG. 1 ; and

[0023] FIG. 4 is a block diagram of one possible and non-limiting exemplary system in which the exemplary embodiments may be practiced.DETAIEED DESCRIPTION OF THE DRAWINGS

[0024] Abbreviations that may be found in the specification and / or the drawing figures are defined below, at the end of the detailed description section.

[0025] The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments. All of the embodiments described in this Detailed Description are exemplary embodiments provided to enable persons skilled in the art to make or use the examples.

[0026] When more than one drawing reference numeral, word, or acronym is used within this description with “ / ”, and in general as used within this description, the “ / ” may be interpreted as “or”, “and”, or “both”. 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.

[0027] As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0028] It is noted that capital and lowercase words or phrases are considered to be the same herein. For instance, the words Slice, slice, and SEICE are the same, as are the phrases Network Repository Function, network repository function, and NETWORK REPOSITORY FUNCTION.

[0029] Each of the signaling diagram in FIG. 1 or the block diagram in FIG. 3 is considered to be a logic flow diagram, and illustrates the operation of an exemplary method, results of execution of computer program instructions embodied on a computer readable memory, and / or functions performed by logic implemented in circuitry. For methods, flow diagrams, and signaling diagrams, the orders of method steps, blocks in the flow, or signaling are not critical and instead are examples.

[0030] Technical context is now provided for technical areas related to the understanding of the examples. The following uses a nested topical structure for ease of reference. This nested topical structure has the following key: I, II, III. . . are main categories; a, b, c. . . are subcategories; 1, 2, 3. .. are further subcategories; and i, ii, iii. . . are even further subcategories. For Artificial Intelligence and Machine Eearning, the phrases AIML and AL / ML are considered to be the same herein.

[0031] 3GPP (third generation partnership project) RANI and RAN2 have been studying AIML (Artificial Intelligence and Machine Learning)-based features to advance cellular communication technologies since Rel-18 (release 18). The focus of the study is MIMO (Multiple Input and Multiple Output) and Positioning technologies. This feature would likely be the key foundations of the next generation of cellular systems such as 6G (sixth generation).

[0032] The following is a part of the Rel-19 AIML Work Item description.

[0033] I) AI / ML general framework for one-sided AI / ML models is within the realm of what has been studied in the FS_NR_AIML_Air project [RAN2]:

[0034] a) Signaling and protocol aspects of Life Cycle Management (LCM) enabling functionality and model (if justified) selection, activation, deactivation, switching, fallback.

[0035] 1) Identification related signaling is part of the above objective

[0036] b) Necessary signaling / mechanism(s) for LCM to facilitate model training, inference, performance monitoring, data collection (collection of UE-sided model training data) for both UE-sided (user equipment-sided) and NW-sided (network-sided) models.

[0037] c) Signaling mechanism of applicable functionalities / models

[0038] II) Beam management - DL Tx (downlink transmission) beam prediction for both UE-sided model and NW-sided model, encompassing the following:

[0039] a) Spatial-domain DL Tx beam prediction for Set A of beams based on measurement results of Set B of beams (“BM-Casel”, beam management-Casel);

[0040] b) Temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams (“BM-Case2”);

[0041] c) Specify necessary signaling / mechanism(s) to facilitate LCM operations specific to the Beam Management (BM) use cases, if any.

[0042] d) Enabling method(s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE.

[0043] NOTE: Strive for common framework design to support both BM-Casel and BM-Case2

[0044] III) Positioning accuracy enhancements, encompassing[RAN1 / RAN2 / RAN3]:

[0045] a) Direct AI / ML positioning:

[0046] 1) (1st priority) Case 1: UE-based positioning with UE-side model, directAI / ML positioning.

[0047] 2) (2nd priority) Case 2b: UE-assisted / LMF-based positioning with LMF- side model, direct AI / ML positioning.

[0048] 3) (1st priority) Case 3b: NG-RAN node assisted positioning with LMF- side model, direct AI / ML positioning.

[0049] b) AI / ML assisted positioning

[0050] 1) (2nd priority) Case 2a: UE-assisted / LMF-based positioning with UE- side model, AI / ML assisted positioning.

[0051] 2) (1st priority) Case 3a: NG-RAN node assisted positioning with gNB- side model, AI / ML assisted positioning.

[0052] c) Specify necessary measurements, signaling / mechanism(s) to facilitate LCM operations specific to the Positioning accuracy enhancements use cases, if any.

[0053] d) Investigate and specify the necessary signaling of necessary measurement enhancements (if any).

[0054] e) Enabling method(s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE for relevant positioning sub use cases.

[0055] IV) Core requirements for the above two use cases for AI / ML LCM procedures and UE features:

[0056] a) Specify necessary RAN4 core requirements for the above two use cases.

[0057] b) Specify necessary RAN4 core requirements for LCM procedures including performance monitoring.

[0058] Study objectives with corresponding checkpoints in RAN#105 (September 2024):

[0059] I) CSI feedback enhancement:

[0060] a) For CSI compression (two-sided model), further study ways to:

[0061] 1) Improve trade-off between performance and complexity / o verhead:

[0062] i) e.g., considering extending the spatial / frequency compression to spatial / temporal / frequency compression, cell / site specific models, CSI (channel state information) compression plus prediction (compared to Rel-18 non-AI / ML based approach), or the like.

[0063] 2) Alleviate / resolve issues related to inter- vendor training collaboration.

[0064] While addressing other aspects requiring further study / conclusion as captured in the conclusions section of the 3GPP TR 38.843.

[0065] b) For CSI prediction (UE-sided model), further study performance gain over Rel-18 non-AI / ML based approach and associated complexity, while addressing other aspects requiring further study / conclusion as captured in the conclusions section of the 3GPP TR 38.843 (e.g., cell / site specific model could be considered to improve performance gain).

[0066] II) Necessity and details of model Identification concept and procedure in the context of LCM.

[0067] III) Collection of UE-sided model training data:

[0068] a) For the FS_NR_AIML_Air study use cases, identify the corresponding contents of UE data collection.

[0069] b) Analyze the UE data collection mechanisms identified during the FS_NR_AIML_Air (3GPP TR 38.843 section 7.2.1.3.2) study along with the implications and limitations of each of the methods

[0070] IV) Model transfer / delivery:

[0071] a) Determine whether there is a need to consider standardized solutions for transferring / delivering AI / ML model(s) considering at least the solutions identified during the FS_NR_AIML_Air study.

[0072] V) Testability and interoperability:

[0073] a) Finalize the testing framework and procedure for one-sided models and further analyze the various testing options for two-sided models, in collaboration with RANI, and including at least:

[0074] 1) Relation to legacy requirements.

[0075] 2) Performance monitoring and LCM aspects considering use-case specifics.

[0076] 3) Generalization aspects.

[0077] 4) Static / non-static scenarios / conditions and propagation conditions for testing (e.g., CDL (clustered delay line), field data, or the like).

[0078] 5) UE processing capability and limitations.

[0079] 6) Post-deployment validation due to model change / drift.

[0080] b) RAN5 aspects related to testability and interoperability to be addressed on a request basis.

[0081] NOTE: offline training is assumed for the purpose of this project.

[0082]

[0083]

[0084] In Rel-19, AIML positioning has the following use cases identified in 3GPP TR 38.843. The following are selected as representative sub-use cases:

[0085] I) Direct AI / ML positioning:

[0086] II) AI / ML model output: UE location.

[0087] III) e.g., fingerprinting based on channel observation as the input of AI / ML model.

[0088] IV) AI / ML assisted positioning:

[0089] V) AI / ML model output: new measurement and / or enhancement of existing measurement.

[0090] VI) e.g., LOS / NLOS (line of sight / non-line of sight) identification, timing and / or angle of measurement, likelihood of measurement.

[0091] a) More specifically, the following Cases are considered for the study:

[0092] 1) Case 1: UE-based positioning with UE-side model, direct AI / ML orAI / ML assisted positioning.

[0093] 2) Case 2a: UE-assisted / LMF-based positioning with UE-side model,AI / ML assisted positioning.

[0094] 3) Case 2b: UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning.

[0095] 4) Case 3a: NG-RAN node assisted positioning with gNB-side model,AI / ML assisted positioning.

[0096] 5) Case 3b: NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning.

[0097] 6) One-sided model whose inference is performed entirely at the UE or at the network is prioritized.

[0098] By using AIML-based positioning, inference can be used for the following features [see 3GPP TR 38.843].

[0099] I) Model Inference related:

[0100] a) For direct AI / ML positioning (Case 2b and 3b), type of measurement(s) as model inference input considering performance impact and associated signaling overhead

[0101] b) Potential new measurement: CIR / PDP (channel impulse response / power delay profile).

[0102] c) Existing measurement: e.g., RSRP / RSRPP / RSTD (reference signal received power / reference signal received path power / reference signal time difference).

[0103] d) Note: details of potential new measurement and / or potential enhancement to existing measurement is to be studied.

[0104] e) For AI / ML assisted positioning with UE-assisted (Case 2a) and NG- RAN (next generation radio access network) node assisted positioning (Case 3a), measurement report to carry model output to LMF (location management function).

[0105] f) measurement report: e.g., ToA (time of arrival), path phase.

[0106] g) measurement report: e.g., RSTD (Reference signal time difference), LOS / NLOS (line of sight / non-line of sight) indicator, RSRPP.

[0107] h) Enhancement of existing measurement report: e.g., soft information / high resolution of RSTD.

[0108] i) Assistance signaling and procedure to facilitate model inference for both UE-side and Network-side model.

[0109] j) RS configurations.

[0110] In 3GPP TR 38.843, the LCM procedure assumes that AI / ML model has a model ID (identification) with associated information and / or model functionality at least forsome AI / ML operations. For example, 3GPP TR 38.843 states how LCM can be performed in AIML-based positioning.

[0111] In functionality-based LCM, the network indicates activation / deactivation / fallback / switching of AI / ML functionality via 3GPP signaling (e.g., RRC, radio resource control, MAC-CE, Medium Access Control-Control element; DCI, Downlink control information). Models may not be identified at the network, and the UE may perform model-level LCM. Whether and how much awareness / interaction the NW should have about model-level LCM will be studied. For functionality identification, there may be either one or more than one Functionalities defined within an AI / ML-enabled feature, whereby AI / ML-enabled feature refers to a feature where AI / ML may be used.

[0112] For AI / ML functionality identification and functionality-based LCM of UE-side models and / or UE-part of two-sided models, functionality refers to an AI / ML- enabled feature / FG (feature group) enabled by configuration(s), where configuration(s) is (are) supported based on conditions indicated by UE capability. Correspondingly, functionality-based LCM operates based on, at least, one configuration of AI / ML-enabled feature / FG or specific configurations of an AI / ML-enabled feature / FG.

[0113] In model-ID-based LCM, models are identified at the network, and the network / UE may activate / deactivate / select / s witch individual AI / ML models via model ID.

[0114] For AI / ML model identification and model-ID-based LCM of UE-side models and / or UE-part of two-sided models, model-ID-based LCM operates based on identified models, where a model may be associated with specific configurations / conditions associated with UE capability of an AI / ML-enabled Feature / FG and additional conditions (e.g., scenarios, sites, and datasets) as determined / identified between the UE-side and NW- side.

[0115] From a RAN 1 perspective, an AI / ML model identified by a model ID may be logical, and how it maps to physical AI / ML model(s) may be up to implementation. When distinction is necessary for discussion purposes, companies may use the term a logical AI / ML model to refer to a model that is identified and assigned a model ID, and physical AI / ML model(s) to refer to an actual implementation of such a model.

[0116] Artificial Intelligence and Machine Learning (AIML) models have been extensively studied for various use cases in wireless communication systems, particularly since Rel-18 in the 3GPP TR 38.843. Key use cases include Channel State Information (CSI) enhancement, which encompasses CSI prediction and CSI compression, beam management,and positioning accuracy enhancements. Different types of AIML models, such as Multilayer Perceptrons (MLP), Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Transformer-based networks (TF), have been applied to these use cases, resulting in significant performance gains. For CSI prediction, AIML models (as an AIML functionality) predict future channel states based on past and present CSI information, improving resource allocation and reducing latency. For CSI compression, the UE uses AIML encoders (as an AIML functionality) to compress the estimated downlink channel and reports the quantized approximation of it to the gNB, where the AIML decoder (as an AIML functionality) at the gNB dequantizes and recovers the codeword back to the original information. In beam management, AIML models (as an AIML functionality) assist in selecting the optimal beams and mitigating interference with the least number of beam measurements. For positioning accuracy, AIML models (as an AIML functionality) can be used either directly providing user positioning or assisting in positioning to refine user location for improved accuracy.

[0117] Now that technical context has been described, problems in these areas are described. In the native NR (new radio) positioning, the UE is requested to report positioning measurements such as timing (e.g., RSTD, UE Rx-Tx time difference), carrier phase, RSRP, and RSRPP. The location server uses the reported measurements to estimate the UE location. Which measurements are used for the actual location estimation is up to the LMF implementation. In NR Rel-18, an extensive study on AIML-based positioning shows a potential of AIML technique, which lead to introduce the Rel-19 NR positioning work item.

[0118] The accuracy enhancement and overhead reduction are critical issues of AIML positioning. There are ongoing discussions about model selection, model indication, functionality indication and so forth for the goal. For the positioning purpose, it is necessary to use many TRPs / gNBs (transmission-reception points / gNode Bs). In NR, the LMF can configure up to 64 TRPs for positioning. In order for the optimal location estimation, the location estimation from all of the possible combinations of 64 TRPs such as K(>3) out of 64 TRPs should be performed. It is too complicated to perform an exhaustive search as it needs exhaustive search for all K.

[0119] Examples herein address these problems. An overview is provided now. By taking advantage of an AIML technique, it may be effectively possible to perform location estimation with 64 TRPs, and it is proposed to have an AIML functionality association depending on, e.g., a relative location / distance between a UE and TRP groups.For instance, a UE is initially configured with multiple AIML functionalities. When the UE is configured to generate a measurement with the different TRP groups, the network also provides the criteria to select (e.g., and activate) a suitable AIML functionality to process the received signal from each TRP group. To this end, the UE acquires the positioning measurements from the TRP groups and applies criteria to select the AIML functionality for each TRP group. The acquired positioning measurements are also used as the input of the selected AIML functionality to generate the final positioning measurements. Consequently, the UE may send a report on the AIML-generated positioning measurements.

[0120] In terms of the AI / ML functionality, the term “AI / ML functionality” is mainly used herein, and this term is intended to cover at least the following: (i) functionality that is performed by a single model or multiple models that implement the functionality; (ii) an AI / ML-enabled feature or feature group that perform the functionality; and / or model ID(s) of model(s) (identifications) that perform the functionality, where the UE may activate / deactivate / select / switch individual AI / ML functionality via model ID. For instance, for positioning, the AI / ML functionality may include measurements of received signals to be used in an estimate of location of a UE position within a network. This AI / ML functionality may be performed by a single model. There may, however, be multiple models that meet the requirements for the AI / ML functionality, and any of these models individually could be used. Alternatively, there could also be multiple models that together determine the measurements used for UE position within a network. These multiple models may implement the AI / ML functionality. This may be extended to use of model IDs, e.g., where a unique ID is used to identify each model. If a single model with a unique ID is used, the single model would perform the AI / ML functionality. Any of the models or functionality may be performed by one or more neural networks, as an example of AI / ML that could be used. In case multiple AIML models are used to implement a functionality, a functionality ID may be associated with the multiple AIML model IDs.

[0121] In terms of TRPs, a TRP is a device that communicates with a UE and produces a cell under control of another device (such as a CU, central unit, of a gNB), and performs the operations described herein. As described below, TRPs may be one part of a functional split of a base station like a gNB.

[0122] Now that an overview has been provided, more details are provided. A method of association / switching between TRP (Transmission and Reception Point) groups and AIML functionalities is described. Refer to FIG. 1 , which is a signaling diagram used toexplain a method of generalization of AIML based positioning. FIG. 1 shows a UE 10, network location element a TRP 70, and an LMF 99-1, which is one possible version of a network location element 110. The UE 10 is connected to the TRP 70 in this example, and through the TRP 70 to the LMF 99-1.

[0123] I. Step 1) The network initiates location estimation. This step includes an information exchange between a TRP 70 and a network 1 , particularly a network location element 110, such as the LMF 99-1 that is shown, or a location server, or a sensing server, whichever element is in charge of location estimation of a specific UE 10.

[0124] II. Step 2) The network location element 110 (e.g., LMF 99-1, location server, or sensing server, or other element in charge of location estimation of a specific UE) provides the configuration required for positioning (e.g., location estimation) such as downlink RS (reference signal) resource configuration for positioning, and TRP information associated with DL PRS (positioning reference signal).

[0125] III. Step 3) TRP-group-based AIML functionality

[0126] a) The network 1 provides the UE 10 with information on grouping of TRPs. Many TRPs (up to 64 in NR) are divided into multiple groups, and a specific AIML functionality is used for each TRP group in an example. More specifically, the UE 10 is configured with TRP group information and is provided with which applicable AIML functionality should be associated with each TRP group and with a criterion used to select between functionalities for the corresponding groups. It is noted that this may also be generalized to providing applicable AIML functionalities for TRP groups. Also, this assumes that one criterion is used per TRP group to select an AIML functionality for that group, but it is possible to have multiple criteria (see block 107) per TRP group to select an AIML functionality for that group, and it is possible to select multiple AIML functionalities for individual groups.

[0127] It should be noted that this does not mean an AIML functionality is fixed for a specific TRP group. Instead, the AIML functionality for a specific TRP may change.

[0128] b) The network 1 may provide the UE 10 with multiple AIML functionalities, and one of the functionalities is used for each TRP group. A criterion may be provided (as in Step 3) to select a functionality from multiple AIML functionalities for each TRP. The UE 10 may be configured with a functionality switching criterion for each TRP group. For example, the UE may be configured to select an AIML functionality for a specific TRP group according to a detected physical cell ID, cell portion ID, and / or input parameterfor AIML functionalities. See Step 3.1, where the UE performs selecting an AIML functionality) for each TRP group based on the provided criterion.

[0129] 1) Consider Example #1. Refer to FIGS. 2A and 2B, which show an illustrative example of functionality associations for TRP groups and corresponding configurations used as the UE starts in cell #1 (FIG. 2A), where it is connected originally, and moves to cell #2 (FIG. 2B), to which the UE connects, e.g., after handover. These figures involve a group #1 220-1 of TRPs 70 (TRP 70-1; TRP 70-2; TRP 70-3; and TRP 70-4) and a group #2 220-2 of TRPs 70 (TRP 70-5; TRP 70-6; TRP 70-7; and TRP 70-8). In FIG. 2A, the UE 10 is in and connected to cell #1 210-1, formed by the group #1 220-1 of TRPs, and moving along path 250 toward cell #2 210-2, formed by the group #2 220-2 of TRPs. The cells 210-1 and 210-2 are illustrated as being distinguished by an edge 205. The UE 10 uses configuration 230-1 while in cell #1 210-1. FIG. 2B illustrates that the UE 10, after following path 250, is now in cell #2 210-2 and uses configuration 230-2 while in cell #2.

[0130] In this figure, Cell #1 210-1 is a physically single cell, and Cell #2 210-2 is a physically single cell. A corresponding gNB 71 has a functional split into a central unit (CU) 69 and each group 220 of TRPs 70, interconnected using a “fronthaul” interface 14. Cell #1 210-1 corresponds to gNB #1 71-1, which is functionally split into the CU 69-1 and the group #1 220-1 of TRPs 70 (TRP 70-1; TRP 70-2; TRP 70-3; and TRP 70-4), where the TRPs 70-1 through 70-4 are connected to the CU #1 69-1 via fronthaul interface 14-1. Similarly, Cell #2 210-2 corresponds to gNB #2 71-2, which is functionally split into the CU 69-2 and the group #2 220-2 of TRPs 70 (TRP 70-5; TRP 70-6; TRP 70-7; and TRP 70-8), where the TRPs 70-5 through 70-8 are connected to the CU #2 69-2 via fronthaul interface 14-2. Depending on implementation, the nomenclature may change. For example, in 5G, the terms CU / DU (central unit / distributed unit), where DU is being referred to as a TRP herein. In LTE (long-term evolution), the CU may be referred to as BBU (base band unit) and the TRP may be referred to as an RRH (remote radio head).

[0131] From the UE’s perspective, a TRP 70 is transparent in this example for data communication. Other than positioning functionality, the UE 10 may not be not provided with TRP information. The gNB 71 can transmit signals from any TRP 70 (in a corresponding group 220), but the gNB 71 does not inform which TRPs transmitted the signals. For example, assume that the UE 10 receives a PDSCH (physical downlink shared channel) from the gNB. The gNB 71 can use TRPs 70-1 / 2 / 3 / 4 in group #1, but the PDSCH is from physical cell #1. The UE, in this example, cannot tell which TRP transmitted.

[0132] The UE 10 may be configured to switch / select AIML functionality of TRP group#l and TRP group #2 depending on the location of UE. The UE may be unable to know its location by itself, but the UE can obtain the cell information.

[0133] i) The UE 10 is configured (via configuration 230-1 in FIG. 2 A) to use AIML functionality #A for group #1 220-1 and AIML functionality #B for group #2 220-2 when the UE is in cell #1.

[0134] ii) The UE 10 is configured (via configuration 230-2 in FIG. 2B) to use AIML functionality #A for group #2 220-2 and AIML functionality #B for group #1 220-1 when the UE is in cell #2 210-2.

[0135] 2) Consider Example #2. The network 1 may configure a criterion using a fingerprinting technique-based AIML functionality selection and subsequent switching between AIML functionality, e.g., based on a criterion. In this example, for simplicity, it is assumed there is a scenario where a group 220 of TRPs 70 is closely located as shown in FIGS. 2 A and 2B . Depending on the measurement values, the network 1 has information on rough UE location. That is, the network may have already made a map between locations / coordinates and measurement value ranges. For example, the network may configure the criterion of the configuration 230 as follows.

[0136] i) RSRP measurement range from XI to X2 (>X1) is associated with AIML functionality #A.

[0137] ii) RSRP measurement range from X3(>X2) to X4 (>X3) is associated with AIML functionality #B.

[0138] iii) Angle measurement range from Z1 to Z2 is associated with functionality #C.

[0139] iv) Angle measurement range from Z3 to Z4 is associated with functionality #D.

[0140] v) For specific positioning measurements for 64 TRPs, the network 1 may provide a map between AIML functionalities and measurement values. For a specific TRP group, in case the UE obtains RSRP measurements ranging from XI to X2, the associated AIML functionality #A is triggered as per the map. For instance, consider the following: Range 1 = model A; Range 2 = model B; and Range 3 = model C. Then if the RSRP measurements ranging from XI to X2 fit within Range 2, model B may be chosen.

[0141] For the angle measurement ranges, consider the following Angle measurements can be defined as the estimated azimuth angle and vertical angle of atransmitter (e.g., UE or gNB / TRP) with respect to a reference direction, wherein the reference direction is defined. One option is the global coordinate system (GCS), wherein estimated azimuth angle is measured relative to geographical North and is positive in a counter-clockwise direction and estimated vertical angle is measured relative to zenith and positive to horizontal direction. Another option is the local coordinate system (LCS), wherein estimated azimuth angle is measured relative to x-axis of LCS and positive in a counterclockwise direction and estimated vertical angle is measured relative to z-axis of LCS and positive to x-y plane direction. The bearing, downtilt and slant angles of LCS are defined according to 3GPP TS 38.901. Thus, the relationships between Zl, Z2, Z3, and Z4 can depend on the particular techniques for measuring the angles.

[0142] These are examples, and other examples are possible. For instance, the configuration may include RSRPP measurement range to select the individual TRP group; and / or timing measurement range to select the individual TRP group.

[0143] A simple example is illustrated by block 270-1 in FIG. 2A, where the criterion (or criteria) could be RSRP that is within a range or less than a threshold so that the UE 10 determines the distance of TRP group #1 220-1 is less than the distance of TRP group #2 220-2, and the configuration 230-1 is selected. Propagation time may be alternatively or additionally used, e.g., a propagation time less than a threshold (or within a range) so that the UE 10 determines the distance of TRP group #1 220-1 is less than the distance of TRP group #2 220-2, and the configuration 230-1 is selected. Consider block 270-2 in FIG. 2B, where the criterion (or criteria) could be RSRP that is within a range or less than a threshold so that the UE 10 determines the distance of TRP group #2 220-2 is less than the distance of TRP group #1 220-1, and the configuration 230-2 is selected. Propagation time may be alternatively or additionally used, e.g., a propagation time less than a threshold (or within a range) so that the UE 10 determines the distance of TRP group #2 220-2 is less than the distance of TRP group #1 220-1, and the configuration 230-2 is selected.

[0144] In Step 3.2, the TRP 70 sends PRS(s) to the UE 10. The PRS(s) will be analyzed by the UE to provide, e.g., positioning measurements.

[0145] IV. Step 4) Turning back to FIG. 1, the UE 10 receives reference signals configured for location estimation from each (TRP in each) TRP group. The UE, based on the received reference signals, determines positioning measurements.

[0146] V. Step 5) The UE uses the received signals from each TRP group as an input for the associated / selected AIML functionality for each TRP groups. Specifically, theUE performs running AIML functionality for each TRP group to generate PRS-based measurements.

[0147] a) For example, the functionality #A may be designed for TRP groups 220 based on distance, such as TRP groups 220 which are very close to the UE. For example, from the TRP groups 220, if the UE obtains RSRP measurements which are greater than a specific threshold value, the UE can determine the TRP groups 220 that have a distance determined to be very close. Similarly, if the UE obtains RSRP measurements less than another threshold value, the UE can determine the TRP groups that have a distance that are far away. Those two threshold values may be provided by the network. In this case, the UE may be able to obtain higher quality received signals than those than from another group. The functionality #B may be designed for TRP groups 220 that are far away in terms of distance, or functionality #B may be designed considering blockage between the TRPs and the UE. In terms of TRP groups 220, a distance for a group could be based on RSRP measurements (or another criterion) of any one of the TRPs 70 in the group 220, especially if the individual TRPs 70 in the group 220 are unknown to the UE. That is, if there are two groups 220-1 and 220-1 (as in FIG. 2 A for instance), the UE 10 could select Functionality #A for TRP group 220-2 based on the RSRP meeting a threshold for signals from the group 220-1 (e.g., from TRP 70-3), and thus meeting a distance (e.g., “close”) for the group 220-1; meanwhile, the UE could select Functionality #B for TRP 220-2 based on the RSRP not meeting a threshold for the TRP group 220-2 (e.g., signals from TRP 70-7), and thus not meeting a distance (e.g., “close”) for the group 220-2 (or, alternatively, meeting a distance, e.g., of “too far”). Another option for distance estimation is the UE can determine rough distance based on estimation of propagation time of downlink reference signals. So, distance is roughly measured on propagation time, and a criterion can be set for propagation time to determine “close” groups 220 (via signals from their corresponding TRP(s) 70) or “far” groups 220 (and their corresponding TRP(s) 70).

[0148] b) The AIML functionality output includes at least positioning measurements in an example for the best location estimation. For example, the number of output measurements of the different AIML functionality would be different. In NR, the maximum number of TRPs is 64. The AIML functionality may decide how many measurements and which measurements will be used. For example, without the help of the AIML functionality, if one assumes use of 8 TRPs is the best, the number of the possible cases are the combinations of 8 out of 64, thus requiring too high a complexity to find thebest combination. Furthermore, if using 8 TRPs is not the best option, the UE should find the best number of measurements given the obtained measurement.

[0149] c) Also, an additional information such as blockage surrounding buildings or expected NLoS probability for a certain group could be an input of the AIML functionality. Depending on the input, the number of output measurements would be different.

[0150] VI. Step 6) Once the AIML functionality provides the measurements, the UE reports the measurements to the LMF 99-1 (e.g., as part of the network 1). The UE informs that the reported measurements are the best combination of measurements based on the AIML functionalities. The LMF 99-1 would use the received measurements for determining location of the UE within the network 1. Although not shown in the figure, the LMF 99-1 performs estimation of the location of the UE with the provided positioning measurements. This process for doing this is completely up to the LMF implementation.

[0151] Note that at least the received reference signals from each group are the input of each AIML functionality. For example, AIML functionality #A is designed to obtain the best measurements from a close TRP group 220 which is closer to the target UE, but AIML functionality #B may be designed to obtain the best measurements from a TRP group 220 which is relatively far from the target UE. The AIML functionalities #A and #B provide output which includes the measurements for the best location estimation. Then these outputs are input for a functionality of the optimal estimation of location.

[0152] Referring to FIG. 3, this figure is a block diagram of an example of a proposed UE behavior 300 for the method of FIG. 1 , and provides a detailed description of possible UE behavior 300 of the proposed method of FIG. 1. The UE receives positioning reference signals (PRSs) 310-1 and 310-2 from TRPs in the TRP group #1 220-1 and TRP group #2 220-2 and uses the received PRSs as input to AIML functionality #A 320-1 and #B 320-2 according to the association (e.g., defined by configuration 230) between the TRP groups and AIML functionality. The received signals correspond to Step 4 of FIG. 1. The AIML functionality #A 320-1 and #B 320-2 are run, which corresponds to Step 5 of FIG.1. The output 325-1, 325-2 of each AIML functionality 320-1, 320-2, respectively, includes positioning measurements. That is, each AIML functionality provides output 325-1, 325-2 of measurements, and the output 325 of the overall AIML functionalities is the input for the next functionality 330 on optional estimation of location of the UE within the network 1. The functionality 330 may be implemented by a model(s), e.g., using a neural network (NN) orNNs. The output 340 of this functionality 330 could be estimated location (or measurements). If the UE is provided with TRP / gNB locations from the network, the UE is able to estimate its own location based on the obtained measurements. There are two different modes: (1) UE- assisted positioning, where the LMF calculates UE location based on measurement information; or (2) UE-based positioning, where the UE calculates its own location by using obtained measurements. As one example, the number of input measurements could be X and the final output measurements could be Y (Y<X). This functionality 330 determines how many measurements and which measurements could be optimal. Ideally, all combinations of the available measurements should be considered to find the optimal combination of the measurements. The final output 340 (and possibly 325) is the information that the UE should report, e.g., via Step 6 of FIG. 1.

[0153] Turning to FIG. 4, this figure shows a block diagram of one possible and non-limiting example of a cellular network 1 that is connected to a user equipment (UE) 10. A number of network elements are shown in the cellular network of FIG. 4: a TRP 70; and a core network 90.

[0154] In FIG. 4, a user equipment (UE) 10 is in wireless communication via radio link 11 with the gNB 71 via a TRP 70 of the cellular network 1. A UE 10 is a wireless communication device, such as a mobile device, that is configured to access a cellular network. The UE 10 is illustrated with one or more antennas 28. The ellipses 2 indicate there could be multiple UEs 10 in wireless communication via radio links with the TRP 70 (or another TRP of the gNB 71). The UE 10 includes one or more processors 13, one or more memories 15, and other circuitry 16. The other circuitry 16 includes one or more receivers (Rx(s)) 17 and one or more transmitters (Tx(s)) 18. A program 12 is used to cause the UE 10 to perform the operations described herein. For a UE 10, the other circuitry 16 could include circuitry such as for user interface elements (not shown) like a display. The program 12 may be implemented via instructions stored in memory / memories 15 and executed by processor(s) 13, or by circuitry such being implemented as part of the processor(s) or other circuitry elements, or both.

[0155] The gNB 71, as a network element of the network 1 (e.g., a cellular network), provides the UE 10 access to network 1 and to the data network 91 via the core network 90 (e.g., via a user plane function (UPF) of the core network 90). As such, the gNB 71 may be considered to be an access node, which provides access by UE(s) 10 to the network 1. The gNB 71 may also be considered to be a base station, which is a maincommunication point for the UE. This example uses the functional split previously described, where the gNB 71 is split into a CU 69 and one or more TRPs 70. The CU 69 includes one or more processors 73, one or more memories 75, and other circuitry 76. The other circuitry 76 includes one or more receivers (Rx(s)) 77 and one or more transmitters (Tx(s)) 78. A program 72 is used to cause the CU 69 to perform the operations described herein. The program 72 may be implemented via instructions stored in memory / memories 75 and executed by processor(s) 73, or by circuitry such being implemented as part of the processor(s) or other circuitry elements, or both.

[0156] The TRP 70 is assumed to have a program 72 (and corresponding instructions), one or more processors 73, one or more memories 75, and other circuitry 76, e.g., wireless receivers 77 and transmitters 78 to communicate using the radio link 11 through the one or more antennas 58.

[0157] It is noted that the TRP 70 may instead be implemented via other wireless technologies, such as Wi-Fi (a wireless networking protocol that devices use to communicate without direct cable connections). In the case of Wi-Fi, the link 11 could be characterized as a wireless link. The program 72 is used to cause the TRP 70 to perform the operations described herein. The program 72 may be implemented via instructions stored in memory / memories 75 and executed by processor(s) 73, or by circuitry such being implemented as part of the processor(s) or other circuitry elements, or both.

[0158] Two or more gNBs 71 communicate using, e.g., link(s) 79, which are controlled by the CU 69 in this example. The link(s) 79 may be wired or wireless or both and may implement, e.g., an Xn interface for 5G (fifth generation), an X2 interface for UTE (Fong Term Evolution), or other suitable interface for other standards. This is often referred to as a “backhaul” link.

[0159] The network 1 may include a core network 90, as a second network element or elements, that may include core network functionality, and which provide connectivity via a link or links 81 with a data network 91, such as a telephone network and / or a data communications network (e.g., the Internet). The core network 90 includes one or more processors 93, one or more memories 95, and other circuitry 96. The other circuitry 96 includes one or more receivers (Rx(s)) 97 and one or more transmitters (Tx(s)) 98. A program 92 is used to cause the core network 90 to perform the operations described herein. The program 92 may be implemented via instructions stored in memory / memories 95 andexecuted by processor(s) 93, or by circuitry such being implemented as part of the processor(s) or other circuitry elements, or both.

[0160] The core network 90 could be a 5GC (5G core network). The core network 90 can implement or comprise multiple network functions (NF(s)) 99, and the program 92 may comprise one or more of the NFs 99. A 5G core network may use circuitry such as memory and processors, which may implement a virtualization layer. It could be a single standalone computing system, a distributed computing system, or a cloud computing system. The NFs 99, as network elements, of the core network could be containers or virtual machines running on the circuitry of the computing system(s) making up the core network 90.

[0161] This example has a network location entity 110 that could be an LMF 99- 1 , location server, or sensing server, or other element in charge of location estimation of a specific UE. The LMF 99-1 is a network function (NF). The location server, or sensing server, or other element could be part of the core network 90 but, e.g., not as an NF.

[0162] Core network functionality for 5G may include access and mobility management functionality that is provided by a network function 99 such as an access and mobility management function (AMF), session management functionality that is provided by a network function such as a session management function (SMF). Core network functionality for access and mobility management in an LTE (Long Term Evolution) network may be provided by an MME (Mobility Management Entity) and / or SGW (Serving Gateway) functionality, which routes data to the data network. Many others are possible, as illustrated by the examples in FIG. 4: AMF; SMF; MME; SGW; GMLC (Gateway Mobile Location Center); LMF (Location Management Function) 99-1; UDM (Unified Data Management) / UDR (Unified Data Repository); NRF (Network Repository Function); and / or E-SMLC (Evolved Serving Mobile Location Center). These are merely exemplary core network functionality that may be provided by the core network 90, and note that both 5G and LTE core network functionality might be provided by the core network 90. The TRP 70 is coupled via a backhaul link 31 to the core network 90. The TRP 70 and the core network 90 may include an NG (Next Generation) interface for 5G, or an SI interface for LTE, or other suitable interface for other radio access technologies for communicating via the backhaul link 31.

[0163] In the data network 91, there are instructions 94 stored in a computer- readable storage medium 4-1, which could be circuitry such as long-term memory such as ahard drive or a solid-state drive, a short-term memory such as dynamic random-access memory, or a combination of both (e.g., reading from long-term memory for temporary placement into short-term memory and subsequent downloading). The computer-readable medium 4-1 contains instructions 94 that, when downloaded and installed into the programs 12, 72, and 92 and / or memories 15, 75, or 95 of the corresponding UE 10, base station 70, and / or core network element(s) 90, and executed by processor(s) 13, 73, or 93, cause the respective device to perform corresponding actions described herein. The computer-readable storage medium 4 may be implemented in other forms, such as via instructions 94 on a compact disc (as a computer-readable storage medium 4-2) or a memory stick.

[0164] The programs 12, 72, and 92 contain instructions (as part of a corresponding program 12, 72, and 92) stored by corresponding one or more memories 15, 75, or 95. These instructions, when executed by the corresponding one or more processors 13, 73, or 93, cause the corresponding apparatus 10, 70, or 90, to perform the operations described herein. The computer readable memories 15, 75, or 95 are circuitry and may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, firmware, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The processors 13, 73, and 93, are circuitry and may be of any type suitable to the local technical environment. For example, these processors may include one or more of general-purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), processors based on a multicore processor architecture, and may also include specialized circuits such as field- programmable gate arrays (FPGAs), application specific circuits (ASICs), signal processing devices and other devices, or combinations of these devices, as non-limiting examples. The processors 13, 73, and 93 are circuitry that can be programmed to perform functions via software, firmware or the like (including microcode), but are not solely software.

[0165] The receivers 17, 77, and 97, and the transmitters 18, 78, and 98 may implement wired or wireless interfaces. The receivers and transmitters may be grouped together as transceivers.

[0166] The network 1 may implement network virtualization, which is the process of combining circuitry and software network resources and network functionality into a single, software-based administrative entity, a virtual network. Network virtualization involves platform virtualization, often combined with resource virtualization. Networkvirtualization is categorized as either external, combining many networks, or parts of networks, into a virtual unit, or internal, providing network-like functionality to software containers on a single system. Note that the virtualized entities (such as network functions 99) that result from the network virtualization are still implemented, at some level, using circuitry such as processors 73 and / or 93 and memories 75 and / or 95, and also such virtualized entities create technical effects.

[0167] In general, the various embodiments of the user equipment 10 can include, but are not limited to, devices implementing cellular technologies (such as smart phones, mobile phones, cellular phones, voice over Internet Protocol (IP) (VoIP) phones, and / or wireless local loop phones), tablets, portable computers, vehicles or vehicle-mounted devices for, e.g., wireless V2X (vehicle-to-everything) communication, image capture devices such as digital cameras, gaming devices, music storage and playback appliances, Internet appliances (including Internet of Things, loT, devices), loT devices with sensors and / or actuators for, e.g., automation applications, as well as portable units or terminals that incorporate combinations of such functions, laptop-embedded equipment (LEE), laptopmounted equipment (LME), Universal Serial Bus (USB) dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. That is, the UE 10 could be any end device that may be capable of wireless communication. By way of example rather than limitation, the UE may also be referred to as a communication device, terminal device (MT), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT).

[0168] Without in any way limiting the scope, interpretation, or application of the claims appearing below, a technical effect and / or advantage of one or more of the example embodiments disclosed herein is that the positioning accuracy performance can be improved, e.g., (e.g., optimal) measurements could be selected to be reported by the AIML. Another technical effect and / or advantage of one or more of the example embodiments disclosed herein is examples reduce measurement reporting overhead, as only certain (e.g., optimal) measurements are reported. The redundant measurements may be filtered out before the UE reports them.

[0169] The following are additional examples.

[0170] Example 1. A method, comprising: receiving, at a user equipment from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, by the user equipment at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining, by the user equipment, positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting, by the user equipment, the determined positioning measurements.

[0171] Example 2. The method according to example 1, wherein the configuration comprises information instructing the user equipment to select an AIML functionality of the multiple AIML functionalities for a specific one of the multiple TRP groups based on a cell to which the user equipment is connected.

[0172] Example 3. The method according to example 2, wherein the information comprises information associating individual TRP groups with corresponding AIML functionality, of the multiple AIML functionalities, to be performed for the individual TRP group.

[0173] Example 4. The method according to example 3, wherein the information associating individual TRP groups with corresponding AIML functionality uses cell identification to which the user equipment is connected to associate the corresponding AIML functionality with an individual TRP group.

[0174] Example 5. The method according to example 1, wherein the configuration comprises information instructing the user equipment to select an AIML functionality for a specific one of the multiple TRP groups based on provided information associating reference signal received power (RSRP) measurements from a cell corresponding to individual TRP groups with corresponding individual AIML functionality, of the multiple AIML functionalities, to be performed for the corresponding TRP group.

[0175] Example 6. The method according to example 5, wherein the individual AIML functionality is indicated by an identifier.

[0176] Example 7. The method according to example 1, wherein the configuration comprises at least one of the following for individual ones of the multiple TRP groups: RSRP measurement range to select tan individual one of the multiple TRP groups; RSRPP measurement range to select an individual one of the multiple TRP groups; timing measurement range to select an individual one of the multiple TRP groups; or angle measurement range to select an individual one of the multiple TRP groups.

[0177] Example 8. The method according to example 1, wherein: the configuration comprises indication of location based on information linking one or more cells created to individual ones of the one or more TRP groups and indication of associated functionality; and selecting the AIML functionality for a TRP group is performed dependent on which of the one or more TRP groups has a cell in which the user equipment is connected.

[0178] Example 9. The method according to example 1, wherein: the configuration comprises indication of individual distances between an estimate of location of the user equipment and of individual TRP groups and corresponding indication of associated functionality for the individual distances; and selecting the AIML functionality for a TRP group is performed dependent on the individual distances between the user equipment and individual TRP groups.

[0179] Example 10. The method according to example 1, wherein the configuration comprises at least one of the following: RSRP measurement range from XI to X2 (>X1) for a TRP group is associated with a first of the multiple AIML functionalities; RSRP measurement range from X3(>X2) to X4 (>X3) for a TRP group is associated with a second of the one or more AIML functionalities; angle measurement range from Z1 to Z2 for a TRP group is associated with a third of the multiple AIML functionalities; angle measurement range from Z3 to Z4 for a TRP group is associated with a fourth of the multiple AIML functionalities; or for specific positioning measurements for multiple TRP groups, a map between AIML functionality and corresponding measurement values is to be used and for a specific TRP group, in case the user equipment obtains RSRP measurements ranging from XI to X2, an associated AIML functionality is selected based on the map.

[0180] Example 11. The method according to any of examples 2 to 6, wherein: the selecting comprises selecting individual AIML functionality for at least two TRP groups; the method further comprises running, by the user equipment, the individual AIML functionality for individual TRP groups of the at least two TRP groups to select a part of thepositioning measurements; and the reporting comprises reporting indications of the positioning measurements.

[0181] Example 12. The method according to example 1 to 11, wherein: the selecting comprises selecting individual AIML functionality for at least first and second TRP groups; the determining positioning measurements to be reported to the network at least based on the selected AIML functionality further comprises: receiving signals from the first and second TRP groups; performing, using the received signals from the first TRP group, a first artificial intelligence or machine learning functionality to determine a first output; performing, using the received signals from the second TRP group, a second artificial intelligence or machine learning functionality to determine a second output; and performing functionality on estimation of location using the first and second outputs to determine one of measurements or estimated location; and the reporting comprises reporting the one of the measurements or the estimated location.

[0182] Example 13. A method, comprising: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

[0183] Example 14. The method according to example 13, wherein the received positioning measurements comprise one or both of measurements from the TRPs or estimated location.

[0184] Example 15. An apparatus, comprising means for: receiving, from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signalsreceived from individual ones of the multiple TRP groups; determining positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting the determined positioning measurements.

[0185] Example 16. The apparatus according to example 15, wherein the configuration comprises information instructing the apparatus to select an AIML functionality of the multiple AIML functionalities for a specific one of the multiple TRP groups based on a cell to which the apparatus is connected.

[0186] Example 17. The apparatus according to example 16, wherein the information comprises information associating individual TRP groups with corresponding AIML functionality, of the multiple AIML functionalities, to be performed for the individual TRP group.

[0187] Example 18. The apparatus according to example 17, wherein the information associating individual TRP groups with corresponding AIML functionality uses cell identification to which the apparatus is connected to associate the corresponding AIML functionality with an individual TRP group.

[0188] Example 19. The apparatus according to example 15, wherein the configuration comprises information instructing the apparatus to select an AIML functionality for a specific one of the multiple TRP groups based on provided information associating reference signal received power (RSRP) measurements from a cell corresponding to individual TRP groups with corresponding individual AIML functionality, of the multiple AIML functionalities, to be performed for the corresponding TRP group.

[0189] Example 20. The apparatus according to example 19, wherein the individual AIML functionality is indicated by an identifier.

[0190] Example 21. The apparatus according to example 15, wherein the configuration comprises at least one of the following for individual ones of the multiple TRP groups: RSRP measurement range to select tan individual one of the multiple TRP groups; RSRPP measurement range to select an individual one of the multiple TRP groups; timing measurement range to select an individual one of the multiple TRP groups; or angle measurement range to select an individual one of the multiple TRP groups.

[0191] Example 22. The apparatus according to example 15, wherein: the configuration comprises indication of location based on information linking one or more cells created to individual ones of the one or more TRP groups and indication of associatedfunctionality; and selecting the AIML functionality for a TRP group is performed dependent on which of the one or more TRP groups has a cell in which the apparatus is connected.

[0192] Example 23. The apparatus according to example 15, wherein: the configuration comprises indication of individual distances between an estimate of location of the apparatus and of individual TRP groups and corresponding indication of associated functionality for the individual distances; and selecting the AIML functionality for a TRP group is performed dependent on the individual distances between the apparatus and individual TRP groups.

[0193] Example 24. The apparatus according to example 15, wherein the configuration comprises at least one of the following: RSRP measurement range from XI to X2 (>X1) for a TRP group is associated with a first of the multiple AIML functionalities; RSRP measurement range from X3(>X2) to X4 (>X3) for a TRP group is associated with a second of the one or more AIML functionalities; angle measurement range from Z1 to Z2 for a TRP group is associated with a third of the multiple AIML functionalities; angle measurement range from Z3 to Z4 for a TRP group is associated with a fourth of the multiple AIML functionalities; or for specific positioning measurements for multiple TRP groups, a map between AIML functionality and corresponding measurement values is to be used and for a specific TRP group, in case the apparatus obtains RSRP measurements ranging from XI to X2, an associated AIML functionality is selected based on the map.

[0194] Example 25. The apparatus according to any of examples 16 to 20, wherein: the selecting comprises selecting individual AIML functionality for at least two TRP groups; the means are further configured for running the individual AIML functionality for individual TRP groups of the at least two TRP groups to select a part of the positioning measurements; and the reporting comprises reporting indications of the positioning measurements.

[0195] Example 26. The apparatus according to example 15 to 25, wherein: the selecting comprises selecting individual AIML functionality for at least first and second TRP groups; the determining positioning measurements to be reported to the network at least based on the selected AIML functionality further comprises: receiving signals from the first and second TRP groups; performing, using the received signals from the first TRP group, a first artificial intelligence or machine learning functionality to determine a first output; performing, using the received signals from the second TRP group, a second artificial intelligence or machine learning functionality to determine a second output; and performingfunctionality on estimation of location using the first and second outputs to determine one of measurements or estimated location; and the reporting comprises reporting the one of the measurements or the estimated location.

[0196] Example 27. An apparatus, comprising means for: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

[0197] Example 28. The apparatus according to example 27, wherein the received positioning measurements comprise one or both of measurements from the TRPs or estimated location.

[0198] Example 29. An apparatus, comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the apparatus at least to perform: receiving, from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting the determined positioning measurements.

[0199] Example 30. The apparatus according to example 29, wherein the configuration comprises information instructing the apparatus to select an AIML functionality of the multiple AIML functionalities for a specific one of the multiple TRP groups based on a cell to which the apparatus is connected.

[0200] Example 31. The apparatus according to example 30, wherein the information comprises information associating individual TRP groups with corresponding AIML functionality, of the multiple AIML functionalities, to be performed for the individual TRP group.

[0201] Example 32. The apparatus according to example 31 , wherein the information associating individual TRP groups with corresponding AIML functionality uses cell identification to which the apparatus is connected to associate the corresponding AIML functionality with an individual TRP group.

[0202] Example 33. The apparatus according to example 29, wherein the configuration comprises information instructing the apparatus to select an AIML functionality for a specific one of the multiple TRP groups based on provided information associating reference signal received power (RSRP) measurements from a cell corresponding to individual TRP groups with corresponding individual AIML functionality, of the multiple AIML functionalities, to be performed for the corresponding TRP group.

[0203] Example 34. The apparatus according to example 33, wherein the individual AIML functionality is indicated by an identifier.

[0204] Example 35. The apparatus according to example 29, wherein the configuration comprises at least one of the following for individual ones of the multiple TRP groups: RSRP measurement range to select tan individual one of the multiple TRP groups; RSRPP measurement range to select an individual one of the multiple TRP groups; timing measurement range to select an individual one of the multiple TRP groups; or angle measurement range to select an individual one of the multiple TRP groups.

[0205] Example 36. The apparatus according to example 29, wherein: the configuration comprises indication of location based on information linking one or more cells created to individual ones of the one or more TRP groups and indication of associated functionality; and selecting the AIML functionality for a TRP group is performed dependent on which of the one or more TRP groups has a cell in which the apparatus is connected.

[0206] Example 37. The apparatus according to example 29, wherein: the configuration comprises indication of individual distances between an estimate of location of the apparatus and of individual TRP groups and corresponding indication of associated functionality for the individual distances; and selecting the AIML functionality for a TRP group is performed dependent on the individual distances between the apparatus and individual TRP groups.

[0207] Example 38. The apparatus according to example 29, wherein the configuration comprises at least one of the following: RSRP measurement range from XI to X2 (>X1) for a TRP group is associated with a first of the multiple AIML functionalities; RSRP measurement range from X3(>X2) to X4 (>X3) for a TRP group is associated with a second of the one or more AIML functionalities; angle measurement range from Z1 to Z2 for a TRP group is associated with a third of the multiple AIML functionalities; angle measurement range from Z3 to Z4 for a TRP group is associated with a fourth of the multiple AIML functionalities; or for specific positioning measurements for multiple TRP groups, a map between AIML functionality and corresponding measurement values is to be used and for a specific TRP group, in case the apparatus obtains RSRP measurements ranging from XI to X2, an associated AIML functionality is selected based on the map.

[0208] Example 39. The apparatus according to any of examples 30 to 34, wherein: the selecting comprises selecting individual AIML functionality for at least two TRP groups; the one or more memories further store instructions that, when executed by the one or more processors, cause the apparatus at least to perform running the individual AIML functionality for individual TRP groups of the at least two TRP groups to select a part of the positioning measurements; and the reporting comprises reporting indications of the positioning measurements.

[0209] Example 40. The apparatus according to example 29 to 39, wherein: the selecting comprises selecting individual AIML functionality for at least first and second TRP groups; the determining positioning measurements to be reported to the network at least based on the selected AIML functionality further comprises: receiving signals from the first and second TRP groups; performing, using the received signals from the first TRP group, a first artificial intelligence or machine learning functionality to determine a first output; performing, using the received signals from the second TRP group, a second artificial intelligence or machine learning functionality to determine a second output; and performing functionality on estimation of location using the first and second outputs to determine one of measurements or estimated location; and the reporting comprises reporting the one of the measurements or the estimated location.

[0210] Example 41. An apparatus, comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the apparatus at least to perform: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurementswhich includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

[0211] Example 42. The apparatus according to example 41, wherein the received positioning measurements comprise one or both of measurements from the TRPs or estimated location.

[0212] Example 43. A computer program, comprising instructions which, when the program is executed by an apparatus, cause the apparatus to carry out the methods of any of examples 1 to 14.

[0213] Example 44. The computer program according to example 44, wherein the computer program is a computer program product comprising a computer-readable medium bearing the instructions embodied therein for use with the apparatus.

[0214] Example 45. The computer program according to example 44, wherein the computer program is directly loadable into an internal memory of the apparatus.

[0215] As used in this application, the term “circuitry” may refer to one or more or all of the following:

[0216] (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and

[0217] (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) (including digital signal processor(s)) with software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and

[0218] (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.

[0219] 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 (ormultiple 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.

[0220] Embodiments herein may be implemented in software (executed by one or more processors), hardware (e.g., an application specific integrated circuit), or a combination of software and hardware. In an example embodiment, the software (e.g., application logic, an instruction set) is maintained on any one of various conventional computer-readable media. In the context of this document, a “computer-readable medium” may be any media or means that can contain, store, communicate, propagate or transport the instructions for use by or in connection with an instruction execution system, apparatus, or device, such as a computer, with one example of a computer described and depicted, e.g., in FIG. 4. A computer-readable medium may comprise a computer-readable storage medium (e.g., memories 15, 75, and 95 or other device) that may be any media or means that can contain, store, and / or transport the instructions for use by or in connection with an instruction execution system, apparatus, or device, such as a computer. A computer-readable storage medium does not comprise propagating signals, and therefore may be considered to be non- transitory. The term “non-transitory”, as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM, random access memory, versus ROM, read-only memory).

[0221] If desired, the different functions discussed herein may be performed in a different order and / or concurrently with each other. Furthermore, if desired, one or more of the above-described functions may be optional or may be combined.

[0222] Although various aspects of the invention are set out in the independent claims, other aspects of the invention comprise other combinations of features from the described embodiments and / or the dependent claims with the features of the independent claims, and not solely the combinations explicitly set out in the claims.

[0223] It is also noted herein that while the above describes example embodiments of the invention, these descriptions should not be viewed in a limiting sense. Rather, there are several variations and modifications which may be made without departing from the scope of the present invention as defined in the appended claims.

[0224] The following abbreviations that may be found in the specification and / or the drawing figures are defined as follows:

[0225] 5G fifth generation

[0226] 6G sixth generation

[0227] AIML or AL / ML Artificial Intelligence and Machine Learning

[0228] AMF access and mobility management function

[0229] BBU base band unit.

[0230] BM beam management

[0231] CDL clustered delay line

[0232] CN core network

[0233] CSI channel state information

[0234] CU central unit

[0235] DL downlink (from network to UE)

[0236] DU distributed unit

[0237] E-SMLC evolved serving mobile location center

[0238] eNB (or eNodeB) evolved Node B (e.g., an LTE base station)

[0239] FG feature group

[0240] GMLC Gateway Mobile Location Center

[0241] gNB (or gNodeB) base station for 5G / NR

[0242] I / F interface

[0243] LCM Life Cycle Management

[0244] LMF Location Management Function

[0245] LOS or LoS line of sight

[0246] LTE long term evolution

[0247] NLOS non-line of sight

[0248] MIMO Multiple Input and Multiple Output

[0249] MME mobility management entity

[0250] NF network function

[0251] ng or NG next generation

[0252] NN neural network

[0253] NR new radio

[0254] NRF Network Repository Function

[0255] N / W or NW network

[0256] OAM Operation, Administration, and Maintenance

[0257] PRS positioning reference signal

[0258] RAN radio access network

[0259] Rel release

[0260] RRH remote radio head

[0261] PRS Positioning reference signal

[0262] RS reference signal

[0263] RSRP Reference Signal Received Power

[0264] RSRPP reference signal received path power

[0265] RSTD Reference signal time difference

[0266] Rx receiver

[0267] SGW serving gateway

[0268] SMF session management function

[0269] TRP transmission-reception point

[0270] Tx transmitter

[0271] UDM unified data management

[0272] UDR unified data repository

[0273] UE user equipment (e.g., a wireless, typically mobile device)

[0274] UPF user plane function

Claims

What is claimed is:

1. An apparatus, comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the apparatus at least to perform: receiving, from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting the determined positioning measurements.

2. The apparatus according to claim 1, wherein the configuration comprises information instructing the apparatus to select an AIML functionality of the multiple AIML functionalities for a specific one of the multiple TRP groups based on a cell to which the apparatus is connected.

3. The apparatus according to claim 2, wherein the information comprises information associating individual TRP groups with corresponding AIML functionality, of the multiple AIML functionalities, to be performed for the individual TRP group.

4. The apparatus according to claim 3, wherein the information associating individual TRP groups with corresponding AIML functionality uses cell identification to whichthe apparatus is connected to associate the corresponding AIML functionality with an individual TRP group.

5. The apparatus according to any of claims 1-4, wherein the configuration comprises information instructing the apparatus to select an AIML functionality for a specific one of the multiple TRP groups based on provided information associating reference signal received power (RSRP) measurements from a cell corresponding to individual TRP groups with corresponding individual AIML functionality, of the multiple AIML functionalities, to be performed for the corresponding TRP group.

6. The apparatus according to claim 5, wherein the individual AIML functionality is indicated by an identifier.

7. The apparatus according to any of claims 1-6, wherein the configuration comprises at least one of the following for individual ones of the multiple TRP groups:RSRP measurement range to select tan individual one of the multiple TRP groups; RSRPP measurement range to select an individual one of the multiple TRP groups; timing measurement range to select an individual one of the multiple TRP groups; or angle measurement range to select an individual one of the multiple TRP groups.

8. The apparatus according to any of claims 1-7, wherein: the configuration comprises indication of location based on information linking one or more cells created to individual ones of the one or more TRP groups and indication of associated functionality; and selecting the AIML functionality for a TRP group is performed dependent on which of the one or more TRP groups has a cell in which the apparatus is connected.

9. The apparatus according to any of claims 1-8, wherein: the configuration comprises indication of individual distances between an estimate of location of the apparatus and of individual TRP groups and corresponding indication of associated functionality for the individual distances; and selecting the AIML functionality for a TRP group is performed dependent on the individual distances between the apparatus and individual TRP groups.

10. The apparatus according to any of claims 1-9, wherein the configuration comprises at least one of the following:RSRP measurement range from XI to X2 (>X1) for a TRP group is associated with a first of the multiple AIML functionalities;RSRP measurement range from X3(>X2) to X4 (>X3) for a TRP group is associated with a second of the one or more AIML functionalities; angle measurement range from Z1 to Z2 for a TRP group is associated with a third of the multiple AIML functionalities; angle measurement range from Z3 to Z4 for a TRP group is associated with a fourth of the multiple AIML functionalities; or for specific positioning measurements for multiple TRP groups, a map between AIML functionality and corresponding measurement values is to be used and for a specific TRP group, in case the apparatus obtains RSRP measurements ranging from XI to X2, an associated AIML functionality is selected based on the map.

11. The apparatus according to any of claims 2-6, wherein: the selecting comprises selecting individual AIML functionality for at least two TRP groups; the one or more memories further store instructions that, when executed by the one or more processors, cause the apparatus at least to perform running the individual AIML functionality for individual TRP groups of the at least two TRP groups to select a part of the positioning measurements; and the reporting comprises reporting indications of the positioning measurements.

12. The apparatus according to any of claims 1-11, wherein: the selecting comprises selecting individual AIML functionality for at least first and second TRP groups; the determining positioning measurements to be reported to the network at least based on the selected AIML functionality further comprises: receiving signals from the first and second TRP groups;performing, using the received signals from the first TRP group, a first artificial intelligence or machine learning functionality to determine a first output; performing, using the received signals from the second TRP group, a second artificial intelligence or machine learning functionality to determine a second output; and performing functionality on estimation of location using the first and second outputs to determine one of measurements or estimated location; and the reporting comprises reporting the one of the measurements or the estimated location.

13. A method, comprising: receiving, at a user equipment from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, by the user equipment at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining, by the user equipment, positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting, by the user equipment, the determined positioning measurements.

14. The method according to claim 13, wherein the configuration comprises information instructing the user equipment to select an AIML functionality of the multiple AIML functionalities for a specific one of the multiple TRP groups based on a cell to which the user equipment is connected.

15. The method according to claim 14, wherein the information comprises information associating individual TRP groups with corresponding AIML functionality, of the multiple AIML functionalities, to be performed for the individual TRP group.

16. The method according to claim 15, wherein the information associating individual TRP groups with corresponding AIML functionality uses cell identification to which the user equipment is connected to associate the corresponding AIML functionality with an individual TRP group.

17. The method according to any of claims 13-16, wherein the configuration comprises information instructing the user equipment to select an AIML functionality for a specific one of the multiple TRP groups based on provided information associating reference signal received power (RSRP) measurements from a cell corresponding to individual TRP groups with corresponding individual AIML functionality, of the multiple AIML functionalities, to be performed for the corresponding TRP group.

18. The method according to claim 17, wherein the individual AIML functionality is indicated by an identifier.

19. The method according to any of claims 13-18, wherein the configuration comprises at least one of the following for individual ones of the multiple TRP groups:RSRP measurement range to select tan individual one of the multiple TRP groups; RSRPP measurement range to select an individual one of the multiple TRP groups; timing measurement range to select an individual one of the multiple TRP groups; or angle measurement range to select an individual one of the multiple TRP groups.

20. The method according to any of claims 13-19, wherein: the configuration comprises indication of location based on information linking one or more cells created to individual ones of the one or more TRP groups and indication of associated functionality; and selecting the AIML functionality for a TRP group is performed dependent on which of the one or more TRP groups has a cell in which the user equipment is connected.

21. The method according to any of claims 13-20, wherein: the configuration comprises indication of individual distances between an estimate of location of the user equipment and of individual TRP groups and corresponding indication of associated functionality for the individual distances; and selecting the AIML functionality for a TRP group is performed dependent on the individual distances between the user equipment and individual TRP groups.

22. The method according to any of claims 13-21, wherein the configuration comprises at least one of the following:RSRP measurement range from XI to X2 (>X1) for a TRP group is associated with a first of the multiple AIML functionalities;RSRP measurement range from X3(>X2) to X4 (>X3) for a TRP group is associated with a second of the one or more AIML functionalities; angle measurement range from Z1 to Z2 for a TRP group is associated with a third of the multiple AIML functionalities; angle measurement range from Z3 to Z4 for a TRP group is associated with a fourth of the multiple AIML functionalities; or for specific positioning measurements for multiple TRP groups, a map between AIML functionality and corresponding measurement values is to be used and for a specific TRP group, in case the user equipment obtains RSRP measurements ranging from XI to X2, an associated AIML functionality is selected based on the map.

23. The method according to any of claims 14-18, wherein: the selecting comprises selecting individual AIML functionality for at least two TRP groups; the method further comprises running, by the user equipment, the individual AIML functionality for individual TRP groups of the at least two TRP groups to select a part of the positioning measurements; and the reporting comprises reporting indications of the positioning measurements.

24. The method according to any of claims 13-23, wherein: the selecting comprises selecting individual AIML functionality for at least first and second TRP groups; the determining positioning measurements to be reported to the network at least based on the selected AIML functionality further comprises: receiving signals from the first and second TRP groups; performing, using the received signals from the first TRP group, a first artificial intelligence or machine learning functionality to determine a first output; performing, using the received signals from the second TRP group, a second artificial intelligence or machine learning functionality to determine a second output; and performing functionality on estimation of location using the first and second outputs to determine one of measurements or estimated location; and the reporting comprises reporting the one of the measurements or the estimated location.

25. An apparatus, comprising means for: receiving, from a network, a configuration to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select an individual AIML functionality to perform for a corresponding TRP group; selecting, at least based on the one or more criteria in the configuration, an AIML functionality to perform positioning measurements based at least on reference signals received from individual ones of the multiple TRP groups; determining positioning measurements to be reported to the network at least based on the selected AIML functionality; and reporting the determined positioning measurements.

26. An apparatus, comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the apparatus at least to perform: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

27. The apparatus according to claim 26, wherein the received positioning measurements comprise one or both of measurements from the TRPs or estimated location.

28. A method, comprising: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at least transmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

29. An apparatus, comprising means for: sending a configuration to a user equipment to perform artificial intelligence / machine learning (AIML)-based positioning measurements which includes at leasttransmission-reception point (TRP)-group information for multiple TRP groups and multiple AIML functionalities, wherein individual TRP groups comprise one or more TRPs, and the configuration comprises one or more criteria to select individual AIML functionality to perform for a corresponding TRP group; and receiving positioning measurements based on the TRPs in one or more of the multiple TRP groups at least based on the AIML functionality selected based on the one or more criteria provided in the configuration.

30. A computer program, comprising instructions which, when the program is executed by an apparatus, cause the apparatus to carry out the methods of any of claims 13 to 24.

Images