Training machine learning positioning model in wireless communication network

Abstract

There is provided a network node in a wireless communication network, the network node comprising a transmitter arranged to transmit a positioning training dataset configuration to at least one data source of the wireless communication network, the positioning training dataset configuration includes a request for a positioning training dataset for training the machine learning positioning model, and a required data format for the positioning training dataset based on a location of the network node. The network node further comprises a receiver arranged to receive a response from the at least one data source, the response comprising a set of localization training data according to a desired data format. The network node further comprises a processor arranged to train a machine-learned localization model using the localization training data set.

Description

Technical Field

[0001] The subject matter disclosed herein generally relates to the field of implementing training of machine learning positioning models in wireless communication networks. This document defines a network node in a wireless communication network, and a method in a network node, the network node in the wireless communication network. Background Art

[0002] Positioning requirements for 3GPP's New Radio (NR) air interface (Uu) signals and standalone (SA) architectures (e.g., beam-based transmissions) are specified in 3GPP Release 16. Target use cases also include commercial and regulatory (emergency services) scenarios as provided in 3GPP Release 15. In addition, the current 3GPP Release 17 positioning recently defined positioning performance requirements for commercial and Industrial Internet of Things (IIoT) use cases.

[0003] Positioning techniques in 3GPP can currently be configured and performed based on the requirements of the Location Management Function (LMF) and UE capabilities. These techniques seek to be able to calculate a position estimate for the UE. Summary of the invention

[0004] Artificial Intelligence (AI) and / or Machine Learning (ML) for the air interface within the 3GPP framework corresponding to the targeted use cases related to CSI feedback, beam management and positioning accuracy enhancement, covering aspects such as performance, complexity and potential for specification impact. There is a particular interest in using AI / ML based procedures to enhance different positioning procedures (including 3GPP positioning procedures and / or signaling at the RAN and / or UE and / or Location Server (LMF)), and enhancements to the above aspects may be required.

[0005] For example, AI / ML techniques can be implemented to optimize and predict different metrics (e.g., PRS / SRS configuration, final location accuracy) in time and space within a positioning session of a target UE. Therefore, it is necessary to support efficient model training and inference signaling mechanisms to enhance measurements and reporting within the positioning framework, provided that the described training and inference models are already deployed at the location server or NG-RAN / UE.

[0006] However, in the current positioning framework, there is no known way to select, trigger and configure the collection of positioning data required for the training of the configured AI / ML positioning model. This includes both online and offline training of positioning data for a specific AI / ML model. In addition, the type of data source is key to the statistical significance of the input training data set, which affects the accuracy of the AI / ML model to be trained.

[0007] The present disclosure presents apparatus and methods that detail support for different scenarios that can implement selection, triggering, and signaling of positioning training data to support an AI / ML framework for positioning. Disclosed herein is a process for training a machine learning positioning model in a wireless communication network. The above process can be implemented by a network node, and a method in a network node.

[0008] A network node in a wireless communication network is provided, the network node comprising a transmitter, the transmitter being arranged to: send a positioning training data set configuration to at least one data source of the wireless communication network, the positioning training data set configuration comprising: a request for a positioning training data set for training a machine learning positioning model, and a required data format of the positioning training data set based on the location of the network node. The network node also comprises a receiver, the receiver being arranged to: receive a response from at least one data source, the response comprising: a positioning training data set according to the required data format. The network node also comprises a processor, the processor being arranged to: train the machine learning positioning model using the positioning training data set.

[0009] A method in a network node is also provided, the network node being in a wireless communication network, the method comprising: sending a positioning training data set configuration to at least one data source of the wireless communication network, the positioning training data set configuration comprising: a request for a positioning training data set for training a machine learning positioning model, and a required data format of the positioning training data set based on the location of the network node. The method further comprises: receiving a response from at least one data source, the response comprising: a positioning training data set according to the required data format. The method further comprises: using the positioning training data set to train the machine learning positioning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to describe the manner in which the advantages and features of the present disclosure can be obtained, the present disclosure is described by reference to certain devices and methods shown in the accompanying drawings. Each of these drawings depicts only certain aspects of the present disclosure and should not be considered as limiting its scope. For the sake of clarity, the drawings may have been simplified and are not necessarily drawn to scale.

[0011] A method and apparatus for training a machine learning positioning model in a wireless communication network will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0012] Figure 1 An embodiment of a wireless communication system is illustrated;

[0013] Figure 2 An illustration of an embodiment of a user equipment device is provided;

[0014] Figure 3An illustration of an embodiment of a network node is provided;

[0015] Figure 4 An embodiment of a system demonstrating NR beam-based positioning in a wireless communication network is illustrated;

[0016] Figure 5 An embodiment of a multi-cell RTT positioning process for a wireless communication network is illustrated;

[0017] Figure 6 An embodiment of relative distance estimation using an existing single gNodeB RTT positioning framework is illustrated;

[0018] Figure 7 illustrates a RequestLocationInformation message body in an LPP message used by a location server to request positioning measurements;

[0019] Figure 8 illustrates a ProvideLocationInformation message body in an LPP message used by a target device to provide positioning measurements;

[0020] Fig. 9 An embodiment of an AI / ML functional block diagram for RAN intelligence is illustrated;

[0021] Fig.10 An embodiment of a method in a network node is illustrated, the network node being in a wireless communication network;

[0022] Fig.11 An embodiment of a system showing an entity / node capable of performing AI / ML training using positioning input data in a wireless communication network is illustrated;

[0023] Fig.12 An embodiment of LMF-based collection and training of positioning measurement data is illustrated;

[0024] Fig.13 An embodiment of a method and apparatus for NG-RAN based collection and training of positioning data is illustrated;

[0025] Fig.14 An embodiment of a method and apparatus for UE-based collection and training of positioning data is illustrated;

[0026] Fig.15 An embodiment of a method and apparatus for collecting requests and responses for locating a training data set is illustrated;

[0027] Fig.16 An embodiment of an AI / ML direct positioning training database structure is illustrated; and

[0028] Fig.17 An embodiment of an AI / ML-assisted positioning training database structure is illustrated. DETAILED DESCRIPTION

[0029] Direct artificial intelligence (AI)-based positioning and AI-assisted positioning methods can be utilized to improve the location accuracy performance of UEs within the positioning framework defined by 3GPP. Training AI / machine learning (ML) models with accurate and reliable positioning data is a key component of this process to achieve the desired AI / ML positioning output. The disclosure herein details methods for supporting the selection, triggering, and signaling of positioning training data from configured data sources for both offline and online training of positioning data. As an overview, these methods provide for the selection and configuration of data sources based on the network entity performing AI / ML training; LMF configuration for the collection of AI / ML training data for positioning purposes; generation of training data sets based on whether AI / ML direct (independent) positioning or AI / ML assisted positioning is configured; or any combination thereof.

[0030] For the purpose of this disclosure, a positioning-related reference signal may be referred to as a reference signal used for positioning procedures / purposes in order to estimate the position of a target UE, such as a PRS, or based on an existing reference signal (such as a CSI-RS or SRS); a target UE may be referred to as a device / entity to be localized / positioned. In various embodiments, the term "PRS" may refer to any signal, such as a reference signal, that may or may not be primarily used for positioning.

[0031] For the purpose of this disclosure, the target UE may be referred to as an interested UE, whose position (absolute or relative position) will be acquired by the network or by the UE itself.

[0032] For purposes of this disclosure, the terms AI and ML are used interchangeably to refer to intelligent software components or systems.

[0033] Those skilled in the art will appreciate that aspects of the present disclosure may be embodied as systems, devices, methods or program products. Therefore, the arrangements described herein may be implemented in full hardware form, full software form (including firmware, resident software, microcode, etc.), or in a combination of software and hardware.

[0034] For example, the disclosed methods and apparatus may be implemented as hardware circuits, including custom very large scale integrated (VLSI) circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed methods and apparatus may also be implemented in programmable hardware devices, such as field programmable gate arrays, programmable array logic, programmable logic devices, etc. As another example, the disclosed methods and apparatus may include one or more physical or logical blocks of executable code, which may be organized, for example, as objects, procedures, or functions.

[0035] In addition, the method and apparatus may take the form of a program product embodied in one or more computer-readable storage devices storing machine-readable code, computer-readable code, and / or program code, hereinafter referred to as code. The storage device may be tangible, non-transient, and / or non-transmitting. The storage device may not embody a signal. In some arrangements, the storage device uses only a signal for accessing the code.

[0036] Any combination of one or more computer readable media may be used. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing code. The storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical or semiconductor system, device or apparatus, or any suitable combination of the above.

[0037] More specific examples of storage devices (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the context of this document, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0038] In this specification, references to examples or similar language of a particular method or device indicate that the specific features, structures, or characteristics described in conjunction with the example are included in at least one implementation of the methods and devices described herein. Therefore, unless otherwise expressly provided, references to examples or similar language features of a particular method or device may, but need not, all refer to the same example, but to "one or more but not all examples". Unless otherwise expressly provided, the terms "comprise", "include", "have" and their variations mean "including but not limited to". Unless otherwise expressly provided, the enumerated list of items does not mean that any or all items are mutually exclusive. Unless otherwise expressly provided, the terms "a", "an" and "the" also mean "one or more".

[0039] As used herein, a list with the conjunction "and / or" includes any single item in the list or a combination of items in the list. For example, a list of A, B, and / or C includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C, or a combination of A, B, and C. As used herein, a list using the term "one or more of ..." includes any single item in the list or a combination of items in the list. For example, one or more of A, B, and C includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C, or a combination of A, B, and C. As used herein, a list using the term "one of ..." includes one and only one of any single item in the list. For example, "one of A, B, and C" includes only A, only B, or only C, and does not include a combination of A, B, and C. As used herein, "a member selected from A, B, and C" includes one and only one of A, B, or C, and does not include a combination of A, B, and C. As used herein, "a member selected from A, B and C and combinations thereof" includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C, or a combination of A, B and C.

[0040] In addition, the features, structures or characteristics described herein may be combined in any suitable manner. In the following description, many specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a comprehensive understanding of the present disclosure. However, those skilled in the relevant art will recognize that the disclosed methods and apparatus may be practiced without one or more of the specific details, or may be practiced using other methods, components, materials, etc. In other cases, well-known structures, materials or operations are not shown or described in detail to avoid confusing aspects of the present disclosure.

[0041] The following is a description of various aspects of the disclosed method and apparatus with reference to schematic flow charts and / or schematic block diagrams of methods, apparatuses, systems, and program products. It will be understood that each frame of the schematic flow chart and / or schematic block diagram, and the combination of frames in the schematic flow chart and / or schematic block diagram can be implemented by code. The code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, so that instructions executed by a processor of a computer or other programmable data processing device can create a component for implementing the function / action specified in the schematic flow chart and / or schematic block diagram.

[0042] The code may also be stored in a storage device that can instruct a computer, other programmable data processing apparatus, or other device to work in a specific manner so that the instructions stored in the storage device produce an article of manufacture that includes instructions for implementing the functions / actions specified in the schematic flowchart and / or schematic block diagram.

[0043] The code may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are executed on the computer, other programmable apparatus, or other device, thereby producing a computer-implemented process, so that the code executed on the computer or other programmable apparatus provides a process for implementing the functions / actions specified in the schematic flowchart and / or schematic block diagram.

[0044] The schematic flow charts and / or schematic block diagrams in the figure illustrate the architecture, functions and operations of possible implementations of the device, system, method and program product. In this regard, each box in the schematic flow chart and / or schematic block diagram can represent a code module, segment or portion, which includes one or more executable instructions for implementing the code of (multiple) specified logical functions.

[0045] It should also be noted that in some alternative implementations, the functions shown in the blocks may not appear in the order shown in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order, depending on the functions involved. Other steps and methods may be envisioned that are equivalent in function, logic or effect to one or more blocks or portions thereof of the illustrated figures.

[0046] The description of an element in each figure may refer to the elements of the subsequent figures. The same reference numerals represent the same elements in all figures.

[0047] Figure 1 An embodiment of a wireless communication system 100 for training a machine learning positioning model in a wireless communication network is depicted. In one embodiment, the wireless communication system 100 includes a remote unit 102 and a network unit 104. Figure 1A specific number of remote units 102 and network units 104 are depicted in FIG. 1 , but one skilled in the art will recognize that any number of remote units 102 and network units 104 may be included in the wireless communication system 100.

[0048] In one embodiment, the remote unit 102 may include a computing device such as a desktop computer, a laptop computer, a personal digital assistant (PDA), a tablet computer, a smart phone, a smart TV (e.g., a TV connected to the Internet), a set-top box, a game console, a security system (including a security camera), a car computer, a network device (e.g., a router, a switch, a modem), an aircraft, a drone, etc. In some embodiments, the remote unit 102 includes a wearable device such as a smart watch, a fitness band, an optical head-mounted display, etc. In addition, the remote unit 102 may be referred to as a subscriber unit, a mobile station, a mobile station, a user, a terminal, a mobile terminal, a fixed terminal, a subscriber station, a UE, a user terminal, a device, or other terms used in the art. The remote unit 102 may communicate directly with one or more of the network units 104 via UL communication signals. In some embodiments, the remote unit 102 may communicate directly with other remote units 102 via sidelink communication.

[0049] The network elements 104 may be distributed over a geographical area. In some embodiments, the network elements 104 may also be referred to as access points, access terminals, base stations, base stations, node Bs, eNBs, gNBs, home node Bs, relay nodes, devices, core networks, air servers, radio access nodes, APs, NRs, network entities, access and mobility management functions (AMFs), unified data management functions (UDMs), unified databases (UDRs), UDM / UDRs, policy control functions (PCFs), location management functions (LMFs), radio access networks (RANs), network slice selection functions (NSSFs), operations, maintenance, and management (OAMs), session management functions (SMFs), user plane functions (UPFs), application functions, authentication server functions (AUSFs), security anchor functions (SEAFs), trusted non-3GPP gateway functions (TNGFs), application functions, service enablement architecture layer (SEAL) functions, vertical application enablement servers, edge enablement servers, border configuration servers, mobile edge computing platform functions, mobile edge computing applications, application data analysis enablement servers, SEAL data delivery servers, middleware entities, network slice capability management servers, or any other terminology used in the art. The network elements 104 are typically part of a radio access network that includes one or more controllers communicatively coupled to one or more corresponding network elements 104. The radio access network is typically communicatively coupled to one or more core networks, which may be coupled to other networks, such as the Internet and a public switched telephone network, etc. These and other elements of the radio access network and core network are not shown, but are generally known to those of ordinary skill in the art.

[0050] In one implementation, the wireless communication system 100 complies with the New Radio (NR) protocol standardized in 3GPP, wherein the network unit 104 transmits on the downlink (DL) using an orthogonal frequency division multiple access (OFDM) modulation scheme, and the remote unit 102 transmits on the uplink (UL) using a single carrier frequency division multiple access (SC-FDMA) scheme or an OFDM scheme. More generally, however, the wireless communication system 100 may implement some other open or proprietary communication protocol, such as WiMAX, IEEE 802.11 variants, GSM, GPRS, UMTS, LTE variants, CDMA2000, ZigBee, Sigfoxx, etc. The present disclosure is not intended to be limited to any particular wireless communication system architecture or protocol implementation.

[0051] The network unit 104 can serve a number of remote units 102 within a service area (eg, a cell or cell sector) via wireless communication links. The network unit 104 sends DL communication signals to serve the remote units 102 in the time, frequency, and / or spatial domains.

[0052] Figure 2 A user equipment device 200 is depicted that can be used to implement the methods described herein. The user equipment device 200 is used to implement one or more of the solutions described herein. The user equipment device 200 conforms to one or more of the user equipment devices described in the embodiments herein. Specifically, the user equipment device 200 can be Figure 1 Equipment 102, Figure 4 Equipment 540, Figure 6 Equipment 630, Fig.11 Device 1150 or 1160, Fig.14 The device 1410, 1420, 1430 of the present invention and therefore, the reference numeral 200 is used hereinafter to indicate a user equipment device according to 102, 540, 630, 1150, 1160, 1410, 1420 and 1430. The user equipment device 200 includes a processor 205, a memory 210, an input device 215, an output device 220, and a transceiver 225.

[0053] The input device 215 and the output device 220 may be combined into a single device, such as a touch screen. In some implementations, the user equipment apparatus 200 does not include any input device 215 and / or output device 220. The user equipment apparatus 200 may include one or more of a processor 205, a memory 210, and a transceiver 225, and may not include an input device 215 and / or an output device 220.

[0054] As depicted, the transceiver 225 includes at least one transmitter 230 and at least one receiver 235. The transceiver 225 can communicate with one or more cells (or wireless coverage areas) supported by one or more base units. The transceiver 225 can be operable on an unlicensed spectrum. In addition, the transceiver 225 can include multiple UE panels supporting one or more beams. In addition, the transceiver 225 can support at least one network interface 240 and / or application interface 245. (Multiple) application interface 245 can support one or more APIs. (Multiple) network interface 240 can support 3GPP reference points such as Uu, N1, PC5, etc. As understood by those of ordinary skill in the art, other network interfaces 240 can be supported.

[0055] The processor 205 may include any known controller capable of executing computer-readable instructions and / or capable of performing logical operations. For example, the processor 205 may be a microcontroller, a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processing unit, a field programmable gate array (FPGA), or a similar programmable controller. The processor 205 may execute instructions stored in the memory 210 to perform the methods and routines described herein. The processor 205 is communicatively coupled to the memory 210, the input device 215, the output device 220, and the transceiver 225.

[0056] Processor 205 may control user equipment device 200 to implement the user equipment device behaviors described herein. Processor 205 may include an application processor (also referred to as a main processor) that manages application domain and operating system (OS) functions, and a baseband processor (also referred to as a baseband radio processor) that manages radio functions.

[0057] The memory 210 may be a computer-readable storage medium. The memory 210 may include a volatile computer storage medium. For example, the memory 210 may include a RAM, including a dynamic RAM (DRAM), a synchronous dynamic RAM (SDRAM), and / or a static RAM (SRAM). The memory 210 may include a non-volatile computer storage medium. For example, the memory 210 may include a hard drive, a flash memory, or any other suitable non-volatile computer storage device. The memory 210 may include both volatile and non-volatile computer storage media.

[0058] The memory 210 may store data related to implementing the traffic class field as described herein. The memory 210 may also store program code and related data, such as an operating system or other controller algorithms operating on the device 200.

[0059] Input device 215 may include any known computer input device, including a touchpad, buttons, keyboard, stylus, microphone, etc. Input device 215 may be integrated with output device 220, for example, as a touch screen or similar touch-sensitive display. Input device 215 may include a touch screen so that text can be entered using a virtual keyboard displayed on the touch screen, and / or entered by handwriting on the touch screen. Input device 215 may include two or more different devices, such as a keyboard and a touchpad.

[0060] The output device 220 may be designed to output visual, auditory, and / or tactile signals. The output device 220 may include an electronically controllable display or display device capable of outputting visual data to a user. For example, the output device 220 may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, an organic LED (OLED) display, a projector, or a similar display device capable of outputting images, text, etc. to a user. As another non-limiting example, the output device 220 may include a wearable display that is separate from the rest of the user device apparatus 200 but communicatively coupled, such as a smart watch, smart glasses, a head-up display, etc. In addition, the output device 220 may be a component of a smart phone, a personal digital assistant, a television, a desktop computer, a notebook (laptop) computer, a personal computer, a vehicle dashboard, etc.

[0061] Output device 220 may include one or more speakers for producing sound. For example, output device 220 may produce an audible alarm or notification (e.g., a beep or buzzer). Output device 220 may include one or more tactile devices for producing vibration, motion, or other tactile feedback. All or part of output device 220 may be integrated with input device 215. For example, input device 215 and output device 220 may form a touch screen or similar touch-sensitive display. Output device 220 may be located near input device 215.

[0062] The transceiver 225 communicates with one or more network functions of the mobile communication network via one or more access networks. The transceiver 225 operates under the control of the processor 205 to send messages, data and other signals, and also receives messages, data and other signals. For example, the processor 205 can selectively activate the transceiver 225 (or part thereof) at a specific time to send and receive messages.

[0063] The transceiver 225 includes at least one transmitter 230 and at least one receiver 235. One or more transmitters 230 can be used to provide uplink communication signals to a base unit of a wireless communication network. Similarly, one or more receivers 235 can be used to receive downlink communication signals from the base unit. Although only one transmitter 230 and one receiver 235 are shown, the user equipment device 200 can have any suitable number of transmitters 230 and receivers 235. In addition, (multiple) transmitters 230 and (multiple) receivers 235 can be any suitable type of transmitter and receiver. The transceiver 225 may include a first transmitter / receiver pair for communicating with a mobile communication network through a licensed radio spectrum, and a second transmitter / receiver pair for communicating with a mobile communication network through an unlicensed radio spectrum.

[0064] A first transmitter / receiver pair that can be used to communicate with a mobile communication network through a licensed radio spectrum, and a second transmitter / receiver pair that can be used to communicate with a mobile communication network through an unlicensed radio spectrum can be combined into a single transceiver unit, such as a single chip that performs functions for use with both licensed and unlicensed radio spectrums. The first transmitter / receiver pair and the second transmitter / receiver pair can share one or more hardware components. For example, some transceivers 225, transmitters 230, and receivers 235 can be implemented as physically independent components that access shared hardware resources and / or software resources, such as network interface 240.

[0065] One or more transmitters 230 and / or one or more receivers 235 may be implemented and / or integrated into a single hardware component, such as a multi-transceiver chip, a system on chip, an application specific integrated circuit (ASIC), or other types of hardware components. One or more transmitters 230 and / or one or more receivers 235 may be implemented and / or integrated into a multi-chip module. Other components such as a network interface 240 or other hardware components / circuits may be integrated into a single chip with any number of transmitters 230 and / or receivers 235. Transmitters 230 and receivers 235 may be logically arranged as transceivers 225 using one or more common control signals, or may be arranged as modular transmitters 230 and receivers 235 implemented in the same hardware chip or multi-chip module.

[0066] The memory 210 of the user equipment device 200 can host or store a machine learning positioning model for training using a positioning training data set. The machine learning positioning model can be stored before and / or after training. The positioning training data set can also be stored in the memory 210, which has been received by the receiver 235, or received from a local data source at the user equipment device 200, or received through measurements made by the user equipment device 200. In some embodiments, the processor 205 is arranged to train the machine learning positioning model.

[0067] Figure 3 300 that can be used to implement the methods described herein. The network node 300 can be an implementation of an entity in a wireless communication network (e.g., one or more of the wireless communication networks described herein), for example, Figure 1 104 of them; Figure 4 420, 430 or 440; Figure 6 610 or 620; Fig.11 1135, 1141, 1150, 1160, 1144; Fig.12 of 1210; Fig.131320; Fig.14 1410, 1420, 1430. The network node 300 may be, for example, the UE 200 described above, or a network function (NF) or an application function (AF) or another entity of one or more wireless communication networks of the embodiments described herein. The network node 300 includes a processor 305, a memory 310, an input device 315, an output device 320, and a transceiver 325.

[0068] The input device 315 and the output device 320 may be combined into a single device, such as a touch screen. In some implementations, the network node 300 does not include any input device 315 and / or output device 320. The network node 300 may include one or more of a processor 305, a memory 310, and a transceiver 325, and may not include an input device 315 and / or an output device 320.

[0069] As depicted, the transceiver 325 includes at least one transmitter 330 and at least one receiver 335. Here, the transceiver 325 communicates with one or more remote units 300. In addition, the transceiver 325 can support at least one network interface 340 and / or an application interface 345. The (multiple) application interface 345 can support one or more APIs. The (multiple) network interface 340 can support 3GPP reference points such as Uu, N1, N2, and N3. As understood by those of ordinary skill in the art, other network interfaces 340 can be supported.

[0070] The processor 305 may include any known controller capable of executing computer-readable instructions and / or capable of performing logical operations. For example, the processor 305 may be a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, or a similar programmable controller. The processor 305 may execute instructions stored in the memory 310 to perform the methods and routines described herein. The processor 305 is communicatively coupled to the memory 310, the input device 315, the output device 320, and the transceiver 325.

[0071] The memory 310 may be a computer readable storage medium. The memory 310 may include a volatile computer storage medium. For example, the memory 310 may include a RAM, including a dynamic RAM (DRAM), a synchronous dynamic RAM (SDRAM), and / or a static RAM (SRAM). The memory 310 may include a non-volatile computer storage medium. For example, the memory 310 may include a hard drive, a flash memory, or any other suitable non-volatile computer storage device. The memory 310 may include both volatile and non-volatile computer storage media.

[0072] The memory 310 may store data related to establishing a multipath unicast link and / or mobile operation. For example, as described herein, the memory 310 may store parameters, configurations, resource allocations, policies, etc. The memory 310 may also store program code and related data, such as an operating system or other controller algorithms operating on the network node 300.

[0073] Input device 315 may include any known computer input device, including a touchpad, buttons, keyboard, stylus, microphone, etc. Input device 315 may be integrated with output device 320, for example, as a touch screen or similar touch-sensitive display. Input device 315 may include a touch screen so that text can be entered using a virtual keyboard displayed on the touch screen and / or by handwriting on the touch screen. Input device 315 may include two or more different devices, such as a keyboard and a touchpad.

[0074] Output device 320 can be designed to output visual, auditory and / or tactile signals. Output device 320 may include an electronically controllable display or display device capable of outputting visual data to a user. For example, output device 320 may include, but is not limited to, an LCD display, an LED display, an OLED display, a projector, or a similar display device capable of outputting images, text, etc. to a user. As another non-limiting example, output device 320 may include a wearable display that is separate from the rest of network node 300 but communicatively coupled, such as a smart watch, smart glasses, a head-up display, etc. In addition, output device 320 may be a component of a smart phone, a personal digital assistant, a television, a desktop computer, a notebook (laptop) computer, a personal computer, a vehicle dashboard, etc.

[0075] Output device 320 may include one or more speakers for producing sound. For example, output device 320 may produce an audible alarm or notification (e.g., a beep or buzzer). Output device 320 may include one or more tactile devices for producing vibration, motion, or other tactile feedback. All or part of output device 320 may be integrated with input device 315. For example, input device 315 and output device 320 may form a touch screen, or a similar touch-sensitive display. Output device 320 may be located near input device 315.

[0076] The transceiver 325 includes at least one transmitter 330 and at least one receiver 335. One or more transmitters 330 can be used to communicate with the UE, as described herein. Similarly, one or more receivers 335 can be used to communicate with network functions in the PLMN and / or RAN, as described herein. Although only one transmitter 330 and one receiver 335 are shown, the network node 300 can have any suitable number of transmitters 330 and receivers 335. In addition, the (multiple) transmitters 330 and (multiple) receivers 335 can be any suitable type of transmitter and receiver.

[0077] The memory 310 of the network node 300 may host or store a machine learning positioning model for training using a positioning training data set. The machine learning positioning model may be stored before and / or after training. The positioning training data set may also be stored in the memory 310, which has been received by the receiver 335, or received from a local data source at the network node 300, or received by measurements performed by the network node 300. In some embodiments, the processor 305 is arranged to train the machine learning positioning model.

[0078] Positioning requirements for 3GPP's New Radio (NR) air interface (Uu) signals and standalone (SA) architectures (e.g., beam-based transmissions) are specified in 3GPP Release 16. Target use cases also include commercial and regulatory (emergency services) scenarios as provided in 3GPP Release 15. The performance requirements for specification #38.855 are provided in Table 1 and include 80% of indoor UEs having a horizontal positioning error of less than 3m; and 80% of outdoor UEs having a horizontal positioning error of less than 10m. For vertical positioning, the performance requirements include 80% of UEs having a vertical positioning error of less than 3m; and 80% of outdoor UEs having a vertical positioning error of less than 3m.

[0079] Positioning error indoor outdoor Horizontal positioning 80% of UEs are less than 3m 80% of UEs are less than 10m Vertical positioning 80% of UEs are less than 3m 80% of UEs are less than 3m

[0080] Table 1

[0081] In addition, current 3GPP Release 17 positioning has recently defined positioning performance requirements for commercial and Industrial Internet of Things (IIoT) use cases. These performance requirements for specification #38.857 are provided in Table 2, and for commercial use cases, include 90% of UEs having a positioning error less than 1m when positioning horizontally; 90% of UEs having a positioning error less than 3m when positioning vertically; the physical layer delay of the UE's position estimate is less than 10ms; and the end-to-end delay of the UE's position estimate is less than 100ms. For IIoT use cases, the performance requirements include 90% of UEs having a positioning error less than 0.2m when positioning horizontally; 90% of UEs having a positioning error less than 1m when positioning vertically; the physical layer delay of the UE's position estimate is less than 10ms; and the end-to-end delay of the UE's position estimate is less than 100ms (although orders of magnitude of 10ms are required).

[0082]

[0083] Table 2

[0084] The individual positioning techniques of specification #38.305 in 3GPP Release 16 are indicated in Table 3. These positioning techniques can currently be configured and executed based on the requirements of the Location Management Function (LMF) and UE capabilities.

[0085]

[0086]

[0087] Table 3

[0088] The transmission of a Positioning Reference Signal (PRS) enables the UE to perform UE positioning related measurements to enable the calculation of a position estimate of the UE and is configured for each Transmit Reception Point (TRP), where a TRP may transmit one or more beams. Figure 4An illustration of one embodiment of a system 400 is provided that demonstrates NR beam-based positioning available since 3GPP Release 16. The system 400 includes a location server or LMF 410, a first gNodeB TRP 420, a second gNodeB TRP 430, a third gNodeB TRP 440, and a UE 450. The PRS may be transmitted by different base stations 420, 430, 440 (serving base station and neighboring base stations) using beams on frequency ranges / bands FR1 and FR2, which is relatively different compared to LTE, where the PRS is transmitted over the entire cell. The PRS may be locally associated with a PRS resource ID and a resource set ID of a base station (TRP). Similarly, unlike the case in LTE, UE positioning measurements (such as reference signal time difference (RSTD) and PRS reference signal received power (RSRP) measurements) are performed on a per-beam basis (e.g., based on a downlink (DL) PRS resource or a DL PRS resource set). In addition, the network may also utilize other UL positioning methods to calculate the position of the target UE. Tables 4 and 5 show the reference signal to measurement mapping required for each supported radio access technology (RAT) related positioning technique at the UE and gNode-B, respectively. RAT related positioning techniques involve 3GPP RAT and core network entities to perform the position estimation of the UE, which is different from RAT independent positioning techniques that rely on GNSS, IMU sensors, WLAN and Bluetooth technologies to perform the positioning of the target device (UE).

[0089]

[0090]

[0091] Table 4

[0092]

[0093] Table 5

[0094] The following paragraphs briefly describe the RAT-related positioning technologies supported since 3GPP Release 16 (Specification #38.305).

[0095] The DL-TDOA positioning method utilizes the DL RSTD (and optionally the DL PRS RSRP) of downlink signals received at the UE from multiple TPs. The UE uses the assistance data received from the positioning server to measure the DL RSTD (and optionally its DL PRS RSRP) of the received signal, and the resulting measurements are used together with other configuration information to position the UE relative to neighboring TPs.

[0096] The DL AoD positioning method utilizes the measured DL PRS RSRP of downlink signals received from multiple TPs at the UE. The UE uses assistance data received from a positioning server to measure the DL PRS RSRP of the received signals, and the resulting measurements are used together with other configuration information to position the UE relative to neighboring TPs.

[0097] The multi-cell RTT positioning process 500 Figure 5 3, and utilizes UE Rx-Tx measurements and DL PRS RSRP (measured by the UE) of downlink signals received from multiple TRPs, and measured gNB Rx-Tx measurements and UL SRS-RSRP of uplink signals sent from the UE measured at multiple TRPs. The UE measures the UE Rx-Tx measurements (and optionally the DL PRS RSRP of the received signals) using assistance data received from the positioning server, and the TRP measures the gNB Rx-Tx measurements (and optionally the UL SRS-RSRP of the received signals) using assistance data received from the positioning server. The measurements are used to determine the RTT at the positioning server, which is used to estimate the position of the UE. As shown in Table 3, multi-RTT is only supported for UE-assisted / NG-RAN-assisted positioning techniques. Figure 6 An illustration 600 of relative distance estimation using an existing single gNodeB RTT positioning framework is provided. A positioning server 610 (LMF), a gNodeB 620, and multiple target UEs 630 are shown. Relative distances 640 between UEs 630 can be calculated, and RTT can be calculated 650 to obtain absolute positions. In addition to relative UE-to-UE distance / orientation 670, signals 660 of UL-SRS 661, DL-SRS 662 are also illustrated.

[0098] In the enhanced cell ID (CID) positioning method, the UE's position is estimated based on knowledge of its serving ng-eNB, gNB, and cell, and is based on LTE signals. Information about the serving ng-eNB, gNB, and cell can be obtained through paging, registration, or other methods. NR enhanced cell ID (NR E CID) positioning refers to a technique that uses NR signals to improve the UE position estimate using additional UE measurements and / or NR radio resources and other measurements. Although NR E-CID positioning can utilize some of the same measurements as the measurement control system in the RRC protocol, it is generally not expected that the UE will perform additional measurements solely for positioning; that is, the positioning process does not provide measurement configuration or measurement control messages, and the UE reports its available measurements rather than requiring additional measurement actions to be taken.

[0099] The UL TDOA positioning method utilizes the UL TDOA (and optionally the UL SRS-RSRP) of an uplink signal sent from a UE at multiple RPs. The RP uses the assistance data received from the positioning server to measure the UL TDOA (and optionally its UL SRS-RSRP) of the received signal, and the resulting measurement results are used together with other configuration information to estimate the UE's position.

[0100] The UL AoA positioning method utilizes the measured azimuth and zenith angles of arrival of uplink signals sent from the UE at multiple RPs. The RP uses the assistance data received from the positioning server to measure the A-AoA and Z-AoA of the received signal, and the resulting measurement results are used together with other configuration information to estimate the position of the UE.

[0101] According to 3GPP Release 16, PRS can be transmitted by different base stations (serving base station and neighboring base stations) using narrow beams on frequency bands FR1 and FR2, which is relatively different from LTE (where PRS is transmitted over the entire cell). PRS can be locally associated with the PRS resource ID and resource set ID of the base station (TRP). Similarly, UE positioning measurements (such as reference signal time difference (RSTD) and PRS RSRP measurements) are performed between beams (e.g., between different pairs of DL PRS resources or DL ​​PRS resource sets), rather than between different cells as in the case of LTE. In addition, the network can also utilize other UL positioning methods to calculate the position of the target UE.

[0102] The different DL measurements required for the supported RAT-related positioning techniques, including DL PRS-RSRP, DL RSTD and UE Rx-Tx time difference, are shown in Table 6. The measurement configuration specified in 3GPP specification #38.215 includes: 4 pairs of DL RSTD measurements can be performed for each pair of cells, each measurement is performed between a different pair of DL PRS resources / resource sets with a single reference timing; 8 DL PRS RSRP measurements can be performed on different DL PRS resources from the same cell.

[0103]

[0104]

[0105]

[0106] Table 6

[0107] The following paragraphs briefly introduce the RAT-independent positioning technology (3GPP specification #38.305) that relies on GNSS, IMU sensors, WLAN and Bluetooth technologies to perform target device (UE) positioning.

[0108] The network-assisted GNSS method utilizes a UE equipped with a radio receiver capable of receiving GNSS signals. In the 3GPP specification, the term GNSS covers both global and regional / augmented navigation satellite systems. Examples of global navigation satellite systems include GPS, modernized GPS, Galileo, GLONASS, and BeiDou Navigation Satellite System (BDS). Regional navigation satellite systems include the Quasi-Zenith Satellite System (QZSS), while many augmentation systems are classified under the general term "Space-Based Augmentation System (SBAS)" and provide regional augmentation services. Different GNSS (e.g., GPS, Galileo, etc.) can be used alone or in combination to determine the position of the UE.

[0109] Air pressure sensor positioning uses an air pressure sensor to determine the vertical component of the UE's position. The UE measures the air pressure (optionally with assistance data) to calculate the vertical component of its position, or sends the measurement to a positioning server for position calculation. This method should be combined with other positioning methods to determine the 3D position of the UE.

[0110] The WLAN positioning method uses WLAN measurements (AP identifiers, and optionally other measurements) and a database to determine the location of the UE. The UE measures the signals received from the WLAN access points (optionally supplemented with assistance data) to send the measurements to the positioning server for position calculation. Using the measurement results and the reference database, the UE's position is calculated. Alternatively, the UE uses WLAN measurements provided by the positioning server, and optional WLAN AP assistance data, to determine its position.

[0111] The Bluetooth positioning method uses Bluetooth measurements (beacon identifiers, and optionally other measurements) to determine the location of the UE. The UE measures the signals received from the Bluetooth beacons. Using the measurement results and a reference database, the UE's location is calculated. The Bluetooth method can be combined with other positioning methods (e.g., WLAN) to improve the positioning accuracy of the UE.

[0112] The Terrestrial Beacon System (TBS) consists of a network of ground-based transmitters to broadcast signals for positioning purposes only. The current types of TBS positioning signals are MBS (Metropolitan Beacon System) signals and Positioning Reference Signals (PRS) (3GPP specification #36.211). The UE measures the received TBS signals (optionally supplemented with assistance data) to calculate its position, or sends the measurements to a positioning server for position calculation.

[0113] The motion sensor positioning method uses different sensors such as accelerometers, gyroscopes, magnetometers, etc. to calculate the displacement of the UE. The UE estimates the relative displacement based on a reference position and / or a reference time. The UE sends a report including the determined relative displacement, which can be used to determine the absolute position. This method should be used for hybrid positioning with other positioning methods.

[0114] Measurements and reporting are performed for the configured RAT-dependent / RAT-independent positioning methods. Overall measurement configuration and reporting are in Figure 7 and Figure 8 Specifically, Figure 7 An illustration 700 of a RequestLocationInformation message body in an LPP message used by a location server to request a positioning measurement or position estimate from a target device, such as UE 102, is provided. Figure 8 An illustration 800 of an embodiment of a ProvideLocationInformation message body in an LPP message used by a target device, such as UE 102, to provide positioning measurements or a location estimate to a location server is provided.

[0115] AI / ML provides opportunities for enhanced positioning accuracy within wireless communication networks. Some opportunities and use cases are briefly described below.

[0116] Direct AI / ML positioning, where the output of AI / ML model inference is the UE location (examples include fingerprinting based on channel observations as input to the AI / ML model; FFS is details of channel observations as input to the AI / ML model such as CIR, RSRP and / or other types of channel observations; (multiple) FFS applicable scenarios and (multiple) AI / ML model generalization aspects).

[0117] AI / ML-assisted positioning, where the output of AI / ML model reasoning is new measurements and / or enhancements of existing measurements (e.g., LOS / NLOS identification, timing and / or angle or measurement, measurement possibility; FFS is the input and output details of (multiple) corresponding AI / ML models; (multiple) FFS applicable scenarios and (multiple) AI / ML model generalization aspects.

[0118] In addition, 3GPP specifications may have an impact on various aspects of AI / ML methods for positioning accuracy enhancement, including but not limited to AI / ML model training (training data type / size; training data source determination, such as UE / PRU / TRP; auxiliary signaling and procedures for training data collection), AI / ML model indication / configuration (auxiliary signaling and procedures, such as for model configuration; model activation / deactivation; model recovery / termination; model selection), AI / ML model monitoring and updating (auxiliary, signaling and procedures, such as for model performance monitoring; model updating / tuning), AI / ML model reasoning input (reporting / feedback of model input for reasoning, such as UE feedback as input for network-side pattern reasoning; model input acquisition and preprocessing; type / definition of model input), AI / ML model reasoning output (reporting / feedback of pattern reasoning output; post-processing of model reasoning output), UE capabilities of (multiple) AI / ML models (e.g., for model training, model reasoning, and model monitoring). However, not all of these aspects apply to all AI / ML methods in a specific use case.

[0119] The opportunities and use cases discussed in this article for improving positioning in wireless communication networks require an evolution of certain aspects of the positioning framework. In the current positioning framework and those described in this article, there is no known method for selecting, triggering, and configuring the collection of positioning data required for training of the configured AI / ML positioning model. This includes both online and offline training of positioning data for a specific AI / ML model. In addition, the type of data source is key to the statistical significance of the input training data set, which affects the accuracy of the AI / ML model to be trained. This application proposes a solution to this problem.

[0120] Fig. 9 An embodiment of an AI / ML functional block diagram 900 in a functional framework for RAN intelligence is illustrated. This introduces common terminology related to the functional framework for RAN intelligence. The functional block diagram 900 includes data collection 910, model training 920, model reasoning 930, and actuator 940.

[0121] Data collection 910 is a function that provides input data to the model training 920 and model reasoning 930 functions. AI / ML algorithm specific data preparation (e.g., data preprocessing and cleaning, formatting and transformation) is not performed in the data collection 910 function. Examples of input data may include measurements from UEs or different network entities, feedback 941 from actuators 940, and outputs from AI / ML models. Training data 911 is data required as input to the AI / ML model training 920 function. Reasoning data 912 is data required as input to the AI / ML model reasoning 930 function.

[0122] Model training 920 is a function that performs ML model training, validation, and testing, which can generate model performance metrics as part of the model testing process. If necessary, the model training 920 function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data 911 delivered by the data collection 910 function. Model deployment / update 921 is used to initially deploy the trained, validated, and tested AI / ML model to the model reasoning 930 function, or to deliver an updated model to the model reasoning 930 function.

[0123] Model reasoning 930 is a function that provides AI / ML model reasoning output 931 (e.g., prediction or decision). It has not yet been determined whether it provides model performance feedback 932 to the model training 920 function. If necessary, the model reasoning 930 function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the reasoning data 912 delivered by the data collection 910 function. The details of the reasoning output 931 are use case specific. If certain information derived from the model reasoning 930 function is suitable for improving the AI / ML model trained in the model training 920 function, it remains to be determined whether model performance feedback 932 is applied. Feedback 941 from an actuator 940 or other network entity (via the data collection 910 function) may be required at the model reasoning 930 function to create model performance feedback 932.

[0124] Actuator 940 is a function that receives output 931 from model reasoning 930 function and triggers or executes corresponding actions. Actuator 940 can trigger actions for other entities or itself. Feedback 941 is information that may be needed to derive training or reasoning data or performance feedback.

[0125] The network nodes and methods described herein provide selection and configuration of data sources depending on the training type of positioning data and which network entity is performing the training of the AI / ML positioning model.

[0126] A network node in a wireless communication network is described herein, the network node comprising: a transmitter, the transmitter being arranged to: send a positioning training data set configuration to at least one data source of the wireless communication network, the positioning training data set configuration comprising: a request for a positioning training data set for training a machine learning positioning model, and a required data format of the positioning training data set based on the location of the network node. The network node also comprises a receiver, the receiver being arranged to: receive a response from at least one data source, the response comprising: a positioning training data set according to a required data format. The network node also comprises a processor, the processor being arranged to: train a machine learning positioning model using the positioning training data set.

[0127] In some embodiments, at least one data source includes a data source selected from a group of data sources, the group of data sources including: a serving or adjacent gNode B; a serving or adjacent transmitting and receiving point; a positioning reference unit user device; a positioning reference unit transmitting and receiving point; a reference user device; a target user device; an auxiliary user device; a third party user device; a network data analysis function; and a location management function.

[0128] In some embodiments, the network node is selected from a group of network nodes, the group of network nodes including: a location server node; a next generation radio access network node; a positioning reference unit gNode B; a positioning reference unit transmission reception point; a positioning reference unit user equipment; a reference user equipment; an auxiliary user equipment; a third party user equipment; and a target user equipment. The next generation radio access network node may include: a serving or neighboring gNode-B, or a serving or neighboring transmission reception point. The serving or neighboring gNode-B may be applicable to terrestrial and / or non-terrestrial networks.

[0129] In some embodiments, the positioning training data set configuration includes: instantaneous, periodic, event-based, or a combination thereof reporting configuration.

[0130] In some embodiments, the machine learning positioning model includes: a machine learning direct positioning model (e.g., where input positioning training data is provided to the machine learning model to output a final position estimate of the target UE), or a machine learning assisted positioning model (e.g., where input positioning training data is provided to the machine learning model to output an enhanced positioning-related measurement or metric for ultimately calculating a position estimate of the target UE). Some machine learning positioning models can be used for both types of training (direct and assisted). However, the trained data used to develop the machine learning positioning model can vary depending on whether the model is direct or assisted.

[0131] In some embodiments, the required data format is structured according to the type of machine learning positioning model.

[0132] In some embodiments, the required data format includes: a fingerprint number, a positioning measurement, configurable location information of the location where the positioning measurement is performed, time information of the positioning measurement, quality of the positioning measurement, or any combination thereof. The configurable location information may include at least one of the following: 2D or 3D coordinates; a region identifier; a grid identifier; a velocity or speed; an orientation; a heading; an altitude; a rectangular grid having a length and a width. The coordinates may include geodesic coordinates or spherical coordinates. The length and width may be configured according to the location accuracy granularity.

[0133] In some embodiments, the receiver is further arranged to: receive an activation request, the activation request being used to activate: sending of a positioning training data set configuration, receiving of a positioning training data set, and / or training of a machine learning positioning model.

[0134] In some embodiments, the receiver is further arranged to: receive a deactivation request, the deactivation request being used to deactivate: sending of a positioning training data set configuration, receiving of a positioning training data set, and / or training of a machine learning positioning model.

[0135] In some embodiments, the transmitter is further arranged to: send an output of the trained machine learning positioning model to the first network node.

[0136] In some embodiments, the processor is further arranged to: train the machine learning positioning model using a positioning training data set received from a local data source.

[0137] In some embodiments, the training dataset configuration also includes an indication of whether the positioning training dataset is intended for online and / or offline training of the machine learning positioning model.

[0138] Fig.10 An illustration of an embodiment of a method 1000 in a network node in a wireless communication network is provided. In a first step 1010, a positioning training data set configuration is sent to at least one data source of the wireless communication network, the positioning training data set configuration comprising: a request for a positioning training data set for training a machine learning positioning model, and a required data format of the positioning training data set based on the location of the network node. In a second step 1020, a response is received from the at least one data source, the response comprising: a positioning training data set according to the required data format. In a third step 1030, the machine learning positioning model is trained using the positioning training data set.

[0139] In some embodiments, at least one data source includes a data source selected from a group of data sources, the group of data sources including: a serving or adjacent gNode B; a serving or adjacent transmitting and receiving point; a positioning reference unit user device; a positioning reference unit transmitting and receiving point; a reference user device; a target user device; an auxiliary user device; a third party user device; a network data analysis function; and a location management function.

[0140] In some embodiments, the network node is selected from a group of network nodes, the group of network nodes including: a location server node; a next generation radio access network node; a positioning reference unit gNode B; a positioning reference unit transmission reception point; a positioning reference unit user equipment; an auxiliary user equipment; a third party user equipment; a reference user equipment; and a target user equipment. The next generation radio access network node may include: a serving or neighboring gNode-B, or a serving or neighboring transmission reception point.

[0141] In some embodiments, the positioning training data set configuration includes: instantaneous, periodic, event-based, or a combination thereof reporting configuration.

[0142] In some embodiments, the machine learning positioning model is a machine learning direct positioning model, or a machine learning assisted positioning model.

[0143] In some embodiments, the required data format is structured according to the type of machine learning positioning model.

[0144] In some embodiments, the required data format includes: a signature number, a positioning measurement, configurable location information of a location where the positioning measurement was performed, time information of the positioning measurement, quality of the positioning measurement, or any combination thereof.

[0145] In some embodiments, the configurable location information includes at least one of: a 2D or 3D coordinate; an area identifier; a grid identifier; a speed or velocity; an orientation; a heading; an altitude; a rectangular grid having a length and a width.

[0146] Some embodiments also include: receiving an activation request, wherein the activation request is used to activate: sending of a positioning training data set configuration, receiving of a positioning training data set, and / or training of a machine learning positioning model.

[0147] Some embodiments also include: receiving a deactivation request, the deactivation request being used to deactivate: sending of a positioning training data set configuration, receiving of a positioning training data set, and / or training of a machine learning positioning model.

[0148] Some embodiments further comprise the step of sending the output of the trained machine learning positioning model to the first network node.

[0149] Some embodiments further include the step of training the machine learning positioning model using a positioning training data set received from a local data source. The local data source may be a data source at the network node, such as stored location measurement information, or the local data source may include acquisition of location information and / or measurements by the network node (e.g., if the network node is a UE or gNodeB).

[0150] In some embodiments, the training dataset configuration also includes an indication of whether the positioning training dataset is intended for online and / or offline training of the machine learning positioning model.

[0151] Fig.11 An embodiment of a system 1100 showing entities / nodes within a positioning network establishment capable of performing AI / ML training using positioning input data in a wireless communication network is illustrated. These entities / nodes can also act as configured data sources for providing positioning training data sets to other entities / nodes. The system 1100 includes an LCS client 1110 and an application function 1120, a 5G core network 1130, a radio access network (NG-RAN) 1140, a target UE 11500 and an LCS client 1151, and a PRU-UE 1160. The 5G core network 1130 includes a GMLC / LRF 1131, a UDM 1132, a NEF 1133, an AMF 1134, and a LMF 1135. The radio access network 1140 includes a first neighboring gNodeB 1141, a second neighboring gNodeB 1142, a serving gNodeB 1143, and a PRU 1144 as a TRP. The LMF 1135 of the 5G core network 1130 can perform LMF training using the positioning data set. The gNodeBs 1141, 1142, and 1143 can perform training using the positioning data set. The target UE 1150 can perform training using the positioning data set. The PRU UE 1160 can perform training using the positioning data set. The PRU TRP 1144 can perform training using the positioning data set.

[0152] An embodiment will now be described in more detail in which the LMF 1135 performs training of a machine learning positioning model using a positioning training data set. The LMF 1135 is supported to request a training data set from one or more configured data sources. In another implementation, the LMF 1135 may request a portion of the training data set from data source A and another portion of the training data set from data source B. The configured data sources may be one or more of the following entities, including: a serving and / or neighboring gNode-B / TRP, such as 1141, 1142, 1143, 1144; a positioning reference unit as a UE and / or TRP, such as 1160 and 1144; a reference UE; or a NWDAF.

[0153] Serving and / or neighboring gNB / TRPs (such as 1141, 1142, 1143, 1144) can act as data sources and provide training data sets in the form of UL-based positioning measurements, including UL-RTOA, gNB Rx-Tx time difference measurements, UL-AoA (including LCS to GCS transition information), SRS-RSRP and SRS-RSRPP (RSRP per path). The training data set should include ground truth measurements, including at least the location information associated with each measurement, and its measurement quality may vary depending on the training type. For example, online positioning training data may require different location granularity and update intervals compared to positioning data trained in an offline manner.

[0154] In another implementation option, PRU TRPs (such as 1144) may also act as a data source and be evenly distributed in different indoor / outdoor scenes so as to capture ground truth measurements of each area of ​​the indoor / outdoor scene based on the fixed location of the deployed PRU TRPs (such as 1144). For example, an example of such a scenario may include an IIoT indoor factory scenario where TRPs are deployed in a distributed manner throughout the entire area of ​​the factory floor.

[0155] The PRU 1160 as a UE can also act as a data source to collect ground truth measurements, including DL-based measurements such as RSTD, UE Rx-Tx time difference measurement, PRS RSRP, PRS RSRPP (RSRP per path), and the UE is based on different configuration location granularity. It can be applied to both offline training and online training of AI / ML models. Similarly, the reference UE can also collect information related to the training data set in terms of pre-classifying measurements as LOS and / or NLOS. This can also be applied to both offline training and online training of AI / ML models.

[0156] Normal positioning UEs (also referred to as target UEs) can also be configured to provide positioning training data in a best-effort manner to update the measured offline training database. This is suitable for situations where the AI / ML model may need to be updated based on real-time environmental changes in measurements that were not captured during the offline training phase.

[0157] The type of location information associated with each positioning measurement in the training data set may include one or more of the following: 2D (x, y) or 3D (x, y, z) coordinates of the UE, including geodesic or spherical or latitude / longitude coordinates; area ID / grid ID; UE rate / speed; orientation; heading; altitude; antenna array position information.

[0158] In an extended implementation, location information may be provided to a configured data source based on, for example, RAT-independent positioning measurements / methods such as GNSS, Bluetooth, WiFi, Inertial Measurement Unit (IMU), e.g., accelerometer, gyroscope.

[0159] Fig.12 An embodiment 1200 of LMF-based collection and training of positioning measurement data is illustrated, including a systematic signaling process for training based on a location server 1210 (LMF). The configured data source can be one or more of the following entities, including a serving and / or neighboring gNB / TRP 1220, a positioning reference unit 1230 as a TRP, a positioning reference unit 1240 as a UE, a reference UE 1250, a target UE 1260. In some implementations, separate measurement configurations for AI / ML positioning purposes can be configured for the above data sources, which can be different from the measurement configurations for non-AI / ML positioning methods. These can include the type of positioning method, different PRS configurations including different comb patterns, number of symbols, repetitions, QCL assumptions, muting configurations, periods, or combinations thereof.

[0160] The steps in embodiment 1200 of LMF-based collection and training of positioning measurement data will now be described.

[0161] In a first step 1201, a request for training data (ground truth data collection) is sent. In this step 1201, the location server node 1210 (e.g., LMF) requests a training data set from the NG-RAN nodes 1220 and 1230, including whether the requested training data (measurement data) is used for offline and / or online training, and an indication of the location of each measurement. The request may include a request for RAT-independent and UL-based positioning measurements. The request may be signaled using the NRPPa interface. In a further step 1202, the location server node 1210 (e.g., LMF) requests a training data set from a UE node (PRU UE 1240, reference UE 1250 and / or target UE 1260), including whether the requested training data (measurement data) is used for offline and / or online training, and an indication of the location of each measurement. The request may include RAT-independent and DL-based positioning measurements. The request may be signaled using LPP.

[0162] In a further step 1203, the UE node 1240, 1250, 1260 performs measurements over a certain period of time which provide statistical significance for each position, or is ready to provide stored measurements with the requested timestamp and the position of each stored position.

[0163] In a further step 1204, the gNB nodes 1220 and 1230 perform measurements over a period of time that provide statistical significance for each location, or are prepared to provide stored measurements with a requested timestamp and the location of each stored location.

[0164] In a further step 1205, the UE node 1240, 1250, 1260 responds with a set of structured training data comprising measurements and the location of each measurement. The response may be signaled using LPP.

[0165] In a further step 1206, the gNB nodes 1220 and 1230 respond with a set of structured training data including measurements and a timestamp / location of each measurement. The response may be signaled using NRPPa.

[0166] In a further step 1207 , the LMF 1210 performs training using the data collected from the data source.

[0167] In an alternative extended implementation, the type of learning and AI / ML models used for positioning can also be signaled along with the data collection configuration. These can include: the type of learning model, such as unsupervised or supervised learning, clustering, classification, dimensionality reduction, regression. These can also include the type of AI / ML model, such as deep neural network, support vector machine (SVM), k-nearest neighbor (KNN) classifier, etc.

[0168] According to some embodiments, the NG-RAN node and / or the PRU as TRP is supported to request training datasets from one or more configured data sources. Training at the NG-RAN node and / or the PRU as TRP provides an opportunity to train the AI / ML model at the gNB side using both RAT-independent positioning measurements and UL-based positioning measurement data, which may save training dataset signaling overhead depending on the scenario. Fig.13 An embodiment 1300 of NG-RAN node based training and signaling is illustrated.

[0169] The configured data source may be one or more of the following entities, including a positioning reference unit 1330 as a UE, a reference UE 1340, a target UE 1350. In another implementation, the NG-RAN node 1320 may request a positioning data set from the LMF 1310 alone, including measurements / data received from other cells as additional information.

[0170] The steps in embodiment 1300 of NG-RAN node based training are as follows.

[0171] In a first step 1301, the LMF 1310 may activate the collection and training of positioning AI / ML models at the desired NG-RAN node / PRU TRP 1320. This may include requesting the output of the trained model. This step 1301 may be signaled using NRPPa.

[0172] In a further step 1302, the NG-RAN node 1320 may request collection of positioning training data from a configured data source, such as a UE 1330, 1340, 1350, which may include RAT-independent positioning measurements / position estimates and an SRS configuration for the UE to transmit SRS, for measurement collection and training at the NG-RAN node 1320. The request may use RRC.

[0173] In a further step 1303, a response to the NG-RAN 1320 request is provided by the UE (such as 1330, 1340, 1350), including reporting RAT-independent positioning measurements / position estimates, such as GNSS reported using MDT, RAT-independent location information reported using RRCCommonLocationInfo messages, and transmission of SRS for positioning. In another implementation, in addition to sending the location information of the SRS, timing information (e.g., in the form of a timestamp) and data points including location information may also be reported.

[0174] In a further step 1304, the NG-RAN node 1320 performs and collects measurements.

[0175] In a further step 1305 , the NG-RAN node 1320 performs training of the collected measurements.

[0176] In a further step 1306, the NG-RAN node 1320 may transmit the output of the trained model depending on the type of AI / ML positioning task, for example for direct AI / ML positioning or AI / ML assisted positioning. The output may be a position estimate or an enhanced measurement result. The output may use NRPPa.

[0177] In a further step 1307, the LMF 1310 may deactivate the collection and training of AI / ML models for positioning. This deactivation may use NRPPa.

[0178] In some embodiments, the PRU-UE and target UE nodes are supported to request positioning training data from one or more configured data sources. Training at the PRU UE as a node provides an opportunity to perform extensive ground truth collection, including measurements and related positions. On the other hand, performing training for UE-based positioning methods supported by the target UE can help update the ground truth positioning database at certain locations where the UE reports measurements. Fig.14 An illustration of an embodiment 1400 of a systematic signaling process for UE-based collection and training of positioning data and UE-based training for positioning is provided. The configured data source may be one or more of the following entities, including a target UE 1410, a PRU UE 1420, other UEs 1440 including a reference UE 1430, and a location server (LMF) 1450.

[0179] The steps shown in embodiment 1400 are as follows.

[0180] In the first step 1401, UE 1410, 1420, 1430 can perform configured SL (PC5) / DL PRS measurements at specific time periods and locations and / or use past stored SL (PC5) / DL PRS measurements (based on historical measurements, the time period of past historical measurements can also be further configured in the training phase).

[0181] In a further step 1402, the UEs 1410, 1420, 1430 may use the PC5 interface to request positioning training data (including SL or DL ​​positioning measurements or a combination thereof) from other UEs / PRUs UE 1440. The positioning training data set may be based on online / offline training RAT-independent and DL-based positioning measurements.

[0182] In a further step 1403, the UE 1410, 1420, 1430 may request positioning training data from the LMF 1450 using the LPP interface. The positioning training data may include DL and / or SL measurements (if available). The request for the positioning training data set may be based on online / offline training.

[0183] In a further step 1404, the UE 1410, 1420, 1430 receives responses with the requested measurement / positioning data from other surrounding / nearby UEs 1440. In different responses, the UE 1410, 1420, 1430 may receive an indication that the requested training data set will not be available or will be available in a future time period / time instance. The response may use the PC5 interface.

[0184] In a further step 1405, the UE 1410, 1420, 1430 receives a response with the requested measurement / positioning data from the LMF 1450. In a different response, the UE 1410, 1420, 1430 may receive an indication that the requested training data set will not be available or will be available in a future time period / time instance. The response may use the LPP interface.

[0185] In a further step 1406 , the UE 1410 , 1420 , 1430 performs training based on data collected from the configured data sources.

[0186] In other implementations, the positioning data to be collected may include DL-based or SL-based measurements, or a combination thereof.

[0187] In some embodiments, a service request trigger for performing positioning data collection is used. Since the LMF / NG-RAN nodes / UEs are consumers of measurement data for AI / ML training, a separate AI / ML positioning data collection service request should be managed by the LMF. Since training can be performed in different nodes, a common framework for data collection should be established, where the LMF can act as a centralized coordination entity. Fig.13 , in case of NG-RAN node 1320 training, the LMF 1310 may activate 1301 and deactivate 1307 the collection of positioning data at the NG-RAN node 1320, and the training of the AI / ML model. In a similar manner, for all embodiments described herein, the LMF may initiate the configuration of a data source for the purpose of training data collection. The data source may be identified via a separate capability that confirms the UE's ability to collect positioning data / measurements for AI / ML model training. Fig.15 An exemplary description 1500 of such requests and responses collected for positioning a training data set is illustrated.

[0188] In a first step 1501, a location server (LMF) 1510 requests a positioning training data set collection capability from at least one data source, which may include a PRU UE 1520, a reference UE 1530, and a normal UE 1540. The request may use an LPP interface.

[0189] In another step 1502, the UE 1520, 1530, 1540 provides a response with positioning training data set collection capability to the LMF 1510. The response may use the LPP interface.

[0190] In an extended implementation, the capability request 1501 and response 1502 are distinguished as the ability to collect training data for online training and / or offline training, support for direct AI / ML methods (e.g., signature recognition), AI / ML-assisted methods (AI / ML-assisted DL-TDOA, AoD, RTT), and the ability to provide known locations and related location determination sources. In another implementation, for AI / ML and non-AI / ML positioning methods, these capabilities can be requested and responded to for each positioning method. Non-AI / ML methods refer to positioning methods that do not require AI / ML support.

[0191] The data collection report configuration can be designed based on the following types of reports (which can also be requested by LMF 1510). Immediate (instantaneous) positioning data collection report: based on an immediate request from LMF 1510 with a configured response time, or LMF 1510 can configure UE 1520, 1530, 1540 to store all measurements and ground truth for a specific time period (e.g., 24 hours), and then UE 1520, 1530, 1540 can report all data to LMF 1510 upon request. Periodic data collection report: based on reporting interval and reporting amount parameters, or the period of measurement / log and reporting period can be the same or different. Event-based data collection report: based on event change scenarios, for example, UE 1540 moves to a new positioning area with a different area ID, or when the PRU UE 1520 moves another 10cm or 1cm from the last position that has been reported to LMF 1510.

[0192] The structure of an embodiment of a positioning training dataset will now be described, which can facilitate different AI / ML-based positioning schemes, including direct AI / ML positioning, such as using signature recognition and / or AI / ML-assisted positioning, such as intermediate positioning measurement optimization. In addition, the input training dataset structure varies depending on the AI / ML model type and task (classification, prediction (regression algorithm)). The structure of the training dataset may affect the size of the training dataset (e.g., payload) and the type of signaling configured to transmit such information, such as user plane or control plane signaling. For the purposes of this solution, the user plane (new LCS user plane protocol) or control plane signaling (e.g., LPP) can be configured to transmit the training dataset configuration.

[0193] The training data set may be constructed as an N-dimensional database including multiple features. In the case of direct AI / ML positioning and / or AI / ML assisted positioning, the signature database may be used to directly determine the location of the UE.

[0194] For example, in the case of AI / ML direct targeting, the training database (dataset structure / configuration / required data format) can be as follows: Fig.16 The AI / ML direction positioning training database structure 1600 is an N-dimensional database / configuration, where N is the number of column features / labels associated with a feature code, including multiple feature codes 1610, and for each feature code 1610, location information 1620 (with configurable granularity); positioning measurement 1630; timestamp 1640; quality 1650 are provided.

[0195] Positioning measurements 1630 may include at least one of the following items (depending on whether the UE or NG-RAN node performs the measurement): DL RSTD (DL-based measurement); DL PRS RSRP (DL-based measurement); DL PRS RSRPP (DL-based measurement); UE Rx-Tx time difference (DL-based measurement); SS-RSRP (RSRP for RRM); SS-RSRQ (for RRM); CSI-RSRP (for RRM); CSI-RSRQ (for RRM); SS-RSRPB (for RRM) (DL-based measurement); UL RTOA (UL-based measurement); UL SRS-RSRP (UL-based measurement); UL SRS-RSRPP (UL-based measurement); UL RTOA (UL-based measurement); gNB Rx-Tx time difference UL RTOA (UL-based measurement); UL-AoA and UL-ZoA UL RTOA (UL-based measurement).

[0196] In the case of UL-based measurements, the UE location of the SRS transmission may also be provided. The timestamp 1640 may be implemented using a defined time base in milliseconds, seconds, minutes, hours, etc. In addition, in other implementations, absolute time units may also be used, such as UTC time, etc.

[0197] The database 1600 may be signaled using control plane or user plane signaling. In the case of control plane signaling, an exemplary signaling mechanism may include LPP signaling, while in the case of user plane signaling, new protocols such as LCUP (LCS User Plane) may be used.

[0198] As another example, in the case of AI / ML assisted positioning training database structure, such as Fig.17 The dataset structure / configuration / required data format 1700 includes a plurality of feature codes 1710, and for each feature code: location information 1720 (with configurable granularity); channel impulse response peak power (CIR) 1730; path number 1740; time (window) range 1750. The features of the channel impulse response 1730 are extracted based on generating ground truth measurements.

[0199] The location 1720 may be a specific point in a 2D or 3D space, and in another implementation, the location 1720 may include a 2D or 3D rectangular grid of length L, width W, and height H, where L, W, and H may be configured according to the location accuracy granularity.

[0200] It is desirable to study a 3GPP framework for AI / ML over the air interface that corresponds to each target use case, including CSI feedback, beam management, and positioning accuracy enhancement with respect to aspects such as performance, complexity, and potential regulatory impact. In the current positioning framework, there is no known way to select, trigger, and configure the collection of positioning data required for the training of the configured AI / ML positioning model. This includes both online and offline training of positioning data for a specific AI / ML model based on the network entity performing the training. In addition, the type of data source and the collection method are key components for the statistical significance of the input training dataset, which affects the accuracy of the AI / ML model.

[0201] Training of AI / ML positioning models can be supported in various scenarios where different network entities can request (multiple) positioning datasets and then subsequently train the AI / ML models. A process is described where the network entity or node performing the training can configure and request positioning datasets based on a set of defined criteria (i.e., based on AI / ML direct and AI / ML assisted positioning methods). A method is also presented where the LMF can know that the node / entity is capable of performing positioning data collection while also configuring the manner in which such data is reported. The next aspect of the invention describes a general structure of positioning training datasets that will be trained and signaled on different interfaces, which distinguishes based on AI / ML direct and AI / ML assisted positioning methods.

[0202] In DOI:10.1109 / OJVT.2021.3110134, some architectural enhancements related to data collection for AI / ML assisted positioning methods are discussed, but this relies on the existing MDT data collection process. The MDT data collection process is designed with different network operation and maintenance objectives and may not be well suited or optimized for the types of AI / ML tasks required for UE positioning. In SMM920210198-US-PSPF, a measurement and reporting framework for 3GPP positioning is discussed, but the configuration of the data source is not addressed based on the training location and the content of the training dataset. Currently, TR 37.817 describes the deployment of training and inference models in the context of 3GPP for use cases such as mobility optimization and load balancing, without considering any positioning specific use cases for AI / ML model training and data collection.

[0203] As described herein, in one embodiment, a method for selecting and configuring a data source based on a network entity performing AI / ML training is described. These include AI / ML positioning training performed at a location server (LMF), an NG-RAN node, a PRU as a UE, or a normally positioned UE, and an indication of whether the training is online or offline, which affects the configuration and reporting of positioning data set collection. In another embodiment, methods are detailed for configuring the collection of AI / ML training data for positioning purposes using different reporting methods for the LMF, which can be configured based on the data collection scenario. In a final embodiment, a method for generating a training data set based on whether AI / ML direct (standalone) positioning or AI / ML assisted positioning is proposed, which will affect the structure of the training data set to be signaled.

[0204] Various aspects described herein relate to a method in a wireless communication network, wherein: a network entity performing training of a desired AI / ML positioning model configures at least one data source to provide a positioning training data set; based on the location of the network entity performing AI / ML model training for positioning, the positioning training data set configuration may include at least a request for a data source and format of the training data set; the data source responds to the above-mentioned data set configuration by providing the required training data set according to the desired data format; and the network entity performs training of the desired AI / ML model based on the collected training data set.

[0205] In some embodiments, the data source may include: a serving or neighboring gNB / TRP, a positioning reference unit UE or a positioning reference unit TRP, a reference UE, a target UE, other UEs, or a combination thereof.

[0206] In some embodiments, the training data set may be provided based on whether the training occurs at at least one of the following: a serving or neighboring gNB / TRP, a positioning reference unit UE or a positioning reference unit TRP, a reference UE, a target UE, or other UEs.

[0207] In some embodiments, the AI / ML positioning model can perform AI / ML direct positioning or AI / ML assisted positioning.

[0208] In some embodiments, the positioning training data set configuration includes a reporting configuration, which can be instantaneous, periodic, event-based, or a combination thereof.

[0209] In some embodiments, the training data set structure or database may be formatted according to the type of AI / ML positioning model, including AI / ML direct positioning, AI / ML assisted positioning, or a combination thereof.

[0210] In some embodiments, the network entity may be a positioning reference unit UE, a reference UE, a target UE, a reference UI, a NG-RAN node, a positioning reference unit gNB, a location server, etc.

[0211] In some embodiments, the NG-RAN node may include a serving gNB or TRP, a neighboring gNB or TRP.

[0212] In some embodiments, the data format may include a signature number, a configurable location where a positioning measurement is performed, the positioning measurement, time information regarding the occurrence of the measurement, the quality of the positioning measurement performed, or a combination thereof.

[0213] In some embodiments, the training data set configuration may include an indication of whether the data collection is intended for online and / or offline training of a machine learning positioning model.

[0214] It should be noted that the above methods and apparatus illustrate rather than limit the present invention, and that those skilled in the art will be able to design many alternative arrangements without departing from the scope of the appended claims. The word "comprising" does not exclude the presence of other elements or steps than those listed in the claims, "a" or "an" does not exclude a plurality, and a single processor or other unit may perform the functions of several units described in the claims. Any reference signs in the claims should not be construed as limiting their scope.

[0215] Furthermore, although examples have been given in the context of specific communication standards, these examples are not intended to limit the communication standards to which the disclosed methods and apparatus may be applied. For example, although specific examples have been given in the context of 3GPP, the principles disclosed herein may also be applied to another wireless communication system, and indeed to any communication system that uses routing rules.

[0216] The method may also be embodied in an instruction set stored on a computer-readable medium, which, when loaded into a computer processor, a digital signal processor (DSP), etc., causes the processor to perform the above method.

[0217] The described methods and apparatus may be practiced in other specific forms. The described methods and apparatus are considered in all respects to be illustrative only and not restrictive. Therefore, the scope of the present invention is indicated by the appended claims rather than by the foregoing description. All changes within the meaning and equivalent range of the claims should be included within their scope.

[0218] The following abbreviations used herein will be apparent to those skilled in the art:

[0219] ADR Accumulative Increment Range

[0220] GNSS Assisted GNSS

[0221] AI

[0222] AP Access Point

[0223] ARFCN Absolute Radio Frequency Channel Number

[0224] ARP Antenna Reference Point

[0225] BFD Beam Fault Detection

[0226] BSSID Basic Service Set Identifier

[0227] BTS Base Transceiver Station (GERAN)

[0228] BWP Bandwidth Part

[0229] CBR Channel Busy Rate

[0230] CG Configuration Authorization

[0231] CID Cell-ID (positioning method)

[0232] CRS Cell-specific reference signal

[0233] CSI Channel State Information

[0234] CSI-RS Channel State Information Reference Signal

[0235] DCI Downlink Control Information

[0236] DL Downlink

[0237] DL-AoD Downlink Angle of Departure

[0238] DL-TDOA Downlink Time Difference of Arrival

[0239] DM-RS Demodulation Reference Signal

[0240] DS-TWR Dual-sided two-way ranging

[0241] ECEF Earth Centered, Earth Fixed

[0242] ECGI Evolved Cell Global Identifier

[0243] E CID Enhanced Cell ID (positioning method)

[0244] E-SMLC Enhanced Service Mobile Location Center

[0245] E-UTRAN Evolved Universal Terrestrial Radio Access Network

[0246] EOP Earth Orientation Parameter

[0247] EPDU External Protocol Data Unit

[0248] FDMA Frequency Division Multiple Access

[0249] FEC Forward Error Correction

[0250] FTA Fine Time Assist

[0251] GAGAN GPS-Assisted Geographic Enhanced Navigation

[0252] GNSS Global Navigation Satellite System

[0253] GPS Global Positioning System

[0254] HA GNSS High-precision GNSS (RTK, PPP)

[0255] IMU Inertial Measurement Unit

[0256] IS Interface Specification

[0257] LMC Location Management Component

[0258] LMF Location Management Function LMU Location Measurement Unit LOS Line of Sight

[0259] LPP LTE Positioning Protocol LPPa LTE Positioning Protocol Annex LSB Least Significant Bit MAC Primary Secondary Concept Media Access Control MAC CE Media Access Control Element MBS Metropolitan Beacon System ML Machine Learning MO-LR Mobile Originated Location Request MSB Most Significant Bit MT-LR Mobile Terminated Location Request Multi-RTT Multiple Round Trip Time NAV Navigation

[0260] NB-IoT Narrowband Internet of ThingsNCGI NR Cell Global IdentifierNI-LR Network Induced Location RequestNLOS Non Line of SightNPRS Narrowband Positioning Reference SignalNR NR Radio AccessNRPPa NR Positioning Protocol AnnexNRSRP Narrowband Reference Signal Received PowerNRSRQ Narrowband Reference Signal Received QualityNWDAF Network Data Analysis FunctionOSR Observation Space RepresentationOTDOA Observed Time Difference of ArrivalPDU Protocol Data UnitPDCP Packet Data Convergence ProtocolPDCCH Physical Downlink Control ChannelPDSCH Physical Downlink Shared ChannelPHY Physical LayerPSCCH Physical Sidelink Control ChannelPSSCH Physical Sidelink Shared ChannelPSBCH Physical Sidelink Broadcast ChannelPPP Precise Point PositioningPRB Physical Resource BlockPRC Pseudorange Correction

[0261] PRS Positioning Reference Signal posSIB Positioning System Information Block P-RNTI Paging Radio Network Temporary Identifier PT-RS Phase Tracking Reference Signal PUCCH Physical Uplink Control Channel PUSCH Physical Uplink Shared Channel QCL Quasi-Concatenated

[0262] RAT Radio Access Technology RF Radio Frequency

[0263] RLC Radio Link ControlRRC Range Rate CorrectionRadio Resource ControlRRM Radio Resource ManagementRS Reference Signal

[0264] RSRP Reference signal received power RSRPP Reference signal received power per path RSRQ Reference signal received quality RSTD Reference signal time difference RSU Road side unit

[0265] RTK Real-time Kinematics

[0266] RTT Round Trip Time

[0267] SBAS Space-based Augmentation System SBCH Sidelink Broadcast Channel SCCH Sidelink Control Channel SCI Sidelink Control Information SET SUPL-supported Terminal SFN System Frame Number

[0268] SL Side Link

[0269] SL-PRS Sidelink Positioning Reference Signal SLP SUPL Positioning Platform SPS Semi-Persistent

[0270] SS / PBCH Synchronization Signal / Physical Broadcast Channel SSBRI SS / PBCH Block Resource Index SSID Service Set Identifier SSR State Space Representation SS-TWR Single-Side Two-Way Ranging STCH Side Link Transmission Channel SUPL Secure User Plane Location TB Terrestrial Beacon TBS Terrestrial Beacon System TCI Transmission Configuration Indicator TECU TEC Unit TLM Telemetry

[0271] TOA Time of Arrival TOF Time of Flight TP Transmission Point TRP Transmission Reception Point UE User Equipment UDRE User Differential Range Error ULP User Plane Positioning Protocol URA User Range Accuracy UTC Coordinated Universal Time WGS 84 World Geodetic System 1984 WLAN Wireless Local Area Network

Claims

1. A network node in a wireless communication network, comprising: A transmitter, the transmitter being arranged to: send a positioning training data set configuration to at least one data source of the wireless communication network, the positioning training data set configuration comprising: a request for a positioning training data set for training a machine learning positioning model, and a required data format of the positioning training data set based on the location of the network node; a receiver, the receiver being arranged to: receive a response from the at least one data source, the response comprising: the positioning training data set in accordance with the required data format; and A processor is arranged to: train the machine learning positioning model using the positioning training data set.

2. The network node of claim 1 , wherein at least one data source comprises a data source selected from a group of data sources, the group of data sources comprising: Serving or neighboring gNode B; Service or adjacent sending and receiving points; Positioning reference unit user equipment; Positioning reference unit sending and receiving points; Reference User Equipment; Target user device; auxiliary user equipment; Third-party user equipment; Web data analysis capabilities; and Location management functionality.

3. The network node according to any of the preceding claims, wherein the network node is selected from a group of network nodes, the group of network nodes comprising: Location server node; Next generation radio access network nodes; Positioning reference unit gNode B; Positioning reference unit sending and receiving points; Positioning reference unit user equipment; Reference User Equipment; auxiliary user equipment; Third-party user equipment; as well as Target user device.

4. The network node according to claim 3, wherein the next generation radio access network node comprises: Serving or neighboring gNode-B, or serving or neighboring transmitting and receiving point.

5. The network node according to any one of the preceding claims, wherein the positioning training data set configuration comprises: Report configurations that are instantaneous, periodic, event-based, or a combination thereof.

6. A network node according to any one of the preceding claims, wherein the machine learning positioning model comprises: Machine learning direct positioning model, or machine learning assisted positioning model.

7. A network node according to any one of the preceding claims, wherein the required data format is constructed according to the type of the machine learning positioning model.

8. A network node according to any one of the preceding claims, wherein the required data format comprises: A signature code number, a positioning measurement, configurable location information of a location where the positioning measurement is performed, time information of the positioning measurement, a quality of the positioning measurement, or any combination thereof.

9. The network node according to claim 8, wherein the configurable location information comprises at least one of the following: 2D or 3D coordinates; Region identifier; Grid identifier; rate or speed; orientation; course; high; A rectangular grid with length and width.

10. A network node according to any one of the preceding claims, wherein the receiver is further arranged to: receive an activation request, wherein the activation request is used to activate: the sending of the positioning training data set configuration, the receiving of the positioning training data set, and / or the training of the machine learning positioning model.

11. A network node according to any of the preceding claims, wherein the receiver is further arranged to: receive a deactivation request, the deactivation request being used to deactivate: the sending of the positioning training data set configuration, the receiving of the positioning training data set, and / or the training of the machine learning positioning model.

12. A network node according to any one of the preceding claims, wherein the transmitter is further arranged to: send an output of the trained machine learning positioning model to a first network node.

13. A network node according to any one of the preceding claims, wherein the processor is further arranged to: train the machine learning positioning model using a positioning training data set received from a local data source.

14. The network node according to any one of the preceding claims, wherein the training data set configuration further comprises: An indication of whether the positioning training dataset is intended for online and / or offline training of the machine learning positioning model.

15. A method in a network node, the network node being in a wireless communication network, the method comprising: Sending a positioning training data set configuration to at least one data source of the wireless communication network, the positioning training data set configuration comprising: a request for a positioning training data set for training a machine learning positioning model, and a required data format of the positioning training data set based on the location of the network node; Receive a response from the at least one data source, the response comprising: the positioning training data set in the required data format; and The positioning training data set is used to train the machine learning positioning model.

16. The method of claim 15, wherein the at least one data source comprises a data source selected from a group of data sources, the group of data sources comprising: Serving or neighboring gNode B; Service or adjacent sending and receiving points; Positioning reference unit user equipment; Positioning reference unit sending and receiving points; Reference User Equipment; Target user device; auxiliary user equipment; Third-party user equipment; Web data analysis capabilities; and Location management functionality.

17. The method according to any one of claims 15 to 16, wherein the network node is selected from a group of network nodes, the group of network nodes comprising: Location server node; Next generation radio access network nodes; Positioning reference unit gNode B; Positioning reference unit sending and receiving points; Positioning reference unit user equipment; Reference User Equipment; auxiliary user equipment; Third-party user equipment; as well as Target user device 18. The method of claim 17, wherein the next generation radio access network node comprises: Serving or neighboring gNode-B, or serving or neighboring transmitting and receiving point.

19. The method according to any one of claims 15 to 18, wherein the positioning training data set configuration comprises: Report configurations that are instantaneous, periodic, event-based, or a combination thereof.

20. The method according to any one of claims 15 to 19, wherein the machine learning positioning model is a machine learning direct positioning mode or a machine learning assisted positioning model.

21. A method according to any one of claims 15 to 20, wherein the required data format is constructed according to the type of the machine learning positioning model.

22. A method according to any one of claims 15 to 21, wherein the required data format includes a feature code number, a positioning measurement, configurable location information of the location where the positioning measurement is performed, time information of the positioning measurement, the quality of the positioning measurement, or any combination thereof.

23. The method of claim 22, wherein the configurable location information comprises at least one of the following: 2D or 3D coordinates; Region identifier; Grid identifier; rate or speed; orientation; course; high; A rectangular grid with length and width.

24. The method according to any one of claims 15 to 23, further comprising: An activation request is received, where the activation request is used to activate: the sending of the positioning training data set configuration, the receiving of the positioning training data set, and / or the training of the machine learning positioning model.

25. The method according to any one of claims 15 to 24, further comprising: A deactivation request is received, wherein the deactivation request is used to deactivate: the sending of the positioning training data set configuration, the receiving of the positioning training data set, and / or the training of the machine learning positioning model.

26. The method according to any one of claims 15 to 25, further comprising: The step of sending the trained output of the machine learning positioning model to a first network node.

27. The method according to any one of claims 15 to 26, further comprising: The step of training the machine learning positioning model using a positioning training dataset received from a local data source.

28. The method according to any one of claims 15 to 27, wherein the training data set configuration further comprises: An indication of whether the positioning training dataset is intended for online and / or offline training of the machine learning positioning model.

Images