Data collection configuration for AIML positioning

Abstract

A method comprises: receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples; determining a starting time, within the configured range, to collect the data samples; determining a time offset based on the starting time and a reference time; and collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

Description

DATA COLLECTION CONFIGURATION FOR AIML POSITIONINGTECHNICAL FIELD

[0001] The examples and non-limiting example embodiments relate generally to communications and, more particularly, to a data collection configuration for AIML positioning.BACKGROUND

[0002] A communication device may gain access to a communication network through an access network node.SUMMARY

[0003] Example implementations of the present disclosure are directed to communications and, in particular, to a data collection configuration for AIML positioning. According to some aspects, the present disclosure includes the subject matter of the independent claims. Some further aspects are defined in the dependent claims.

[0004] The above-referenced aspects and other aspects, features, and advantages of the present disclosure will be apparent from a reading of the following detailed description together with the accompanying figures, which are briefly described below. The present disclosure includes any combination of two, three, four or more features or elements set forth in this disclosure, regardless of whether such features or elements are expressly combined or otherwise recited in a specific example implementation described herein. The present disclosure is intended to be read holistically such that any separable features or elements of the disclosure, in any of its aspects and example implementations, should be viewed as combinable unless the context of the disclosure clearly dictates otherwise.

[0005] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The foregoing aspects and other features are explained in the following description, taken in connection with the accompanying drawings.

[0007] FIG. 1 is a block diagram of one possible and non-limiting system in which the example embodiments may be practiced.

[0008] FIG. 2 shows time domain channel samples Nt and sub-samples Nt’ .

[0009] FIG. 3 shows channel state information in the time domain.

[0010] FIG. 4 shows an example signaling flow based on the examples described herein.

[0011] FIG. 5 shows an example suitable offset and search window selection.

[0012] FIG. 6 shows an example signaling flow based on the examples described herein.

[0013] FIG. 7 is an example apparatus configured to implement the examples described herein.

[0014] FIG. 8 shows a representation of an example of non-volatile memory media used to store instructions that implement the examples described herein.

[0015] FIG. 9 is an example method, based on the examples described herein.

[0016] FIG. 10 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 non-limiting example in which the examples may be practiced. A user equipment (UE) 110, radio access 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, andthe 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 gNodeB (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 that control 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 isconsidered 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 195.

[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 forLTE 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. In another example, when describing transceiver 160, TRP 51 may correspond to transceiver 160, or TRP 52 may correspond to transceiver 160.

[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 cell makes 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 witha 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 mobility robustness optimization (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) andprocessors based on a multi-core processor architecture, as non-limiting 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. Computer program 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] The examples described herein are related to AI / ML-based positioning within the scope of artificial intelligence (AI) / machine learning (ML) for the NR air interface. For direct AI / ML positioning, Case 1 refers to UE-based positioning with a UE-side model, Case 2b refers to UE-assisted and / or LMF-based positioning with an LMF-side model, and Case 3b refers to NG-RANnode assisted positioning with an LMF-side model. For AI / ML assisted positioning, Case 2a refers to UE-assisted and / or LMF-based positioning with a UE-side model, and Case 3a refers to NG-RAN node assisted positioning with a gNB-side model.

[0033] For AI / ML-based positioning, time domain channel measurements are used for model input. In an example embodiment, a measurement is composed of Nt’ samples of the estimated channel response in the time domain. The timing information for the Nt’ samples is reported with a timing granularity T, where T=2kx Tc, k represents the timing reporting granularity factor, Tc is the basic time unit for NR, and x is a multiplication operation. In an example embodiment, Nt’ samples are selected out of a list of Nt consecutive samples, where the Nt samples have a timing granularity T. The timing information is defined relative to a reference time.

[0034] For an estimated channel response between a pair including a UE and a TRP, options for down-selection for determining the starting time of the list of Nt consecutive samples may include Option A, Option B, Option C, and Option D. For Option A, the starting time of the list of Nt samples is the timing of the first detected path (with timing granularity T). For Option B, the starting time of the list of Nt consecutive samples is the timing of the earliest sample that the first path power is detectable. For Option C, the starting point of the Nt consecutive samples is determined by a fixed offset (with timing granularity T) relative to the reference time. For Option D, the starting point of the Nt consecutive samples is determined by a configured offset (with timing granularity T) relative to the reference time.

[0035] The number and resolution of time-domain samples obtained from a time-domain channel measurement may impact a granularity of a channel estimation based on the timedomain channel measurement. Thus, the selection of samples to be collected and reported may impact AI / ML inference input and thereby positioning accuracy.

[0036] FIG. 2 shows time domain channel samples Nt (202) and sub-samples Nt’ (204). The input dimension for the measurements may be NTRP * Nport * Nt, where NTRP is the number of TRPs, Nport is the number of transmit / receive antenna port pairs, and Nt (202) is the number of consecutive time domain samples. If Nt’ (Nt’ < Nt) samples with the strongest power are selected as model input, with remaining (Nt - Nt’) time domain samples set to zero, it is also assumed that timing info for the Nt’ samples (204) need to be provided as model input. The value of Nt (202) for sample measurement may follow heuristic approaches for sample selection as also illustrated in FIG. 2.

[0037] Accordingly, different types of measurements as well as associated configurations may be used for AI / ML-based positioning. The examples described herein relate to, when configuring these at the UE (or gNB), e.g., when LMF requests sample measurements (e.g., data collection for training), how to select an appropriate size of search window and offset for the range of samples (i.e., consecutive samples) to ensure required positioning accuracy.

[0038] The number and resolution of time domain samples significantly influence the granularity of the channel estimation. The choice of sampling and the selection of which specific samples to collect and report are important for both training input and for inference input and thereby improving positioning information, as illustrated in FIG. 2. The measurement may be composed of Nt’ values (204) of the estimated channel response in time domain. The Nt’ values (204) are selected from a list of Nt consecutive channel response values (202), which have timing granularity T.

[0039] FIG. 3 shows channel state information in the time domain. Referring to FIG. 3, for both the EMF-side model and the UE-side model, when defining the starting time of the Nt samples, two pieces of information are required, the reference time 302 which establishes a baseline for the time measurement and offset 304 which specifies the difference between the reference time 302 and the actual starting time 306 of the Nt samples as shown in FIG. 3. In an example embodiment, if the starting time is the time of the first detected path, the offset 304 may also or alternatively specify the difference between the reference time 302 and the timing of the first detected path. The examples described herein relate to how to configure the offset 304 with respect to the reference time 302. A special solution is used to configure the proper offset (option C / D) and reporting conditions would be desirable not only for training but also for reporting. Furthermore, having an uncontrolled offset may pose mismatch in the measurement configuration and may lead to inconsistent sample collection or inaccurate position estimation and thereby, a standardized solution is required where the NW can configure the UE / gNB proactively and reactively to report the used offset. Additionally, the NW can also configure the UE / gNB for an offset range to efficiently define a window size for searching potential samples and thereby enforcing an efficient strategy for sample collection as part of AI / ME-driven data collection.

[0040] To address the gaps previously discussed, described herein is an efficient method for sample collection with the aim to enhance the AI / ME inference inputs, while preemptively considering radio conditions (e.g., cell radius, service area, coverage, link budget) and accuracyrequirements. The methods described herein include the following aspects.

[0041] A network node (e.g., LMF) determines one or more configurations for sample selection and reporting conditions to UE / gNB with respect to a reference time while taking into account propagation delay and UE capability for data collection purposes.

[0042] In an example such configuration may comprise a range of the offset with respect to a reference time to i.e., a minimum and maximum offset. For instance, a possible case could involve cell-radius to determine the maximum offset whereas, the minimum offset can be based on the breakpoint distance. The details of the offset range is described herein.

[0043] The offset can be a variable based on the propagation delay of the UE or can be fixed over the cell.

[0044] In an example such configuration may consist of reporting conditions that may or may not combined with offset, for training data collection to avoid redundant data samples.

[0045] In an example, the NW may configure the UE / gNB to proactively or reactively report the chosen / configured / selected offset value.

[0046] In an embodiment, the UE determines / selects one suitable value for the offset or configuration from the options indicated by the network based on e.g., a (max min) offset range. The UE collects requested (sub-)samples considering the selected offset and reports back the selected offset (i.e., within offset range) and the samples to the network node.

[0047] In an embodiment, the UE can utilize the selected offset to configure the search window for the sample measurement.

[0048] In an embodiment, the network may provide the maximum and minimum range of the offset in terms of configured timing granularity for the given UE capability.

[0049] In an embodiment, the network may provide the information on the adjacent cells / TRPs, e.g., ISD, as the parameter used to determine the offset.

[0050] The methods described herein are applicable to use cases for AIML including for Case 1 / Case 2a (UE-side model), Case 3a (gNB-side model) and Case 2b / 3b (LMF-side model) where Case l / 2a / 2b focus on DL and Case 3a / Case 3b focus on UL.

[0051] Case 1 / Case 2:

[0052] The solution described in the flow chart is given in FIG. 4. In particular, FIG. 4 shows an example signaling flow for Case 1 / Case 2a / Case 2b. FIG. 4 shows a signaling exchange between UE 110, UE2 110-2, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, and LMF 190.

[0053] At 401, UE 110-1 performs data collection for a UE-side model (Case 1 / Case 2a) for inference and training. Alternatively or additionally, at 402, LMF 190 performs data collection for an LMF-side model (Case 2b) for inference and training. At 403, the UE 110, UE2 110-2, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, and LMF 190 perform LPP capability transfer. At 404, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, and LMF perform NRPPa procedures.

[0054] At 406, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, and / or LMF 190 determine one or more options for a configuration for samples collection, where the configuration for samples collection may include a reporting configuration that configures conditions for reporting of the collected samples. At 408, LMF 190 sends to the UE 110 the one or more options for the configuration. At 410, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, and neighbor gNB / TRP 170-3 perform PRS transmission to the UE 110, UE 110-2.

[0055] At 412, UE 110 selects a suitable configuration from the options provided (e.g. provided at 408), which may include selection of a suitable reporting configuration from the options provided. At 414, UE 110 reports to the LMF 190 at least one of the selected configuration, the selected offset with respect to a reference time to, or the reporting condition. In example embodiments, the UE may report the collected data. At 416, the LMF 190 utilizes the collected data, for example to monitor or train or re-train AI / ML models. At 418, LMF 190 provides to UE2 110-2 the collected data for monitoring or training or re-training by indicating a utilized offset in measurements. In an example embodiment, LMF 190 may generate a set of collected data based on the report from UE 110 and / or other UEs, e.g., UE2 110-2, and provide the set of collected data to UE110 and / or other UEs, e.g., UE2 110-2.

[0056] The steps of the herein described method are further described as follows, and include the following.

[0057] Step-1: Network node (e.g., LMF / gNB) determines options / configuration and optionally reporting conditions.

[0058] In an embodiment, the LMF determines one or more options or configuration for the offset (e.g. at 406) to ensure efficient data collection for AUML-based channel training / inference ensuring positioning accuracy. The configuration may involve, but is not limited to, offset range e.g., based on the service area defined by cell radius for samples collections.

[0059] In an embodiment, offset range = [Minimum offset, Maximum offset].

[0060] The maximum offset can be tied to the cell radius, which reflects the maximum possible propagation delay in the cell, such that:Cell Radius [m]Maximum offset = - - — — - c [m / s]

[0061] In the above equation, c is the speed of light. The minimum offset can be defined as a fraction of the cell radius, which reflects the minimum possible propagation delay in the cell, such thata x Cell Radius [m]Minimum offset = - - — — ; - , 0 < a « 1c [m / s]

[0062] In the above equation, c is the speed of light. The value of a could correspond to the smallest propagation delay for a UE positioned, and the value of a may depend on the deployment of the network node, placement of the UE and / or the breakpoint distance as defined in 38.901.

[0063] This ensures that the configured offset range is meaningful and does not introduce ambiguity in signal processing.

[0064] In an embodiment, since the difference between to and the starting time varies for multiple UEs and the difference between to and the starting time is representative of the UE environment, therefore, the NW may impose a reporting condition (for training data collection) to determine when to collect and report redundant data for training and overload the interfaces.

[0065] In an embodiment the LMF indicates the information on the distance between neighboring cells. For instance, the value of distance is an inter-site distance (ISD) , e.g., ISD = 200 m or 500 m. The distance information is used by UE to determine the maximum offset thatdefines the ending time of the search window. In this case, the beginning of the search window is the time moment that detects the first path, rounded down with timing granularity. Alternatively, the beginning of the search window is determined by shifting the rounded-down time of first path detection to an earlier time by X*TSwhere X is an integer, e.g., X= I or 2, and where Tsis an amount of time and * is a multiplication operation. The value of the shifted amount of time X can be further configured by the LMF.

[0066] In an embodiment, if the LMF does not have details of propagation delay or service area available at the given time, the LMF may request such information from the gNB / AMF. Therefore, a new information element may be implemented between the LMF and gNB (NRPPa) to retrieve such information for the offset configuration.

[0067] Step-2: Network sends the one or more options of the configuration to UEs (e.g. at 408 of FIG. 4):

[0068] In an embodiment, the network (e.g., LMF) determines the offset configuration for sample collection purposes. In another embodiment, the NW may convert this offset in terms of timing granularity T and share with the UE for selection.

[0069] In an embodiment, the network (e.g., LMF) determines the reporting conditions for sample collection from the UE. For training an AI / ML model, it is critical to use a dataset which provides a good representation of the environment in which the model performs inference in the future.

[0070] For example, assume the UE selects the starting time based on the first detected path in a configured range for data collection from the network. If UEs are co-located the dataset may be imbalanced due to a similar offset and thus measurement reports. In such scenarios, the network may configure different UEs with a condition to create an unbiased dataset while avoiding collection of redundant and highly correlated samples. Alternatively, the NW may indicate different ranges for data collection to the respective different UE(s) for measurement collecting and reporting.

[0071] In one example case, the network node (e.g., LMF) determines a common offset range that is shared with all the UEs within the cell using broadcast e.g., posSIB.

[0072] In another example, the range can be dynamically adjusted and communicated via LPPsignaling for specific UEs based on the UE conditions (e.g., mobile UEs). In another embodiment, instead of having a dynamic offset, the network may determine the minimum offset based on the first detect path of the 1stUE. The network may set the same minimum offset for all the UEs in the given area of interest / cell / area, as shown in FIG. 5. In FIG. 5, UE-1 110 is configured with offsetl 502 or selects offsetl 502, UE-2 110-2 is configured with offset2504 or selects offset2 504, and UE-3 110-3 is configured with offset3 506 or selects offset3 506. The starting time 508 for collection of data samples for UE-1 110 corresponds to offsetl 502 from reference time to 501, the starting time 510 for collection of data samples for UE-2 110 corresponds to offset2504 from reference time to 501, and the starting time 512 for collection of data samples for UE-3 110 corresponds to offset3506 from reference time to 501. The maximum search window 514 is based on the minimum offset 516 and the maximum offset 518. In this example, the minimum offset 516 and the maximum offset 518 may be the same, but the actual search window, i.e., from starting time to the maximum offset, may be different for the different UEs UE-1 110, UE-2 110-2, and UE-3 110-3.

[0073] As shown in FIG. 5, the starting time may be within the configured range that is configured for example by the LMF 190. For example, the starting time 508 of UE-1 is between min offset 516 and max offset 518, the starting time 510 of UE-2 is between min offset 516 and max offset 518, and the starting time 512 of UE-3 is between min offset 516 and max offset 518.

[0074] Step-3: UE determines / selects the offset (e.g. at 412 of FIG. 4):

[0075] In an embodiment, the UE determines / selects a suitable offset within the provided range of the offset. Note that the selection of offset is based on but not limited to first detected path, radio propagation conditions and / or the power delay profile (PDP) of CSI measurements specific to the UE and / or UE capability (timing granularity T), etc. Alternatively, to account for prominent NLOS samples occurring before the first detected path, the UEs may select a fixed offset and / or a delta range preceding the first detected path. The later ensures the robustness under multipath conditions. In an example embodiment, if more than one options for configuration is configured, the UE may determine a suitable option of the configuration.

[0076] In an embodiment, the UE determines the search window and then a suitable offset within the search window for sample / sub-sample measurements.

[0077] Step-4 : UE collects samples: UE collects the samples / sub-samples of Nt / Nt’ samples based on the above selected configuration.

[0078] The offset selection and sample collection as described in Step-3 and Step-4 can be based on the following techniques:

[0079] In one example, the UE configures the search window based on the configured range for data collection and searches for the first detected path (e.g., path with highest power) within the range. The starting time of the list of Nt consecutive values is determined as staring time equal to the first detected path rounded down with timing granularity T.

[0080] Step-5, Reporting samples: the UE reports collected samples to the network node (e.g., LMF), such as at 414 of FIG. 4, and indicates the selected timing offset corresponding to the reference time. As an additional embodiment, the UE can report its reporting condition as well to the NW if requested based on the sent LMF configuration (Step 2).

[0081] In one embodiment, the UE reports the measurements together with its location estimate or other positioning-related estimate such as an intermediate feature, e.g., ToA, TDoA, LOS / NLOS indicator, etc. using AI / ML.

[0082] Step-6, Usage of reported samples: the LMF may utilize the collected measurements, for example at 416 of FIG. 4, to perform various AI / ML-related operations:

[0083] In one embodiment, the LMF collects measurements from the UE / PRU in order to generate a dataset to be used for monitoring or (re-)training AI / ML models, which could be located in other entities, e.g., another UE or gNB. For this, the LMF provides the collected data to these entities, for example at 418 of FIG. 4, whereby indicating the utilized measurement configuration including the utilized offset value(s) along with the measurement samples. This would help the entities to check and ensure consistency between their training and inference. That is, they want to utilize the same offset value when performing inference, as they did in training their models.

[0084] In one embodiment, the LMF utilizes the measurement sample to perform a positioning estimate also on its side (for example at 416 of FIG. 4), which may also use an AI / ML model, i.e., as in Case 2b.

[0085] In a further embodiment, the LMF monitors the performance of the UE’s estimation, e.g., by comparing its location estimate with its own estimate, using the same measurement reported by the UE as input.

[0086] Case 3a / Case 3b: AI / ML assisted positioning gNB / LMF-side model

[0087] The previous description focused on a downlink PRS based technique for sample subset selection. The described method, however, can be extended to assisted AIML positioning by employing the uplink SRS based technique, as illustrated in the signaling flow diagram of FIG.6.

[0088] FIG. 6 is an example signaling flow for Case 3a and Case 3b. FIG. 6 shows a signaling exchange between UE 110, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, and LMF 190. At 601, serving gNB / TRP 170-1 performs data collection for a gNB-side model (Case 3a) for training / inference. Alternatively or additionally, at 602, the LMF 190 performs data collection for an LMF-side model (Case 3b) for training / inference. At 604, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, and LMF 190 perform NRPPa procedures 604.

[0089] At 606, the serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, and / or LMF 190 determine one or more options for a configuration for samples collection, where the configuration for samples collection may comprise a reporting configuration that configures conditions for reporting of the collected samples. At 608, the LMF 190 transmits to serving gNB / TRP 170-1 the configuration for sample collection, where the configuration for sample collection may comprise the reporting configuration. At 610, the LMF 190 transmits to neighbor gNB / TRP 170-2 the configuration for sample collection, where the configuration for sample collection may comprise the reporting configuration. At 612, the LMF 190 transmits to neighbor gNB / TRP 170-3 the configuration for sample collection, where the configuration for sample collection may comprise the reporting configuration. At 614, if more than one configuration is configured / received, the serving gNB / TRP 170-1 determines a suitable configuration option for samples collection, where the determined suitable configuration option may include a reporting configuration. The neighbor gNB / TRP 170-2 and the neighbor gNB / TRP 170-3 may also determine a suitable configuration option for samples collection, where the determined suitable configuration option may include a reporting configuration. In an example embodiment, after the serving gNB / TRP 170-1 determines the configuration, it may deliver the configuration to neighbor gNB / TRP 170-2 and / or 170-3, e.g., via an Fl interface.

[0090] At 616, UE 110 and serving gNB / TRP 170-1 perform SRS configuration and activation. At 618, UE 110 may perform SRS transmission to serving gNB / TRP 170-1, gNB / TRP 170-2,and / or gNB / TRP 170-3. At 620, serving gNB / TRP 170-1 transmits to LMF 190 at least one of the selected configuration, the selected offset with respect to reference time to, or the reporting condition, and data samples collected based on the selected configuration. At 622, neighbor gNB / TRP 170-2 transmits to LMF 190 at least one of the selected configuration, the selected offset with respect to reference time to, or the reporting condition, and data samples collected based on the selected configuration. At 624, neighbor gNB / TRP 170-3 transmits to LMF 190 at least one of the selected configuration, the selected offset with respect to reference time to, or the reporting condition, and data samples collected based on the selected configuration.

[0091] It is worth noting that, all steps outlined in Case 1 are equally applicable to Case 3a / Case 3b, with the primary difference being the node / entity executing specific steps. For example, Step-3 and Step-4 would now be performed at the gNB-side instead of the UE side. Thus, leveraging the gNB’s relatively high computational capabilities for sample selections improves the achievable positioning accuracy.

[0092] In an embodiment, for Case 3a / Case 3b, the gNB may have the offset based on its implementation but the LMF may configure the gNB to proactively or reactively report the offset value chosen / selected by the gNB to LMF.

[0093] Instead of an LMF, a RAN node can perform the steps above, e.g., gNB. In this case, the communication between gNB and UE can take place via RRC or MAC protocol.

[0094] In one example scenario, the UE may be located indoor, such as within a factory setup, where the suitable sample collection is influenced by the indoor environment. In such cases, the network can further refine the offset range based on geographic disposition of transceiver nodes. For instance, Maxi ■mum o cfcfset = (kCell Radius — P) ' / / cand , M ..i.ni .mumwhere p denotes the distance to the indoor boundary. In a multi-story building, the network can adjust offset ranges by considering vertical distances and inter-floor penetration losses. In another example, p could include an additional parameter for floor height.

[0095] The examples described herein are related to data collection aspects (sample collection), in particular to AIML positioning, related to AIML for an air interface.

[0096] FIG. 7 is an example apparatus 700, which may be implemented in hardware, configured to implement the examples described herein. The apparatus 700 comprises at least one processor 702 (e.g. an FPGA and / or CPU), one or more memories 704 including computerprogram code 705, the computer program code 705 having instructions to carry out the methods described herein, wherein the at least one memory 704 and the computer program code 705 are configured to, with the at least one processor 702, cause the apparatus 700 to implement circuitry, a process, component, module, or function (implemented with control module 706) to implement the examples described herein. The one or more memories 704 may include a non-transitory memory, a transitory memory, a volatile memory (e.g. RAM), or a non-volatile memory (e.g. ROM).

[0097] Offset configuration / selection 730 and reporting condition 740 implement the examples described herein related to a data collection configuration enabling samples offset and a reporting condition for AIML positioning.

[0098] The apparatus 700 includes a display and / or I / O interface 708, which includes user interface (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 700 includes one or more communication e.g. network (N / W) interfaces (I / F(s)) 710. The communication I / F(s) 710 may be wired and / or wireless and communicate over the Internet / other network(s) via any communication technique including via one or more links 724. The link(s) 724 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) 716 and corresponding wireless link(s) 726. The communication I / F(s) 710 may comprise one or more transmitters or one or more receivers.

[0099] The transceiver 716 comprises one or more transmitters 718 and one or more receivers 720. The transceiver 716 and / or communication I / F(s) 710 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 714 used for communication over wireless link 726.

[0100] The control module 706 of the apparatus 700 comprises one of or both parts 706-1 and / or 706-2, which may be implemented in a number of ways. The control module 706 may be implemented in hardware as control module 706-1, such as being implemented as part of the one or more processors 702. The control module 706-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, thecontrol module 706 may be implemented as control module 706-2, which is implemented as computer program code (having corresponding instructions) 705 and is executed by the one or more processors 702. For instance, the one or more memories 704 store instructions that, when executed by the one or more processors 702, cause the apparatus 700 to perform one or more of the operations as described herein. Furthermore, the one or more processors 702, the one or more memories 704, 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.

[0101] The apparatus 700 to implement the functionality of control 706 may be UE 110, RAN node 170 (e.g. gNB), or network element(s) 190 (e.g. LMF 190). Thus, processor 702 may correspond to processor(s) 120, processor(s) 152 and / or processor(s) 175, memory 704 may correspond to one or more memories 125, one or more memories 155 and / or one or more memories 171, computer program code 705 may correspond to computer program code 123, computer program code 153, and / or computer program code 173, control module 706 may correspond to module 140-1, module 140-2, module 150-1, and / or module 150-2, and communication I / F(s) 710 and / or transceiver 716 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 700 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 700 may be part of a self-organizing / optimizing network (SON) node or other node, such as a node in a cloud.

[0102] Apparatus 700 may also correspond to UE2, UE-2 110-2, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, or UE-3 110-3.

[0103] The apparatus 700 may also be distributed throughout the network (e.g. 100) including within and between apparatus 700 and any network element (such as a network control element (NCE) 190 and / or the RAN node 170 and / or UE 110).

[0104] Interface 712 enables data communication and signaling between the various items of apparatus 700, as shown in FIG. 7. For example, the interface 712 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) 705, including control 706 may comprise object-oriented software configured to pass data ormessages between objects within computer program code 705, or computer program code (e.g. instructions) 705, including control 706 may include functional, scripting, or procedural code. The apparatus 700 need not comprise each of the features mentioned, or may comprise other features as well. The various components of apparatus 700 may at least partially reside in a common housing 728, or a subset of the various components of apparatus 700 may at least partially be located in different housings, which different housings may include housing 728.

[0105] FIG. 8 shows a schematic representation of non-volatile memory media 800a (e.g. computer / compact disc (CD) or digital versatile disc (DVD)) and 800b (e.g. universal serial bus (USB) memory stick) and 800c (e.g. cloud storage for downloading instructions and / or parameters 802 or receiving emailed instructions and / or parameters 802) storing instructions and / or parameters 802 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 802 may represent a computer readable medium.

[0106] FIG. 9 is an example method 900 based on the examples described herein. At 910, the method includes receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples. At 920, the method includes determining a starting time, within the configured range, to collect the data samples. At 930, the method includes determining a time offset based on the starting time and a reference time. At 940, the method includes collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time. Method 900 may be performed with UE 110, UE2 110-3, UE-3 110-3, RAN node 170, serving gNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, or apparatus 700.

[0107] FIG. 10 is an example method 1000 based on the examples described herein. At 1010, the method includes determining at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, and wherein a starting time for starting the collection of the data samples is within the range. At 1020, the method includes transmitting, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples. Method 1000 may be performed with RAN node 170, servinggNB / TRP 170-1, neighbor gNB / TRP 170-2, neighbor gNB / TRP 170-3, one or more network elements 190, or apparatus 700.

[0108] The following examples are provided and described herein.

[0109] 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: receive, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples; determine a starting time, within the configured range, to collect the data samples; determine a time offset based on the starting time and a reference time; and collect the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

[0110] Example 2. The apparatus of example 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the network node, the data samples collected based on the configured range.

[0111] Example 3. The apparatus of example 1 or 2, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the network node, an indication of at least one of the determined time offset, or the determined starting time.

[0112] Example 4. The apparatus of example 3, wherein the indication is transmitted to the network node in response to a request received from the network node.

[0113] Example 5. The apparatus of any of examples 1 to 4, wherein the at least one data collection configuration comprises the reference time.

[0114] Example 6. The apparatus of any of examples 1 to 5, wherein the configuration of the range comprises at least one of a minimum time offset with respect to the reference time or a maximum time offset with respect to the reference time, wherein the at least one of the minimum time offset or the maximum time offset defines a range for the time offset.

[0115] Example 7. The apparatus of example 6, wherein the maximum time offset is based on at least one of: a cell radius, an indoor boundary, or a size of a service area or an associated assistance data area.

[0116] Example 8. The apparatus of example 6 or 7, wherein the minimum time offset is based on at least one of: a cell radius, an indoor boundary, a size of a service area or an associated assistance data area, a breakpoint distance, or a propagation delay.

[0117] Example 9. The apparatus of any of examples 6 to 8, wherein the at least one of the minimum time offset or maximum time offset is configured in terms of a timing granularity of the apparatus.

[0118] Example 10. The apparatus of any of examples 1 to 9, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine a size of a search window based on the configuration of the range.

[0119] Example 11. The apparatus of any of examples 1 to 10, wherein the configuration of the range is fixed for a cell, or dynamically configured.

[0120] Example 12. The apparatus of any of examples 1 to 11, wherein the at least one data collection configuration comprises information related to a distance between neighboring cells, and wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine a maximum time offset based on the information related to the distance between neighboring cells received from the network node; wherein the time offset associated with the starting time to start the collection of data samples is less than or equal to the maximum time offset.

[0121] Example 13. The apparatus of any of examples 1 to 12, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine a time instance of detecting a first path of the apparatus, wherein the starting time is determined as the time instance or an earlier time before the time instance by a shifted amount of time.

[0122] Example 14. The apparatus of example 13, wherein the shifted amount of time is indicated in the at least one data collection configuration.

[0123] Example 15. The apparatus of any of examples 1 to 14, wherein the apparatus is a UE, a gNB, or a positioning reference unit, and wherein the network node is an LMF.

[0124] Example 16. The apparatus of any of examples 1 to 14, wherein the apparatus is a UE, and wherein the network node is a gNB.

[0125] Example 17. The apparatus of any of examples 1 to 16, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: perform training or inference using the AIML model based on at least one of the data samples collected, or a set of data samples received from the network node.

[0126] Example 18. The apparatus of example 17, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive the set of data samples from the network node.

[0127] Example 19. The apparatus of any of examples 1 to 18, wherein the time offset is determined as a difference between the starting time and the reference time.

[0128] Example 20. The apparatus of any of examples 1 to 19, wherein the data samples are collected within the configured range.

[0129] Example 21. The apparatus of any of examples 1 to 20, wherein the data samples are collected outside the configured range comprising the starting time and within another range configured by the network node.

[0130] Example 22. The apparatus of any of examples 1 to 21, wherein the data samples are collected within another range configured by the network node.

[0131] Example 23. The apparatus of example 22, wherein the configured range and the another range overlap such that a beginning of the another range is before an ending of the configured range.

[0132] Example 24. 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 data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, and wherein a starting time for starting the collection of the data samples is within the range; and transmit, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

[0133] Example 25. The apparatus of example 24, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one secondapparatus, data samples collected based on the range configured based on the at least one data collection configuration.

[0134] Example 26. The apparatus of example 25, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: generate a set of data samples based on the data samples received from the at least one second apparatus; and transmit the set of data samples to the at least one second apparatus or / and a third apparatus.

[0135] Example 27. The apparatus of example 25 or 26, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: perform training or inference using the AIML model based on the data samples collected.

[0136] Example 28. The apparatus of example 25, wherein the data samples collected received from the at least one second apparatus are collected within the range.

[0137] Example 29. The apparatus of example 25, wherein the data samples collected received from the at least one second apparatus are collected outside the range comprising the starting time and within another range configured by the apparatus.

[0138] Example 30. The apparatus of example 25, wherein the data samples collected received from the at least one second apparatus are collected within another range configured by the apparatus.

[0139] Example 31. The apparatus of example 30, wherein the range and the another range overlap such that a beginning of the another range is before an ending of the range.

[0140] Example 32. The apparatus of any of examples 22 to 31 , wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the at least one second apparatus, an indication of at least one of a time offset, or the starting time, determined by the at least one second apparatus, wherein the time offset is based on the starting time and a reference time.

[0141] Example 33. The apparatus of example 32, wherein the time offset is determined as a difference between the starting time and the reference time.

[0142] Example 34. The apparatus of example 32 or 33, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit a request to the atleast one second apparatus for the indication, wherein the indication is received in response to the request.

[0143] Example 35. The apparatus of any of examples 32 to 34, wherein the at least one data collection configuration comprises the reference time.

[0144] Example 36. The apparatus of any of examples 24 to 35, wherein the configuration of the range comprises at least one of a minimum time offset with respect to a reference time or a maximum time offset with respect to the reference time, wherein the at least one of the minimum time offset or the maximum time offset defines a range for a time offset associated with the starting time.

[0145] Example 37. The apparatus of example 36, wherein the maximum time offset is based on at least one of: a cell radius, an indoor boundary, or a size of a service area or an associated assistance data area.

[0146] Example 38. The apparatus of example 36 or 37, wherein the minimum time offset is based on at least one of: a cell radius, an indoor boundary, a size of a service area or an associated assistance data area, a breakpoint distance, or a propagation delay.

[0147] Example 39. The apparatus of any of examples 36 to 38, wherein the at least one of the minimum time offset or maximum time offset is configured in terms of a timing granularity of the apparatus.

[0148] Example 40. The apparatus of any of examples 24 to 39, wherein the configuration of the range is fixed for a cell, or dynamically configured.

[0149] Example 41. The apparatus of any of examples 24 to 40, wherein the at least one data collection configuration comprises information related to a distance between neighboring cells.

[0150] Example 42. The apparatus of examples 24 to 41, wherein the apparatus is an LMF, and wherein the at least one second apparatus is a UE, a gNB, or a positioning reference unit.

[0151] Example 43. The apparatus of examples 24 to 42, wherein the apparatus is a gNB, and the at least one second apparatus is a UE or a second gNB.

[0152] Example 44. A method including: receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples; determining a starting time, within the configured range, to collect the data samples; determining a time offset based on the starting time and a reference time; and collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

[0153] Example 45. A method including: determining at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, and wherein a starting time for starting the collection of the data samples is within the range; and transmitting, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

[0154] Example 46. An apparatus including: means for receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples; means for determining a starting time, within the configured range, to collect the data samples; means for determining a time offset based on the starting time and a reference time; and means for collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

[0155] Example 47. An apparatus including: means for determining at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, and wherein a starting time for starting the collection of the data samples is within the range; and means for transmitting, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

[0156] Example 48. A computer readable medium including instructions stored thereon for performing at least the following: receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-trainingor / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples; determining a starting time, within the configured range, to collect the data samples; determining a time offset based on the starting time and a reference time; and collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

[0157] Example 49. A computer readable medium including instructions stored thereon for performing at least the following: determining at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, and wherein a starting time for starting the collection of the data samples is within the range; and transmitting, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

[0158] 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.

[0159] 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 a database for storing data.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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):4G fourth generation5G fifth generation5GC 5G core networkAl artificial intelligenceAIML artificial intelligence machine learningAMF access and mobility management functionASIC application-specific integrated circuitCD compact / computer discCPU central processing unitCSI channel state informationCU central unit or centralized unitDC dual connectivityDL downlinkDSP digital signal processorDU distributed unitDVD digital versatile disceNB evolved Node B (e.g., an LTE base station)EN-DC E-UTRAN new radio - dual connectivityen-gNB node providing NR user plane and control plane protocol terminations towards the UE, and acting as a secondary node in EN-DCEPC evolved packet coreE-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 arraygNB next generation node B, or generalized node B, base station for 5G / NR, i.e., a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GCIAB integrated access and backhaulI / F interfaceIFFT inverse Fast Fourier transformI / O input / outputISD inter-site distanceLMF location management functionLOS line of sightLPP LTE positioning procedureLTE long term evolution (4G)MAC medium access controlML machine learningMME mobility management entityMRO mobility robustness optimizationNCE network control elementng or NG new generationng-eNB new generation eNBNG-RAN new generation radio access networkNLOS non-line-of- sightNR new radioNRPPa NR positioning protocol AN / W networkNW networkOFDM orthogonal frequency division multiplexingPDA personal digital assistantPDCP packet data convergence protocolPDP power delay profilePHY physical layerposSIB positioning SIBPRS positioning reference signalPRU positioning reference unitRAM random access memoryRAN radio access networkRE resource elementRLC radio link controlROM read-only memoryRRC radio resource controlRU radio unitRx, RX receive, or receiver, or receptionSI interface between the mobility management entity (MME) in the EPC and the evolved Node B’s in the E-UTRANSDAP service data adaptation protocolSGW serving gatewaySIB system information blockSMF session management functionSON self-organizing / optimizing networkSRS sounding reference signalTDOA, TDoA time difference of arrivalToA time of arrivalTR technical reportTRP transmission reception pointTx, TX transmit, or transmitter, or transmissionUAV unmanned aerial vehicleUE user equipment (e.g., a wireless, typically mobile device)UI user interfaceUL uplinkUMTS Universal Mobile Telecommunications SystemUPF user plane functionUSB universal serial busUTRAN universal terrestrial radio access networkX2 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; andat least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:receive, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples;determine a starting time, within the configured range, to collect the data samples; determine a time offset based on the starting time and a reference time; and collect the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

2. The apparatus of claim 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:transmit, to the network node, the data samples collected based on the configured range.

3. The apparatus of claim 1 or 2, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:transmit, to the network node, an indication of at least one of the determined time offset, or the determined starting time.

4. The apparatus of claim 3, wherein the indication is transmitted to the network node in response to a request received from the network node.

5. The apparatus of any of claims 1 to 4, wherein the at least one data collection configuration comprises the reference time.

6. The apparatus of any of claims 1 to 5, wherein the configuration of the range comprises at least one of a minimum time offset with respect to the reference time or a maximum time offset with respect to the reference time, wherein the at least one of the minimum time offset or the maximum time offset defines a range for the time offset.

7. The apparatus of claim 6, wherein the maximum time offset is based on at least one of: a cell radius, an indoor boundary, or a size of a service area or an associated assistance data area.

8. The apparatus of claim 6 or 7, wherein the minimum time offset is based on at least one of: a cell radius, an indoor boundary, a size of a service area or an associated assistance data area, a breakpoint distance, or a propagation delay.

9. The apparatus of any of claims 6 to 8, wherein the at least one of the minimum time offset or maximum time offset is configured in terms of a timing granularity of the apparatus.

10. The apparatus of any of claims 1 to 9, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:determine a size of a search window based on the configuration of the range.

11. The apparatus of any of claims 1 to 10, wherein the configuration of the range is fixed for a cell, or dynamically configured.

12. The apparatus of any of claims 1 to 11 , wherein the at least one data collection configuration comprises information related to a distance between neighboring cells, and wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: determine a maximum time offset based on the information related to the distance between neighboring cells received from the network node;wherein the time offset associated with the starting time to start the collection of data samples is less than or equal to the maximum time offset.

13. The apparatus of any of claims 1 to 12, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:determine a time instance of detecting a first path of the apparatus, wherein the starting time is determined as the time instance or an earlier time before the time instance by a shifted amount of time.

14. The apparatus of claim 13, wherein the shifted amount of time is indicated in the at least one data collection configuration.

15. The apparatus of any of claims 1 to 14, wherein the apparatus is a UE, a gNB, or a positioning reference unit, and wherein the network node is an LMF.

16. The apparatus of any of claims 1 to 14, wherein the apparatus is a UE, and wherein the network node is a gNB.

17. The apparatus of any of claims 1 to 16, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:perform training or inference using the AIML model based on at least one of the data samples collected, or a set of data samples received from the network node.

18. The apparatus of claim 17, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:receive the set of data samples from the network node.

19. The apparatus of any of claims 1 to 18, wherein the time offset is determined as a difference between the starting time and the reference time.

20. The apparatus of any of claims 1 to 19, wherein the data samples are collected within the configured range.

21. The apparatus of any of claims 1 to 20, wherein the data samples are collected outside the configured range comprising the starting time and within another range configured by the network node.

22. The apparatus of any of claims 1 to 21, wherein the data samples are collected within another range configured by the network node.

23. The apparatus of claim 22, wherein the configured range and the another range overlap such that a beginning of the another range is before an ending of the configured range.

24. An apparatus, comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:determine at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference,wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, andwherein a starting time for starting the collection of the data samples is within the range; andtransmit, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

25. The apparatus of claim 24, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:receive, from the at least one second apparatus, data samples collected based on the range configured based on the at least one data collection configuration.

26. The apparatus of claim 25, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:generate a set of data samples based on the data samples received from the at least one second apparatus; andtransmit the set of data samples to the at least one second apparatus or / and a third apparatus.

27. The apparatus of claim 25 or 26, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:perform training or inference using the AIML model based on the data samplescollected.

28. The apparatus of claim 25, wherein the data samples collected received from the at least one second apparatus are collected within the range.

29. The apparatus of claim 25, wherein the data samples collected received from the at least one second apparatus are collected outside the range comprising the starting time and within another range configured by the apparatus.

30. The apparatus of claim 25, wherein the data samples collected received from the at least one second apparatus are collected within another range configured by the apparatus.

31. The apparatus of claim 30, wherein the range and the another range overlap such that a beginning of the another range is before an ending of the range.

32. The apparatus of any of claims 24 to 31, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:receive, from the at least one second apparatus, an indication of at least one of a time offset, or the starting time, determined by the at least one second apparatus, wherein the time offset is based on the starting time and a reference time.

33. The apparatus of claim 32, wherein the time offset is determined as a difference between the starting time and the reference time.

34. The apparatus of claim 32 or 33, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to:transmit a request to the at least one second apparatus for the indication, wherein the indication is received in response to the request.

35. The apparatus of any of claims 32 to 34, wherein the at least one data collection configuration comprises the reference time.

36. The apparatus of any of claims 24 to 35, wherein the configuration of the range comprises at least one of a minimum time offset with respect to a reference time or a maximum time offset with respect to the reference time, wherein the at least one of the minimum time offset or the maximum time offset defines a range for a time offset associated with the starting time.

37. The apparatus of claim 36, wherein the maximum time offset is based on at least one of: a cell radius, an indoor boundary, or a size of a service area or an associated assistance data area.

38. The apparatus of claim 36 or 37, wherein the minimum time offset is based on at least one of: a cell radius, an indoor boundary, a size of a service area or an associated assistance data area, a breakpoint distance, or a propagation delay.

39. The apparatus of any of claims 36 to 38, wherein the at least one of the minimum time offset or maximum time offset is configured in terms of a timing granularity of the apparatus.

40. The apparatus of any of claims 24 to 39, wherein the configuration of the range is fixed for a cell, or dynamically configured.

41. The apparatus of any of claims 24 to 40, wherein the at least one data collection configuration comprises information related to a distance between neighboring cells.

42. The apparatus of claims 24 to 41, wherein the apparatus is an LMF, and wherein the at least one second apparatus is a UE, a gNB, or a positioning reference unit.

43. The apparatus of claims 24 to 42, wherein the apparatus is a gNB, and the at least one second apparatus is a UE, or a second gNB.

44. A method, comprising:receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples;determining a starting time, within the configured range, to collect the data samples; determining a time offset based on the starting time and a reference time; and collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

45. A method, comprising:determining at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference,wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, andwherein a starting time for starting the collection of the data samples is within the range; andtransmitting, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

46. An apparatus, comprising:means for receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples;means for determining a starting time, within the configured range, to collect the data samples;means for determining a time offset based on the starting time and a reference time; and means for collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

47. An apparatus, comprising:means for determining at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference,wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, andwherein a starting time for starting the collection of the data samples is within the range; andmeans for transmitting, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

48. A computer readable medium comprising instructions stored thereon for performing at least the following:receiving, from a network node, at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference, wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples;determining a starting time, within the configured range, to collect the data samples; determining a time offset based on the starting time and a reference time; and collecting the data samples based on the configured range, wherein the collection of the data samples starts at the starting time.

49. A computer readable medium comprising instructions stored thereon for performing at least the following:determining at least one data collection configuration for collection of data samples used for AIML model training or / and re-training or / and inference,wherein the at least one data collection configuration for the collection of the data samples comprises a configuration of a range in a time domain for the collection of the data samples, andwherein a starting time for starting the collection of the data samples is within the range; andtransmitting, to at least one second apparatus, the at least one data collection configuration for the collection of the data samples.

Images