Consistency verification of AIML positioning configurations

Abstract

An apparatus including at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and receive, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

Description

CONSISTENCY VERIFICATION OF AIML POSITIONING CONFIGURATIONSTECHNICAL FIELD

[0001] The examples and non-limiting example embodiments relate generally to communications and, more particularly, to consistency verification of AIML positioning configurations.BACKGROUND

[0002] It is known for a communication device to gain access to a communication network via an access network node.SUMMARY

[0003] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and receive, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0004] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and determine information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0005] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and determine information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0006] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: configure at least one user equipment with functionality for which at least one model is used; wherein the at least one model is an artificial intelligence or machine learning model; and receive, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The foregoing aspects and other features are explained in the following description, taken in connection with the accompanying drawings.

[0008] FIG. 1 is a block diagram of one possible and non-limiting system in which the example embodiments may be practiced.

[0009] FIG. 2 shows an example DL-PRS configuration considering PFL.

[0010] FIG. 3 shows signaling for the consistent positioning configuration between model training and inference.

[0011] FIG. 4 is an example apparatus configured to implement the examples described herein.

[0012] FIG. 5 shows a representation of an example of non-volatile memory media used to store instructions that implement the examples described herein.

[0013] FIG. 6 is an example method, based on the examples described herein.

[0014] FIG. 7 is an example method, based on the examples described herein.

[0015] FIG. 8 is an example method, based on the examples described herein.

[0016] FIG. 9 is an example method, based on the examples described herein.DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0017] Turning to FIG. 1, this figure shows a block diagram of one possible and nonlimiting example in which the examples may be practiced. A user equipment (UE) 110, radioaccess network (RAN) node 170, and network element(s) 190 are illustrated. In the example of FIG. 1, the user equipment (UE) 110 is in wireless communication with a wireless network 100. A UE is a wireless device that can access the wireless network 100. The UE 110 includes one or more processors 120, one or more memories 125, and one or more transceivers 130 interconnected through one or more buses 127. Each of the one or more transceivers 130 includes a receiver, Rx, 132 and a transmitter, Tx, 133. The one or more buses 127 may be address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, and the like. The one or more transceivers 130 are connected to one or more antennas 128. The one or more memories 125 include computer program code 123. The UE 110 includes a module 140, comprising one of or both parts 140-1 and / or 140- 2, which may be implemented in a number of ways. The module 140 may be implemented in hardware as module 140-1, such as being implemented as part of the one or more processors 120. The module 140-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the module 140 may be implemented as module 140-2, which is implemented as computer program code 123 and is executed by the one or more processors 120. For instance, the one or more memories 125 and the computer program code 123 may be configured to, with the one or more processors 120, cause the user equipment 110 to perform one or more of the operations as described herein. The UE 110 communicates with RAN node 170 via a wireless link 111.

[0018] The RAN node 170 in this example is a base station that provides access for wireless devices such as the UE 110 to the wireless network 100. The RAN node 170 may be, for example, a base station for 5G, also called New Radio (NR). In 5G, the RAN node 170 may be a NG-RAN node, which is defined as either a gNB or an ng-eNB. A gNB is a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface (such as connection 131) to a 5GC (such as, for example, the network element(s) 190). The ng-eNB is a node providing E-UTRA user plane and control plane protocol terminations towards the UE, and connected via the NG interface (such as connection 131) to the 5GC. The NG-RAN node may include multiple gNBs, which may also include a central unit (CU) (gNB-CU) 196 and distributed unit(s) (DUs) (gNB-DUs), of which DU 195 is shown. Note that the DU 195 may include or be coupled to and control a radio unit (RU). The gNB-CU 196 is a logical node hosting radio resource control (RRC), SDAP and PDCP protocols of the gNB or RRC and PDCP protocols of the en-gNB thatcontrol the operation of one or more gNB-DUs. The gNB-CU 196 terminates the Fl interface connected with the gNB-DU 195. The Fl interface is illustrated as reference 198, although reference 198 also illustrates a link between remote elements of the RAN node 170 and centralized elements of the RAN node 170, such as between the gNB-CU 196 and the gNB- DU 195. The gNB-DU 195 is a logical node hosting RLC, MAC and PHY layers of the gNB or en-gNB, and its operation is partly controlled by gNB-CU 196. One gNB-CU 196 supports one or multiple cells. One cell may be supported with one gNB-DU 195, or one cell may be supported / shared with multiple DUs under RAN sharing. The gNB-DU 195 terminates the Fl interface 198 connected with the gNB-CU 196. Note that the DU 195 is considered to include the transceiver 160, e.g., as part of a RU, but some examples of this may have the transceiver 160 as part of a separate RU, e.g., under control of and connected to the DU 195. The RAN node 170 may also be an eNB (evolved NodeB) base station, for LTE (long term evolution), or any other suitable base station or node.

[0019] The RAN node 170 includes one or more processors 152, one or more memories 155, one or more network interfaces (N / W I / F(s)) 161, and one or more transceivers 160 interconnected through one or more buses 157. Each of the one or more transceivers 160 includes a receiver, Rx, 162 and a transmitter, Tx, 163. The one or more transceivers 160 are connected to one or more antennas 158. The one or more memories 155 include computer program code 153. The CU 196 may include the processor(s) 152, one or more memories 155, and network interfaces 161. Note that the DU 195 may also contain its own memory / memories and processor(s), and / or other hardware, but these are not shown.

[0020] The RAN node 170 includes a module 150, comprising one of or both parts 150-1 and / or 150-2, which may be implemented in a number of ways. The module 150 may be implemented in hardware as module 150-1, such as being implemented as part of the one or more processors 152. The module 150-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the module 150 may be implemented as module 150-2, which is implemented as computer program code 153 and is executed by the one or more processors 152. For instance, the one or more memories 155 and the computer program code 153 are configured to, with the one or more processors 152, cause the RAN node 170 to perform one or more of the operations as described herein. Note that the functionality of the module 150 may be distributed, such as being distributed between the DU 195 and the CU 196, or be implemented solely in the DU

[0021] The one or more network interfaces 161 communicate over a network such as via the links 176 and 131. Two or more gNBs 170 may communicate using, e.g., link 176. The link 176 may be wired or wireless or both and may implement, for example, an Xn interface for 5G, an X2 interface for LTE, or other suitable interface for other standards.

[0022] The one or more buses 157 may be address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, wireless channels, and the like. For example, the one or more transceivers 160 may be implemented as a remote radio head (RRH) 195 for LTE or a distributed unit (DU) 195 for gNB implementation for 5G, with the other elements of the RAN node 170 possibly being physically in a different location from the RRH / DU 195, and the one or more buses 157 could be implemented in part as, for example, fiber optic cable or other suitable network connection to connect the other elements (e.g., a central unit (CU), gNB-CU 196) of the RAN node 170 to the RRH / DU 195. Reference 198 also indicates those suitable network link(s).

[0023] A RAN node / gNB can comprise one or more TRPs to which the methods described herein may be applied. FIG. 1 shows that the RAN node 170 comprises TRP 51 and TRP 52, in addition to the TRP represented by transceiver 160. Similar to transceiver 160, TRP 51 and TRP 52 may each include a transmitter and a receiver. The RAN node 170 may host or comprise other TRPs not shown in FIG. 1.

[0024] A relay node in NR is called an integrated access and backhaul node. A mobile termination part of the IAB node facilitates the backhaul (parent link) connection. In other words, the mobile termination part comprises the functionality which carries UE functionalities. The distributed unit part of the IAB node facilitates the so called access link (child link) connections (i.e. for access link UEs, and backhaul for other IAB nodes, in the case of multi-hop IAB). In other words, the distributed unit part is responsible for certain base station functionalities. The IAB scenario may follow the so called split architecture, where the central unit hosts the higher layer protocols to the UE and terminates the control plane and user plane interfaces to the 5G core network.

[0025] It is noted that the description herein indicates that “cells” perform functions, but it should be clear that equipment which forms the cell may perform the functions. The cellmakes up part of a base station. That is, there can be multiple cells per base station. For example, there could be three cells for a single carrier frequency and associated bandwidth, each cell covering one-third of a 360 degree area so that the single base station’s coverage area covers an approximate oval or circle. Furthermore, each cell can correspond to a single carrier and a base station may use multiple carriers. So if there are three 120 degree cells per carrier and two carriers, then the base station has a total of 6 cells.

[0026] The wireless network 100 may include a network element or elements 190 that may include core network functionality, and which provides connectivity via a link or links 181 with a further network, such as a telephone network and / or a data communications network (e.g., the Internet). Such core network functionality for 5G may include location management functions (LMF(s)) and / or access and mobility management function(s) (AMF(S)) and / or user plane functions (UPF(s)) and / or session management function(s) (SMF(s)). Such core network functionality for LTE may include MME (mobility management entity) / SGW (serving gateway) functionality. Such core network functionality may include SON (self- organizing / optimizing network) functionality. These are merely example functions that may be supported by the network element(s) 190, and note that both 5G and LTE functions might be supported. The RAN node 170 is coupled via a link 131 to the network element 190. The link 131 may be implemented as, e.g., an NG interface for 5G, or an SI interface for LTE, or other suitable interface for other standards. The network element 190 includes one or more processors 175, one or more memories 171, and one or more network interfaces (N / W I / F(s)) 180, interconnected through one or more buses 185. The one or more memories 171 include computer program code 173. Computer program code 173 may include SON and / or MRO functionality 172.

[0027] The wireless network 100 may implement network virtualization, which is the process of combining hardware and software network resources and network functionality into a single, software-based administrative entity, or a virtual network. Network virtualization involves platform virtualization, often combined with resource virtualization. Network virtualization 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 that result from the network virtualization are still implemented, at some level, using hardware such as processors 152 or 175 and memories 155 and 171, and also such virtualized entities create technical effects.

[0028] The computer readable memories 125, 155, and 171 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, magnetic memory devices and systems, optical memory devices and systems, non-transitory memory, transitory memory, fixed memory and removable memory. The computer readable memories 125, 155, and 171 may be means for performing storage functions. The processors 120, 152, and 175 may be of any type suitable to the local technical environment, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on a multi-core processor architecture, as nonlimiting examples. The processors 120, 152, and 175 may be means for performing functions, such as controlling the UE 110, RAN node 170, network element(s) 190, and other functions as described herein.

[0029] In general, the various example embodiments of the user equipment 110 can include, but are not limited to, cellular telephones such as smart phones, tablets, personal digital assistants (PDAs) having wireless communication capabilities, portable computers having wireless communication capabilities, image capture devices such as digital cameras having wireless communication capabilities, gaming devices having wireless communication capabilities, music storage and playback devices having wireless communication capabilities, internet appliances including those permitting wireless internet access and browsing, tablets with wireless communication capabilities, head mounted displays such as those that implement virtual / augmented / mixed reality, as well as portable units or terminals that incorporate combinations of such functions. The UE 110 can also be a vehicle such as a car, or a UE mounted in a vehicle, a UAV such as e.g. a drone, or a UE mounted in a UAV. The user equipment 110 may be a terminal device, such as mobile phone, mobile device, sensor device etc., the terminal device being a device used by the user or not used by the user.

[0030] UE 110, RAN node 170, and / or network element(s) 190, (and associated memories, computer program code and modules) may be configured to implement (e.g. in part) the methods described herein. Thus, computer program code 123, module 140-1, module 140-2, and other elements / features shown in FIG. 1 of UE 110 may implement user equipment related aspects of the examples described herein. Similarly, computer program code 153, module 150-1, module 150-2, and other elements / features shown in FIG. 1 of RAN node 170 may implement gNB / TRP related aspects of the examples described herein. Computerprogram code 173 and other elements / features shown in FIG. 1 of network element(s) 190 may be configured to implement network element related aspects of the examples described herein.

[0031] Having thus introduced a suitable but non-limiting technical context for the practice of the example embodiments, the example embodiments are now described with greater specificity.

[0032] For AIML for positioning accuracy enhancement, Case 1 assumes UE calculates the positioning coordinates based on the AIML model located in the UE. In Case 2a where a model is on the UE’s side, UE performs measurements and uses the AIML model to generate an intermediate feature.

[0033] For positioning configuration (e.g., PFL) used for AIML model data collection, when the dataset collected is used for training an AIML model, the training dataset is a set of measurement samples transmitted via a certain configuration (e.g., configured PFL). Therefore, the trained model has a dependency on the PFL used at the time of training.

[0034] For positioning configuration for inference, in the inference phase, the UE has a configuration for positioning, such as a certain PFL. In Case l / 2a, the UE performs the measurement on the PFL configured for the inference phase. The measurements are used as input to the trained AIML model.

[0035] According to TS 37.355, a positioning frequency layer (PFL) is defined as a collection of DL PRS resource sets where each DL PRS resource set is in turn a collection of DL PRS resources. All DL PRS resources from all DL PRS resource sets from the same positioning frequency layer have some common / same PRS parameters viz. PRS subcarrier spacing, PRS resource bandwidth, PRS start PRB, PRS Point A, PRS Comb size, and PRS cyclic prefix.

[0036] FIG. 2 shows a DL-PRS configuration considering PFL. According to NR positioning specification, DL-PRS configuration is provided in a hierarchy. Referring to FIG. 2, there can be at most 4 frequency layers (in FIG. 2, PFLi, PFL2, PFL3 and PFL4), and each frequency layer has at most 64 TRPs (for example, TRPi to TRP64 for PFLi). Each TRP per frequency layer can have 2 DL-PRS Resource sets (for example, Set IDi and Set ID2 for TRPi of PFLi) thus resulting in a total of 8 resource sets per TRP, and each resource set can haveup to 64 resources (for example, R IDi to R ID64 for Set IDi of TRPi of PFLi). Each resource corresponds to a beam. Having 2 different resource sets per frequency layer per TRP allows gNB to configure one set of wide beams and another set of narrow beams for each frequency layer.

[0037] When collecting data for training UE-side model, the measurements (such as channel samples in the form of OR, PDP, DP) serve as the training input. Consequently, the data collection process that creates the dataset for training models is dependent on the positioning configuration used to obtain these measurements. When the trained model is used in the inference stage, if the current positioning configuration (e.g., PFL) is different from the positioning configuration used in the training stage, it could not be effective to use the trained model for inference.

[0038] Therefore, it is essential to remain in the same positioning configuration (i.e., to maintain consistent configuration) in both training and inference stages. Since, the existing mechanisms are generic, and there is no existing detailed mechanisms to guarantee the same positioning configuration in training and inference, described herein are new mechanisms for a single UE or group configuration and signalization exchange between the NW and UE.

[0039] Described herein is a method to maintain the consistent positioning configuration in training and inference stages. To this end, the consistency checking is performed to verify the same positioning configuration. In particular, the UE and NW (e.g., gNB or LMF) exchange signaling to ensure the positioning configuration during inference phase matches with the training phase’s positioning configuration. Specifically, such configuration may consist of validating the positioning frequency layer (PFL) across training and inference.

[0040] UE stays on a given positioning configuration for a time period for data collection. Once UE acquires the measurement samples from the positioning configuration, the measurements are used to train a model for a certain AIML functionality. Later, the inference operation is performed at the UE using the trained AIML model for the given functionality. NW usually configure the UE with AIML positioning functionality. The following steps are used to verify the consistent positioning configuration on the AIML model. The consistency verification of positioning configuration can be managed by either NW or UE.

[0041] In an embodiment, the positioning configuration may comprise PFL settings:

[0042] A PRS positioning frequency layer may comprise e.g., TRPs, PRS resource sets, SCS, CP, PRS Point A etc. In an example embodiment, the consistency verification is required to validates the parameters related to PFL during the training and inference for model activation and verifications.

[0043] Described herein are two options how the consistency check is performed. The NW / UE determines the consistency score, and later UE can utilize that score for functionality / model selection / switching / (de-)activating or fallback operation. The NW may update the configuration, optionally upon the UE’s request. The consistency score (where the consistency score may be referred to as a consistency degree) shows the degree of matched positioning configuration (e.g., the percentage of matched parameters in positioning configuration). For example, to define how much two configurations are similar, a consistency score can be determined as the percentage of parameters that are identically configured in two configurations. In another example, a consistency score can be calculated as a weighted average if some parameters in a configuration is more important than other parameters.

[0044] FIG. 3 shows signaling for the consistent positioning configuration between model training and inference. FIG. 3 shows a signaling between one or more UEs (such as UE 110) and the network (such as a RAN node 170, e.g., a base station, or one or more network elements 190 such as an LMF). FIG. 3 shows Option 1 and Option 2.

[0045] Option 1: Consistency score determined by the NW (e.g., gNB or LMF)

[0046] Step 1 : NW configure the UE with given AIML positioning functionality

[0047] Step 2: UE indicate the configuration(s) per model or list of models trained for the given functionality (e.g., list of supported PFL).

[0048] Step 3 : NW determines the consistency score using the configuration (e.g., PFL) used for training and inference. It is assumed that inference related configuration are already available at the NW side.

[0049] Step 4: Network indicates to the UE the consistency score corresponding to model or list of models trained for the configured functionality.

[0050] In an embodiment, NW may provide sensitivity level (e.g., threshold) for assistingthe UE to take action. Based on the sensitivity level, the action can result in configuration update, functionality / model selection, activation, deactivation, switching, and fallback operation.

[0051] Step 5: The UE utilizes the consistency score provided by the network to take action, e.g., select / switch / (de-) activate the functionality / model or request NW-assistance for a new configuration.

[0052] Step 6: As an example, if the sensitivity level is below certain threshold the UE may request for new configuration from the network.

[0053] Option 2: Consistency score determined by the UE

[0054] Step 7 : UE determines the consistency score using the configuration (e.g., PFL) used for training and inference.

[0055] Step 8: UE indicates to the NW the consistency score optionally mismatching parameters.

[0056] Step 9 : Based on the determination, the UE takes action, e.g., selecting, switching, or (de)activating the functionality / model, or request NW-assistance for new configuration. A sensitivity level may be configured or predefined for assisting the UE to take action.

[0057] Step 10: As an example, if the sensitivity level is below a certain threshold the UE may request for a new configuration from the network.

[0058] Step 11 : NW determines whether to reconfigure UE with a new configuration.

[0059] Step 12: NW (e.g., gNB or LMF) (re)configures UE (e.g., via TRP) with the new configuration.

[0060] In an example embodiment, consistency check can be performed for a group of UEs: NW first identifies a group of UEs requesting for a common configuration. For example, the UEs in a specific area (for example, a validity area, cell, tracking area) can be selected and grouped if they are configured with the same positioning configuration. If some or all the UEs in the group have consistency scores below specific sensitivity level, for example, the number of UEs with consistency scores below specific sensitivity level being larger than a threshold, the NW may simultaneously reconfigure the group of UEs with a new commonconfiguration using multicast or broadcast signaling.

[0061] While the examples described herein mainly focus on the AIML positioning use cases, the herein described procedures of consistency verification can be generally applied for other AIML use cases, such as beam management use cases, to guarantee the consistent configuration in training and inference.

[0062] The consistency check results may be indicated in terms of consistency score from the UE to the network (e.g.: 80% configuration match, or 30% match) along with the configuration (or a list of configurations) that can be supported / not supported by UE. In this partial matching case, the network may partially reconfigure UE by only updating the mismatched parameters of the current configuration. Alternatively, the network may determine to reconfigure UE with a new configuration.

[0063] For functionality-based LCM, as network is already aware about the supported functionalities for a given UE(s), in an embodiment the UE may use the consistency score to select an appropriate AIML model for a given functionality.

[0064] For model-based LCM, in an embodiment based on the consistency score the UE may select appropriate AIML model and report the selected model to the NW.

[0065] FIG. 4 is an example apparatus 400, which may be implemented in hardware, configured to implement the examples described herein. The apparatus 400 comprises at least one processor 402 (e.g. an FPGA and / or CPU), one or more memories 404 including computer program code 405, the computer program code 405 having instructions to carry out the methods described herein, wherein the at least one memory 404 and the computer program code 405 are configured to, with the at least one processor 402, cause the apparatus 400 to implement circuitry, a process, component, module, or function (implemented with control module 406) to implement the examples described herein. The one or more memories 404 may include a non-transitory memory, a transitory memory, a volatile memory (e.g. RAM), or a non-volatile memory (e.g. ROM).

[0066] Consistency Verification 430 implements the examples described herein related to consistency verification of AIML positioning configurations.

[0067] The apparatus 400 includes a display and / or I / O interface 408, which includes userinterface (UI) circuitry and elements, that may be used to display aspects or a status of the methods described herein (e.g., as one of the methods is being performed or at a subsequent time), or to receive input from a user such as with using a keypad, camera, touchscreen, touch area, microphone, biometric recognition, one or more sensors, etc. The apparatus 400 includes one or more communication e.g. network (N / W) interfaces (I / F(s)) 410. The communication I / F(s) 410 may be wired and / or wireless and communicate over the Internet / other network(s) via any communication technique including via one or more links 424. The link(s) 424 may be the link(s) 131 and / or 176 from FIG. 1. The link(s) 131 and / or 176 from FIG. 1 may also be implemented using transceiver(s) 416 and corresponding wireless link(s) 426. The communication I / F(s) 410 may comprise one or more transmitters or one or more receivers.

[0068] The transceiver 416 comprises one or more transmitters 418 and one or more receivers 420. The transceiver 416 and / or communication I / F(s) 410 may comprise standard well-known components such as an amplifier, filter, frequency-converter, (de)modulator, and encoder / decoder circuitries and one or more antennas, such as antennas 414 used for communication over wireless link 426.

[0069] The control module 406 of the apparatus 400 comprises one of or both parts 406-1 and / or 406-2, which may be implemented in a number of ways. The control module 406 may be implemented in hardware as control module 406-1, such as being implemented as part of the one or more processors 402. The control module 406-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the control module 406 may be implemented as control module 406-2, which is implemented as computer program code (having corresponding instructions) 405 and is executed by the one or more processors 402. For instance, the one or more memories 404 store instructions that, when executed by the one or more processors 402, cause the apparatus 400 to perform one or more of the operations as described herein. Furthermore, the one or more processors 402, the one or more memories 404, and example algorithms (e.g., as flowcharts and / or signaling diagrams), encoded as instructions, programs, or code, are means for causing performance of the operations described herein.

[0070] The apparatus 400 to implement the functionality of control 406 may be UE 110, RAN node 170 (e.g. gNB), or network element(s) 190 (e.g. LMF 190). Thus, processor 402 may correspond to processor(s) 120, processor(s) 152 and / or processor(s) 175, memory 404may correspond to one or more memories 125, one or more memories 155 and / or one or more memories 171, computer program code 405 may correspond to computer program code 123, computer program code 153, and / or computer program code 173, control module 406 may correspond to module 140-1, module 140-2, module 150-1, and / or module 150-2, and communication I / F(s) 410 and / or transceiver 416 may correspond to transceiver 130, antenna(s) 128, transceiver 160, antenna(s) 158, N / W I / F(s) 161, and / or N / W I / F(s) 180. Alternatively, apparatus 400 and its elements may not correspond to either of UE 110, RAN node 170, or network element(s) 190 and their respective elements, as apparatus 400 may be part of a self-organizing / optimizing network (SON) node or other node, such as a node in a cloud.

[0071] The apparatus 400 may also be distributed throughout the network (e.g. 100) including within and between apparatus 400 and any network element (such as a network control element (NCE) 190 and / or the RAN node 170 and / or UE 110).

[0072] Interface 412 enables data communication and signaling between the various items of apparatus 400, as shown in FIG. 4. For example, the interface 412 may be one or more buses such as address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, and the like. Computer program code (e.g. instructions) 405, including control 406 may comprise object-oriented software configured to pass data or messages between objects within computer program code 405, or computer program code (e.g. instructions) 405, including control 406 may include functional, scripting, or procedural code. The apparatus 400 need not comprise each of the features mentioned, or may comprise other features as well. The various components of apparatus 400 may at least partially reside in a common housing 428, or a subset of the various components of apparatus 400 may at least partially be located in different housings, which different housings may include housing 428.

[0073] FIG. 5 shows a schematic representation of non-volatile memory media 500a (e.g. computer / compact disc (CD) or digital versatile disc (DVD)) and 500b (e.g. universal serial bus (USB) memory stick) and 500c (e.g. cloud storage for downloading instructions and / or parameters 502 or receiving emailed instructions and / or parameters 502) storing instructions and / or parameters 502 which when executed by a processor allows the processor to perform one or more of the steps of the methods described herein. Instructions and / or parameters 502may represent a computer readable medium.

[0074] FIG. 6 is an example method 600 based on the examples described herein. At 610, the method includes transmitting, to a network entity, a configuration used when at least one model is trained, wherein the at least one model is an artificial intelligence or machine learning model. At 620, the method includes receiving, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference. Method 600 may be performed with UE 110 or apparatus 400.

[0075] FIG. 7 is an example method 700 based on the examples described herein. At 710, the method includes receiving, from at least one user equipment, a configuration when at least one model is trained, wherein the at least one model is an artificial intelligence or machine learning model. At 720, the method includes determining information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference. Method 700 may be performed with RAN node 170, one or more network elements 190, or apparatus 400.

[0076] FIG. 8 is an example method 800 based on the examples described herein. At 810, the method includes determining at least one model, wherein the at least one model is an artificial intelligence or machine learning model. At 820, the method includes determining information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference. Method 800 may be performed with UE 110 or apparatus 400.

[0077] FIG. 9 is an example method 900 based on the examples described herein. At 910, the method includes configuring at least one user equipment with functionality for which at least one model is used, wherein the at least one model is an artificial intelligence or machine learning model. At 920, the method includes receiving, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference. Method 700 may be performed with RAN node 170, one or more network elements 190, or apparatus 400.

[0078] The following examples are provided and described herein.

[0079] Example 1. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and receive, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0080] Example 2. The apparatus of example 1, wherein the apparatus is further caused to: transmit, to the network entity, a request for a new configuration, in response to the information indicating that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and receive, from the network entity, information related to the new configuration requested from the network entity.

[0081] Example 3. The apparatus of any of examples 1 to 2, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference.

[0082] Example 4. The apparatus of example 3, wherein the apparatus is further caused to: determine whether the consistency indication is less than a threshold sensitivity level; transmit, to the network entity, a request for a new configuration, in response to the consistency indication being less than the threshold sensitivity level; and receive, from the network entity, information related to the new configuration requested from the network entity.

[0083] Example 5. The apparatus of example 4, wherein the apparatus is further caused to: receive, from the network entity, the threshold sensitivity level.

[0084] Example 6. The apparatus of any of examples 1 to 5, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a new configuration, when a consistency indication that represents adegree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference is less than a threshold sensitivity level.

[0085] Example 7. The apparatus of any of examples 4 to 6, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

[0086] Example 8. The apparatus of any of examples 1 to 7, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a new configuration, when the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference.

[0087] Example 9. The apparatus of any of examples 1 to 8, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model, and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the information received from the network entity comprises information related to a consistency between the configuration used during training of the one artificial intelligence or machine learning model and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference.

[0088] Example 10. The apparatus of any of examples 1 to 9, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least one positioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception points per positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of thepositioning frequency layer configuration that is to be applied during inference.

[0089] Example 11. The apparatus of any of examples 1 to 10, wherein: the configuration used when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, and the configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

[0090] Example 12. The apparatus of any of examples 1 to 11, wherein the apparatus is further caused to: transmit, to the network entity, a respective configuration used per model when a respective model of a plurality of models is trained; wherein each of the plurality of models is an artificial intelligence or machine learning model; and receive, from the network entity, information related to a consistency between one of the configurations used when a respective one of the plurality of models is trained and a configuration used when the respective one of the plurality of models is to be applied during inference.

[0091] Example 13. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and determine information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0092] Example 14. The apparatus of example 13, wherein the apparatus is further caused to: transmit, to the user equipment, the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference; receive, from the user equipment, a request for a new configuration, when the information indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and transmit, to the user equipment, information related to the new configuration requested by the user equipment.

[0093] Example 15. The apparatus of any of examples 13 to 14, wherein the information related to the consistency between the configuration used when the at least one model istrained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference.

[0094] Example 16. The apparatus of example 15, wherein the apparatus is further caused to: transmit, to the at least one user equipment, the consistency indication that represents the degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference; receive, from the at least one user equipment, a request for a new configuration, when the consistency indication is less than a threshold sensitivity level; and transmit, to the at least one user equipment, information related to the new configuration requested by the at least one user equipment.

[0095] Example 17. The apparatus of example 16, wherein the apparatus is further caused to: transmit, to the at least one user equipment, the threshold sensitivity level.

[0096] Example 18. The apparatus of any of examples 15 to 17, wherein the apparatus is further caused to: determine whether the consistency indication is less than a threshold sensitivity level; transmit, to the at least one user equipment, information related to a new configuration, in response to the consistency indication being less than the threshold sensitivity level.

[0097] Example 19. The apparatus of any of examples 16 to 18, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

[0098] Example 20. The apparatus of any of examples 13 to 19, wherein the apparatus is further caused to: transmit, to the user equipment, information related to a new configuration, when the information indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference.

[0099] Example 21. The apparatus of any of examples 13 to 20, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model,and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the determined information comprises information related to a consistency between the configuration used during training of the one artificial intelligence or machine learning model and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference.

[0100] Example 22. The apparatus of any of examples 13 to 21, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least one positioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception points per positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of the positioning frequency layer configuration that is to be applied during inference.

[0101] Example 23. The apparatus of any of examples 13 to 22, wherein: the configuration used when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, and the configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

[0102] Example 24. The apparatus of any of examples 13 to 23, wherein the apparatus is further caused to: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one user equipment, a respective configuration used per model when a respective model of a plurality of models is trained; wherein each of the plurality of models is an artificial intelligence or machine learning model; and determine information related to a consistency between one of the configurations used when a respective one of the plurality of models is trained and a configuration used when the respective one of the plurality of models is to be applied during inference.

[0103] Example 25. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and determine information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0104] Example 26. The apparatus of example 25, wherein the apparatus is further caused to: transmit to a network entity a request for a new configuration, when the information indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and receive, from the network entity, information related to the new configuration.

[0105] Example 27. The apparatus of any of examples 25 to 26, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference.

[0106] Example 28. The apparatus of example 27, wherein the apparatus is further caused to: transmit to a network entity a request for a new configuration, when the consistency indication is less than a threshold sensitivity level; and receive, from the network entity, information related to the new configuration, when the consistency indication is less than the threshold sensitivity level.

[0107] Example 29. The apparatus of example 28, wherein the apparatus is further caused to: receive the threshold sensitivity level from the network entity.

[0108] Example 30. The apparatus of example 28 or 29, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

[0109] Example 31. The apparatus of any of examples 25 to 30, wherein the apparatus is further caused to: transmit, to a network entity, the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference.

[0110] Example 32. The apparatus of example 31, wherein the information transmitted to the network entity comprises a set of parameters of the configuration used to train the model that do not match corresponding parameters of the configuration used when the model is to be applied during inference.

[0111] Example 33. The apparatus of example 32, wherein the apparatus is further caused to: receive, from the network entity, information related to a new configuration; wherein the information related to the new configuration is applied so that the set of parameters of the configuration used to train the model match the corresponding parameters of the configuration used when the model is to be applied during inference.

[0112] Example 34. The apparatus of any of examples 25 to 33, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model, and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the determined information comprises information related to a consistency between the configuration used during training of the one artificial intelligence or machine learning model and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference.

[0113] Example 35. The apparatus of any of examples 25 to 34, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least one positioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception points per positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of the positioning frequency layer configuration that is to be applied during inference.

[0114] Example 36. The apparatus of any of examples 25 to 35, wherein: the configurationused when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, and the configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

[0115] Example 37. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: configure at least one user equipment with functionality for which at least one model is used; wherein the at least one model is an artificial intelligence or machine learning model; and receive, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0116] Example 38. The apparatus of example 37, wherein the apparatus is further caused to: determine a new configuration, when the information received from the user equipment indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and transmit, to the at least one user equipment, information related to the new configuration.

[0117] Example 39. The apparatus of any of examples 37 to 38, wherein the information received from the user equipment related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference.

[0118] Example 40. The apparatus of example 39, wherein the apparatus is further caused to: determine whether the consistency indication is less than a threshold sensitivity level; determine a new configuration for the at least one user equipment, in response to the consistency indication being less than the threshold sensitivity level; and transmit information related to the new configuration to the at least one user equipment, when the consistency indication is less than the threshold sensitivity level.

[0119] Example 41. The apparatus of any of examples 37 to 40, wherein the apparatus is further caused to: transmit, to the user equipment, information related to a new configuration,in response to receiving a request for a new configuration from the user equipment.

[0120] Example 42. The apparatus of example 41, wherein the information received from the user equipment related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises the request for the new configuration.

[0121] Example 43. The apparatus of any of examples 40 to 42, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

[0122] Example 44. The apparatus of any of examples 37 to 43, wherein the information received from the at least one user equipment comprises a set of parameters of the configuration used to train the model that do not match corresponding parameters of the configuration used when the model is to be applied during inference.

[0123] Example 45. The apparatus of example 44, wherein the apparatus is caused to: determine a new configuration so that the set of parameters of the configuration used to train the model match corresponding parameters of the configuration used when the model is to be applied during inference; and transmit, to the at least one user equipment, information related to the new configuration.

[0124] Example 46. The apparatus of any of examples 37 to 45, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model, and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the information received from the at least one user equipment comprises information related to a consistency between the configuration used during training of the one artificial intelligence or machine learning model and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference.

[0125] Example 47. The apparatus of any of examples 37 to 46, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least onepositioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception points per positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of the positioning frequency layer configuration that is to be applied during inference.

[0126] Example 48. The apparatus of any of examples 37 to 47, wherein: the configuration used when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, and the configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

[0127] Example 49. A method including: transmitting, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and receiving, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0128] Example 50. A method including: receiving, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0129] Example 51. A method including: determining at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0130] Example 52. A method including: configuring at least one user equipment with functionality for which at least one model is used; wherein the at least one model is anartificial intelligence or machine learning model; and receiving, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0131] Example 53. An apparatus including: means for transmitting, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and means for receiving, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0132] Example 54. An apparatus including: means for receiving, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and means for determining information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0133] Example 55. An apparatus including: means for determining at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and means for determining information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0134] Example 56. An apparatus including: means for configuring at least one user equipment with functionality for which at least one model is used; wherein the at least one model is an artificial intelligence or machine learning model; and means for receiving, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0135] Example 57. A computer readable medium including instructions stored thereon for performing at least the following: transmitting, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and receiving, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and aconfiguration used when the at least one model is to be applied during inference.

[0136] Example 58. A computer readable medium including instructions stored thereon for performing at least the following: receiving, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0137] Example 59. A computer readable medium including instructions stored thereon for performing at least the following: determining at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0138] Example 60. A computer readable medium including instructions stored thereon for performing at least the following: configuring at least one user equipment with functionality for which at least one model is used; wherein the at least one model is an artificial intelligence or machine learning model; and receiving, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

[0139] References to a ‘computer’, ‘processor’, etc. should be understood to encompass not only computers having different architectures such as single / multi-processor architectures and sequential or parallel architectures but also specialized circuits such as field- programmable gate arrays (FPGAs), application specific circuits (ASICs), signal processing devices and other processing circuitry. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.

[0140] The memories as described herein may be implemented using any suitable data storage technology, such as semiconductor based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, non-transitory memory, transitory memory, fixed memory and removable memory. The memories may comprise adatabase for storing data.

[0141] 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 vs. ROM).

[0142] As used herein, the term ‘circuitry’ may refer to the following: (a) hardware circuit implementations, such as implementations in analog and / or digital circuitry, and (b) combinations of circuits and software (and / or firmware), such as (as applicable): (i) a combination of processor(s) or (ii) portions of processor(s) / software including digital signal processor(s), software, and memories that work together to cause an apparatus to perform various functions, and (c) circuits, such as a microprocessor(s) or a portion of a microprocessor(s), that require software or firmware for operation, even if the software or firmware is not physically present. As a further example, as used herein, the term ‘circuitry’ would also cover an implementation of merely a processor (or multiple processors) or a portion of a processor and its (or their) accompanying software and / or firmware. The term ‘circuitry’ would also cover, for example and if applicable to the particular element, a baseband integrated circuit or applications processor integrated circuit for a mobile phone or a similar integrated circuit in a server, a cellular network device, or another network device.

[0143] It should be understood that the foregoing description is only illustrative. Various alternatives and modifications may be devised by those skilled in the art. For example, features recited in the various dependent claims could be combined with each other in any suitable combination(s). In addition, features from different example embodiments described above could be selectively combined into a new example embodiment. Accordingly, this description is intended to embrace all such alternatives, modifications and variances which fall within the scope of the appended claims.

[0144] The following acronyms and abbreviations that may be found in the specification and / or the drawing figures are given as follows (the abbreviations and acronyms may be appended / combined with each other or with other characters using e.g. a dash, hyphen, slash, letter, or number, and may be case insensitive):3GPP third generation partnership project4G fourth generation5G fifth generation5GC 5G core networkAIML artificial intelligence / machine learningAMF access and mobility management functionASIC application- specific integrated circuitCD compact / computer discOR channel impulse responseCP cyclic prefixCPU central processing unitCU central unit or centralized unitDC dual connectivityDL downlinkDP delay profileDSP digital signal processorDU distributed unitDVD digital versatile disc eNB evolved Node B (e.g., an LTE base station)EN-DC E-UTRAN new radio - dual connectivity en-gNB node providing NR user plane and control plane protocol terminations towards the UE, and acting as a secondary node in EN- DCE-UTRA evolved UMTS terrestrial radio access, i.e., the LTE radio access technologyE-UTRAN E-UTRA networkFl interface between the CU and the DUFPGA field-programmable gate array gNB generalized node B, base station for 5G / NR, i.e., a node providingNR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GCIAB integrated access and backhaulID identifierPF interfaceI / O input / outputLCM lifecycle managementLMF location management functionLTE long term evolution (4G)MAC medium access controlMME mobility management entityMRO mobility robustness optimizationNCE network control element ng or NG new generation ng-eNB new generation eNB NG-RAN new generation radio access networkNR new radioNW networkN / W networkPDA personal digital assistantPDCP packet data convergence protocolPDP power delay profilePFL positioining frequency layerPHY physical layerPRB physical resource blockPRS positioning reference signalR resource (e.g. R IDi)RAM random access memoryRAN radio access networkRLC radio link controlROM read-only memoryRRC radio resource controlRU radio unitRx receive, or receiver, or receptionSCS subcarrier spacingSDAP service data adaptation protocolSGW serving gatewaySMF session management functionSON self-organizing / optimizing networkTRP transmission reception pointTS technical specificationTx transmit, or transmitter, or transmissionUAV unmanned aerial vehicleUE user equipment (e.g., a wireless, typically mobile device)UI user interfaceUMTS Universal Mobile Telecommunications System UPF user plane functionUSB universal serial busX2 network interface between RAN nodes and between RAN and the core networkXn network interface between NG-RAN nodes

Claims

CLAIMSWhat is claimed is:

1. An apparatus, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and receive, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

2. The apparatus of claim 1, wherein the apparatus is further caused to: transmit, to the network entity, a request for a new configuration, in response to the information indicating that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and receive, from the network entity, information related to the new configuration requested from the network entity.

3. The apparatus of any of claims 1 to 2, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the atleast one model is to be applied during inference.

4. The apparatus of claim 3, wherein the apparatus is further caused to: determine whether the consistency indication is less than a threshold sensitivity level; transmit, to the network entity, a request for a new configuration, in response to the consistency indication being less than the threshold sensitivity level; and receive, from the network entity, information related to the new configuration requested from the network entity.

5. The apparatus of claim 4, wherein the apparatus is further caused to: receive, from the network entity, the threshold sensitivity level.

6. The apparatus of any of claims 1 to 5, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a new configuration, when a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference is less than a threshold sensitivity level.

7. The apparatus of any of claims 4 to 6, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

8. The apparatus of any of claims 1 to 7, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a new configuration, when the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference.

9. The apparatus of any of claims 1 to 8, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model, and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the information received from the network entity comprises information related to a consistency between the configuration used during training of the one artificial intelligence or machine learning model and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference.

10. The apparatus of any of claims 1 to 9, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least one positioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception points per positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of the positioning frequency layer configuration that is to be applied during inference.

11. The apparatus of any of claims 1 to 10, wherein: the configuration used when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, andthe configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

12. The apparatus of any of claims 1 to 11, wherein the apparatus is further caused to: transmit, to the network entity, a respective configuration used per model when a respective model of a plurality of models is trained; wherein each of the plurality of models is an artificial intelligence or machine learning model; and receive, from the network entity, information related to a consistency between one of the configurations used when a respective one of the plurality of models is trained and a configuration used when the respective one of the plurality of models is to be applied during inference.

13. An apparatus, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and determine information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

14. The apparatus of claim 13, wherein the apparatus is further caused to: transmit, to the user equipment, the information related to the consistency between the configuration used when the at least one model is trained and theconfiguration used when the at least one model is to be applied during inference; receive, from the user equipment, a request for a new configuration, when the information indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and transmit, to the user equipment, information related to the new configuration requested by the user equipment.

15. The apparatus of any of claims 13 to 14, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference.

16. The apparatus of claim 15, wherein the apparatus is further caused to: transmit, to the at least one user equipment, the consistency indication that represents the degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference; receive, from the at least one user equipment, a request for a new configuration, when the consistency indication is less than a threshold sensitivity level; and transmit, to the at least one user equipment, information related to the new configuration requested by the at least one user equipment.

17. The apparatus of claim 16, wherein the apparatus is further caused to: transmit, to the at least one user equipment, the threshold sensitivity level.

18. The apparatus of any of claims 15 to 17, wherein the apparatus is further caused to: determine whether the consistency indication is less than a threshold sensitivitylevel; transmit, to the at least one user equipment, information related to a new configuration, in response to the consistency indication being less than the threshold sensitivity level.

19. The apparatus of any of claims 16 to 18, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

20. The apparatus of any of claims 13 to 19, wherein the apparatus is further caused to: transmit, to the user equipment, information related to a new configuration, when the information indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference.

21. The apparatus of any of claims 13 to 20, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model, and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the determined information comprises information related to a consistency between the configuration used during training of the one artificial intelligence or machine learning model and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference.

22. The apparatus of any of claims 13 to 21, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least one positioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception pointsper positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of the positioning frequency layer configuration that is to be applied during inference.

23. The apparatus of any of claims 13 to 22, wherein: the configuration used when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, and the configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

24. The apparatus of any of claims 13 to 23, wherein the apparatus is further caused to: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one user equipment, a respective configuration used per model when a respective model of a plurality of models is trained; wherein each of the plurality of models is an artificial intelligence or machine learning model; and determine information related to a consistency between one of the configurations used when a respective one of the plurality of models is trained and a configuration used when the respective one of the plurality of models is to be applied during inference.

25. An apparatus, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and determine information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

26. The apparatus of claim 25, wherein the apparatus is further caused to: transmit to a network entity a request for a new configuration, when the information indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and receive, from the network entity, information related to the new configuration.

27. The apparatus of any of claims 25 to 26, wherein the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference.

28. The apparatus of claim 27, wherein the apparatus is further caused to: transmit to a network entity a request for a new configuration, when the consistency indication is less than a threshold sensitivity level; and receive, from the network entity, information related to the new configuration, when the consistency indication is less than the threshold sensitivity level.

29. The apparatus of claim 28, wherein the apparatus is further caused to: receive the threshold sensitivity level from the network entity.

30. The apparatus of claim 28 or 29, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

31. The apparatus of any of claims 25 to 30, wherein the apparatus is further caused to: transmit, to a network entity, the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference.

32. The apparatus of claim 31, wherein the information transmitted to the network entity comprises a set of parameters of the configuration used to train the model that do not match corresponding parameters of the configuration used when the model is to be applied during inference.

33. The apparatus of claim 32, wherein the apparatus is further caused to: receive, from the network entity, information related to a new configuration; wherein the information related to the new configuration is applied so that the set of parameters of the configuration used to train the model match the corresponding parameters of the configuration used when the model is to be applied during inference.

34. The apparatus of any of claims 25 to 33, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model, and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the determined information comprises information related to a consistency between the configuration used during training of the one artificial intelligence or machine learning model and the configuration used when the one artificial intelligenceor machine learning model is to be applied during inference.

35. The apparatus of any of claims 25 to 34, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least one positioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception points per positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of the positioning frequency layer configuration that is to be applied during inference.

36. The apparatus of any of claims 25 to 35, wherein: the configuration used when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, and the configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

37. An apparatus, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: configure at least one user equipment with functionality for which at least onemodel is used; wherein the at least one model is an artificial intelligence or machine learning model; and receive, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

38. The apparatus of claim 37, wherein the apparatus is further caused to: determine a new configuration, when the information received from the user equipment indicates that the configuration used when the at least one model is trained is not consistent with the configuration used when the at least one model is to be applied during inference; and transmit, to the at least one user equipment, information related to the new configuration.

39. The apparatus of any of claims 37 to 38, wherein the information received from the user equipment related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises a consistency indication that represents a degree to which the configuration used when the at least one model is trained matches the configuration used when the at least one model is to be applied during inference.

40. The apparatus of claim 39, wherein the apparatus is further caused to: determine whether the consistency indication is less than a threshold sensitivity level; determine a new configuration for the at least one user equipment, in response to the consistency indication being less than the threshold sensitivity level; and transmit information related to the new configuration to the at least one user equipment, when the consistency indication is less than the threshold sensitivity level.

41. The apparatus of any of claims 37 to 40, wherein the apparatus is further caused to: transmit, to the user equipment, information related to a new configuration, in response to receiving a request for a new configuration from the user equipment.

42. The apparatus of claim 41, wherein the information received from the user equipment related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises the request for the new configuration.

43. The apparatus of any of claims 40 to 42, wherein the threshold sensitivity level depends on a quality of service of positioning accuracy.

44. The apparatus of any of claims 37 to 43, wherein the information received from the at least one user equipment comprises a set of parameters of the configuration used to train the model that do not match corresponding parameters of the configuration used when the model is to be applied during inference.

45. The apparatus of claim 44, wherein the apparatus is caused to: determine a new configuration so that the set of parameters of the configuration used to train the model match corresponding parameters of the configuration used when the model is to be applied during inference; and transmit, to the at least one user equipment, information related to the new configuration.

46. The apparatus of any of claims 37 to 45, wherein: one artificial intelligence or machine learning model of the at least one model that is an artificial intelligence or machine learning model supports multiple configurations comprising: the configuration used during training of the one artificial intelligence or machine learning model, and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference, and the information received from the at least one user equipment comprises information related to a consistency between the configuration used during training ofthe one artificial intelligence or machine learning model and the configuration used when the one artificial intelligence or machine learning model is to be applied during inference.

47. The apparatus of any of claims 37 to 46, wherein: the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference both comprise a positioning frequency layer configuration having at least one parameter comprising one or more of: at least one positioning frequency layer, a maximum bandwidth per positioning frequency layer, a number of transmission reception points per positioning frequency layer, or resource sets per transmission reception point configuration, and the information related to the consistency between the configuration used when the at least one model is trained and the configuration used when the at least one model is to be applied during inference comprises information related to a consistency between the at least one parameter of the positioning frequency layer configuration used when the at least one model is trained and the at least one parameter of the positioning frequency layer configuration that is to be applied during inference.

48. The apparatus of any of claims 37 to 47, wherein: the configuration used when the at least one model is trained comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration, and the configuration used when the at least one model is to be applied during inference comprises a positioning configuration, a beam management configuration, or a configuration other than a positioning frequency layer configuration.

49. A method, comprising: transmitting, to a network entity, a configuration used when at least one model is trained;wherein the at least one model is an artificial intelligence or machine learning model; and receiving, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

50. A method, comprising: receiving, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

51. A method, comprising: determining at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

52. A method, comprising: configuring at least one user equipment with functionality for which at least one model is used; wherein the at least one model is an artificial intelligence or machine learning model; and receiving, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and aconfiguration used when the at least one model is to be applied during inference.

53. An apparatus, comprising: means for transmitting, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and means for receiving, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

54. An apparatus, comprising: means for receiving, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and means for determining information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

55. An apparatus, comprising: means for determining at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and means for determining information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

56. An apparatus, comprising: means for configuring at least one user equipment with functionality for whichat least one model is used; wherein the at least one model is an artificial intelligence or machine learning model; and means for receiving, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

57. A computer readable medium comprising instructions stored thereon for performing at least the following: transmitting, to a network entity, a configuration used when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and receiving, from the network entity, information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

58. A computer readable medium comprising instructions stored thereon for performing at least the following: receiving, from at least one user equipment, a configuration when at least one model is trained; wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between the configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

59. A computer readable medium comprising instructions stored thereon for performing at least the following:determining at least one model, wherein the at least one model is an artificial intelligence or machine learning model; and determining information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

60. A computer readable medium comprising instructions stored thereon for performing at least the following: configuring at least one user equipment with functionality for which at least one model is used; wherein the at least one model is an artificial intelligence or machine learning model; and receiving, from the at least one user equipment, information related to a consistency between a configuration used when the at least one model is trained and a configuration used when the at least one model is to be applied during inference.

Images