Positioning configuration management for ML training and reasoning

Abstract

Aspects presented herein can improve the efficiency and accuracy of machine learning (ML) training and reasoning, where entities associated with ML training / reasoning can identify whether same / similar configuration sets are used in ML training and ML reasoning. In one aspect, a UE receives a configuration for a set of positioning measurements from a network entity, where the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of reference signals (RSs). The UE performs a set of positioning measurements based on the configuration and the set of RSs. The UE stores at least one parameter for ML data collection or loads a first neural network (NN) based on the at least one configuration ID.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of Greek patent application serial number 20220100636, filed on August 3, 2022, entitled “POSITIONING CONFIGURATION MANAGEMENT FOR ML TRAINING AND INFERENCE”, the entire contents of which are expressly incorporated herein by reference. Technical Field

[0002] Generally speaking, the present disclosure relates to positioning systems, and more specifically, the present disclosure relates to positioning systems incorporating machine learning (ML). Background Art

[0003] Wireless communication systems have been widely deployed to provide a variety of telecommunication services such as telephony, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple access technologies that can support communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0004] Such multiple access technologies have been adopted in a variety of telecommunication standards to provide a common protocol that enables different wireless devices to communicate on a city-wide, national-wide, regional-wide, and even global scale. An exemplary telecommunication standard is 5G New Radio (NR). 5G NR is part of the continuous mobile broadband evolution released by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT)) and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine type communications (mMTC), and ultra-reliable low-latency communications (URLLC). Some aspects of 5G NR may be based on the 4G Long Term Evolution (LTE) standard. There is a need to further improve 5G NR technology. In addition, these improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0005] In order to have a basic understanding of one or more aspects of the present invention, a brief summary of these aspects is given below. This summary is not an exhaustive overview of all expected aspects. This summary is not intended to identify the key or important elements of all aspects, nor is it intended to describe the scope of any or all aspects. Its only purpose is to present some concepts of one or more aspects in a simple form as a prelude to the detailed description below.

[0006] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus receives a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration identifier (ID) associated with machine learning (ML) data collection or ML reasoning for a set of reference signals (RS). The apparatus performs the set of positioning measurements based on the configuration and the set of RSs. The apparatus stores at least one parameter for the ML data collection, or loads a first neural network (NN) based on the at least one configuration ID.

[0007] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus sends a configuration for a set of positioning measurements to a UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs. The apparatus receives at least one parameter for the ML data collection or the ML reasoning based on the at least one configuration ID.

[0008] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus receives a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs. The apparatus sends a Tx / Rx configuration to the network entity based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs. The apparatus sends the set of RSs based on the Tx / Rx configuration for the ML data collection or the ML reasoning.

[0009] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus sends a configuration for a set of positioning measurements to a UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs. The apparatus receives a Tx / Rx configuration based on the at least one configuration ID from the UE, wherein the Tx / Rx configuration is associated with reception of the set of RSs. The apparatus receives the set of RSs based on the Tx / Rx configuration for the ML data collection or the ML reasoning.

[0010] To achieve the foregoing and related ends, one or more aspects include the features described in detail below and particularly pointed out in the claims. The following description and the accompanying drawings describe in detail certain exemplary features of one or more aspects. However, these features are merely illustrative of some of the various ways in which the basic principles of these various aspects can be employed, and this description is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a diagram showing an example of a wireless communication system and an access network.

[0012] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0013] Figure 2B is a diagram illustrating an example of downlink (DL) channels within a subframe according to various aspects of the present disclosure.

[0014] Figure 2C is a diagram illustrating an example of a second frame according to various aspects of the present disclosure.

[0015] Figure 2D is a diagram illustrating examples of uplink (UL) channels within a subframe in accordance with various aspects of the present disclosure.

[0016] Figure 3 is a diagram showing an example of a base station and a user equipment (UE) in an access network.

[0017] Figure 4 is a diagram showing an example of UE positioning based on reference signal measurement.

[0018] Figure 5 is a diagram illustrating an example architecture of a functional framework associated with a machine learning (ML) model according to various aspects of the present disclosure.

[0019] Figure 6 is a diagram illustrating example advancements in ML architectures in cellular networks over the past few years, in accordance with various aspects of the present disclosure.

[0020] Figure 7 is a diagram illustrating example configurations of assistance data for downlink time difference of arrival (DL-TDOA) in accordance with various aspects of the present disclosure.

[0021] Figure 8 is a diagram illustrating exemplary downlink positioning reference signal (DL-PRS) assistance data in accordance with various aspects of the present disclosure.

[0022] Fig. 9is a diagram illustrating exemplary DL-PRS assistance data according to various aspects of the present disclosure.

[0023] Fig.10 is a diagram showing an example of associating or defining a configuration identifier (ID) for covering the entire assistance data according to various aspects of the present disclosure.

[0024] Fig.11 is a diagram illustrating an example configuration ID including multiple parts according to various aspects of the present disclosure.

[0025] Fig.12 is a diagram showing an example of associating or defining a configuration ID for each frequency layer according to various aspects of the present disclosure.

[0026] Fig.13 2 is a communication flow illustrating an example of associating a configuration ID for ML training and inference to a positioning associated with a PRS according to various aspects of the present disclosure.

[0027] Fig.14 1 is a communication flow illustrating an example of associating a configuration ID for ML training and inference to a positioning associated with an SRS according to various aspects of the present disclosure.

[0028] Fig.15 A flow chart of a wireless communication method.

[0029] Fig.16 A flow chart of a wireless communication method.

[0030] Fig.17 are diagrams illustrating examples of hardware implementations for example apparatuses and / or network entities.

[0031] Fig.18 A flow chart of a wireless communication method.

[0032] Fig.19 A flow chart of a wireless communication method.

[0033] Fig. 20 are diagrams illustrating examples of hardware implementations for example apparatuses and / or network entities.

[0034] Fig.21 A flow chart of a wireless communication method.

[0035] Fig. 22 A flow chart of a wireless communication method.

[0036] Fig.23 are diagrams illustrating examples of hardware implementations for example apparatuses and / or network entities.

[0037] Fig.24 A flow chart of a wireless communication method.

[0038] Fig.25 A flow chart of a wireless communication method.

[0039] Fig.26 are diagrams illustrating examples of hardware implementations for example apparatuses and / or network entities. DETAILED DESCRIPTION

[0040] The various aspects presented herein can improve the efficiency and accuracy of ML training and reasoning, where entities associated with ML training / reasoning can identify whether the same / similar configuration set is used in ML training and ML reasoning. For example, in one aspect of the present disclosure, a configuration identifier (ID) can be used to define the entire reference signal (RS) of the positioning signal in a part of the network (e.g., which can include a base station, a base station, an ML model, etc.). Then, for each configuration used by the network (e.g., a configuration of a PRS and / or SRS), the network can assign a unique configuration ID and record the configuration ID and its associated configuration (e.g., the parameters of the configured PRS and / or SRS) (e.g., recorded as [ID, Config]). For example, the configuration ID can be signaled or configured to a positioning entity (e.g., a UE, a base station, a location server, etc.) in a positioning configuration (e.g., if the positioning entity is a UE, it is sent via auxiliary data), and recorded by the positioning entity together with the data set used for ML training. For each positioning configuration, there may be a separate NN trained. Then, during ML reasoning, the positioning entity can receive the configuration ID and determine the corresponding NN to load and perform ML reasoning. As such, the various aspects presented herein may improve ML training / inference of localized entities since similar localization configurations are used for ML training / inference.

[0041] The specific embodiments described below in conjunction with the accompanying drawings describe various configurations, rather than representing that the concepts described herein can be implemented only in these configurations. In order to have a thorough understanding of the various concepts, the specific embodiments include specific details. However, these concepts can be implemented without using these specific details. In some instances, in order to avoid obscuring these concepts, known structures and components are shown in block diagram form.

[0042] Some aspects of telecommunication systems are presented with reference to various devices and methods. These devices and methods are described in the following detailed description and depicted in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). Such elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0043] For example, an element or any part of an element or any combination of elements can be implemented as a "processing system" including one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on chip (SoCs), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, separate hardware circuits, and other suitable hardware configured to perform various functions described throughout the present disclosure. One or more processors in a processing system can execute software. Software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes, functions, or any combination thereof, whether referred to as software, firmware, middleware, microcode, hardware description language, or other terms.

[0044] Therefore, in one or more example aspects, embodiments and / or use cases, the functions described herein may be implemented with hardware, software, or any combination thereof. When implemented using software, these functions may be stored or encoded into one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media. Storage media may be any available medium that a computer can access. By way of example, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer executable code in the form of instructions or data structures and can be accessed by a computer.

[0045] Although various aspects, embodiments and / or use cases are described in this application by describing some examples, additional or different aspects, embodiments and / or use cases can be implemented in many different arrangements and scenarios. The various aspects, embodiments and / or use cases described herein can be implemented across multiple different platform types, devices, systems, shapes, sizes and packaging arrangements. For example, various aspects, embodiments and / or use cases can be implemented by integrated chip implementations and other devices based on non-module components (e.g., end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchase equipment, medical equipment, devices supporting artificial intelligence (AI), etc.) or combinations thereof. Although some examples may be specifically targeted at use cases or applications, they may not be specifically targeted at use cases or applications, but various applicability of the described examples may occur. The scope of various aspects, embodiments and / or use cases can be from chip-level or modular components to non-modular, non-chip-level implementations, and can also be aggregated, distributed or original equipment manufacturer (OEM) devices or systems containing one or more technologies herein. In some actual settings, the equipment containing the described aspects and features may also be necessary to include other components and features for implementing and practicing the claimed and described aspects. For example, the transmission and reception of wireless signals necessarily include multiple components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / accumulators, etc.). The techniques described herein can be practiced in a wide variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc., having different sizes, shapes, and configurations.

[0046] The deployment of a communication system such as a 5G NR system may be arranged in a variety of ways with various components or constituent parts. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element, or a network device (e.g., a base station (BS) or one or more units (or one or more components) performing base station functions) may be implemented in an aggregated or decomposed architecture. For example, a BS (e.g., a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmission reception point (TRP), or a cell, etc.) may be implemented as an aggregated base station (also referred to as a stand-alone BS or a monolithic BS) or a decomposed base station.

[0047] The aggregated base station can be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node. The decomposed base station can be configured to utilize a protocol stack that is physically or logically distributed between two or more units (e.g., one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs)). In some aspects, the CU can be implemented within a RAN node, and one or more DUs can be co-located with the CU, or alternatively, can be geographically or virtually distributed in one or more other RAN nodes. The DU can be implemented to communicate with one or more RUs. Each of the CU, DU, and RU can also be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit.

[0048] Base station operations or network design may take into account the aggregated nature of base station functionality. For example, a decomposed network may be utilized in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (e.g., a network configuration sponsored by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality between two or more units at different physical locations, as well as distributing functionality for at least one unit virtually, which may enable flexibility in network design. Individual units of a decomposed base station or decomposed RAN architecture may be configured to communicate wired or wirelessly with at least one other unit.

[0049] Figure 1 100 is a diagram illustrating an example of a wireless communication system and access network. The wireless communication system shown includes a decomposed base station architecture. The decomposed base station architecture may include one or more CUs 110 that may communicate directly with a core network 120 via a backhaul link, or indirectly with the core network 120 through one or more decomposed base station units (e.g., a near real-time (near RT) RAN intelligent controller (RIC) 125 via an E2 link, or a non-real-time (non-RT) RIC 115 associated with a service management and orchestration (SMO) framework 105, or both). The CU 110 may communicate with one or more DUs 130 via corresponding mid-haul links such as an F1 interface. The DU 130 may communicate with one or more RUs 140 via respective fronthaul links. The RU 140 may communicate with each UE 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served simultaneously by multiple RUs 140.

[0050] Each unit (i.e., CU 110, DU 130, RU 140, near-RT RIC 125, non-RT RIC 115, and SMO framework 105) may include one or more interfaces or be coupled to one or more interfaces, and the one or more interfaces are configured to receive or transmit signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each unit or an associated processor or controller that provides instructions to the communication interface of the unit may be configured to communicate with one or more other units via a transmission medium. For example, these units may include a wired interface that is configured to receive signals from or send signals to one or more other units via a wired transmission medium. In addition, these units may include a wireless interface, which may include a receiver, a transmitter, or a transceiver (e.g., an RF transceiver) that is configured to receive signals from or send signals to, or both, one or more other units via a wireless transmission medium.

[0051] In some aspects, CU 110 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface configured to communicate signals with other control functions hosted by CU 110. CU 110 may be configured to process user plane functions (i.e., central unit-user plane (CU-UP)), control plane functions (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some implementations, CU 110 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface such as an E1 interface. CU 110 may be implemented to communicate with DU130 as needed for network control and signaling.

[0052] DU 130 may correspond to a logical unit that includes one or more base station functions to control the operation of one or more RU 140. In some aspects, DU 130 may host one or more of the following based on functional splitting: a radio link control (RLC) layer, a media access control (MAC) layer, and one or more high physical (PHY) layers (e.g., modules for forward error correction (FEC) encoding and decoding, scrambling, modulation, demodulation, etc.), such as those defined by 3GPP. In some aspects, DU 130 may further host one or more low PHY layers. Each layer (or module) may be implemented with an interface that is configured to communicate signals with other layers (and modules) hosted by DU 130, or with control functions hosted by CU 110.

[0053] Lower layer functions may be implemented by one or more RUs 140. In some deployments, based at least in part on a functional split such as a partitioning of lower layer functions, a RU 140 controlled by a DU 130 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (e.g., performing fast Fourier transforms (FFTs), inverse FFTs (iFFTs), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both. In such an architecture, the RU 140 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some implementations, real-time and non-real-time aspects of control and user plane communications with the RU 140 may be controlled by the corresponding DU 130. In some scenarios, this configuration may enable the implementation of the DU 130 and CU 110 in a cloud-based RAN architecture (e.g., a vRAN architecture).

[0054] The SMO framework 105 may be configured to support RAN deployment and provisioning of non-virtualized and virtualized network elements. For non-virtualized network elements, the SMO framework 105 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, and RAN coverage requirements may be managed through an operation and maintenance interface (e.g., an O1 interface). For virtualized network elements, the SMO framework 105 may be configured to interact with a cloud computing platform (e.g., an open cloud (O-Cloud) 190) to perform network element lifecycle management (e.g., instantiating virtualized network elements) via a cloud computing platform interface (e.g., an O2 interface). Such virtualized network elements may include, but are not limited to, CU 110, DU 130, RU 140, and near-RT RIC 125. In some implementations, the SMO framework 105 may communicate with hardware aspects of the 4G RAN (e.g., an open eNB (O-eNB) 111) via an O1 interface. In addition, in some implementations, the SMO framework 105 may communicate directly with one or more RUs 140 via an O1 interface. The SMO framework 105 may also include a non-RT RIC 115 that is configured to support the functionality of the SMO framework 105 .

[0055] The non-RT RIC 115 may be configured to include logic functions that implement non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) / machine learning (ML) (AI / ML) workflows (including model training and updating), or policy-based guidance of applications / features in the near-RT RIC 125. The non-RT RIC 115 may be coupled to or communicate with the near-RT RIC 125 (e.g., via an A1 interface). The near-RT RIC 125 may be configured to include logic functions that implement control and optimization of RAN elements and resources in near real time through data collection and actions on interfaces connecting one or more CUs 110, one or more DUs 130, or both, and O-eNBs to the near-RT RIC 125 (e.g., via an E2 interface).

[0056] In some implementations, in order to generate the AI / ML model to be deployed in the near-RT RIC 125, the non-RT RIC 115 may receive parameters or external enrichment information from an external server. Such information may be used by the near-RT RIC 125 and may be received from a non-network data source or from a network function at the SMO framework 105 or the non-RT RIC 115. In some examples, the non-RT RIC 115 or the near-RT RIC 125 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 115 may monitor long-term trends and patterns in performance and employ AI / ML models to perform corrective actions through the SMO framework 105 (e.g., via reconfiguration of O1) or via the creation of RAN management policies (e.g., A1 policies).

[0057] At least one of the CU 110, the DU 130, and the RU 140 may be referred to as a base station 102. Therefore, the base station 102 may include one or more of the CU 110, the DU 130, and the RU 140 (each component is represented by a dotted line to indicate that each component may be included in the base station 102 or may not be included in the base station 102). The base station 102 provides an access point for the core network 120 for the UE 104. The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). Small cells include femto cells, pico cells, and micro cells. A network including small cells and macro cells may be referred to as a heterogeneous network. A heterogeneous network may also include a home evolved Node B (eNB) (HeNB), which may provide services to a restricted group called a closed subscriber group (CSG). The communication link between RU 140 and UE 104 may include an uplink (UL) (also known as a reverse link) transmission from UE 104 to RU 140 and / or a downlink (DL) (also known as a forward link) transmission from RU 140 to UE 104. The communication link may use multiple-input multiple-output (MIMO) antenna technology including spatial multiplexing, beamforming and / or transmit diversity. The communication link may be through one or more carriers. The base station 102 / UE 104 may use a spectrum of up to Y MHz (e.g., 5, 10, 15, 20, 100, 400, etc. MHz) bandwidth per carrier allocated in carrier aggregation, with a total of Yx MHz (x component carriers) in each direction for transmission. These carriers may be adjacent to each other or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​than for UL). These component carriers may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell), and the secondary component carrier may be referred to as a secondary cell (SCell).

[0058] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL wireless wide area network (WWAN) spectrum. The D2D communication link 158 may use one or more side link channels, such as a physical side link broadcast channel (PSBCH), a physical side link discovery channel (PSDCH), a physical side link shared channel (PSSCH), and a physical side link control channel (PSCCH). D2D communication may be performed through various wireless D2D communication systems such as Bluetooth, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0059] The wireless communication system may also include a Wi-Fi AP 150 that communicates with a UE 104 (also referred to as a Wi-Fi station (STA)) via a communication link 154 (e.g., in a 5 GHz unlicensed spectrum, etc.). When communicating in an unlicensed spectrum, the UE 104 / AP 150 may perform a clear channel assessment (CCA) prior to communication to determine whether a channel is available.

[0060] The electromagnetic spectrum is usually subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified with the frequency range names FR1 (410MHz-7.125GHz) and FR2 (24.25GHz-52.6GHz). Although a portion of FR1 is greater than 6GHz, FR1 is often (interchangeably) referred to as the "sub-6GHz" band in various documents and articles. FR2 sometimes presents a similar naming issue, although it is different from the extremely high frequency (EHF) band (30GHz-300 GHz), which is defined as the "millimeter wave" band by the International Telecommunication Union (ITU), but it is often (interchangeably) referred to as the "millimeter wave" band in various documents and articles.

[0061] Frequencies between FR1 and FR2 are often referred to as mid-band frequencies. Recent 5G NR research has identified the operating frequency bands for these mid-band frequencies as the frequency range FR3 (7.125 GHz–24.25 GHz). Frequency bands that fall within FR3 may inherit FR1 characteristics and / or FR2 characteristics, and thus may effectively extend the characteristics of FR1 and / or FR2 to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations above 52.6 GHz. For example, three higher operating frequency bands have been identified as the frequency range names FR2-2 (52.6 GHz–71 GHz), FR4 (71 GHz–114.25 GHz), and FR5 (114.25 MHz–300 GHz). Each of these higher frequency bands falls within the EHF band.

[0062] In view of the above, unless otherwise explicitly stated, the term "sub-6 GHz" and the like (if used herein) may broadly refer to frequencies less than 6 GHz, which may be within FR1, or may include mid-band frequencies. In addition, unless otherwise explicitly stated, the term "millimeter wave" and the like (if used herein) may broadly refer to frequencies including mid-band frequencies, which may be within FR2, FR4, FR2-2 and / or FR5, or may be within the EHF band.

[0063] The base station 102 and the UE 104 may each include multiple antennas (e.g., antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming. The base station 102 may send a beamformed signal 182 to the UE 104 in one or more transmit directions. The UE 104 may receive the beamformed signal from the base station 102 in one or more receive directions. The UE 104 may also send a beamformed signal 184 to the base station 102 in one or more transmit directions. The base station 102 may receive the beamformed signal from the UE 104 in one or more receive directions. The base station 102 / UE 104 may perform beam training to determine the best receive and transmit directions for each of the base stations 102 / UE 104. The transmit and receive directions of the base station 102 may be the same or different. The transmit and receive directions of the UE 104 may be the same or different.

[0064] The base station 102 may include and / or be referred to as a gNB, a Node B, an eNB, an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmission reception point (TRP), a network node, a network entity, a network device, or some other appropriate term. The base station 102 may be implemented as an integrated access and backhaul (IAB) node, a relay node, a sidelink node, an aggregated (monolithic) base station having a baseband unit (BBU) (including a CU and a DU) and a RU, or as a decomposed base station including one or more of a CU, a DU, and / or a RU. A set of base stations including decomposed base stations and / or aggregated base stations may be referred to as a next generation (NG) RAN (NG-RAN).

[0065] The core network 120 may include an access and mobility management function (AMF) 161, a session management function (SMF) 162, a user plane function (UPF) 163, a unified data management (UDM) 164, one or more location servers 168, and other functional entities. AMF 161 is a control node that handles signaling between UE 104 and core network 120. AMF 161 supports registration management, connection management, mobility management, and other functions. SMF 162 supports session management and other functions. UPF 163 supports packet routing, packet forwarding, and other functions. UDM 164 supports the generation of authentication and key agreement (AKA) credentials, user identification processing, access authorization, and subscription management. One or more location servers 168 are shown as including a gateway mobile positioning center (GMLC) 165 and a location management function (LMF) 166. However, in general, the one or more location servers 168 may include one or more location / positioning servers, which may include one or more of the GMLC 165, LMF 166, position determination entity (PDE), serving mobile location center (SMLC), mobile positioning center (MPC), etc. GMLC 165 and LMF 166 support UE positioning services. GMLC 165 provides an interface for clients / applications (e.g., emergency services) to access UE positioning information. LMF 166 receives measurement and assistance information from NG-RAN and UE 104 via AMF 161 to calculate the location of UE 104. NG-RAN can determine the location of UE 104 using one or more positioning methods. Positioning UE 104 may include signal measurements, position estimation, and optional speed calculation based on measurements. Signal measurements may be performed by UE 104 and / or serving base station 102. The measured signal can be based on one or more of the following: a satellite positioning system (SPS) 170 (e.g., one or more of a global navigation satellite system (GNSS), a global positioning system (GPS), a non-terrestrial network (NTN), or other satellite positioning / positioning systems), an LTE signal, a wireless local area network (WLAN) signal, a Bluetooth signal, a terrestrial beacon system (TBS), sensor-based information (e.g., a pressure sensor, a motion sensor), an NR enhanced cell ID (NR E-CID) method, an NR signal (e.g., multi-round trip time (Multi-RTT), DL departure angle (DL-AoD), DL arrival time difference (DL-TDOA), UL arrival time difference (UL-TDOA), and UL arrival angle (UL-AoA) positioning) and / or other systems / signals / sensors.

[0066] Examples of UE 104 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablet devices, smart devices, wearable devices, vehicles, electric meters, gas pumps, large or small kitchen appliances, medical devices, implants, sensors / actuators, displays, or any other similarly functional devices. Some of UE 104 may be referred to as IoT devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as stations, mobile stations, user stations, mobile units, user units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile user stations, access terminals, mobile terminals, wireless terminals, remote terminals, handheld devices, user agents, mobile clients, clients, or some other appropriate terminology. In some scenarios, the term UE may also be applied to one or more companion devices (e.g., in a device constellation arrangement). One or more of these devices may access the network collectively and / or individually.

[0067] Reference again Figure 1 In some aspects, the UE 104 may be configured to: receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs; perform the set of positioning measurements based on the configuration and the set of RSs; and store at least one parameter for ML data collection, or load a first NN based on the at least one configuration ID (e.g., via a configuration ID associating component 198). In some aspects, the UE 104 may be configured to: receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs; send a Tx / Rx configuration to the network entity based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs; send the set of RSs based on the Tx / Rx configuration for ML data collection or ML reasoning (e.g., via a configuration ID associating component 198).

[0068] In certain aspects, the base station 102 may be configured to: send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs; and based on the at least one configuration ID, receive at least one parameter for ML data collection or ML reasoning (e.g., via the configuration ID association component 199). In certain aspects, the base station 102 may be configured to: send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs; receive a Tx / Rx configuration from the UE based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs; and receive the set of RSs based on the Tx / Rx configuration for ML data collection or ML reasoning (e.g., via the configuration ID association component 199).

[0069] Figure 2A Figure 200 shows an example of the first subframe in the 5G NR frame structure. Figure 2B FIG230 is a diagram showing an example of DL channels in a 5G NR subframe. Figure 2C Figure 250 shows an example of a second subframe in a 5G NR frame structure. Figure 2D FIG280 is a diagram showing an example of UL channels in a 5G NR subframe. The 5G NR frame structure can be either frequency division duplex (FDD) or time division duplex (TDD), where in the case of FDD, for a particular set of subcarriers (carrier system bandwidth), the subframes within the set of subcarriers are dedicated to DL or UL, and in the case of TDD, for a particular set of subcarriers (carrier system bandwidth), the subframes within the set of subcarriers are dedicated to both DL and UL. Figure 2A , 2C In the example provided, it is assumed that the 5G NR frame structure is TDD, where subframe 4 is configured with slot format 28 (primarily DL), where D is DL, U is UL, and F is used flexibly between DL / UL, and subframe 3 is configured with slot format 1 (all UL). Although subframes 3 and 4 are shown with slot formats 1 and 28, respectively, any particular subframe can be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are full DL and UL, respectively. Other slot formats 2-61 include a mix of DL, UL and flexible symbols. The slot format is configured for the UE through the received slot format indicator (SFI) (dynamically configured through DL control information (DCI), or semi-statically / statically configured through radio resource control (RRC) signaling). It should be noted that the following description also applies to the 5G NR frame structure of TDD.

[0070] Figures 2A-2DThe frame structure is shown, and various aspects of the present disclosure can be applied to other wireless communication technologies, which may have different frame structures and / or different channels. A frame (10ms) can be divided into 10 subframes (1ms) of equal size. Each subframe may include one or more time slots. A subframe may also include a micro time slot, which may include 7, 4 or 2 symbols. Depending on whether the cyclic prefix (CP) is normal or extended, each time slot may include 14 or 12 symbols. For a normal CP, each time slot may include 14 symbols, and for an extended CP, each time slot may include 12 symbols. The symbol on the DL may be a CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) extended OFDM (DFT-s-OFDM) symbol (also known as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single-stream transmission). The number of time slots within a subframe is based on the CP and parameter set. The parameter set specifies the subcarrier spacing (SCS) and effectively defines the symbol length / duration (which is equal to 1 / SCS). Table 1

[0071] For normal CP (14 symbols / slot), different parameter sets μ0 to 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For extended CP, parameter set 2 allows 4 slots per subframe. Thus, for normal CP and parameter set μ, there are 14 symbols / slot and 2 μ timeslots / subframe. The subcarrier spacing can be equal to 2 μ *15kHz, where μ is parameter set 0 to 4. Thus, the subcarrier spacing is 15kHz for parameter set μ=0 and 240kHz for parameter set μ=4. The symbol length / duration is inversely proportional to the subcarrier spacing. Figures 2A-2D An example of a parameter set μ=2 with a normal CP of 14 symbols per slot and 4 slots per subframe is provided. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs. Within a set of frames, there may be one or more different bandwidth parts (BWPs) for frequency division multiplexing (see Figure 2B ). Each BWP can have a specific parameter set and CP (normal or extended).

[0072] A resource grid may be used to represent the frame structure. Each slot includes a resource block (RB) (also called a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a plurality of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0073] like Figure 2A As shown in , some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) (indicated as R for a particular configuration, but other DM-RS configurations are also possible) and a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement (BRRS), and a phase tracking RS (PT-RS).

[0074] Figure 2B Examples of various DL channels in a subframe of a frame are shown. The physical downlink control channel (PDCCH) carries DCI in one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE including six RE groups (REGs), each REG including 12 consecutive REs in an OFDM symbol of an RB. The PDCCH within a BWP may be referred to as a control resource set (CORESET). The UE is configured to monitor PDCCH candidates in a PDCCH search space (e.g., a common search space, a UE-specific search space) during a PDCCH monitoring opportunity on the CORESET, wherein the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at higher and / or lower frequencies on the channel bandwidth. The primary synchronization signal (PSS) may be within symbol 2 of a specific subframe of a frame. The UE 104 uses the PSS to determine subframe / symbol timing and physical layer identification. The secondary synchronization signal (SSS) may be located within symbol 4 of a specific subframe of a frame. The UE uses the SSS to determine the physical layer cell identification group number and radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine the physical cell identifier (PCI). Based on the PCI, the UE can determine the location of the DM-RS. The physical broadcast channel (PBCH) carrying the master information block (MIB) can be logically combined with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also known as an SS block (SSB)). The MIB provides the number of RBs in the system bandwidth and the system frame number (SFN). The physical downlink shared channel (PDSCH) carries user data, broadcast system information that is not sent through the PBCH (e.g., system information block (SIB)), and paging messages.

[0075] like Figure 2CAs shown in , some of the REs carry DM-RS (indicated as R for a specific configuration, but other DMRS configurations are also possible) for channel estimation at the base station. The UE can send DM-RS for the physical uplink control channel (PUCCH) and DM-RS for the physical uplink shared channel (PUSCH). The PUSCH DM-RS can be sent in the first one or two symbols of the PUSCH. Depending on whether a short or long PUCCH is sent and depending on the specific PUCCH format used, the PUCCH DM-RS can be sent in different configurations. The UE can send a sounding reference signal (SRS). The SRS can be sent in the last symbol of the subframe. The SRS can have a comb structure, and the UE can send the SRS on one of these comb structures. The base station can use the SRS for channel quality estimation to achieve frequency-dependent scheduling on the UL.

[0076] Figure 2D Examples of various UL channels in a subframe of a frame are shown. The PUCCH may be located as indicated in one configuration. The PUCCH carries uplink control information (UCI) such as scheduling requests, channel quality indicator (CQI), precoding matrix indicator (PMI), rank indicator (RI), and hybrid automatic repeat request (HARQ) acknowledgement (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACK / negative ACK (NACK)). The PUSCH carries data and may also be used to carry a buffer status report (BSR), a power headroom report (PHR), and / or UCI.

[0077] Figure 33 is a block diagram of the communication between the base station 310 and the UE 350 in the access network. In the DL, the Internet Protocol (IP) packets are provided to the controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functions. Layer 3 includes the radio resource control (RRC) layer, and layer 2 includes the service data adaptation protocol (SDAP) layer, the packet data convergence protocol (PDCP) layer, the radio link control (RLC) layer, and the medium access control (MAC) layer. The controller / processor 375 provides: RRC layer functions associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), mobility between radio access technologies (RATs), and measurement configuration for UE measurement reporting; PDCP layer functions associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functions associated with transmission of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; MAC layer functions associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0078] The transmit (TX) processor 316 and the receive (RX) processor 370 implement layer 1 functions associated with various signal processing functions. Layer 1, including the physical (PHY) layer, may include error detection on the transmission channel, forward error correction (FEC) encoding / decoding of the transmission channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The TX processor 316 processes the mapping for the signal constellation based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase phase shift keying (M-PSK), M-order quadrature amplitude modulation (M-QAM)). Subsequently, the coded and modulated symbols may be split into parallel streams. Subsequently, each stream may be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time domain and / or frequency domain, and then combined using an inverse Fourier transform (IFFT) to generate a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially precoded to generate multiple spatial streams. Channel estimates from the channel estimator 374 may be used to determine the coding and modulation schemes and to implement spatial processing. The channel estimates may be derived from reference signals and / or channel condition feedback sent by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318Tx. Each transmitter 318Tx may modulate a radio frequency (RF) carrier using each spatial stream for transmission.

[0079] At the UE 350, each receiver 354Rx receives a signal through its respective antenna 352. Each receiver 354Rx recovers the information modulated onto the RF carrier and provides the information to a receive (RX) processor 356. The TX processor 368 and the RX processor 356 implement layer 1 functions associated with various signal processing functions. The RX processor 356 can perform spatial processing on the information to recover any spatial streams destined for the UE 350. If multiple spatial streams are destined for the UE 350, the RX processor 356 can combine them into a single OFDM symbol stream. Subsequently, the RX processor 356 uses a fast Fourier transform (FFT) to transform the OFDM symbol stream from the time domain to the frequency domain. The frequency domain signal includes a separate OFDMA symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier and the reference signal are recovered and demodulated by determining the most likely signal constellation point sent by the base station 310. These soft decisions can be based on the channel estimates calculated by the channel estimator 358. These soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by base station 310. These data and control signals are then provided to controller / processor 359, which implements layer 3 and layer 2 functions.

[0080] The controller / processor 359 may be associated with a memory 360 that stores program codes and data. The memory 360 may be referred to as a computer readable medium. In the UL, the controller / processor 359 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0081] Similar to the functions described in conjunction with the DL transmission of the base station 310, the controller / processor 359 provides: RRC layer functions associated with system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functions associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functions associated with transmission of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; MAC layer functions associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority processing, and logical channel prioritization.

[0082] Channel estimates derived by the channel estimator 358 from a reference signal or feedback sent by the base station 310 may be used by the TX processor 368 to select appropriate coding and modulation schemes and to facilitate spatial processing. The spatial streams generated by the TX processor 368 may be provided to different antennas 352 via respective transmitters 354Tx. Each transmitter 354Tx may modulate an RF carrier with a respective spatial stream for transmission.

[0083] The base station 310 processes UL transmissions in a manner similar to that described in conjunction with the receiver functionality at the UE 350. Each receiver 318Rx receives signals through its respective antenna 320. Each receiver 318Rx recovers information modulated onto an RF carrier and provides the information to the RX processor 370.

[0084] The controller / processor 375 may be associated with a memory 376 that stores program codes and data. The memory 376 may be referred to as a computer readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0085] At least one of the TX processor 368, the RX processor 356, and the controller / processor 359 may be configured to perform operations related to Figure 1 Aspects related to the configuration ID associated with component 198.

[0086] At least one of the TX processor 316, the RX processor 370, and the controller / processor 375 may be configured to perform operations related to Figure 1 The configuration ID is associated with component 199 related aspects.

[0087] Figure 4 FIG. 4 is a diagram illustrating an example of UE positioning based on reference signal measurements (also referred to as “network-based positioning”) according to various aspects of the present disclosure. UE 404 may be at time T SRS_TX UL-SRS 412 is sent and at time T PRS_RX Receive a DL positioning reference signal (PRS) (DL-PRS) 410. TRP 406 may be at time T SRS_RX Receive UL-SRS 412, and at time T PRS_TX 410. UE 404 may receive DL-PRS 410 before transmitting UL-SRS 412, or may transmit UL-SRS 412 before receiving DL-PRS 410. In both cases, a positioning server (e.g., location server 168) or UE 404 may determine the UL-SRS 412 based on ||T SRS_RX –T PRS_TX |–|T SRS_TX –T PRS_RX || determines RTT 414. Thus, multi-RTT positioning can utilize UE Rx-Tx time difference measurements (i.e., |T SRS_TX –T PRS_RX |) and DL-PRS reference signal received power (RSRP) (DL-PRS-RSRP), and TRP Rx-Tx time difference measurements measured at multiple TRPs 402, 406 for uplink signals sent from UE 404 (i.e., |T SRS_RX –T PRS_TX|). UE 404 measures UE Rx-Tx time difference measurements (and / or DL-PRS-RSRP of received signals) using assistance data received from the positioning server, and TRP 402, 406 measures gNB Rx-Tx time difference measurements (and / or UL-SRS-RSRP of received signals) using assistance data received from the positioning server. These measurements may be used at the positioning server or UE 404 to determine RTT, which is used to estimate the position of UE 404. Other methods may also be used, such as using downlink (DL)-time difference of arrival (TDOA) (DL-TDOA) and / or uplink TODA (UL-TDOA) measurements to determine RTT.

[0088] DL AoD positioning can utilize DL-PRS-RSRP measured at the UE 404 for downlink signals received from multiple TRPs 402, 406. The UE 404 uses the assistance data received from the positioning server to measure the DL-PRS-RSRP of the received signals, and uses the obtained measurements together with the azimuth angle deviation (A-AoD), the zenith angle deviation (Z-AoD) and other configuration information to position the UE 404 relative to the neighboring TRPs 402, 406.

[0089] DL-TDOA positioning can utilize DL reference signal time difference (RSTD) (and / or DL-PRS-RSRP) of downlink signals received from multiple TRPs 402, 406 at UE 404. UE 404 uses assistance data received from a positioning server to measure the DL RSTD (and / or DL-PRS-RSRP) of the received signals, and uses the obtained measurements together with other configuration information to position UE 404 relative to neighboring TRPs 402, 406.

[0090] UL-TDOA positioning can utilize the UL relative time of arrival (RTOA) (and / or UL-SRS-RSRP) of uplink signals sent from UE 404 at multiple TRPs 402, 406. TRPs 402, 406 use assistance data received from a positioning server to measure the UL-RTOA (and / or UL-SRS-RSRP) of the received signals, and use the obtained measurements together with other configuration information to estimate the position of UE 404.

[0091] UL-AoA positioning can utilize the azimuth angle of arrival (A-AoA) and the zenith angle of arrival (Z-AoA) measured at multiple TRPs 402, 406 of uplink signals sent from the UE 404. The TRPs 402, 406 measure the A-AoA and Z-AoA of the received signals using assistance data received from a positioning server, and use the obtained measurements together with other configuration information to estimate the position of the UE 404.

[0092] Other positioning methods (e.g., UE-side UL-AoD and / or DL-AoA) may be used to estimate the position of UE 404. It should be noted that the data / measurements from the various techniques may be combined in various ways to improve accuracy, determine and / or enhance certainty, supplement / supplement measurements, and / or replace / provide missing information. For ease of description of the present disclosure, the suffixes "based on" and "assisted" may refer to a node responsible for performing positioning calculations (and may also provide measurements) and a node providing measurements (but may not perform positioning calculations), respectively. For example, the operation of a UE providing measurements to a base station / positioning entity for use in calculating a position estimate may be described as "UE-assisted," "UE-assisted positioning," and / or "UE-assisted position calculation," while the operation of a UE calculating its own position may be described as "UE-based," "UE-based positioning," and / or "UE-based position calculation."

[0093] The speed, bandwidth, latency, and reliability of wireless communications (and network-based positioning) have increased significantly over the past few decades, which in some cases has increased the complexity of deploying wireless networks. To improve the management of various network nodes and functions, wireless communications operators and providers have begun to adopt artificial intelligence and machine learning (AI / ML) for their services. In one example, artificial intelligence can be broadly defined as configuring computers / electronic devices to perform tasks that are considered to be uniquely human. ML is a category of artificial intelligence technology that includes algorithms that can automatically improve performance without explicit programming.

[0094] In some examples, ML algorithms may include supervised learning, unsupervised learning, and / or reinforcement learning. Under supervised learning, the ML model can be given labeled input and output data during the training phase of ML. This training data is usually labeled by a data scientist during the preparation phase and then used to train and test the ML model. Once the ML model learns the relationship between the input and output data, it can be used to classify and predict outcomes for new and unseen data sets. Under unsupervised learning, the ML model can be trained based on raw and unlabeled training data, where the ML model is often used to identify patterns and trends in the raw data set or cluster similar data into a specific number of groups. Unsupervised machine learning may be more of a hands-off approach compared to supervised learning, where the ML model can be configured to effectively process large amounts of data without human supervision. Under reinforcement learning, the ML model can be trained based on rewarding appropriate actions and / or punishing inappropriate actions. For example, positive values ​​can be assigned to appropriate actions to encourage the ML model, while negative values ​​can be assigned to inappropriate actions. This can enable the ML model to seek long-term and maximum overall rewards to achieve the best solution. ML models are often associated with neural networks (NNs), which may also be called artificial neural networks (ANNs) or simulated neural networks (SNNs). A neural network may refer to a computer architecture in which many processors are interconnected in a way that suggests the connections between neurons in the human brain and are able to learn through a process of trial and error.

[0095] For the purposes of this disclosure, "inference" or "ML inference" may refer to the process of running data points into an ML model (e.g., via an inference host) to compute an output (e.g., a single number score), such as making a prediction using a trained ML algorithm. "Inference host" or "ML inference host" may refer to a network function that hosts an ML model during inference mode. On the other hand, "training" or "ML training" may refer to the process of running data points to train or teach an ML model (e.g., via a training host). "Training host" or "ML training host" may refer to a network function that hosts an ML model during training mode.

[0096] Figure 5500 is a diagram of an example architecture of a functional framework associated with an ML model according to various aspects of the present disclosure. In some scenarios, data collection can be further enhanced by use cases and / or examples to implement the functional framework of the ML model. In one example, as shown in Figure 500, the functional framework of the ML model may include multiple logical entities, such as a model training host 502, a model reasoning host 504, a data source 506, and / or an actuator 508, etc. In some examples, multiple logical entities may be co-located on the same device (e.g., UE, positioning device, etc.) or network node (e.g., base station, component of base station, server, etc.). In other examples, different logical entities may be located on different devices or network nodes.

[0097] The model inference host 504 can be configured to run the ML model based on the inference data provided by the data source 506, and the model inference host 506 can generate output (e.g., prediction) using the inference data input to the executor 508. The executor 508 can be a device or entity. For example, the executor 508 can be a GNSS device or a location server associated with the GNSS device, etc. In addition, the executor 508 can also depend on the type of task performed by the model inference host 504, the type of inference data provided to the model inference host 504, and / or the type of output generated by the model inference host 504, etc.

[0098] After the actuator 508 receives the output from the model inference host 504, the actuator 508 can determine whether or how to act based on the output. For example, if the actuator 508 is a location server and the output from the model inference host 504 is associated with a PR measurement classification, the actuator 508 can determine how to classify one or more PR measurements performed based on the output. The actuator 508 can then indicate the classification to at least one actor 510. In some examples, the actuator 508 and the at least one actor 510 can be the same entity (e.g., a UE).

[0099] The data source 506 may also be configured to collect data that will be used as training data for training the ML model or as inference data for feeding the ML model inference operation. For example, the data source 506 may collect data from one or more UEs, base stations, or location servers (which may include the actor 510) and provide the collected data to the model training host 502 for ML model training. In some examples, if the output provided by the actuator 508 is inaccurate (or the accuracy is below an accuracy threshold), the model training host 502 may determine to modify or retrain the ML model used by the model inference host, such as through ML model deployment / update.

[0100] Figure 6600 is a diagram illustrating an example progression of ML architectures (e.g., ML-based algorithms) in cellular networks over the past few years, in accordance with various aspects of the present disclosure. As shown at 602, initially, the ML models used in cellular networks may include a fixed neural network (NN) architecture, where everything is trained offline. Although ML inference is performed online, it is based on a fixed rate. Then, as shown at 604, at some later point in time, while the NN architecture remains fixed and the initial ML training is still offline, inference may be performed online with weight adaptation. Thus, the ML model may perform some basic refinement and / or retraining online. As shown at 606, at some later point in time, while the NN architecture remains fixed, both ML training and ML inference may be online with weight adaptation for ML inference. At a more current point in time, as shown at 608, the ML model begins to adopt a dynamic NN architecture, where both ML training and ML inference are online, and ML inference may be performed with dynamic weight adaptation. As more and more ML functions come online and become dynamic, the signaling between different entities associated with ML (e.g., between UE and base station or server) may also increase significantly.

[0101] In some examples, for network-based positioning, the NN used in association with UE positioning (which may be referred to as the positioning NN) may be configured to utilize DL-PRS and UL-SRS to derive channels, where the input to the positioning NN may be derived from the channels. In addition, the NN may be trained at one point in time, while reasoning may be performed at a later point in time. In some scenarios, it may be more appropriate to have the same DL-PRS and UL-SRS configuration during ML training and ML reasoning in order to obtain the best results. For example, although some parameter changes in the DL-PRS / UL-SRS configuration may not significantly affect the ML training / reasoning results, it may be important / critical to maintain consistency in other parameters of the DL-PRS / UL-SRS configuration throughout the ML training / reasoning process. In some examples, the network and / or UE may have different NNs trained for different DL-PRS / UL-SRS configurations. Therefore, the NN, the network, and / or the UE may not be able to determine or identify whether the same configuration is used in ML training and ML reasoning, which may affect the accuracy of ML training / reasoning.

[0102] The various aspects proposed herein can improve the efficiency and accuracy of ML training and reasoning, where entities associated with ML training / reasoning can identify whether the same / similar configuration set is used in ML training and ML reasoning. For example, in one aspect of the present disclosure, a configuration identifier (ID) can be used to define the entire reference signal (RS) of the positioning signal in a part of the network (e.g., which can include a base station, a base station, an ML model, etc.). Then, for each configuration used by the network (e.g., a configuration for PRS and / or SRS), the network can assign a unique configuration ID and record the configuration ID and its associated configuration (e.g., the parameters of the configured PRS and / or SRS) (e.g., recorded as [ID, Config]). For example, the configuration ID can be signaled or configured to a positioning entity (e.g., UE, base station, location server, etc.) in the positioning configuration (e.g., if the positioning entity is a UE, it is sent via auxiliary data), and recorded by the positioning entity together with the data set used for ML training. For each positioning configuration, there may be a separate NN training. Then, during ML reasoning, the positioning entity can receive the configuration ID and determine the corresponding NN to load and perform ML reasoning. As such, the various aspects presented herein may improve ML training / inference of localized entities since similar localization configurations are used for ML training / inference.

[0103] Figure 7 700 is a diagram illustrating an example configuration of assistance data for DL-TDOA according to various aspects of the present disclosure. In one example, for each defined positioning method (e.g., DL-TDOA, DL-AoD, UL-TDOA, UL-AoA, etc.), overall assistance data (e.g., NR-DL-TDOA-ProvideAssistanceData) may be defined for the positioning method, which may include DL-PRS assistance data (e.g., nr-DL-PRS-AssistanceData), positioning calculation assistance data (e.g., nr-PositionCalculationAssistance) and / or error event data (e.g., nr-DL-TDOA-Error).

[0104] Figure 8 800 is a diagram illustrating example DL-PRS assistance data in accordance with various aspects of the present disclosure. In one example, the DL-PRS assistance data may include assistance data for a TRP sequence for each frequency layer and a definition for each frequency layer.

[0105] Fig. 9900 is a diagram illustrating example DL-PRS assistance data according to various aspects of the present disclosure. In one example, the positioning calculation assistance data may include TRP position information, beam information, and / or real time difference (RTD) information, among other things.

[0106] In one aspect of the present disclosure, during a UE positioning session, a positioning entity (e.g., UE, base station, location server, LMF, etc.) may indicate to another positioning party whether one or more reference signals configured for the UE positioning session are associated with ML training / inference. For example, the positioning entity (e.g., base station or UE) may use a flag (or specific signaling) to indicate whether PRS and / or SRS are used for ML data collection of an ML model. ML data collection may refer to one or more parameters of PRS / SRS collected as input / training data for an ML model or NN. In addition, the positioning entity may also indicate the type of ML data collection, such as whether the ML data collection is used for ML training, ML reasoning, and / or ML refinement. In some examples, the positioning entity may also indicate a priority associated with ML data collection. For example, the network entity may indicate the priority of ML data collection to the UE in a priority field. If the priority field indicates a high priority, ML data collection may take precedence over some other signals (e.g., PDSCH) or processing. In other words, if ML data collection cannot be used at the same time to perform certain tasks or signaling, the UE may be configured to abandon these tasks or signaling. However, if the priority field indicates a low priority, the UE may be configured to optionally perform ML data collection (eg, when the UE has sufficient resources to do so). The network entity may signal a range of priorities that have different effects on processing other signals.

[0107] Fig.101000 is a diagram showing an example of associating or defining a configuration ID for covering the entire auxiliary data according to various aspects of the present disclosure. In one aspect, for ML training, it may be more appropriate and more efficient to have the same TRP location, antenna configuration, and / or per-TRP configuration so that the ML data (e.g., positioning-related measurements) collected during the ML training or UE positioning session can be more consistent. In this way, as shown at 1002, a configuration ID can be defined to cover the corresponding overall auxiliary data. For example, a configuration ID of

[0001] can be used for a first overall auxiliary data associated with a first group of TRPs, a first group of antenna configurations, and a first group of per-TRP configurations, a configuration ID of

[0002] can be used for a second overall auxiliary data associated with a second group of TRPs, a second group of antenna configurations, and a second group of per-TRP configurations, and so on. Therefore, when the ML model is performing ML training or ML inference, the ML model is able to more accurately determine whether two sets of ML collected data are based on the same TRP / antenna configuration. For example, to optimize ML training / inference, a higher ML training / inference weight may be given to ML training / inference for a group of UE positioning sessions based on the same configuration ID (e.g., with the same TRP / antenna configuration) compared to ML training / inference for a group of UE positioning sessions with different configuration IDs (e.g., with different TRP / antenna configurations).

[0108] Fig.11 is a diagram 1100 showing an example configuration ID including multiple parts according to various aspects of the present disclosure. In another aspect of the present disclosure, instead of or in addition to assigning a configuration ID to the entire assistance data, the configuration ID includes multiple parts, where different parts can correspond to different parameters in the assistance data.

[0109] For example, as shown at 1102 and 1104, the configuration ID in the overall assistance data may include a first part (e.g., a first sub-ID) corresponding to the DL-PRS assistance data and a second part (e.g., a second sub-ID) corresponding to the positioning calculation assistance data. Therefore, DL-PRS assistance data with the same parameters / configuration may share the same first sub-ID, and positioning calculation assistance data with the same parameters / configuration may share the same second sub-ID. Table 1 below shows an example configuration ID with two parts. For example, the overall assistance data including the first group of configurations for DL-PRS assistance data and the first group of configurations for positioning calculation assistance data may be assigned a configuration ID of [00010001] or [0001,0001], the overall assistance data including the first group of configurations for DL-PRS assistance data and the second group of configurations for positioning calculation assistance data (which is different from the first group of configurations for positioning calculation assistance data) may be assigned a configuration ID of [00010002] or [0001,0002], and the overall assistance data including the fourth group of configurations for DL-PRS assistance data and the second group of configurations for positioning calculation assistance data may be assigned a configuration ID of [00040002] or [0004,0002], and so on. Table 1 - Example Configuration ID with two parts

[0110] By configuring or defining the configuration ID to have multiple parts (e.g., multiple sub-IDs), the positioning entity and the ML model can use more flexible configuration and signaling. For example, compared with the positioning calculation assistance data, the DL-PRS assistance data may have more options / parameters that can be configured (e.g., the fields in the positioning calculation assistance data may not change frequently). Therefore, in one example, the positioning entity may indicate a sub-ID instead of a complete configuration ID to another positioning entity in order to reduce signaling overhead. For example, if the configuration for the positioning calculation assistance data is the same for a group of UE positioning sessions, the network entity may only indicate the sub-IDs corresponding to the different configurations of the DL-PRS assistance data to the UEs participating in the group of UE positioning sessions to reduce signaling overhead. In another example, multiple sub-IDs can also improve the efficiency of ML training / inference by enabling the ML model to focus or identify ML training / inference on a specific part. For example, the ML model can perform ML training that is just related to the positioning calculation assistance data. Therefore, the ML model can be configured to focus on the sub-ID corresponding to the positioning calculation assistance data and ignore other sub-IDs. In another example, the ML model may focus on parameters associated with positioning computation assistance data while ignoring parameters associated with DL-PRS assistance data, which may greatly reduce the load at the ML model during ML training / inference.

[0111] Fig.12 1200 is a diagram showing an example of associating or defining a configuration ID for each frequency layer according to various aspects of the present disclosure. A positioning frequency layer (PFL) (also referred to as a "frequency layer") may refer to a set of one or more PRS resource sets on one or more TRPs that have the same values ​​for certain parameters. Specifically, the set of PRS resource sets may have the same subcarrier spacing and cyclic prefix (CP) type (e.g., this means that all parameter sets supported by PDSCH also support PRS), the same downlink PRS bandwidth value, the same starting PRB (and center frequency) and / or the same comb size, etc. In some examples, the downlink PRS bandwidth may have a granularity of four PRBs, with a minimum of 24 PRBs and a maximum of 272 PRBs. In other examples, up to four frequency layers may be configured, and up to two PRS resource sets may be configured for each TRP of each frequency layer. In some examples, the concept of frequency layers can be similar to CC and BWP, where one base station (or macro cell base station and small cell base station) can use CC and BWP to send data channels, and multiple (e.g., two or more) base stations can use frequency layers to send PRS. When the UE sends its positioning capabilities to the network, such as during a positioning protocol session, the UE can indicate the number of frequency layers it can support. For example, the UE can indicate whether it can support one or four PFLs.

[0112] In one example (as shown at 1202 and 1204), a configuration ID may be defined for each frequency layer, such that a first configuration ID (or a first portion of a configuration ID) is associated with a DL-PRS configured for each frequency layer (e.g., DL-PRS-PRSPerFreqLayer-ConfigID), and a second configuration ID (or a second portion of a configuration ID) is associated with DL-PRS assistance data configured for each frequency layer (e.g., DL-PRS-AssistanceDataPerFreqLayer-ConfigID). In some examples, a positioning entity such as a UE may use one or more PFLs depending on its capabilities or network configuration. Thus, if the positioning entity uses multiple PFLs to assist in training a NN, the positioning entity may include corresponding configuration IDs of the PFLs used to assist an ML model in ML training and inference.

[0113] In another aspect of the present disclosure, a configuration ID may be associated with only a subset of parameters in a PRS / SRS configuration. Since some parameters in an SRS / PRS configuration may be more important, while other parameters may be less important (e.g., from an ML perspective), a configuration ID may be associated with only important parameters, and / or have multiple ranges or sets of values ​​for less important values.

[0114] For example, parameters such as subframe number (SFN), subframe, time slot, symbol, tone mapping and / or changing cell ID, etc. for PRS / SRS may not be so important and can be changed without significantly affecting the overall positioning configuration used to train the NN. For example, PRS / SRS resources can be mapped to an offset set of time domain resources, which may not affect the overall training of the NN. On the other hand, parameters such as the beam used to send PRS, the elevation angle of the beam used to send PRS, the bandwidth of PRS and / or the subcarrier spacing (SCS) of PRS may be more important. Therefore, the configuration ID can be associated with only these important parameters, while less important parameters can have different values ​​for the same configuration ID. Table 2 below provides an example of associating a configuration ID with selected parameters, where different configuration IDs can be assigned to PRS assistance data with different SCS, bandwidth and / or comb size (e.g., more important parameters), and the same configuration ID can be assigned to PRS assistance data with the same SCS, bandwidth and comb size but different values ​​of SFN (e.g., values ​​of less important parameters). Table 2 – Example of associating a configuration ID with selected parameters

[0115] In another aspect of the present disclosure, some parameters associated with a configuration ID may be within a range. For example, instead of assigning a first configuration ID to assistance data including a first PRS bandwidth (e.g., 10 MHz) and assigning a second configuration ID to assistance data including a second PRS bandwidth (e.g., 12 MHz), the same configuration ID may be assigned to a range of PRS bandwidths (e.g., 10 to 15 MHz). Thus, the same configuration ID may be assigned to any PRS bandwidth that falls within the range (assuming that the other parameters selected also have the same values).

[0116] In another aspect of the present disclosure, a configuration ID can be further associated with a region ID to keep the configuration space smaller. For example, a first geographic region can be associated with a first region ID, and a different second geographic region can be associated with a second region ID. By coupling each configuration ID with a region ID, the ML model can narrow its training scope to a more specific region to improve the efficiency of ML training and inference. For example, if the ML model performs ML training and inference for a first geographic region, the ML model can collect ML data that includes the first region ID, and can exclude ML data that does not include the first region ID.

[0117] In another aspect of the present disclosure, different configuration IDs may be independently defined for different positioning methods. For example, a first type / format of configuration ID may be defined for DL-AoD positioning, a second type / format of configuration ID may be defined for DL-TDOA positioning, and a third type / format of configuration ID may be defined for UL-TDOA positioning, and so on.

[0118] In another aspect of the present disclosure, when the network entity catalogs data in the server, the network entity may also be configured to record the SRS reception configuration ID (eg, the beam set for each TRP).

[0119] In another aspect of the present disclosure, for positioning methods involving UL signals (e.g., UL-TDOA positioning and UL AoA positioning, etc.), a configuration for UL-SRS can be defined in a radio control resource (RRC), where different UEs can have orthogonal SRS configurations. Thus, in one aspect, a base station can indicate a UL-SRS configuration ID that is common to multiple UEs, where such a configuration ID can be independent of a specific resource allocation (e.g., comb offset, symbol, slot offset, etc.).

[0120] In another example, the UE may have a transmission configuration and / or reception configuration that can be indicated to the network (e.g., in UE-Transmission-Config-ID and / or in UE-Reception-Config ID, etc.). For example, the UE may indicate to the network a first transmission configuration ID indicating that the UE is using one specific antenna to transmit SRS, and the UE may indicate to the network a second transmission configuration ID indicating that the UE is using two antennas to transmit based on time division multiplexing (TDM) (e.g., port cycling), and / or the UE may indicate to the network a third transmission configuration ID indicating that the UE is using some specific beamforming strategy to receive DL signals and transmit UL signals, etc. In some examples, the configuration ID may be configured to apply to SRS transmission and PRS reception at the UE. In other examples, a corresponding configuration ID (e.g., two types of configuration IDs) may be configured for each of SRS transmission and PRS transmission. In some scenarios, since the transmission / reception strategy / configuration may be different between different UEs, the network (e.g., NN and ML) may also be trained to be robust and flexible to different UE transmission / reception strategies / configurations.

[0121] Fig.13 1 is a communication flow 1300 illustrating an example of associating a configuration ID for ML training and inference to a location associated with a PRS according to various aspects of the present disclosure. The numbers associated with the communication flow 1300 do not specify a particular time sequence, but are merely used as a reference for the communication flow 1300. Various aspects presented herein may enable a UE and a network entity (e.g., a base station) to associate a configuration ID with a PRS configuration, which may be used to assist an ML model in ML training, inference, and / or refinement.

[0122] At 1320, UE 1302 may receive a configuration 1306 for positioning measurements from base station 1304, wherein configuration 1306 may include at least one configuration ID 1308 associated with ML data collection, ML training, ML inference, and / or ML retraining / refinement for a set of reference signals (RS) 1310, e.g., in conjunction with Figures 10 to 12 The set of RS 1310 may include at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof. Positioning measurements may include measuring DL-AoD, DL-TDOA, and / or RTT associated with a DL reference signal, for example, in combination with Figure 4 As described.

[0123] In one example, the at least one configuration ID 1308 can be associated with one or more parameters of overall assistance data configured for a positioning session of the UE 1302, such as described in conjunction with FIG. In addition, the overall assistance data can include PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0124] In another example, the at least one configuration ID 1308 can be associated with a frequency layer selected based on the capabilities of the UE 1302.

[0125] In another example, the at least one configuration ID 1308 can be associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values, such as described in conjunction with Table 2.

[0126] In another example, the at least one configuration ID 1308 can be associated with a region ID.

[0127] In another example, the at least one configuration ID 1308 can be associated with a specific positioning mechanism.

[0128] At 1322, the base station 1304 may send the set of RS 1310 to the UE 1302 based on the configuration 1306. The set of RS 1310 may be associated with one or more DL channels, such that the UE 1302 may receive the set of RS 1310 via the one or more DL channels.

[0129] At 1324 , after receiving the configuration 1306 and the set of RSs 1310 , the UE 1302 may perform positioning measurements for the set of RSs 1310 based on the configuration 1306 , for example, measuring TDOA, AoA, and / or RTT for the set of RSs 1310 .

[0130] At 1326 , the UE 1302 may store at least one parameter for ML data collection or load a first NN (or a first ML model) based on the at least one configuration ID 1308 .

[0131] In one example, at 1326, if the UE 1302 is configured to store at least one parameter for ML data collection (e.g., PRS bandwidth, PRS SCS, PRS beam ID, etc.) based on at least one configuration ID 1308, the UE 1302 can perform ML data collection based on the at least one parameter. Then, as shown at 1328, the UE 1302 can send at least one parameter for an ML training process to an ML model or NN 1312 associated with the ML data collection or to the base station 1304 (e.g., if the ML model / NN is at the base station 1304). In one example, the ML training process can be associated with a second NN different from the first NN (e.g., the NN used for ML data collection is different from the NN used for ML training).

[0132] In another example, at 1334, the base station 1304 may send a priority indication of ML data collection to the UE 1302. For example, the priority indication may indicate whether the ML data collection is a high priority or a low priority. In response, the UE 1302 may determine whether to perform ML data collection based on the indication. For example, if the priority indication is high, the UE 1302 may be configured to perform ML data collection and abandon some other tasks (e.g., reception of PDSCH) when there is a conflict, and if the priority indication is low, the UE 1302 may be configured to perform ML data collection when it has sufficient resources.

[0133] In another example, at 1326 , if the UE 1302 is configured to load the first NN based on the at least one configuration ID, then at 1330 , the UE 1302 may perform ML inference for positioning measurements via the first NN.

[0134] In another example, at 1332, the base station 1304 can send an indication to the UE 1302 to indicate whether the set of RSs 1310 is used for ML data collection or for ML reasoning. In some examples, the indication can be included in the configuration 1306. In addition, the indication can also indicate the data collection type, such as whether the ML data collection is used for ML training, ML reasoning, and / or ML refinement / retraining, etc.

[0135] Fig.141400 is a communication flow illustrating an example of associating a configuration ID for ML training and inference to a location associated with an SRS according to various aspects of the present disclosure. The numbers associated with the communication flow 1400 do not specify a particular time sequence, but are merely used as a reference for the communication flow 1400. Various aspects presented herein may enable a UE and a network entity (e.g., a base station) to associate a configuration ID with an SRS configuration, which may be used to assist an ML model in ML training, inference, and / or refinement.

[0136] At 1420, UE 1402 may receive a configuration 1406 for positioning measurements from base station 1404, wherein configuration 1406 may include at least one configuration ID 1408 associated with ML data collection, ML training, ML inference, and / or ML retraining / refinement of a set of reference signals (RS) 1410, such as in conjunction with Figures 10 to 12 The group of RS 1410 may be SRS. The UE 1402 may receive the configuration 1406 via RRC signaling / message. The positioning measurement may include measuring UL-AoA, UL-TDOA, and / or RTT associated with the UL reference signal, for example, in combination with Figure 4 As described.

[0137] In one example, configuration 1406 can be applied to multiple UEs. In another example, configuration 1406 can be associated with a specific resource allocation.

[0138] In another example, the at least one configuration ID 1408 can be associated with a frequency layer selected based on the capabilities of the UE 1402.

[0139] In another example, the at least one configuration ID 1408 can be associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values, as described in conjunction with Table 2.

[0140] In another example, the at least one configuration ID 1408 can be associated with a region ID.

[0141] In another example, the at least one configuration ID 1408 may be associated with a specific positioning mechanism.

[0142] In another example, as shown at 1422 , before sending the configuration 1406 , the base station 1422 may configure at least one configuration ID 1408 for the configuration 1406 .

[0143] At 1424, UE 1402 may send a transmission or reception (Tx / Rx) configuration to a network entity based on at least one configuration ID, wherein the Tx / Rx configuration is associated with reception or transmission of the group of RS 1410. In one example, the Tx / Rx configuration indicates: at least one antenna used by UE 1402 to transmit the group of RS 1410, UE 1402 is using at least two antennas to transmit the group of RS 1410 based on TDM, and / or a beamforming strategy used to transmit the group of RS 1410, and the like.

[0144] In another example, at 1432, the base station 1404 can send an indication to the UE 1402 to indicate that the set of RSs 1410 is used for ML data collection or for ML reasoning. In some examples, the indication can be included in the configuration 1406. In addition, the indication can also indicate the data collection type, such as the ML data collection is used for ML training, ML reasoning and / or ML refinement / retraining, etc.

[0145] In another example, at 1434, the base station 1404 may send a priority indication for ML data collection to the UE 1402. For example, the priority indication may indicate whether the ML data collection is a high priority or a low priority. In response, the UE 1402 may determine whether to perform ML data collection based on the indication. For example, if the priority indication is high, the UE 1402 may be configured to perform ML data collection and abandon some other tasks (e.g., reception of PDSCH) when there is a conflict, and if the priority indication is low, the UE 140 may be configured to perform ML data collection when it has sufficient resources.

[0146] At 1436 , the UE 1402 may transmit the set of RS 1410 based on the Tx / Rx configuration for ML data collection and / or ML inference.

[0147] At 1438 , after sending the configuration 1406 and receiving the set of RS 1410 , the base station 1404 may perform positioning measurements on the set of RS 1410 based on the configuration 1406 , such as measuring TDOA, AoA, and / or RTT of the set of RS 1410 .

[0148] At 1440 , the base station 1404 may store at least one parameter for ML data collection or load a first NN (or a first ML model) based on at least one configuration ID 1408 .

[0149] In one example, at 1440, if the base station 1404 is configured to store at least one parameter for ML data collection (e.g., SRS bandwidth, SRS SCS, SRS beam ID, etc.) based on at least one configuration ID 1408, the base station 1404 can perform ML data collection based on the at least one parameter. Then, as shown at 1442, the base station 1404 can send at least one parameter for the ML training process to the ML model or NN 1414 associated with the ML data collection. In one example, the ML training process can be associated with a second NN different from the first NN (e.g., the NN used for ML data collection is different from the NN used for ML training).

[0150] In another example, at 1440, if the base station 1404 is configured to load the first NN based on the at least one configuration ID, the base station 1404 may perform ML inference for positioning measurements via the first NN.

[0151] Fig.15 1500 is a flow chart of a method of wireless communication. The method may be performed by a UE (e.g., UE 104, 404, 1302, 1402; device 1704). The method may enable the UE to associate positioning configurations and measurements with a configuration ID to assist an ML model in ML training, inference, and / or refinement.

[0152] At 1502, the UE may receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, e.g., in conjunction with Fig.13 For example, at 1320, UE 1302 may receive a configuration 1306 for positioning measurements from base station 1304, wherein configuration 1306 includes at least one configuration ID 1308 associated with ML data collection / training / inference for a set of RSs 1310. Fig.17 The configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704 performs reception of the configuration.

[0153] In one example, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0154] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0155] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0156] In another example, the at least one configuration ID is associated with a region ID.

[0157] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0158] In another example, the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0159] At 1504, the UE may receive a priority indication for ML data collection and determine whether to perform ML data collection based on the priority indication, for example, in conjunction with Fig.13 For example, at 1334, UE 1302 may receive a priority indication for ML data collection from base station 1304, and determine whether to perform ML data collection based on the priority indication. Fig.17 The reception of the priority indication may be performed by the configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704.

[0160] At 1506, the UE may receive an indication indicating whether the set of RSs is used for ML data collection or for ML reasoning, e.g., in conjunction with Fig.13 For example, at 1332, UE 1302 may receive an indication from base station 1304 indicating whether a group of RS 1310 is used for ML data collection or for ML reasoning. Fig.17 The reception of the indication is performed by the configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704.

[0161] In one example, the indication further indicates a data collection type.

[0162] At 1508, the UE may receive the set of RSs via one or more DL channels, wherein the set of positioning measurements is associated with the one or more DL channels, such as in conjunction with Fig.13 For example, at 1322, UE 1302 may receive a set of RS 1310 from base station 1304. Fig.17 The configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704 in performs reception of the set of RSs.

[0163] At 1510, the UE may perform a set of positioning measurements based on the configuration and a set of RSs, such as in conjunction with Fig.13 For example, at 1324, UE 1302 may perform positioning measurements based on configuration 1306 and a set of RSs 1310. Fig.17 The configuration ID association component 198, cellular baseband processor 1724 and / or transceiver 1722 of the device 1704 in performs the positioning measurement.

[0164] At 1512, the UE may store at least one parameter for ML data collection based on the at least one configuration ID, or load a first NN, for example in conjunction with Fig.13 For example, at 1326, UE 1302 may store at least one parameter for ML data collection or load a first NN based on the at least one configuration ID 1308. Fig.17 The configuration ID of the device 1704 in the apparatus 1704 is associated with the component 198, the cellular baseband processor 1724 and / or the transceiver 1722 to perform storage of at least one parameter for ML data collection, and / or loading of the first NN.

[0165] In one example, the UE may store at least one parameter for ML data collection based on the at least one configuration ID. In such an example, the UE may perform ML data collection based on the at least one parameter. In another example, the UE may send at least one parameter for an ML training process, wherein the ML training process is associated with a second NN different from the first NN.

[0166] In another example, the UE may load the first NN based on the at least one configuration ID. In such an example, at 1514, the UE may perform ML reasoning for a set of positioning measurements via the first NN, for example in conjunction with Fig.13 For example, at 1330, UE 1302 may perform ML inference for positioning measurements via the first NN. Fig.17 The ML reasoning is performed by associating component 198, cellular baseband processor 1724, and / or transceiver 1722 of device 1704 in the embodiment.

[0167] Fig.16 1600 is a flow chart of a method of wireless communication. The method may be performed by a UE (e.g., UE 104, 404, 1302, 1402; device 1704). The method may enable the UE to associate positioning configurations and measurements with a configuration ID to assist an ML model in ML training, inference, and / or refinement.

[0168] At 1602, the UE may receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, e.g., in conjunction with Fig.13 For example, at 1320, UE 1302 may receive a configuration 1306 for positioning measurements from base station 1304, wherein configuration 1306 includes at least one configuration ID 1308 associated with ML data collection / training / inference for a set of RSs 1310. Fig.17 The configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704 performs reception of the configuration.

[0169] In one example, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0170] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0171] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0172] In another example, the at least one configuration ID is associated with a region ID.

[0173] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0174] In another example, the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0175] In another example, the UE may receive a priority indication for ML data collection, and determine whether to perform ML data collection based on the priority indication, for example, in combination with Fig.13 For example, at 1334, UE 1302 may receive a priority indication for ML data collection from base station 1304, and determine whether to perform ML data collection based on the priority indication. Fig.17 The reception of the priority indication may be performed by the configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704.

[0176] In another example, the UE may receive an indication indicating whether the set of RSs is used for ML data collection or for ML reasoning, for example in conjunction with Fig.13 For example, at 1332, UE 1302 may receive an ML data collection indication from base station 1304 indicating whether a set of RSs 1310 is used for ML data collection or for ML reasoning. Fig.17 The reception of the indication is performed by the configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704.

[0177] In another example, the indication further indicates a data collection type.

[0178] In another example, the UE may receive the set of RSs via one or more DL channels, wherein the set of positioning measurements is associated with the one or more DL channels, for example, in conjunction with Fig.13 For example, at 1322, UE 1302 may receive a set of RS 1310 from base station 1304. Fig.17 The configuration ID association component 198, the cellular baseband processor 1724 and / or the transceiver 1722 of the device 1704 in performs reception of the set of RSs.

[0179] At 1610, the UE may perform a set of positioning measurements based on the configuration and a set of RSs, such as in conjunction with Fig.13 For example, at 1324, UE 1302 may perform positioning measurements based on configuration 1306 and a set of RSs 1310. Fig.17 The configuration ID association component 198, cellular baseband processor 1724 and / or transceiver 1722 of the device 1704 in performs the positioning measurement.

[0180] At 1612, the UE may store at least one parameter for ML data collection based on the at least one configuration ID, or load a first NN, for example in conjunction with Fig.13 For example, at 1326, UE 1302 may store at least one parameter for ML data collection or load a first NN based on the at least one configuration ID 1308. Fig.17 The configuration ID of the device 1704 in the apparatus 1704 is associated with the component 198, the cellular baseband processor 1724 and / or the transceiver 1722 to perform storage of at least one parameter for ML data collection, and / or loading of the first NN.

[0181] In one example, the UE may store at least one parameter for ML data collection based on the at least one configuration ID. In such an example, the UE may perform ML data collection based on the at least one parameter. In another example, the UE may send at least one parameter for an ML training process, wherein the ML training process is associated with a second NN different from the first NN.

[0182] In another example, the UE may load the first NN based on the at least one configuration ID. In such an example, at 1614, the UE may perform ML reasoning for a set of positioning measurements via the first NN, for example in conjunction with Fig.13 For example, at 1330, UE 1302 may perform ML inference for positioning measurements via the first NN. Fig.17 The ML reasoning is performed by associating component 198, cellular baseband processor 1724, and / or transceiver 1722 of device 1704 in the embodiment.

[0183] Fig.171700 is a diagram illustrating an example of a hardware implementation for an apparatus 1704. The apparatus 1704 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, the apparatus 1704 may include a cellular baseband processor 1724 (also referred to as a modem) coupled to one or more transceivers 1722 (e.g., a cellular RF transceiver). The cellular baseband processor 1724 may include on-chip memory 1724'. In some aspects, the apparatus 1704 may also include one or more subscriber identity module (SIM) cards 1720 and an application processor 1706 coupled to a secure digital (SD) card 1708 and a screen 1710. The application processor 1706 may include on-chip memory 1706'. In some aspects, the device 1704 may also include a Bluetooth module 1712, a WLAN module 1714, an SPS module 1716 (e.g., a GNSS module), one or more sensor modules 1718 (e.g., a barometric pressure sensor / altimeter; a motion sensor such as an inertial management unit (IMU), a gyroscope, and / or an accelerometer; a magnetometer, audio, and / or other technologies for positioning), other memory modules 1726, a power supply 1730, and / or a camera 1732. The Bluetooth module 1712, the WLAN module 1714, and the SPS module 1716 may include an on-chip transceiver (TRX) (or in some cases, only a receiver (RX)). The Bluetooth module 1712, the WLAN module 1714, and the SPS module 1716 may include their own dedicated antennas and / or communicate using antennas 1780. The cellular baseband processor 1724 communicates with the UE 104 and / or RUs associated with the network entity 1702 via one or more antennas 1780 through the transceiver 1722. The cellular baseband processor 1724 and the application processor 1706 may each include a computer-readable medium / memory 1724', 1726', respectively. The other memory module 1726 may also be considered as a computer-readable medium / memory. Each computer-readable medium / memory 1724', 1706', 1726 may be non-temporary. The cellular baseband processor 1724 and the application processor 1706 are each responsible for general processing, which includes executing software stored on a computer-readable medium / memory. When the software is executed by the cellular baseband processor 1724 / application processor 1706, the cellular baseband processor 1724 / application processor 1706 performs the various functions described above. The computer-readable medium / memory may also be used to store data manipulated by the cellular baseband processor 1724 / application processor 1706 when executing the software. The cellular baseband processor 1724 / application processor 1706 may be a component of the UE 350 and may include at least one of the memory 360 and / or the TX processor 368, the RX processor 356, and the controller / processor 359.In one configuration, the device 1704 may be a processor chip (modem and / or applications) and include only the cellular baseband processor 1724 and / or the application processor 1706, and in another configuration, the device 1704 may be an entire UE (eg, see. Figure 3 350) and includes other modules of device 1704.

[0184] As described above, the configuration ID association component 198 can be configured to receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs. The configuration ID association component 198 can also be configured to perform a set of positioning measurements based on the configuration and a set of RSs. The configuration ID association component 198 can also be configured to store at least one parameter for ML data collection, or load the first NN based on at least one configuration ID. The configuration ID association component 198 can be in the cellular baseband processor 1724, the application processor 1706, or in both the cellular baseband processor 1724 and the application processor 1706. The configuration ID association component 198 can be one or more hardware components specifically configured to perform the stated processing / algorithms, implemented by one or more processors configured to perform the stated processing / algorithms, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. As shown, the device 1704 can include various components configured to implement various functions. In one configuration, the apparatus 1704 (specifically, the cellular baseband processor 1724 and / or the application processor 1706) may include: a unit for receiving a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference of a set of RSs. The apparatus 1704 may also include: a unit for performing a set of positioning measurements based on the configuration and the set of RSs. The apparatus 1704 may also include: a unit for storing at least one parameter for ML data collection, or loading a first NN based on at least one configuration ID.

[0185] In one configuration, the apparatus 1704 may further include a unit for receiving a configuration for the group of RSs based on an association between the group of RSs and one or more CGs, and wherein the group of RSs is sent based on the configuration.

[0186] In another configuration, the apparatus 1704 may further include means for receiving the set of RSs via one or more DL channels, wherein the set of positioning measurements are associated with the one or more DL channels.

[0187] In another configuration, the apparatus 1704 may further include: means for performing ML data collection based on the at least one parameter.

[0188] In another configuration, the apparatus 1704 may further include: means for transmitting at least one parameter for the ML training process. In such a configuration, the ML training process is associated with a second NN different from the first NN.

[0189] In another configuration, the apparatus 1704 may further include: a unit for receiving a priority indication for ML data collection; and a unit for determining whether to perform ML data collection based on the priority indication.

[0190] In another configuration, the apparatus 1704 may further include means for performing ML inference on the set of positioning measurements via the first NN.

[0191] In another configuration, the apparatus 1704 may further include: a unit for receiving an indication indicating whether the set of RSs is used for ML data collection or for ML reasoning. In such a configuration, the indication further indicates a data collection type.

[0192] In another configuration, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0193] In another configuration, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0194] In another configuration, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0195] In another configuration, the at least one configuration ID is associated with a region ID.

[0196] In another configuration, the at least one configuration ID is associated with a specific positioning mechanism.

[0197] In another configuration, the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0198] These means may be the configuration ID associated component 198 of the apparatus 1704 configured to perform the functions recited by these means. As described above, the apparatus 1704 may include the TX processor 368, the RX processor 356, and the controller / processor 359. Thus, in one configuration, these means may be the TX processor 368, the RX processor 356, and / or the controller / controller 359 configured to perform the functions recited by these means.

[0199] Fig.18 1800 is a flow chart of a method of wireless communication. The method may be performed by a base station (e.g., base station 102, 1304, 1404; network entity 2002). The method may enable the base station to associate positioning configurations and measurements with configuration IDs to assist ML models in ML training, inference, and / or refinement.

[0200] At 1802, the base station may send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, such as in conjunction with Fig.13 For example, at 1320, the base station 1304 may send a configuration 1306 for positioning measurements, wherein the configuration 1306 includes at least one configuration ID 1308 associated with ML data collection / training / inference for a group of RSs 1310. Fig. 20 The configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002 performs the sending of the configuration.

[0201] In one example, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0202] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0203] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0204] In another example, the at least one configuration ID is associated with a region ID.

[0205] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0206] In another example, the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0207] At 1804, the base station may send an indication indicating whether the set of RSs is used for ML data collection or for ML reasoning, for example in conjunction with Fig.13 For example, at 1332, base station 1304 may send an indication indicating whether a group of RSs 1310 is used for ML data collection or for ML reasoning. Fig. 20The sending of the indication is performed by the configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002.

[0208] In one example, the indication further indicates a data collection type.

[0209] At 1806, the base station may transmit the set of RSs via one or more DL channels, wherein the set of positioning measurements is associated with the one or more DL channels, for example, in conjunction with Fig.13 For example, at 1322, base station 1304 may send a set of RS 1310 to UE 1302. Fig. 20 The configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002 performs the sending of the group of RSs.

[0210] At 1808, the base station may send a priority indication for ML data collection, wherein based on the priority indication, at least one parameter for ML data collection or ML reasoning is received, for example, in conjunction with Fig.13 For example, at 1334, base station 1304 may send a priority indication for ML data collection to UE 1302, where at least one parameter for ML data collection or ML reasoning is received based on the priority indication. Fig. 20 The sending of the priority indication is performed by the configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002.

[0211] At 1810, the base station may receive at least one parameter for ML data collection or ML reasoning based on the at least one configuration ID, for example, in conjunction with Fig.13 For example, in Fig.13 At 1328, the base station 1304 may receive at least one parameter for ML data collection or ML reasoning based on the at least one configuration ID 1308 from the UE 1302. Fig. 20 The configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002 in the network entity 2002 is used to perform the reception of the at least one parameter for ML data collection or ML reasoning.

[0212] Fig.19 1900 is a flow chart of a method of wireless communication. The method may be performed by a base station (e.g., base station 102, 1304, 1404; network entity 2002). The method may enable the base station to associate positioning configurations and measurements with configuration IDs to assist ML models in ML training, inference, and / or refinement.

[0213] At 1902, the base station may send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, such as in conjunction with Fig.13 For example, at 1320, the base station 1304 may send a configuration 1306 for positioning measurements, wherein the configuration 1306 includes at least one configuration ID 1308 associated with ML data collection / training / inference for a group of RSs 1310. Fig. 20 The configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002 performs the sending of the configuration.

[0214] In one example, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0215] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0216] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0217] In another example, the at least one configuration ID is associated with a region ID.

[0218] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0219] In another example, the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0220] In another example, the base station may send an indication indicating whether the set of RSs is used for ML data collection or for ML reasoning, for example in conjunction with Fig.13 For example, at 1332, base station 1304 may send an indication indicating whether a group of RSs 1310 is used for ML data collection or for ML reasoning. Fig. 20 The sending of the indication is performed by the configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002.

[0221] In one example, the indication further indicates a data collection type.

[0222] In another example, the base station may transmit the set of RSs via one or more DL channels, wherein the set of positioning measurements is associated with the one or more DL channels, for example, in conjunction with Fig.13 For example, at 1322, base station 1304 may send a set of RS 1310 to UE 1302. Fig. 20 The configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002 performs the sending of the group of RSs.

[0223] In another example, the base station may send a priority indication for ML data collection, wherein based on the priority indication, at least one parameter for ML data collection or ML reasoning is received, for example, in combination with Fig.13 For example, at 1334, base station 1304 may send a priority indication for ML data collection to UE 1302, where at least one parameter for ML data collection or ML reasoning is received based on the priority indication. Fig. 20 The sending of the priority indication is performed by the configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002.

[0224] At 1910, the base station may receive at least one parameter for ML data collection or ML reasoning based on the at least one configuration ID, for example, in conjunction with Fig.13 For example, in Fig.13 At 1328, the base station 1304 may receive at least one parameter for ML data collection or ML reasoning based on the at least one configuration ID 1308 from the UE 1302. Fig. 20 The configuration ID association component 199 and / or the transceiver 2046 of the network entity 2002 in the network entity 2002 is used to perform the reception of the at least one parameter for ML data collection or ML reasoning.

[0225] Fig. 202000 is a diagram illustrating an example of a hardware implementation of a network entity 2002. The network entity 2002 may be a BS, a component of a BS, or may implement BS functionality. The network entity 2002 may include at least one of a CU 2010, a DU 2030, or a RU 2040. For example, depending on the layer functionality processed by the configuration ID association component 199, the network entity 2002 may include a CU 2010; a CU 2010 and a DU 2030; each of the CU 2010, the DU 2030, and the RU 2040; a DU 2030; a DU 2030 and a RU 2040; or a RU 2040. The CU 2010 may include a CU processor 2012. The CU processor 2012 may include an on-chip memory 2012'. In some aspects, the CU 2010 may also include an additional memory module 2014 and a communication interface 2018. CU 2010 communicates with DU 2030 via a mid-haul link such as an F1 interface. DU 2030 may include a DU processor 2032. DU processor 2032 may include on-chip memory 2032'. In some aspects, DU 2030 may also include other memory modules 2034 and a communication interface 2038. DU 2030 communicates with RU 2040 via a front-haul link. RU 2040 may include a RU processor 2042. RU processor 2042 may include on-chip memory 2042'. In some aspects, RU 2040 may also include other memory modules 2044, one or more transceivers 2046, antenna 2080, and communication interface 2048. RU 2040 communicates with UE 104. On-chip memory 2012', 2032', 2042' and other memory modules 2014, 2034, 2044 may each be considered as a computer-readable medium / memory. Each computer readable medium / memory may be non-temporary. Each of processors 2012, 2032, 2042 is responsible for general processing, including executing software stored on the computer readable medium / memory. When the software is executed by the corresponding processor, the processor performs the various functions described above. The computer readable medium / memory can also be used to store data manipulated by the processor when executing the software.

[0226] As described above, the configuration ID association component 199 may be configured to send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs. The configuration ID association component 199 may also be configured to receive at least one parameter for ML data collection or ML reasoning based on the at least one configuration ID from the UE. The configuration ID association component 199 may be within one or more processors of one or more of the CU 2010, DU 2030, and RU 2040. The configuration ID association component 199 may be one or more hardware components specifically configured to perform the stated processing / algorithms, implemented by one or more processors configured to perform the stated processing / algorithms, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. The network entity 2002 may include various components configured to implement various functions. In one configuration, the network entity 2002 may include: a unit for sending a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs. The network entity 2002 may also include: a unit for receiving at least one parameter for ML data collection or ML reasoning based on the at least one configuration ID.

[0227] In one configuration, the network entity 2002 may further include means for transmitting a set of RSs via one or more DL channels, wherein the set of positioning measurements are associated with the one or more DL channels.

[0228] In another configuration, the network entity 2002 may further include: a unit for sending a priority indication for ML data collection, wherein at least one parameter for ML data collection or ML reasoning is received based on the priority indication.

[0229] In another configuration, the network entity 2002 may also include: a unit for sending an indication indicating whether the set of RSs is used for ML data collection or for ML reasoning. In such a configuration, the indication further indicates a data collection type.

[0230] In another configuration, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0231] In another configuration, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0232] In another configuration, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0233] In another configuration, the at least one configuration ID is associated with a region ID.

[0234] In another configuration, the at least one configuration ID is associated with a specific positioning mechanism.

[0235] In another configuration, the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0236] These means may be the configuration ID associated component 199 of the network entity 2002 configured to perform the functions recited by these means. As described above, the network entity 2002 may include a TX processor 316, an RX processor 370, and a controller / processor 375. Thus, in one configuration, these means may be the TX processor 316, the RX processor 370, and / or the controller / controller 375 configured to perform the functions recited by these means.

[0237] Fig.21 Flowchart 2100 of a method of wireless communication. The method may be performed by a UE (e.g., UE 104, 404, 1302, 1402; device 2304). The method may enable the UE to associate positioning configurations and measurements with a configuration ID to assist an ML model in ML training, inference, and / or refinement.

[0238] At 2102, the UE may receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, e.g., in conjunction with Fig.14 For example, at 1420, UE 1302 may receive a configuration 1406 for positioning measurements from base station 1404, wherein configuration 1406 includes at least one configuration ID 1408 associated with ML data collection / training / inference for a set of RSs 1410. Fig.23 The configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304 performs reception of the configuration.

[0239] In one example, the configuration applies to multiple UEs.

[0240] In another example, the configuration is associated with a specific resource allocation.

[0241] In another example, the configuration is received via an RRC message.

[0242] In another example, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0243] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0244] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0245] In another example, the at least one configuration ID is associated with a region ID.

[0246] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0247] In another example, the set of RSs includes at least one SRS.

[0248] At 2104, the UE may send a Tx / Rx configuration to a network entity based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs, for example, in conjunction with Fig.14 For example, at 1424, UE 1302 may send Tx / Rx configuration 1412 to base station 1404 based on the at least one configuration ID 1408. Fig.23 The configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304 in performs the transmission of the Tx / Rx configuration.

[0249] In one example, the Tx / Rx configuration indicates: at least one antenna used by the UE to transmit the set of RSs, at least two antennas that the UE is using to transmit the set of RSs based on TDM, a beamforming strategy used to transmit the set of RSs, or a combination thereof.

[0250] At 2106, the UE may receive an indication indicating whether the set of RSs is for ML data collection or for ML reasoning, e.g., in conjunction with Fig.14 For example, at 1432, UE 1302 may receive an ML data collection indication from base station 1404 indicating whether a set of RSs 1410 is for ML data collection or for ML reasoning. Fig.23 The configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304 performs reception of the indication.

[0251] In one example, the indication further indicates a data collection type.

[0252] At 2108, the UE may transmit a set of RSs based on the Tx / Rx configuration for ML data collection or ML inference, for example in combination with Fig.14 For example, at 1436, UE 1302 may send a set of RS 1410 based on Tx / Rx configuration 1412 for ML data collection or ML inference. Fig.23 The configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304 in performs the transmission of the set of RSs.

[0253] Fig. 22 2200 is a flow chart of a method of wireless communication. The method may be performed by a UE (e.g., UE 104, 404, 1302, 1402; device 2304). The method may enable the UE to associate positioning configurations and measurements with a configuration ID to assist an ML model in ML training, inference, and / or refinement.

[0254] At 2202, the UE may receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, e.g., in conjunction with Fig.14 For example, at 1420, UE 1302 may receive a configuration 1406 for positioning measurements from base station 1404, wherein configuration 1406 includes at least one configuration ID 1408 associated with ML data collection / training / inference for a set of RSs 1410. Fig.23 The configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304 performs reception of the configuration.

[0255] In one example, the configuration applies to multiple UEs.

[0256] In another example, the configuration is associated with a specific resource allocation.

[0257] In another example, the configuration is received via an RRC message.

[0258] In another example, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0259] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0260] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0261] In another example, the at least one configuration ID is associated with a region ID.

[0262] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0263] In another example, the set of RSs includes at least one SRS.

[0264] At 2204, the UE may send a Tx / Rx configuration to a network entity based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs, for example, in conjunction with Fig.14 For example, at 1424, UE 1302 may send Tx / Rx configuration 1412 to base station 1404 based on the at least one configuration ID 1408. Fig.23 The configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304 in performs the transmission of the Tx / Rx configuration.

[0265] In one example, the Tx / Rx configuration indicates: at least one antenna used by the UE to transmit the set of RSs, at least two antennas that the UE is using to transmit the set of RSs based on TDM, a beamforming strategy used to transmit the set of RSs, or a combination thereof.

[0266] In another example, the UE may receive an indication indicating whether the set of RSs is for ML data collection or for ML reasoning, for example in conjunction with Fig.14 For example, at 1432, UE 1302 may receive an ML data collection indication from base station 1404 indicating whether a set of RSs 1410 is for ML data collection or for ML reasoning. Fig.23 The receiving of the indication is performed by the configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304. In such an example, the indication further indicates the data collection type.

[0267] At 2208, the UE may transmit a set of RSs based on the Tx / Rx configuration for ML data collection or ML inference, for example in combination with Fig.14 For example, at 1436, UE 1302 may send a set of RS 1410 based on Tx / Rx configuration 1412 for ML data collection or ML inference. Fig.23The configuration ID association component 198, the cellular baseband processor 2324 and / or the transceiver 2322 of the device 2304 in performs the transmission of the set of RSs.

[0268] Fig.232300 is a diagram illustrating an example of a hardware implementation for an apparatus 2304. The apparatus 2304 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, the apparatus 2304 may include a cellular baseband processor 2324 (also referred to as a modem) coupled to one or more transceivers 2322 (e.g., a cellular RF transceiver). The cellular baseband processor 2324 may include on-chip memory 2324'. In some aspects, the apparatus 2304 may also include one or more subscriber identity module (SIM) cards 2320 and an application processor 2306 coupled to a secure digital (SD) card 2308 and a screen 2310. The application processor 2306 may include on-chip memory 2306'. In some aspects, the device 2304 may also include a Bluetooth module 2312, a WLAN module 2314, an SPS module 2316 (e.g., a GNSS module), one or more sensor modules 2318 (e.g., a barometric pressure sensor / altimeter; a motion sensor such as an inertial management unit (IMU), a gyroscope, and / or an accelerometer; a magnetometer, audio, and / or other technologies for positioning), other memory modules 2326, a power supply 2330, and / or a camera 2332. The Bluetooth module 2312, the WLAN module 2314, and the SPS module 2316 may include an on-chip transceiver (TRX) (or in some cases, just a receiver (RX)). The Bluetooth module 2312, the WLAN module 2314, and the SPS module 2316 may include their own dedicated antennas and / or communicate using antennas 2380. The cellular baseband processor 2324 communicates with the UE 104 and / or RUs associated with the network entity 2302 via one or more antennas 2380 through the transceiver 2322. The cellular baseband processor 2324 and the application processor 2306 may each include a computer-readable medium / memory 2324', 2306', respectively. Other memory modules 2326 may also be considered as computer-readable medium / memory. Each computer-readable medium / memory 2324', 2306', 2326 may be non-temporary. The cellular baseband processor 2324 and the application processor 2306 are each responsible for general processing, which includes executing software stored on a computer-readable medium / memory. When the software is executed by the cellular baseband processor 2324 / application processor 2306, the cellular baseband processor 2324 / application processor 2306 performs the various functions described above. The computer-readable medium / memory may also be used to store data manipulated by the cellular baseband processor 2324 / application processor 2306 when executing the software. The cellular baseband processor 2324 / application processor 2306 may be a component of the UE 350 and may include at least one of the memory 360 and / or the TX processor 368, the RX processor 356, and the controller / processor 359.In one configuration, the device 2304 may be a processor chip (modem and / or applications) and include only the cellular baseband processor 2324 and / or the application processor 2306, and in another configuration, the device 2304 may be the entire UE (eg, see. Figure 3 350) and includes other modules of device 2304.

[0269] As described above, the configuration ID association component 198 can be configured to receive a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning of a set of RSs. The configuration ID association component 198 can also be configured to send a Tx / Rx configuration to the network entity based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with the reception of the set of RSs. The configuration ID association component 198 can also be configured to send a set of RSs based on the Tx / Rx configuration for ML data collection or ML reasoning. The configuration ID association component 198 can be in the cellular baseband processor 2324, the application processor 2306, or in both the cellular baseband processor 2324 and the application processor 2306. The configuration ID association component 198 can be one or more hardware components specifically configured to perform the stated processing / algorithms, implemented by one or more processors configured to perform the stated processing / algorithms, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. As shown, the device 2304 can include various components configured to implement various functions. In one configuration, the apparatus 2304 (specifically, the cellular baseband processor 2324 and / or the application processor 2306) may include: a unit for receiving a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning of a set of RSs. The apparatus 2304 may also include: a unit for sending a Tx / Rx configuration to the network entity based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs. The apparatus 2304 may also include: a unit for sending a set of RSs based on the Tx / Rx configuration for ML data collection or ML reasoning.

[0270] In one configuration, the apparatus 2304 may further include: a unit for receiving an indication indicating whether the set of RSs is for ML data collection or for ML reasoning.

[0271] In one configuration, the Tx / Rx configuration indicates: at least one antenna used by the UE to transmit the set of RSs, the UE is using at least two antennas to transmit the set of RSs based on TDM, a beamforming strategy used to transmit the set of RSs, or a combination thereof.

[0272] In another configuration, the configuration applies to multiple UEs.

[0273] In another configuration, the configuration is associated with a specific resource allocation.

[0274] In another configuration, the configuration is received via an RRC message.

[0275] In another configuration, the at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and the assistance data includes at least one of PRS assistance data, positioning calculation assistance data, error event data, or a combination thereof.

[0276] In another configuration, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0277] In another configuration, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0278] In another configuration, the at least one configuration ID is associated with a region ID.

[0279] In another configuration, the at least one configuration ID is associated with a specific positioning mechanism.

[0280] In another configuration, the set of RSs includes at least one SRS.

[0281] These means may be the configuration ID associated component 198 of the apparatus 2304 configured to perform the functions recited by these means. As described above, the apparatus 2304 may include a TX processor 368, an RX processor 356, and a controller / processor 359. Thus, in one configuration, these means may be the TX processor 368, the RX processor 356, and / or the controller / controller 359 configured to perform the functions recited by these means.

[0282] Fig.24 2400 is a flow chart of a method of wireless communication. The method may be performed by a base station (e.g., base station 102, 1304, 1404; network entity 2602). The method may enable the base station to associate positioning configurations and measurements with a configuration ID to assist an ML model in ML training, inference, and / or refinement.

[0283] At 2402, the base station may configure at least one configuration ID for a configuration for a set of positioning measurements, wherein before sending the configuration, the at least one configuration ID is configured, for example, in conjunction with Fig.14For example, at 1422, the base station 1404 may configure at least one configuration ID 1408 for the configuration 1406 for positioning measurements. Fig.26 The configuration of the at least one configuration ID is performed by the configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602.

[0284] At 2404, the base station may send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, such as in conjunction with Fig.14 For example, at 1420, the base station 1404 may send a configuration 1406 for positioning measurements, wherein the configuration 1406 includes at least one configuration ID 1408 associated with ML data collection / training / inference for a group of RSs 1410. Fig.26 The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs the sending of the configuration.

[0285] In one example, the configuration is applied to multiple UEs including the UE.

[0286] In another example, the configuration is associated with a specific resource allocation.

[0287] In another example, the configuration is received via an RRC message.

[0288] In another example, the Tx / Rx configuration indicates: at least one antenna used by the UE to transmit the set of RSs, the UE is using at least two antennas to transmit the set of RSs based on TDM, a beamforming strategy used to transmit the set of RSs, or a combination thereof.

[0289] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0290] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0291] In another example, the at least one configuration ID is associated with a region ID.

[0292] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0293] In another example, the set of RSs includes at least one SRS.

[0294] At 2406, the base station may receive a Tx / Rx configuration based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of a set of RSs, for example, in conjunction with Fig.14 For example, at 1424, the base station 1404 may receive a Tx / Rx configuration 1412 based on the at least one configuration ID 1408 from the UE 1402. Fig.26 The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs reception of the Tx / Rx configuration.

[0295] At 2408, the base station may send an indication indicating whether the set of RSs is for ML data collection or for ML reasoning, for example in conjunction with Fig.14 For example, at 1432, base station 1404 may send an indication to UE 1402 indicating whether a group of RS 1410 is for ML data collection or for ML reasoning. Fig.26 The sending of the indication is performed by the configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602. In such an example, the indication further indicates the data collection type.

[0296] At 2410, the base station may receive a set of RSs based on a Tx / Rx configuration for ML data collection or ML inference, such as in conjunction with Fig.14 For example, at 1436, the base station 1404 may receive a set of RS 1410 based on the Tx / Rx configuration 1412 for ML data collection or ML inference. Fig.26 The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs reception of the set of RSs.

[0297] At 2412, the base station may perform a set of positioning measurements based on the configuration and a set of RSs, such as in conjunction with Fig.14 For example, at 1438, base station 1404 may perform positioning measurements based on configuration 1406 and a set of RSs 1410. Fig.26 The positioning measurement is performed by the configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602.

[0298] At 2414, the base station may store at least one parameter for ML data collection based on the at least one configuration ID, for example, in conjunction with Fig.14 For example, at 1440, the base station 1404 may store at least one parameter for ML data collection based on the at least one configuration ID 1408. Fig.26The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs the sending of the configuration.

[0299] In one example, the base station can perform ML data collection based on the at least one parameter.

[0300] In another example, the base station may transmit at least one parameter for an ML training process.

[0301] In another example, the base station can load the NN based on the at least one configuration ID. In such an example, the base station can perform ML inference for a set of positioning measurements via the NN.

[0302] Fig.25 2500 is a flow chart of a method of wireless communication. The method may be performed by a base station (e.g., base station 102, 1304, 1404; network entity 2602). The method may enable the base station to associate positioning configurations and measurements with configuration IDs to assist ML models in ML training, inference, and / or refinement.

[0303] At 2504, the base station may send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML inference for a set of RSs, such as in conjunction with Fig.14 For example, at 1420, the base station 1404 may send a configuration 1406 for positioning measurements, wherein the configuration 1406 includes at least one configuration ID 1408 associated with ML data collection / training / inference for a group of RSs 1410. Fig.26 The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs the sending of the configuration.

[0304] In one example, the base station may configure at least one configuration ID for a configuration for a group of positioning measurements, wherein before sending the configuration, the at least one configuration ID is configured, for example, in conjunction with Fig.14 For example, at 1422, the base station 1404 may configure at least one configuration ID 1408 for the configuration 1406 for positioning measurements. Fig.26 The configuration of the at least one configuration ID is performed by the configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602.

[0305] In another example, the configuration is applied to a plurality of UEs including the UE.

[0306] In another example, the configuration is associated with a specific resource allocation.

[0307] In another example, the configuration is received via RRC messaging.

[0308] In another example, the Tx / Rx configuration indicates: at least one antenna used by the UE to transmit the set of RSs, the UE is using at least two antennas to transmit the set of RSs based on TDM, a beamforming strategy used to transmit the set of RSs, or a combination thereof.

[0309] In another example, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0310] In another example, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0311] In another example, the at least one configuration ID is associated with a region ID.

[0312] In another example, the at least one configuration ID is associated with a specific positioning mechanism.

[0313] In another example, the set of RSs includes at least one SRS.

[0314] At 2506, the base station may receive a Tx / Rx configuration based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of a set of RSs, for example, in conjunction with Fig.14 For example, at 1424, the base station 1404 may receive a Tx / Rx configuration 1412 based on the at least one configuration ID 1408 from the UE 1402. Fig.26 The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs reception of the Tx / Rx configuration.

[0315] In one example, the base station may send an indication indicating whether the set of RSs is used for ML data collection or for ML reasoning, for example in conjunction with Fig.14 For example, at 1432, base station 1404 may send an indication to UE 1402 indicating whether a group of RS 1410 is for ML data collection or for ML reasoning. Fig.26 The sending of the indication is performed by the configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602. In such an example, the indication further indicates the data collection type.

[0316] At 2510, the base station may receive a set of RSs based on a Tx / Rx configuration for ML data collection or ML inference, such as in conjunction with Fig.14For example, at 1436, the base station 1404 may receive a set of RS 1410 based on the Tx / Rx configuration 1412 for ML data collection or ML inference. Fig.26 The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs reception of the set of RSs.

[0317] In one example, the base station may perform a set of positioning measurements based on the configuration and a set of RSs, such as in conjunction with Fig.14 For example, at 1438, base station 1404 may perform positioning measurements based on configuration 1406 and a set of RSs 1410. Fig.26 The positioning measurement is performed by the configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602.

[0318] In another example, the base station may store at least one parameter for ML data collection based on the at least one configuration ID, for example, in combination with Fig.14 For example, at 1440, the base station 1404 may store at least one parameter for ML data collection based on the at least one configuration ID 1408. Fig.26 The configuration ID association component 199 and / or the transceiver 2646 of the network entity 2602 performs the sending of the configuration.

[0319] In another example, the base station may perform ML data collection based on the at least one parameter.

[0320] In another example, the base station may transmit at least one parameter for an ML training process.

[0321] In another example, the base station can load the NN based on the at least one configuration ID. In such an example, the base station can perform ML inference for a set of positioning measurements via the NN.

[0322] Fig.262600 is a diagram illustrating an example of a hardware implementation of a network entity 2602. The network entity 2602 may be a BS, a component of a BS, or may implement BS functionality. The network entity 2602 may include at least one of a CU 2610, a DU 2630, or a RU 2640. For example, depending on the layer functionality processed by the configuration ID association component 199, the network entity 2602 may include a CU 2610; a CU 2610 and a DU 2630; each of the CU 2610, the DU 2630, and the RU 2640; a DU 2630; a DU 2630 and a RU 2640; or a RU 2640. The CU 2610 may include a CU processor 2612. The CU processor 2612 may include an on-chip memory 2612'. In some aspects, the CU 2610 may also include an additional memory module 2614 and a communication interface 2618. CU 2610 communicates with DU 2630 via a mid-range link such as an F1 interface. DU 2630 may include a DU processor 2632. DU processor 2632 may include on-chip memory 2632'. In some aspects, DU 2630 may also include other memory modules 2634 and a communication interface 2638. DU 2630 communicates with RU 2640 via a front-range link. RU 2640 may include a RU processor 2642. RU processor 2642 may include on-chip memory 2642'. In some aspects, RU 2640 may also include other memory modules 2644, one or more transceivers 2646, antenna 2680, and communication interface 2648. RU 2640 communicates with UE 104. On-chip memory 2612', 2632', 2642' and other memory modules 2614, 2634, 2644 may each be considered as a computer-readable medium / memory. Each computer readable medium / memory may be non-temporary. Each of processors 2612, 2632, 2642 is responsible for general processing, including executing software stored on the computer readable medium / memory. When the software is executed by the corresponding processor, the processor performs the various functions described above. The computer readable medium / memory can also be used to store data manipulated by the processor when executing the software.

[0323] As described above, the configuration ID association component 199 may be configured to send a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning of a set of RSs. The configuration ID association component 199 may also be configured to receive a Tx / Rx configuration based on the at least one configuration ID from the UE, wherein the Tx / Rx configuration is associated with the reception of a set of RSs. The configuration ID association component 199 may also be configured to receive a set of RSs based on the Tx / Rx configuration for ML data collection or ML reasoning. The configuration ID association component 199 may be within one or more processors of one or more of the CU 2610, DU 2630, and RU 2640. The configuration ID association component 199 may be one or more hardware components specifically configured to perform the stated processing / algorithms, implemented by one or more processors configured to perform the stated processing / algorithms, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. The network entity 2602 may include various components configured to implement various functions. In one configuration, the network entity 2602 may include: a unit for sending a configuration for a set of positioning measurements to the UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning of a set of RSs. The network entity 2602 may also include: a unit for receiving a Tx / Rx configuration based on the at least one configuration ID from the UE, wherein the Tx / Rx configuration is associated with reception of a set of RSs. The network entity 2602 may also include: a unit for receiving a set of RSs based on the Tx / Rx configuration for ML data collection or ML reasoning.

[0324] In one configuration, the network entity 2602 may further include: means for configuring at least one configuration ID for configuration for a set of positioning measurements, wherein the at least one configuration ID is configured before sending the configuration.

[0325] In another configuration, the network entity 2602 may further include means for performing a set of positioning measurements based on the configuration and a set of RSs.

[0326] In another configuration, the network entity 2602 may further include: means for storing at least one parameter for ML data collection based on the at least one configuration ID.

[0327] In another configuration, the network entity 2602 may also include means for performing ML data collection based on the at least one parameter.

[0328] In another configuration, the network entity 2602 may further include: a unit for sending at least one parameter for the ML training process.

[0329] In another configuration, the network entity 2602 may further include: a unit for loading the NN based on the at least one configuration ID.

[0330] In another configuration, the network entity 2602 may also include means for performing ML inference for a set of positioning measurements via the NN.

[0331] In another configuration, the configuration is applied to a plurality of UEs including the UE.

[0332] In another configuration, the configuration is associated with a specific resource allocation.

[0333] In another configuration, the configuration is received via an RRC message.

[0334] In another configuration, the Tx / Rx configuration indicates: at least one antenna used by the UE to transmit the set of RSs, the UE is using at least two antennas to transmit the set of RSs based on TDM, a beamforming strategy used to transmit the set of RSs, or a combination thereof.

[0335] In another configuration, the at least one configuration ID is associated with a frequency layer selected based on capabilities of the UE.

[0336] In another configuration, the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0337] In another configuration, the at least one configuration ID is associated with a region ID.

[0338] In another configuration, the at least one configuration ID is associated with a specific positioning mechanism.

[0339] In another configuration, the set of RSs includes at least one SRS.

[0340] These means may be the configuration ID associated component 199 of the network entity 2602 configured to perform the functions recited by these means. As described above, the network entity 2602 may include the TX processor 316, the RX processor 370, and the controller / processor 375. Thus, in one configuration, these means may be the TX processor 316, the RX processor 370, and / or the controller / controller 375 configured to perform the functions recited by these means.

[0341] It should be understood that the specific order or block hierarchy in the process / flow chart disclosed herein is only an example of an exemplary method. It should be understood that the specific order or block hierarchy in these processes / flow charts can be rearranged based on design preferences. In addition, some blocks can be combined or omitted. The attached method claims provide the elements of various blocks in an exemplary order, but are not limited to the specific order or hierarchy provided.

[0342] To enable any person of ordinary skill in the art to implement the various aspects described herein, the above description is made around various aspects. It is obvious to a person of ordinary skill in the art that various modifications to these aspects are possible, and the general principles defined herein may also be applicable to other aspects. Therefore, the present invention is not limited to the aspects described herein, but is consistent with the full scope of the present invention. Modifying a certain component with a singular form does not mean "one and only one", but may be "one or more". Terms such as "if", "when..." and "when..." do not imply a direct time relationship or reaction. That is, these phrases (e.g., "when...") do not mean to take action immediately in response to an action or to take action during the occurrence of an action, but simply mean that if the conditions are met, an action will occur, but there is no need to have a specific or immediate time constraint on the occurrence of the action. The word "exemplary" used herein means "used as an example, illustration or description". Any aspect described as "exemplary" herein should not be interpreted as being more preferred or more advantageous than other aspects. Unless otherwise specifically stated, the term "some" refers to one or more. Combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, which may include multiple A, multiple B, or multiple C. Specifically, combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, wherein any such combination may contain one or more members or some members of A, B, or C. A set should be interpreted as a group of elements, where the elements are numbered one or more. Thus, for a group X, X will include one or more elements. If a first device receives data from or sends data to a second device, the data may be received / sent directly between the first device and the second device, or indirectly between the first device and the second device through a group of devices. All structural and functional equivalents of the components of the various aspects described throughout the present disclosure are expressly incorporated herein by reference and are intended to be covered by the claims, which are known or will be known to those of ordinary skill in the art. In addition, no disclosure herein is intended to be dedicated to the public, regardless of whether such disclosure is clearly recorded in the claims. Words such as "module", "device", "element", "equipment", etc. are not substitutes for the word "unit".Therefore, a constituent element of a claim should not be construed as a functional module unless the constituent element is explicitly described using the wording of “functional module”.

[0343] As used herein, the phrase "based on" shall not be interpreted as a reference to a closed set of information, one or more conditions, one or more factors, etc. In other words, the phrase "based on A" (where "A" may be information, a condition, a factor, etc.) shall be interpreted as "based at least on A" unless specifically stated otherwise.

[0344] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein, but are not limited thereto.

[0345] Aspect 1 is a method for wireless communication at a UE, the method comprising: receiving a configuration for a set of positioning measurements from a network entity, wherein the configuration comprises at least one configuration ID associated with ML data collection or ML inference of a set of RSs; performing the set of positioning measurements based on the configuration and the set of RSs; and storing at least one parameter for the ML data collection or loading a first NN based on the at least one configuration ID.

[0346] Aspect 2 is a method according to aspect 1, further comprising: receiving the set of RSs via one or more DL channels, wherein the set of positioning measurements is associated with the one or more DL channels.

[0347] Aspect 3 is a method according to any one of aspects 1 or 2, wherein the at least one processor is configured to: store the at least one parameter for the ML data collection based on the at least one configuration ID.

[0348] Aspect 4 is a method according to aspect 3, further comprising: performing the ML data collection based on the at least one parameter.

[0349] Aspect 5 is a method according to aspect 3, further comprising: sending the at least one parameter used for the ML training process.

[0350] Aspect 6 is a method according to aspect 3, wherein the ML training process is associated with a second NN different from the first NN.

[0351] Aspect 7 is a method according to aspect 3, further comprising: receiving a priority indication for the ML data collection; and determining whether to perform the ML data collection based on the priority indication.

[0352] Aspect 8 is a method according to any one of aspects 1 to 7, wherein the at least one processor is configured to load the first NN based on the at least one configuration ID.

[0353] Aspect 9 is the method according to aspect 8, further comprising: performing the ML inference on the set of positioning measurements via the first NN.

[0354] Aspect 10 is a method according to any one of aspects 1 to 9, further comprising: receiving an indication indicating whether the set of RSs is used for the ML data collection or for the ML reasoning.

[0355] Aspect 11 is a method according to aspect 10, wherein the indication further indicates a data collection type.

[0356] Aspect 12 is a method according to any one of Aspects 1 to 11, wherein the at least one configuration ID is associated with one or more parameters of auxiliary data configured for the positioning session of the UE, and wherein the auxiliary data includes at least one of PRS auxiliary data, positioning calculation assistance data, error event data, or a combination thereof.

[0357] Aspect 13 is a method according to any one of aspects 1 to 12, wherein the at least one configuration ID is associated with a frequency layer selected based on the capability of the UE.

[0358] Aspect 14 is a method according to any one of aspects 1 to 13, wherein the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0359] Aspect 15 is a method according to any one of aspects 1 to 14, wherein the at least one configuration ID is associated with a region ID.

[0360] Aspect 16 is a method according to any one of aspects 1 to 15, wherein the at least one configuration ID is associated with a specific positioning mechanism.

[0361] Aspect 17 is a method according to any one of aspects 1 to 16, wherein the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0362] Aspect 18 is an apparatus for wireless communication at a UE, comprising: a memory; and at least one processor coupled to the memory, and based at least in part on information stored in the memory, the at least one processor is configured to implement a method according to any one of Aspects 1 to 17.

[0363] Aspect 19 is the apparatus of aspect 18, further comprising at least one of a transceiver or an antenna coupled to the at least one processor.

[0364] Aspect 20 is an apparatus for wireless communication, comprising means for implementing the method according to any one of aspects 1 to 17.

[0365] Aspect 21 is a computer-readable medium (eg, a non-transitory computer-readable medium) storing computer-executable code, wherein when the code is executed by a processor, the processor is caused to implement the method according to any one of aspects 1 to 17.

[0366] Aspect 22 is a method for wireless communication at a base station, the method comprising: sending a configuration for a set of positioning measurements to a UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning for a set of RSs; and receiving at least one parameter for the ML data collection or the ML reasoning based on the at least one configuration ID.

[0367] Aspect 23 is a method according to aspect 22, further comprising: transmitting the set of RSs via one or more DL channels, wherein the set of positioning measurements is associated with the one or more DL channels.

[0368] Aspect 24 is a method according to any one of aspects 22 or 23, further comprising: sending a priority indication for the ML data collection, wherein the at least one parameter for the ML data collection or the ML reasoning is received based on the priority indication.

[0369] Aspect 25 is a method according to any one of aspects 22 to 24, further comprising: sending an indication indicating whether the set of RSs is used for the ML data collection or for the ML reasoning.

[0370] Aspect 26 is a method according to aspect 25, wherein the indication further indicates a data collection type.

[0371] Aspect 27 is a method according to any one of Aspects 22 to 26, wherein the at least one configuration ID is associated with one or more parameters of auxiliary data configured for the positioning session of the UE, and wherein the auxiliary data includes at least one of PRS auxiliary data, positioning calculation assistance data, error event data, or a combination thereof.

[0372] Aspect 28 is a method according to any one of aspects 22 to 27, wherein the at least one configuration ID is associated with a frequency layer selected based on the capability of the UE.

[0373] Aspect 29 is a method according to any one of aspects 22 to 28, wherein the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0374] Aspect 30 is a method according to any one of aspects 22 to 29, wherein the at least one configuration ID is associated with a region ID.

[0375] Aspect 31 is a method according to any one of aspects 22 to 30, wherein the at least one configuration ID is associated with a specific positioning mechanism.

[0376] Aspect 32 is a method according to any one of aspects 22 to 31, wherein the set of RSs includes at least one PRS, at least one SSB, at least one CSI-RS, or a combination thereof.

[0377] Aspect 33 is an apparatus for wireless communication at a base station, comprising: a memory; and at least one processor coupled to the memory, and based at least in part on information stored in the memory, the at least one processor is configured to implement a method according to any one of Aspects 22 to 32.

[0378] Aspect 34 is the apparatus of aspect 33, further comprising at least one of a transceiver or an antenna coupled to the at least one processor.

[0379] Aspect 35 is an apparatus for wireless communication, comprising means for implementing the method according to any one of aspects 22 to 32.

[0380] Aspect 36 is a computer-readable medium (eg, a non-transitory computer-readable medium) storing computer-executable code, wherein when the code is executed by a processor, the processor is caused to implement the method according to any one of aspects 22 to 32.

[0381] Aspect 37 is a method for wireless communication at a UE, the method comprising: receiving a configuration for a set of positioning measurements from a network entity, wherein the configuration comprises at least one configuration ID associated with ML data collection or ML reasoning of a set of RSs; based on the at least one configuration ID, sending a Tx / Rx configuration to the network entity, wherein the Tx / Rx configuration is associated with reception of the set of RSs; and sending the set of RSs based on the Tx / Rx configuration for the ML data collection or the ML reasoning.

[0382] Aspect 38 is a method according to aspect 37, wherein the configuration is applied to multiple UEs.

[0383] Aspect 39 is a method according to any one of aspects 37 or 38, wherein the configuration is associated with a specific resource allocation.

[0384] Aspect 40 is a method according to any one of aspects 37 to 39, wherein the configuration is received via RRC messaging.

[0385] Aspect 41 is a method according to any one of Aspects 37 to 40, wherein the Tx / Rx configuration indicates: at least one antenna used by the UE to send the set of RSs, the UE using at least two antennas to send the set of RSs based on TDM, a beamforming strategy used to send the set of RSs, or a combination thereof.

[0386] Aspect 42 is a method according to any one of aspects 37 to 41, further comprising: receiving an indication indicating whether the set of RSs is used for the ML data collection or for the ML reasoning.

[0387] Aspect 43 is a method according to aspect 42, wherein the indication further indicates a data collection type.

[0388] Aspect 44 is a method according to any one of aspects 37 to 43, wherein the at least one configuration ID is associated with a frequency layer selected based on the capabilities of the UE.

[0389] Aspect 45 is a method according to any one of aspects 37 to 44, wherein the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0390] Aspect 46 is a method according to any one of aspects 37 to 45, wherein the at least one configuration ID is associated with a region ID.

[0391] Aspect 47 is a method according to any one of aspects 37 to 46, wherein the at least one configuration ID is associated with a specific positioning mechanism.

[0392] Aspect 48 is a method according to any one of aspects 37 to 47, wherein the set of RSs includes at least one SRS.

[0393] Aspect 49 is an apparatus for wireless communication at a UE, comprising: a memory; and at least one processor coupled to the memory, and based at least in part on information stored in the memory, the at least one processor is configured to implement a method according to any one of Aspects 37 to 48.

[0394] Aspect 50 is the apparatus of aspect 49, further comprising at least one of a transceiver or an antenna coupled to the at least one processor.

[0395] Aspect 51 is an apparatus for wireless communication, comprising means for implementing the method according to any one of aspects 37 to 48.

[0396] Aspect 52 is a computer-readable medium (eg, a non-transitory computer-readable medium) storing computer-executable code, wherein when the code is executed by a processor, the processor is caused to implement the method according to any one of aspects 37 to 48.

[0397] Aspect 53 is a method for wireless communication at a base station, the method comprising: sending a configuration for a set of positioning measurements to a UE, wherein the configuration includes at least one configuration ID associated with ML data collection or ML reasoning of a set of RSs; receiving a Tx / Rx configuration based on the at least one configuration ID from the UE, wherein the Tx / Rx configuration is associated with reception of the set of RSs; and receiving the set of RSs based on the Tx / Rx configuration for the ML data collection or the ML reasoning.

[0398] Aspect 54 is a method according to aspect 53, further comprising: configuring the at least one configuration ID for the configuration for the set of positioning measurements, wherein the at least one configuration ID is configured before sending the configuration.

[0399] Aspect 55 is a method according to any one of aspects 53 or 54, further comprising: performing the set of positioning measurements based on the configuration and the set of RSs.

[0400] Aspect 56 is a method according to aspect 55, further comprising: storing at least one parameter for the ML data collection based on the at least one configuration ID.

[0401] Aspect 57 is a method according to aspect 56, further comprising: performing the ML data collection based on the at least one parameter.

[0402] Aspect 58 is a method according to aspect 56, further comprising: sending the at least one parameter for the ML training process.

[0403] Aspect 59 is a method according to any one of aspects 53 to 58, wherein the at least one processor is configured to load the NN based on the at least one configuration ID.

[0404] Aspect 60 is a method according to aspect 59, further comprising: performing the ML inference on the set of positioning measurements via the NN.

[0405] Aspect 61 is a method according to any one of aspects 53 to 60, wherein the configuration is applied to a plurality of UEs including the UE.

[0406] Aspect 62 is a method according to any one of aspects 53 to 61, wherein the configuration is associated with a specific resource allocation.

[0407] Aspect 63 is a method according to any one of aspects 53 to 62, wherein the configuration is sent via an RRC message.

[0408] Aspect 64 is a method according to any one of Aspects 53 to 63, wherein the Tx / Rx configuration indicates: at least one antenna used by the UE to send the set of RSs, the UE using at least two antennas to send the set of RSs based on TDM, a beamforming strategy used to send the set of RSs, or a combination thereof.

[0409] Aspect 65 is a method according to any one of aspects 53 to 64, further comprising: sending an indication indicating whether the set of RSs is used for the ML data collection or for the ML reasoning.

[0410] Aspect 66 is a method according to aspect 65, wherein the indication further indicates a data collection type.

[0411] Aspect 67 is a method according to any one of aspects 53 to 66, wherein the at least one configuration ID is associated with a frequency layer selected based on the capabilities of the UE.

[0412] Aspect 68 is a method according to any one of aspects 53 to 67, wherein the at least one configuration ID is associated with a first set of positioning parameters having fixed values ​​and a second set of positioning parameters having multiple values.

[0413] Aspect 69 is a method according to any one of aspects 53 to 68, wherein the at least one configuration ID is associated with a region ID.

[0414] Aspect 70 is a method according to any one of aspects 53 to 69, wherein the at least one configuration ID is associated with a specific positioning mechanism.

[0415] Aspect 71 is a method according to any one of aspects 53 to 70, wherein the set of RSs includes at least one SRS.

[0416] Aspect 72 is an apparatus for wireless communication at a UE, comprising: a memory; and at least one processor coupled to the memory, and based at least in part on information stored in the memory, the at least one processor is configured to implement a method according to any one of Aspects 53 to 71.

[0417] Aspect 73 is the apparatus of aspect 72, further comprising at least one of a transceiver or an antenna coupled to the at least one processor.

[0418] Aspect 74 is an apparatus for wireless communication, comprising means for implementing the method according to any one of aspects 53 to 71.

[0419] Aspect 75 is a computer-readable medium (eg, a non-transitory computer-readable medium) storing computer-executable code, wherein when the code is executed by a processor, the processor is caused to implement the method according to any one of aspects 53 to 71.

Claims

1. An apparatus for wireless communication at a user equipment (UE), comprising: Memory; as well as at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor is configured to: receiving a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration identifier (ID) associated with machine learning (ML) data collection or ML inference for a set of reference signals (RS); performing the set of positioning measurements based on the configuration and the set of RSs; as well as At least one parameter for the ML data collection is stored based on the at least one configuration ID, or a first neural network (NN) is loaded.

2. The device according to claim 1, wherein: The at least one processor is configured to: The set of RSs is received via one or more DL channels, wherein the set of positioning measurements are associated with the one or more DL channels.

3. The device according to claim 1, wherein: The at least one processor is further configured to: performing the ML data collection based on the at least one parameter; and The at least one parameter for the ML training process is transmitted.

4. The device according to claim 3, wherein: The ML training process is associated with a second NN that is different from the first NN.

5. The device according to claim 1, wherein: The at least one processor is further configured to: receiving a priority indication for the ML data collection; and Based on the priority indication, it is determined whether to perform the ML data collection.

6. The device according to claim 1, wherein: The at least one processor is configured to load the first NN based on the at least one configuration ID.

7. The device according to claim 1, wherein: The at least one processor is further configured to: The ML inference is performed, via the first NN, on the set of positioning measurements.

8. The device according to claim 1, wherein: The at least one processor is further configured to: An indication is received indicating whether the set of RSs is used for the ML data collection or for the ML reasoning, wherein the indication further indicates a data collection type.

9. The device according to claim 1, wherein: The at least one configuration ID is associated with one or more parameters of assistance data configured for a positioning session of the UE, and wherein the assistance data comprises at least one of positioning reference signal (PRS) assistance data, positioning calculation assistance data, error event data, or a combination thereof.

10. The device according to claim 1, wherein: The at least one configuration ID is associated with at least one of: The frequency layer is selected based on the capability of the UE, a first set of targeting parameters with fixed values ​​and a second set of targeting parameters with multiple values, Region ID, or Specific positioning mechanism.

11. The device according to claim 1, wherein: The set of RSs includes at least one positioning reference signal (PRS), at least one synchronization signal block (SSB), at least one channel state information reference signal (CSI-RS), or a combination thereof.

12. A method for wireless communication at a user equipment (UE), comprising: receiving a configuration for a set of positioning measurements from a network entity, wherein the configuration includes at least one configuration identifier (ID) associated with machine learning (ML) data collection or ML inference for a set of reference signals (RS); performing the set of positioning measurements based on the configuration and the set of RSs; and At least one parameter for the ML data collection is stored, or a first neural network (NN) is loaded based on the at least one configuration ID.

13. The method according to claim 12, further comprising: performing the ML data collection based on the at least one parameter; as well as The at least one parameter for the ML training process is transmitted.

14. The method according to claim 12, further comprising: receiving a priority indication for the ML data collection; as well as Based on the priority indication, it is determined whether to perform the ML data collection.

15. The method according to claim 12, further comprising: The ML inference is performed, via the first NN, on the set of positioning measurements.

16. An apparatus for wireless communication at a network entity, comprising: Memory; as well as at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor is configured to: Sending a configuration for a set of positioning measurements to a user equipment (UE), wherein the configuration includes at least one configuration identifier (ID) associated with machine learning (ML) data collection or ML inference for a set of reference signals (RS); receiving, from the UE, a transmit (Tx) or receive (Rx) (Tx / Rx) configuration based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs; and The set of RSs is received based on the Tx / Rx configuration for the ML data collection or the ML inference.

17. The device according to claim 1, wherein: The at least one processor is further configured to: For the configuration of the set of positioning measurements, the at least one configuration ID is configured, wherein the at least one configuration ID is configured before sending the configuration.

18. The device according to claim 16, wherein: The at least one processor is further configured to: The set of positioning measurements is performed based on the configuration and the set of RSs.

19. The device according to claim 18, wherein: The at least one processor is further configured to: At least one parameter for the ML data collection is stored based on the at least one configuration ID.

20. The device according to claim 19, wherein The at least one processor is further configured to: The ML data collection is performed based on the at least one parameter.

21. The device according to claim 19, wherein The at least one processor is further configured to: The at least one parameter for the ML training process is transmitted.

22. The device according to claim 16, wherein: The at least one processor is configured to load a neural network (NN) based on the at least one configuration ID.

23. The device according to claim 22, wherein: The at least one processor is further configured to: The ML inference is performed, via the NN, on the set of positioning measurements.

24. The device according to claim 16, wherein: The configuration is applied to a plurality of UEs including the UE.

25. The device according to claim 16, wherein: The configuration is associated with a specific resource allocation.

26. The device according to claim 16, wherein: The configuration is sent via a Radio Resource Control (RRC) message.

27. The device according to claim 16, wherein: The Tx / Rx configuration indicates: at least one antenna used by the UE to transmit the set of RSs, The UE transmits the set of RSs based on time division multiplexing (TDM) using at least two antennas, a beamforming strategy for transmitting the set of RSs, or Its combination.

28. The apparatus of claim 16, wherein: The at least one processor is further configured to: An indication is sent indicating whether the set of RSs is used for the ML data collection or for the ML inference.

29. The device according to claim 16, wherein: The at least one configuration ID is associated with at least one of: The frequency layer is selected based on the capability of the UE, a first set of targeting parameters with fixed values ​​and a second set of targeting parameters with multiple values, Region ID, or Specific positioning mechanism.

30. A method for wireless communication at a network entity, comprising: Sending a configuration for a set of positioning measurements to a user equipment (UE), wherein the configuration includes at least one configuration identifier (ID) associated with machine learning (ML) data collection or ML inference for a set of reference signals (RS); receiving, from the UE, a transmit (Tx) or receive (Rx) (Tx / Rx) configuration based on the at least one configuration ID, wherein the Tx / Rx configuration is associated with reception of the set of RSs; and The set of RSs is received based on the Tx / Rx configuration for the ML data collection or the ML inference.

Images