Similarity learning for crowdsourcing positioning

Abstract

Aspects presented herein may enhance the accuracy and / or latency of UE positioning based on crowdsourcing in which a network entity may compute a location estimate for the UE based on neighbor cell scan data from the UE and one or more reference UEs. In one aspect, a network entity receives, from a UE, a first set of measurements associated with at least one cell. The network entity performs location estimation of the UE via an ML model based on at least one of a first set of measurements associated with the at least one cell, a second set of measurements for each of the set of reference UEs, or a location of each of the set of reference UEs, where the UE and the set of reference UEs include at least one common cell.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. non-provisional patent application serial number 17 / 932,174, filed on September 14, 2022, and entitled “SIMILARITY LEARNING FORCROWD-SOURCED POSITIONING,” which is expressly incorporated herein by reference in its entirety. Technical Field

[0003] Generally, the present disclosure relates to communication systems, and more particularly, the present disclosure relates to wireless communications involving crowdsourced positioning. Background Art

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunication services such as telephony, video, data, messaging, and broadcasts. Typical wireless communication systems may employ multiple access technologies that are capable of supporting communications with multiple users by sharing the available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0005] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at a city, country, region, and even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is a part of the continuous mobile broadband evolution released by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., together with the Internet of Things (IoT)) and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable low latency communication (URLLC). Some aspects of 5G NR may be based on 4G Long Term Evolution (LTE) standards. There is a need for further improvements in 5G NR technology. These improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0006] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects. This summary neither identifies the key or important elements of all aspects, nor depicts the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0007] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus receives a first measurement set associated with at least one cell from a user equipment (UE). The apparatus performs a position estimation of the UE via at least one machine learning (ML) model based on the first measurement set associated with at least one cell, a second measurement set for each reference UE in a reference UE set, or at least one of the positions of each reference UE in the reference UE set, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying at least one common cell between the UE and the reference UE set, and wherein the output of the at least one ML model includes a similarity score between the UE and the reference UE set.

[0008] To accomplish the above and related purposes, one or more aspects include the features fully described below and particularly indicated in the claims. The following description and the accompanying drawings set forth in detail certain illustrative features of one or more aspects. However, these features are only indicative of some of the various ways in which the principles of the various aspects can be employed. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a diagram illustrating an example of a wireless communication system and an access network.

[0010] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0011] Figure 2B is a diagram illustrating an example of downlink (DL) channels within a subframe according to various aspects of the present disclosure.

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

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

[0014] Figure 3 is a diagram showing an example of a base station and a user equipment (UE) in an access network.

[0015] Figure 4 is a diagram showing an example of UE positioning based on reference signal measurement.

[0016] Figure 5 is a diagram illustrating an example of determining a location of a target device based on crowdsourcing in accordance with various aspects of the present disclosure.

[0017] Figure 6 is a diagram illustrating an example architecture of a functional framework associated with a machine learning (ML) model according to various aspects of the present disclosure.

[0018] Figure 7 is a diagram illustrating an example ML model capable of receiving input from a target UE and a plurality of reference UEs and providing weights for the input from each of the plurality of reference UEs in accordance with various aspects of the present disclosure.

[0019] Figure 8 is a diagram illustrating an example of an ML model capable of receiving input from a target UE and a plurality of reference UEs and providing weights for the input from each of the plurality of reference UEs in accordance with various aspects of the present disclosure.

[0020] Fig. 9 is a flow chart of a method of wireless communication.

[0021] Fig.10 is a flow chart of a method of wireless communication.

[0022] Fig.11 are diagrams illustrating examples of hardware implementations for example apparatuses and / or network entities. DETAILED DESCRIPTION

[0023] The various aspects provided herein can enhance the accuracy and / or delay of UE positioning based on crowdsourcing. The various aspects provided herein provide a mechanism for a server (e.g., server 502) to calculate a location estimate of a target device (e.g., target device 506) based on neighbor cell scan data. In one aspect of the present disclosure, the location estimate of the target device based on the neighbor cell scan data (e.g., the mapping of the neighbor cell scan data to the location) can depend on one or more of the following: physics (e.g., reference signal received power (RSRP) inversely related to distance), cell characteristics (e.g., downtilt, transmit (Tx) power, antenna array structure, etc.), device type (e.g., IoT devices may have different antenna characteristics compared to smartphones) and / or the environment (e.g., environmental conditions) around the target device (e.g., terrain, obstacles, building materials, etc.). In another aspect of the present disclosure, an artificial intelligence (AI) or machine learning (ML) framework can be implemented at a server to estimate the location of a target device (such as an IoT user). Therefore, the location estimate of the target device can be a function of the location of one or more reference UEs and / or cells scanned by the target device. In other words, the location of the target device may be determined based on the learned "similarity" between the reference UE / cell and the target device.

[0024] The detailed description set forth below in conjunction with the accompanying drawings describes various configurations and does not represent the only configuration in which the concepts described herein may be implemented. For the purpose of providing a thorough understanding of each concept, the detailed description includes specific details. However, these concepts may be practiced without these specific details. In some cases, well-known structures and components are shown in block diagram form to avoid obscuring such concepts.

[0025] Several aspects of telecommunication systems will be presented with reference to various devices and methods. These devices and methods are described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0026] For example, an element, or any part of an element, or any combination of elements can be implemented as a "processing system" including one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on chip (SoCs), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform various functionalities described throughout the present disclosure. One or more processors in a processing system can execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other, software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, processes, functions, or any combination thereof.

[0027] Thus, in one or more example aspects, implementations, and / or use cases, the described functionality may be implemented in hardware, software, or any combination thereof. If implemented in software, the functionality may be stored or encoded as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media. Storage media may be any available media that can be accessed by a computer. By way of example, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of various types of computer-readable media, or any other medium that can be used to store computer executable code that can be accessed by a computer in the form of instructions or data structures.

[0028] Although aspects, implementations and / or use cases are described in this application by the description of some examples, additional or different aspects, implementations and / or use cases may occur in many different arrangements and scenarios. The aspects, implementations and / or use cases described herein can be implemented across many different platform types, devices, systems, shapes, sizes and packaging arrangements. For example, aspects, implementations and / or use cases may occur via integrated chip implementations and other devices based on non-module components (e.g., end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchase equipment, medical equipment, devices that enable artificial intelligence (AI), etc.). Although some examples may be specifically targeted at use cases or applications, or may not be specifically targeted at use cases or applications, various applicability of the described examples may occur. The scope of aspects, implementations and / or use cases can range from chip-level or modular components to non-modular, non-chip-level implementations, and further to the aggregation, distribution or original equipment manufacturer (OEM) equipment or system of one or more technologies incorporated herein. In some actual settings, the equipment incorporating the described aspects and features may also include additional components and features for implementing and practicing the claimed and described aspects. For example, the transmission and reception of wireless signals must include several components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / accumulators, etc.) The techniques described herein can be practiced in a variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc., of varying sizes, shapes, and structures.

[0029] The deployment of a communication system (e.g., a 5G NR system) can be arranged in a variety of ways using various components or components. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element, or a network device such as a base station (BS), or one or more units (or one or more components) that perform base station functionality can be implemented in an aggregated or decomposed architecture. For example, a BS (such as a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmit receive point (TRP), or a cell, etc.) can be implemented as an aggregated base station (also referred to as an independent BS or a monolithic BS) or a decomposed base station.

[0030] A converged base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. A decomposed base station may be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central or centralized units (CU), one or more distributed units (DU), or one or more radio units (RU). In some aspects, a CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. A DU may be implemented to communicate with one or more RUs. Each of a CU, a DU, and a RU may be implemented as a virtual unit (i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU)).

[0031] Base station operation or network design may take into account the aggregated nature of base station functionality. For example, a decomposed base station may be utilized in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (e.g., a network configuration sponsored by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also referred to as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as distributing functionality virtually for at least one unit, which may enable flexibility in network design. Various units of a decomposed base station or decomposed RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0032] Figure 1 100 is a diagram illustrating an example of a wireless communication system and an access network. The wireless communication system shown includes a decomposed base station architecture. The decomposed base station architecture may include one or more CUs 110, which may communicate directly with a core network 120 via a backhaul link, or indirectly communicate with the core network 120 through one or more decomposed base station units (e.g., a near real-time (near RT) RAN intelligent controller (RIC) 125 via an E2 link, or a non-real-time (non-RT) RIC 115 associated with a service management and orchestration (SMO) framework 105, or both). The CU 110 may communicate with one or more DUs 130 via corresponding mid-haul links (e.g., an F1 interface). The DU 130 may communicate with one or more RUs 140 via corresponding fronthaul links. The RU 140 may communicate with corresponding UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served by multiple RUs 140 at the same time.

[0033] Each of the units (i.e., CU 110, DU 130, RU 140) and near-RT RIC 125, non-RT RIC 115, and SMO framework 105 may include one or more interfaces, or be coupled to one or more interfaces, which are configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of the units or an associated processor or controller that provides instructions to the communication interface of the unit may be configured to communicate with one or more of the other units via a transmission medium. For example, the units may include a wired interface that is configured to receive a signal via a wired transmission medium or to send a signal to one or more of the other units. In addition, the units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (e.g., an RF transceiver) that is configured to receive a signal via a wireless transmission medium, or to send a signal to one or more of the other units, or both.

[0034] In some aspects, CU 110 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface configured to transmit signals with other control functions hosted by CU 110. CU 110 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some implementations, CU 110 may be logically divided into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). CU 110 may be implemented to communicate with DU 130 for network control and signaling when necessary.

[0035] DU 130 may correspond to a logical unit that includes one or more base station functions to control the operation of one or more RU 140. In some aspects, depending at least in part on the functional split (such as the functional split defined by 3GPP), DU 130 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (e.g., modules for forward error correction (FEC) encoding and decoding, scrambling, modulation, demodulation, etc.). In some aspects, DU 130 may further host one or more low PHY layers. Each layer (or module) may be implemented using an interface configured to transmit signals with other layers (and modules) hosted by DU 130 or with control functions hosted by CU 110.

[0036] The low-level functionality may be implemented by one or more RUs 140. In some deployments, a RU 140 controlled by a DU 130 may correspond to a logical node that hosts RF processing functions, or low PHY layer functions (e.g., performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), Digital Beamforming, Physical Random Access Channel (PRACH) extraction and filtering, etc.), or both, based at least in part on a functional split (such as a lower-level functional split). In such an architecture, the RU 140 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some implementations, real-time and non-real-time aspects of control and user plane communications with the RU 140 may be controlled by the corresponding DU 130. In some scenarios, this configuration may enable the DU 130 and the CU 110 to be implemented in a cloud-based RAN architecture (e.g., a vRAN architecture).

[0037] The SMO framework 105 may be configured to support RAN deployment and provisioning of non-virtualized and virtualized network elements. For non-virtualized network elements, the SMO framework 105 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 105 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 190) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 110, DU 130, RU 140, and near-RT RIC 125. In some implementations, the SMO framework 105 may communicate with hardware aspects of a 4G RAN such as an open eNB (O-eNB) 111 via an O1 interface. In addition, in some implementations, the SMO framework 105 may communicate directly with one or more RUs 140 via an O1 interface. The SMO framework 105 may also include a non-RT RIC 115 configured to support the functionality of the SMO framework 105 .

[0038] The non-RT RIC 115 may be configured to include logic functions that implement non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) / machine learning (ML) (AI / ML) workflows including model training and updating, or policy-based guidance of applications / functions in the near-RT RIC 125. The non-RT RIC 115 may be coupled to or communicate with the near-RT RIC 125 (e.g., via an A1 interface). The near-RT RIC 125 may be configured to include logic functions that implement near-real-time control and optimization of RAN elements and resources via data collection and actions on an interface (e.g., via an E2 interface) that connects one or more CUs 110, one or more DUs 130, or both, and the O-eNB with the near-RT RIC 125.

[0039] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 125, the non-RT RIC 115 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 125 and may be received from a non-network data source or from a network function at the SMO framework 105 or the non-RT RIC 115. In some examples, the non-RT RIC 115 or the near-RT RIC 125 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 115 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 105 (such as via reconfiguration of O1) or via the creation of RAN management policies (such as A1 policies).

[0040] At least one of the CU 110, the DU 130, and the RU 140 may be referred to as a base station 102. Thus, the base station 102 may include one or more of the CU 110, the DU 130, and the RU 140 (each component is indicated by a dotted line to indicate that each component may be included or may not be included in the base station 102). The base station 102 provides an access point to the core network 120 for the UE 104. The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). Small cells include femto cells, pico cells, and micro cells. A network including both small cells and macro cells may be referred to as a heterogeneous network. A heterogeneous network may also include a home evolved Node B (eNB) (HeNB), which may provide services to a restricted group referred to as a closed subscriber group (CSG). The communication link between RU 140 and UE 104 may include an uplink (UL) (also referred to as a reverse link) transmission from UE 104 to RU 140 and / or a downlink (DL) (also referred to as a forward link) transmission from RU 140 to UE 104. The communication link may use multiple-input and multiple-output (MIMO) antenna technology (including spatial multiplexing, beamforming and / or transmit diversity). The communication link may be through one or more carriers. Base station 102 / UE 104 may use a spectrum of up to Y MHz (e.g., 5, 10, 15, 20, 100, 400, etc. MHz) bandwidth per carrier allocated in up to a total of Yx MHz (x component carrier) carrier aggregation for transmission in each direction. These carriers may or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​than for UL). Component carriers may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell), and the secondary component carrier may be referred to as a secondary cell (SCell).

[0041] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL wireless wide area network (WWAN) spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH). The D2D communication may be through various wireless D2D communication systems, such as, for example, Bluetooth, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0042] The wireless communication system may further include a Wi-Fi AP 150 that communicates with a UE 104 (also referred to as a Wi-Fi station (STA)) via a communication link 154, such as in a 5 GHz unlicensed spectrum. When communicating in the unlicensed spectrum, the UE 104 / AP 150 may perform a clear channel assessment (CCA) prior to communication to determine whether a channel is available.

[0043] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified with the frequency range names FR1 (410 MHz–7.125 GHz) and FR2 (24.25 GHz–52.6 GHz). Although a portion of FR1 is greater than 6 GHz, FR1 is often (interchangeably) referred to as the “sub-6 GHz” band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and articles, although it is different from the extremely high frequency (EHF) band (30 GHz-300 GHz) identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0044] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as the frequency range name FR3 (7.125GHz-24.25GHz). The frequency bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, and therefore the features of FR1 and / or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to above 52.6GHz. For example, three higher operating bands have been identified as the frequency range names FR2-2 (52.6GHz–71GHz), FR4 (71GHz–114.25GHz), and FR5 (114.25GHz–300GHz). Each of these higher frequency bands falls within the EHF band.

[0045] In view of the above aspects, unless otherwise specifically stated, the term "sub-6 GHz" and the like (if used herein) may broadly refer to frequencies that may be lower than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specifically stated, the term "millimeter wave" and the like (if used herein) may broadly refer to frequencies that may include mid-band frequencies, may be within FR2, FR4, FR2-2 and / or FR5, or may be within the EHF band.

[0046] Each of the base station 102 and the UE 104 may include multiple antennas (such as antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming. The base station 102 may send a beamformed signal 182 to the UE 104 in one or more transmit directions. The UE 104 may receive a beamformed signal from the base station 102 in one or more receive directions. The UE 104 may also send a beamformed signal 184 to the base station 102 in one or more transmit directions. The base station 102 may receive a beamformed signal from the UE 104 in one or more receive directions. The base station 102 / UE 104 may perform beam training to determine the best receive and transmit directions for each of the base station 102 / UE 104. The transmit direction and receive direction for the base station 102 may be the same or may not be the same. The transmit direction and receive direction for the UE 104 may be the same or may not be the same.

[0047] The base station 102 may include and / or be referred to as a gNB, a Node B, an eNB, an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmit receive point (TRP), a network node, a network entity, a network device, or some other suitable term. The base station 102 may be implemented as an integrated access and backhaul (IAB) node, a relay node, a sidelink node, an aggregated (monolithic) base station with a baseband unit (BBU) (including a CU and a DU) and a RU, or as a decomposed base station including one or more of a CU, a DU, and / or a RU. A set of base stations that may include decomposed base stations and / or aggregated base stations may be referred to as a next generation (NG) RAN (NG-RAN).

[0048] The core network 120 may include an access and mobility management function (AMF) 161, a session management function (SMF) 162, a user plane function (UPF) 163, a unified data management (UDM) 164, one or more location servers 168, and other functional entities. AMF 161 is a control node that handles signaling between UE 104 and core network 120. AMF 161 supports registration management, connection management, mobility management, and other functions. SMF 162 supports session management and other functions. UPF 163 supports packet routing, packet forwarding, and other functions. UDM 164 supports the generation of authentication and key agreement (AKA) certificates, user identity processing, access authorization, and subscription management. One or more location servers 168 are shown as including a gateway mobile location center (GMLC) 165 and a location management function (LMF) 166. However, in general, one or more location servers 168 may include one or more location / positioning servers, which may include one or more of the following: GMLC 165, LMF 166, position determination entity (PDE), serving mobile location center (SMLC), mobile positioning center (MPC), etc. GMLC 165 and LMF 166 support UE location services. GMLC 165 provides an interface for accessing UE positioning information for clients / applications (e.g., emergency services). LMF 166 receives measurement and assistance information from NG-RAN and UE 104 via AMF 161 to calculate the location of UE 104. NG-RAN may utilize one or more positioning methods to determine the location of UE 104. Positioning UE 104 may involve signal measurements, position estimation, and optional speed calculation based on measurements. Signal measurements may be performed by UE 104 and / or serving base station 102. The measured signal may be based on one or more of: a satellite positioning system (SPS) 170 (e.g., one or more of a global navigation satellite system (GNSS), a global positioning system (GPS), a non-terrestrial network (NTN), or other satellite positioning / location systems), an LTE signal, a wireless local area network (WLAN) signal, a Bluetooth signal, a terrestrial beacon system (TBS), sensor-based information (e.g., a pressure sensor, a motion sensor), an NR enhanced cell ID (NR E-CID) method, an NR signal (e.g., multi-round trip time (multi-RTT), DL angle of departure (DL-AoD), DL time difference of arrival (DL-TDOA), UL time difference of arrival (UL-TDOA), and UL angle of arrival (UL-AoA) positioning) and / or other systems / signals / sensors.

[0049] Examples of UE 104 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radio units, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablet computers, smart devices, wearable devices, vehicles, electric meters, gas pumps, large or small kitchen appliances, healthcare equipment, implants, sensors / actuators, displays, or any other similar functional devices. Some of the UEs 104 may be referred to as IoT devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as stations, mobile stations, user stations, mobile units, user units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile user stations, access terminals, mobile terminals, wireless terminals, remote terminals, mobile phones, user agents, mobile clients, clients, or some other suitable terms. In some scenarios, the term UE may also be applied to one or more companion devices, such as in a device constellation arrangement. One or more of these devices may access the network together and / or individually.

[0050] Reference again Figure 1 In certain aspects, the base station 102 may be configured to: receive a first measurement set associated with at least one cell from a UE; and perform, via at least one ML model, a position estimation of the UE based on at least one of the first measurement set associated with the at least one cell, a second measurement set for each reference UE in a reference UE set, or a position of each reference UE in the reference UE set, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying at least one common cell between the UE and the reference UE set, and wherein an output of the at least one ML model includes a similarity score between the UE and the reference UE set (e.g., via the crowdsourcing positioning component 199).

[0051] Figure 2A FIG200 is a diagram showing an example of a first subframe within a 5G NR frame structure. Figure 2B FIG230 is a diagram showing an example of DL channels within a 5G NR subframe. Figure 2C FIG250 is a diagram showing an example of a second subframe within a 5G NR frame structure. Figure 2DFIG280 is a diagram showing an example of UL channels within a 5G NR subframe. The 5G NR frame structure can be frequency division duplex (FDD) (wherein, for a particular set of subcarriers (carrier system bandwidth), a subframe within a subcarrier set is dedicated to either DL or UL), or can be time division duplex (TDD) (wherein, for a particular set of subcarriers (carrier system bandwidth), a subframe within a subcarrier set is dedicated to both DL and UL). Figure 2A , Figure 2C In the example provided, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexibly usable between DL / UL, and subframe 3 is configured with slot format 1 (all of which are UL). Although subframes 3 and 4 are shown as having slot formats 1 and 28, respectively, any particular subframe can be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are full DL and full UL, respectively. Other slot formats 2-61 include a mixture of DL, UL and flexible symbols. The UE is configured with a slot format (dynamically configured by DL control information (DCI) or semi-statically / statically configured by radio resource control (RRC) signaling) through a received slot format indicator (SFI). Note that the following description also applies to a 5G NR frame structure that is TDD.

[0052] Figures 2A-2D The frame structure is shown, and various aspects of the present disclosure may be applicable to other wireless communication technologies, which may have different frame structures and / or different channels. A frame (10ms) may be divided into 10 subframes (1ms) of equal size. Each subframe may include one or more time slots. A subframe may also include a microslot, which may include 7, 4, or 2 symbols. Depending on whether the cyclic prefix (CP) is normal or extended, each time slot may include 14 or 12 symbols. For a normal CP, each time slot may include 14 symbols, and for an extended CP, each time slot may include 12 symbols. The symbol on the DL may be a CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbol (also referred to as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single stream transmission). The number of slots within a subframe may be based on the CP and numerology. The numerology defines the subcarrier spacing (SCS) (see Table 1). The symbol length / duration may be proportional to 1 / SCS.

[0053]

[0054] Table 1: Digital scheme, SCS and CP

[0055] For normal CP (14 symbols / slot), different digital schemes μ0 to 4 allow 1, 2, 4, 8 and 16 slots per subframe respectively. For extended CP, digital scheme 2 allows 4 slots per subframe. Therefore, for normal CP and digital scheme μ, there are 14 symbols / slot and 2 μ timeslots / subframe. The subcarrier spacing can be equal to 2 μ *15kHz, where μ is digital scheme 0 to 4. Thus, digital scheme μ=0 has a subcarrier spacing of 15kHz, and digital scheme μ=4 has a subcarrier spacing of 240kHz. The symbol length / duration is inversely proportional to the subcarrier spacing. Figure 2A-2D Examples are provided for a normal CP (with 14 symbols per slot) and a digital scheme μ=2 (with 4 slots per subframe). The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs. Within a frame set, there may be one or more different, frequency-division multiplexed bandwidth parts (BWPs) (see Figure 2B ). Each BWP can have a specific number scheme and CP (normal or extended).

[0056] A resource grid may be used to represent the frame structure. Each slot includes a resource block (RB) (also referred to as a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid may be divided into a plurality of resource elements (REs). The number of bits carried by each RE may depend on the modulation scheme.

[0057] like Figure 2A As shown, some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) for channel estimation at the UE (indicated as R for a particular configuration, but other DM-RS configurations are possible) and a channel state information reference signal (CSI-RS). The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0058] Figure 2BExamples of various DL channels within a subframe of a frame are shown. A physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE including six RE groups (REGs), each REG including 12 consecutive REs in one OFDM symbol of an RB. A PDCCH within a BWP may be referred to as a control resource set (CORESET). The UE is configured to monitor PDCCH candidates in a PDCCH search space (e.g., a common search space, a UE-specific search space) during a PDCCH monitoring opportunity on a CORESET, wherein the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at higher and / or lower frequencies on the channel bandwidth. A primary synchronization signal (PSS) may be within symbol 2 of a particular subframe of a frame. UE 104 uses the PSS to determine subframe / symbol timing and physical layer identification. A secondary synchronization signal (SSS) may be within symbol 4 of a particular subframe of a frame. The UE uses the SSS to determine the physical layer cell identity group number and the radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine the physical cell identifier (PCI). Based on the PCI, the UE can determine the location of the DM-RS. The physical broadcast channel (PBCH) carrying the master information block (MIB) can be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also called SS block (SSB)). The MIB provides the number of RBs in the system bandwidth and the system frame number (SFN). The physical downlink shared channel (PDSCH) carries user data, broadcast system information (such as system information blocks (SIBs)) that is not sent via the PBCH, and paging messages.

[0059] like Figure 2C As shown, some of the REs carry DM-RS for channel estimation at the base station (indicated as R for one specific configuration, but other DM-RS configurations are possible). The UE can send DM-RS for the physical uplink control channel (PUCCH) and DM-RS for the physical uplink shared channel (PUSCH). The PUSCH DM-RS can be sent in the first one or two symbols of the PUSCH. In different configurations, the PUCCH DM-RS can be sent depending on whether a short PUCCH or a long PUCCH is sent and according to the specific PUCCH format used. The UE can send a sounding reference signal (SRS). The SRS can be sent in the last symbol of the subframe. The SRS can have a comb structure, and the UE can send the SRS on one of these combs. The base station can use the SRS for channel quality estimation to achieve frequency-dependent scheduling on the UL.

[0060] Figure 2DAn example of various UL channels within a subframe of a frame is shown. The PUCCH may be positioned as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), precoding matrix indicators (PMI), rank indicators (RI), and hybrid automatic repeat request (HARQ) acknowledgement (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACKs and / or negative ACKs (NACKs)). The PUSCH carries data and may additionally be used to carry buffer status reports (BSRs), power headroom reports (PHRs), and / or UCI.

[0061] Figure 3 is a block diagram of a base station 310 communicating with a UE 350 in an access network. In the DL, Internet Protocol (IP) packets may be provided to a controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and switching support functions; RLC layer functionality associated with transmission of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0062] The transmit (TX) processor 316 and receive (RX) processor 370 implement layer 1 functionality associated with various signal processing functions. Layer 1, including the physical (PHY) layer, may include error detection on the transmission channel, forward error correction (FEC) decoding / decoding of the transmission channel, interleaving, rate matching, mapping to physical channels, modulation / demodulation of physical channels, and MIMO antenna processing. The TX processor 316 processes the mapping to the signal constellation based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), M-quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols can then be divided into parallel streams. Each stream can then be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., pilot) in the time domain and / or frequency domain, and then combined together using an inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially precoded to produce multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine coding and modulation schemes, as well as for spatial processing. Channel estimates may be derived from reference signals and / or channel condition feedback sent by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318Tx. Each transmitter 318Tx may modulate a radio frequency (RF) carrier with a corresponding spatial stream for transmission.

[0063] At the UE 350, each receiver 354Rx receives a signal through its corresponding antenna 352. Each receiver 354Rx recovers the information modulated onto the RF carrier and provides the information to a receive (RX) processor 356. The TX processor 368 and the RX processor 356 implement layer 1 functionality associated with various signal processing functions. The RX processor 356 can perform spatial processing on the information to recover any spatial stream destined for the UE 350. If multiple spatial streams are destined for the UE 350, they can be combined into a single OFDM symbol stream by the RX processor 356. The RX processor 356 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols and reference signals on each subcarrier are recovered and demodulated by determining the most likely signal constellation point sent by the base station 310. These soft decisions can be based on channel estimates calculated by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by the base station 310. The data and control signals are then provided to the controller / processor 359, which implements layer 3 and layer 2 functionality.

[0064] The controller / processor 359 may be associated with a memory 360 that stores program codes and data. The memory 360 may be referred to as a computer readable medium. In the UL, the controller / processor 359 provides demultiplexing, packet reassembly, decryption, header decompression, and control signal processing between transport channels and logical channels to recover IP packets. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0065] Similar to the functionality described in conjunction with DL transmissions performed by the base station 310, the controller / processor 359 provides: RRC layer functionality associated with: system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functionality associated with: header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with: transmission of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with: mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0066] Channel estimates derived by the channel estimator 358 based on a reference signal or feedback sent by the base station 310 may be used by the TX processor 368 to select the appropriate coding and modulation schemes, and to facilitate spatial processing. The spatial streams generated by the TX processor 368 may be provided to different antennas 352 via separate transmitters 354Tx. Each transmitter 354Tx may modulate an RF carrier with a corresponding spatial stream for transmission.

[0067] The UL transmission is processed at the base station 310 in a manner similar to that described in conjunction with the receiver functionality at the UE 350. Each receiver 318Rx receives a signal through its corresponding antenna 320. Each receiver 318Rx recovers information modulated onto an RF carrier and provides the information to the RX processor 370.

[0068] The controller / processor 375 may be associated with a memory 376 that stores program codes and data. The memory 376 may be referred to as a computer readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0069] At least one of the TX processor 316, the RX processor 370, and the controller / processor 375 may be configured to perform operations related to Figure 1 Aspects related to the crowdsourcing positioning component 199.

[0070] Figure 4 4 is a diagram illustrating an example of UE positioning based on reference signal measurements (which may also be referred to as “network-based positioning”) in accordance with various aspects of the present disclosure. UE 404 may be at time T SRS_TX UL SRS 412 is sent at time T PRS_RX The TRP 406 may be received at time T SRS_RX Receive UL SRS 412 at time T PRS_TX UE 404 may receive DL PRS 410 before transmitting UL SRS 412, or may transmit UL SRS 412 before receiving DL PRS 410. In both cases, a positioning server (e.g., location server 168) or UE 404 may determine the UL SRS 412 based on ||T SRS_RX –T PRS_TX |–|T SRS_TX –T PRS_RX || to determine RTT 414. Therefore, multi-RTT positioning can utilize UE Rx-Tx time difference measurement (ie, |T SRS_TX –T PRS_RX |) and the DL PRS reference signal received power (RSRP) (DLPRS-RSRP) of the downlink signal received from the multiple TRPs 402, 406 and measured by the UE 404, and the measured TRP Rx-Tx time difference measurement (ie, |T SRS_RX –T PRS_TX |) and UL SRS-RSRP at multiple TRPs 402, 406 of uplink signals sent from UE 404. UE 404 measures UE Rx-Tx time difference measurement (and / or DL ​​PRS-RSRP of received signals) using assistance data received from the positioning server, and TRPs 402, 406 measure gNB Rx-Tx time difference measurement (and / or UL SRS-RSRP of received signals) using assistance data received from the positioning server. The measurements may be used at the positioning server or UE 404 to determine RTT, which is used to estimate the position of UE 404. Other methods may be used to determine RTT, such as, for example, using DL-TDOA and / or UL-TDOA measurements.

[0071] PRS may be defined for network-based positioning (e.g., NR positioning) to enable UEs to detect and measure more neighbor transmit and receive points (TRPs), with multiple configurations supported to enable various deployments (e.g., indoor, outdoor, sub-6, mmW, etc.). To support PRS beam operation, beam scanning may also be configured for PRS. The UL positioning reference signal may be based on a sounding reference signal (SRS) with enhancements / adjustments for positioning purposes. In some examples, the UL-PRS may be referred to as "SRS for positioning," and a new information element (IE) may be configured for SRS for positioning in RRC signaling.

[0072] DL PRS-RSRP may be defined as the linear average of the power contributions (in [W]) of the resource elements of the antenna ports carrying the DL PRS reference signals configured for RSRP measurement within the considered measurement frequency bandwidth. In some examples, for FR1, the reference point for DL ​​PRS-RSRP may be the antenna connector of the UE. For FR2, DL PRS-RSRP may be measured based on the combined signals from the antenna elements corresponding to a given receiver branch. For FR1 and FR2, if receiver diversity is being used by the UE, the reported DL PRS-RSRP value may not be lower than the corresponding DL PRS-RSRP of any of the individual receiver branches. Similarly, UL SRS-RSRP may be defined as the linear average of the power contributions (in [W]) of the resource elements carrying the sounding reference signal (SRS). UL SRS-RSRP may be measured in the configured measurement opportunities on the configured resource elements within the considered measurement frequency bandwidth. In some examples, for FR1, the reference point for UL SRS-RSRP may be the antenna connector of the base station (e.g., gNB). For FR2, UL SRS-RSRP may be measured based on the combined signals from the antenna elements corresponding to a given receiver branch. For FR1 and FR2, if receiver diversity is being used by the base station, the reported UL SRS-RSRP value may not be lower than the corresponding UL SRS-RSRP of any one of the single receiver branches.

[0073] PRS-path RSRP (PRS-RSRPP) may be defined as the power of the linear average of the channel response at the i-th path delay of the resource element carrying the DL PRS signal configured for measurement, where the DL PRS-RSRPP for the 1st path delay is the power contribution corresponding to the first detected path in time. In some examples, the PRS path phase measurement may refer to the phase associated with the i-th path of the channel derived using the PRS resource.

[0074] DL-AoD positioning can utilize the measured DL PRS-RSRP of downlink signals received from multiple TRPs 402, 406 at the UE 404. The UE 404 uses the assistance data received from the positioning server to measure the DL PRS-RSRP of the received signals, and the resulting measurements are used together with the transmit azimuth angle (A-AoD), the transmit zenith angle (Z-AoD), and other configuration information to position the UE 404 relative to neighboring TRPs 402, 406.

[0075] DL-TDOA positioning can utilize DL reference signal time difference (RSTD) (and / or DL ​​PRS-RSRP) of downlink signals received from multiple TRPs 402, 406 at UE 404. UE 404 uses assistance data received from a positioning server to measure the DL RSTD (and / or DL ​​PRS-RSRP) of the received signals, and the resulting measurements are used together with other configuration information to position UE 404 relative to neighboring TRPs 402, 406.

[0076] UL-TDOA positioning can utilize the UL relative time of arrival (RTOA) (and / or UL SRS-RSRP) at multiple TRPs 402, 406 of uplink signals sent from the UE 404. The TRPs 402, 406 use assistance data received from the positioning server to measure the UL-RTOA (and / or UL SRS-RSRP) of the received signals, and the resulting measurements are used together with other configuration information to estimate the position of the UE 404.

[0077] UL-AoA positioning may utilize the azimuth angle of arrival (A-AoA) and the zenith angle of arrival (Z-AoA) measured at multiple TRPs 402, 406 of uplink signals sent from the UE 404. The TRPs 402, 406 measure the A-AoA and Z-AoA of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with other configuration information to estimate the position of the UE 404. For purposes of this disclosure, positioning operations in which a UE provides measurements to a base station / positioning entity / server for use in calculating the UE's position may be described as "UE-assisted," "UE-assisted positioning," and / or "UE-assisted position calculation," while positioning operations in which a UE measures and calculates its own position may be described as "UE-based," "UE-based positioning," and / or "UE-based position calculation."

[0078] Additional positioning methods may be used to estimate the position of the UE 404, such as, for example, UE-side UL-AoD and / or DL-AoA. Note that data / measurements from various techniques may be combined in various ways to increase accuracy, determine and / or enhance certainty, supplement / complement measurements, and / or replace / provide missing information.

[0079] Note that the terms "positioning reference signal" and "PRS" generally refer to specific reference signals used for positioning in NR and LTE systems. However, as used herein, the terms "positioning reference signal" and "PRS" may also refer to any type of reference signal that may be used for positioning, such as, but not limited to, PRS, TRS, PTRS, CRS, CSI-RS, DMRS, PSS, SSS, SSB, SRS, UL-PRS, etc. as defined in LTE and NR. In addition, unless the context indicates otherwise, the terms "positioning reference signal" and "PRS" may refer to downlink or uplink positioning reference signals. To further distinguish the types of PRS, a downlink positioning reference signal may be referred to as a "DL PRS", and an uplink positioning reference signal (e.g., SRS, PTRS used for positioning) may be referred to as a "UL-PRS". In addition, for signals that may be sent in both uplink and downlink (e.g., DMRS, PTRS), "UL" or "DL" may be prefixed to the signal to distinguish the direction. For example, "UL-DMRS" may be distinguished from "DL-DMRS".

[0080] In some scenarios, the location of a UE (e.g., an Internet of Things (IoT) device) may be determined based on crowdsourced information (or crowdsourcing) (e.g., by a UE or a positioning server). Crowdsourcing may refer to a mechanism for collecting information (which may be referred to as "crowdsourced information") from a group of UEs, typically via an online server. For example, crowdsourcing may involve obtaining data, such as radio frequency (RF) measurements, sensing information (e.g., information obtained via one or more sensors), and / or location information from a group of UEs, where the group of UEs may submit the data to a crowdsourcing server or an Internet platform (e.g., social media, mobile applications, etc.). Based on the data collected from the group of UEs, the crowdsourcing server may aggregate the data, analyze the data, and determine which (which) data sets may be useful to other devices or have good credibility. For example, a crowdsourcing server may collect weather conditions reported by a group of UEs in an area in real time. Based on the weather conditions received from the group of UEs, the crowdsourcing server may be able to determine the current weather conditions in the area, and the crowdsourcing server may share the determined weather conditions with other UEs (e.g., UEs approaching or moving toward the area).

[0081] Figure 55 is a diagram illustrating an example of determining the location of a target device based on crowdsourcing in accordance with various aspects of the present disclosure. Certain UEs, such as IoT devices, may have low-power positioning specifications, where these UEs may specify a positioning accuracy of typically tens (10) meters to hundreds (100) meters. For example, a UE used in association with asset tracking (such as a tracker device for a container) may specify a lower positioning accuracy than a UE used for real-time navigation.

[0082] In one example, the location of a device (which may be referred to as a target device) may be achieved by crowdsourcing. For example, as shown at 506, a set of UEs 504 (which may also be referred to as reference UEs and / or reference IoT devices) may be configured to scan / measure one or more neighboring cells 510, such as measuring the reference signal received power (RSRP) of one or more neighboring cells 510. The set of UEs 504 may then upload their measurements (e.g., RSRP) to a server 502 (e.g., a crowdsourcing server or a positioning server). The server 502 may analyze and aggregate the scan data / measurements from the set of UEs 504 and their known locations. The server 502 may be associated with a network node (such as a base station or a component of a base station). For the purposes of the present disclosure, a reference UE may refer to a UE with a known location that is capable of providing measurements (e.g., RSRP measurements) for one or more cells, such that an entity (e.g., a server or base station) may use the measurements and location of the UE as a reference to determine the location of another UE (e.g., a target device / UE). Similarly, a reference cell may refer to a cell (or base station / TRP) with a known location that can be used as a reference for determining the location of the UE.

[0083] Then, as shown at 508, when the server 502 is requested to determine the location of the target device 506 (e.g., a device with a lower positioning accuracy specification), the server 502 can request scan data / measurements (e.g., RSRP) for one or more neighboring cells around the target device 506 from the target device 506 (or the target device 506 can send the scan data / measurements to the server 502 for location determination without receiving a request from the server 502). Based on the crowdsourced information of the server 502, the server 502 can estimate the location of the target device 506, such as by comparing the similarity between the scan data / measurements from the target device 506 and the scan data / measurements from the set of UEs 504. If there is a high similarity between the scan data / measurements from the target device 506 and the scan data / measurements from one of the set of UEs 504, it is likely that the target device 506 is close to the UE.

[0084] Various aspects presented herein can enhance the accuracy and / or latency of crowdsourcing-based UE positioning. Various aspects presented herein provide a mechanism for a server (e.g., server 502) to calculate a location estimate of a target device (e.g., target device 506) based on neighbor cell scan data. In one aspect of the present disclosure, the location estimate of the target device based on neighbor cell scan data (e.g., a mapping of neighbor cell scan data to location) can depend on one or more of the following: physical (e.g., RSRP, which is inversely related to distance), cell characteristics (e.g., downtilt, transmit (Tx) power, antenna array structure, etc.), device type (e.g., IoT devices may have different antenna characteristics compared to smartphones), and / or the environment (e.g., environmental conditions) surrounding the target device (e.g., terrain, obstacles, building materials, etc.). In one example, the location estimate of the target device (e.g., UE) can refer to, for example, using a combination of Figure 4 Describes one of the positioning mechanisms to calculate the approximate location / position of the target device.

[0085] In another aspect of the present disclosure, an artificial intelligence (AI) or machine learning (ML) framework may be implemented at a server for estimating the location of a target device (such as an IoT user). Thus, the location estimate of the target device may be a function of the location of one or more reference UEs and / or cells scanned by the target device. In other words, the location of the target device may be determined based on the learned "similarity" between the reference UEs / cells and the target device.

[0086] Over the past few decades, there have been significant advances in the speed, bandwidth, latency, and reliability of wireless communications (and network-based positioning), which has also increased the complexity of deploying wireless networks in some cases. In order to improve the management of various network nodes and functions, operators and suppliers of wireless communications have begun to apply artificial intelligence and machine learning (AI / ML) to their services. In one example, AI can be broadly defined as configuring computers / electronic devices to perform tasks that are considered uniquely human. ML can be a category of AI technology that includes algorithms that are able to automatically improve their performance without explicit programming.

[0087] In some examples, ML algorithms may include supervised learning, unsupervised learning, and / or reinforcement learning. Under supervised learning, the ML model may specify labeled input data and output data during the training phase of ML. The training data is typically labeled by a data scientist in the preparation phase before being used to train and test the ML model. Once the ML model has learned the relationship between the input data and the output data, it can be used to classify new and unseen data sets and predict the results. Under unsupervised learning, the ML model can be trained based on raw and unlabeled training data, where the ML model is typically used to identify patterns and trends in the raw data set, or to cluster similar data into a specific number of groups. Compared to supervised learning, unsupervised machine learning may be more like a hands-off approach, where the ML model can be configured to efficiently process large amounts of data without human supervision. Under reinforcement learning, the ML model can be trained based on rewarding appropriate behavior and / or punishing inappropriate behavior. For example, positive values ​​can be assigned to appropriate actions to encourage the ML model, and negative values ​​can be assigned to inappropriate behavior. This may enable the ML model to seek long-term and maximum overall rewards to achieve the optimal solution. ML models are often associated with neural networks (NNs), which may also be called artificial neural networks (ANNs) or simulated neural networks (SNNs). A neural network may refer to a computer architecture in which several processors are interconnected in a manner that suggests the connections between neurons in the human brain and are capable of learning through a trial and error process.

[0088] For purposes of this disclosure, "inference" or "ML inference" may refer to the process of running data points into an ML model (e.g., via an inference host) to compute an output such as a single number score, e.g., to make a prediction using a trained ML algorithm. "Inference host" or "ML inference host" may refer to a network function that hosts an ML model during inference mode. On the other hand, "training" or "ML training" may refer to the process of running data points to train or teach an ML model (e.g., via a training host). "Training host" or "ML training host" may refer to a network function that hosts an ML model during training mode.

[0089] Figure 6600 is a diagram illustrating an example architecture of a functional framework associated with an ML model according to various aspects of the present disclosure. In some scenarios, the functional framework of the ML model can be enabled by further enhancing data collection with use cases and / or examples. In one example, as shown in diagram 600, the functional framework of the ML model can include multiple logical entities, such as a model training host 602, a model reasoning host 604, a data source 606, and / or an actor 608, etc. In some instances, multiple logical entities can be co-located on the same device (e.g., UE, positioning device, etc.) or network node (e.g., base station, component of a base station, server, etc.). In other examples, different logical entities can be located on different devices or network nodes.

[0090] The model inference host 604 can be configured to run the ML model based on the inference data provided by the data source 606, and the model inference host 604 can generate output (e.g., prediction), wherein the inference data is input to the actor 608. The actor 608 can be a device or an entity. For example, the actor 608 can be a GNSS device or a location server associated with the GNSS device, etc. In addition, the actor 608 can also depend on the type of task performed by the model inference host 604, the type of inference data provided to the model inference host 604, and / or the type of output generated by the model inference host 604, etc.

[0091] After actor 608 receives the output from model inference host 604, actor 608 may determine whether or how to act based on the output. For example, if actor 608 is a location server and the output from model inference host 604 is associated with an RSRP measurement classification, actor 608 may determine how to classify one or more RSRP measurements performed based on the output. Actor 608 may then indicate the classification to at least one subject of action 610. In some examples, actor 608 and at least one subject of action 610 may be the same entity (e.g., a UE).

[0092] The data source 606 may also be configured to collect data that is used as training data for training the ML model or as inference data for feeding the ML model inference operation. For example, the data source 606 may collect data from one or more UEs, base stations, or location servers that may include an actor 610, and provide the collected data to the model training host 602 for ML model training. In some examples, if the output provided by the actor 608 is inaccurate (or the accuracy is below an accuracy threshold), the model training host 602 may determine to modify or retrain the ML model used by the model inference host, such as via ML model deployment / update.

[0093] In one aspect of the present disclosure, a location estimate for a target device (e.g., target device 506) may be configured as a function of a reference UE location (e.g., reference UE 504), wherein the location of the target device may be estimated based at least in part on the locations of one or more reference UEs, such as by Figure 5 shown.

[0094] Figure 7 700 is a diagram illustrating an example ML model capable of receiving inputs from a target UE and a plurality of reference UEs and providing weights for the inputs from each of the plurality of reference UEs in accordance with various aspects of the present disclosure. For a target UE(t) (e.g., target device 506), if there is a set of reference UEs with known locations (e.g., reference UE 504), the reference UE set may be represented by R t , and each UE in the reference UE set can be represented by r. In other words, r can be R t An element / member (e.g., r∈R t For example, if there are ten reference UEs in the reference UE set (eg, R t =10), then the reference UE set may include UEr1,r2,r3,...,r 10 In one example, the number of reference UEs in the reference UE set (R t ) may be determined / selected based on a threshold of the number of common cells between the reference UE and the target UE. For example, if there are three (3) common cells between the reference UE and the target UE (e.g., meaning that the reference UE and the target UE are able to scan / measure the same three cells), then the reference UE set (R t ) may include 5 to 10 reference UEs, and if there is one (1) common cell between the reference UEs and the target UE, the reference UE set (R t ) may include 10 to 20 reference UEs, etc. In some scenarios, if the number of common cells between the reference UE and the target UE is small, more reference UEs may be selected to estimate the position of the target UE to improve positioning accuracy.

[0095] The ML model 702 may be used to reason about similarities between each of the plurality of UE pairs (t, r) (e.g., to provide reasoning about similarities between each of the plurality of UE pairs (t, r)). For example, if there are ten reference UEs (R t =10), there may be ten (10) UE pairs: (t,r1), (t,r2), (t,r3), ..., (t,r 10). In other words, the ML model 702 may determine the similarity between the reference UE and the target UE (e.g., in terms of cell scanning / measurement). If there is a high similarity, it may be inferred that the reference UE and the target UE are close to each other, and therefore the target UE is more likely to be at the location of the reference UE. On the other hand, if there is a low similarity, it may be inferred that the reference UE and the target UE are not close to each other, and therefore the target UE is less likely to be at the location of the reference UE. The ML model 702 may be implemented at a server (e.g., server 502, a positioning server, a crowdsourcing server, a location management function (LMF), etc.) or at a network node (e.g., a base station or a component of a base station).

[0096] In one example, the ML model 702 may be able to identify at least one common cell between the target UE and the reference UE set, wherein the output of the ML model may include a similarity score between the UE and the reference UE set. The at least one public cell may be a single public cell, wherein the ML model 702 may identify the at least one public cell based on an identifier (ID) of the single public cell. In another example, the at least one public cell may be a plurality of public cells, wherein the ML model 702 may identify the at least one public cell based on the IDs of the plurality of public cells. The at least one public cell may be a serving cell or a non-serving cell across a plurality of frequency bands of the target UE. In another example, the at least one public cell may share at least one feature, which may include a measurement of the at least one public cell, a UE type, an environmental condition, a cell characteristic associated with the at least one public cell, or a combination thereof.

[0097] In one example, the ML model 702 can be associated with a neural network (NN) capable of receiving one or more defined features from each of the reference UE set and the target UE. t,r). The features may include scanning information of the target UE and the reference UE, such as scanning / measurement performed by the target UE and the reference UE on each of the public cells. For example, the features may include RSRP of at least one cell or one public cell, coverage area of ​​at least one cell or one public cell, channel response of at least one cell or one public cell (for example, the channel response may include at least one of the following: timing advance (TA), reference signal received quality (RSRQ), received signal strength indicator (RSSI), reference signal signal-to-noise ratio (RSSNR), and / or channel quality indicator (CQI), etc.), device characteristics of the target UE or each reference UE in the reference UE set (for example, chipset, antenna, device type, etc.), the position of each reference UE in the reference UE set, the position uncertainty for the position of each reference UE in the reference UE set, or a combination thereof. Then, the ML model 702 may be based on W t,r =NN(features t,r ), r∈R t To assign a weight (w t,r For example, if there are ten reference UEs (R t =10), there may be ten reference UEs r1, r2, r3, ..., r 10 The ten weights Wr1, Wr2, Wr3, ..., Wr 10 For purposes of this disclosure, position uncertainty may refer to the standard deviation of latitude and / or longitude errors. In another example, position uncertainty may correspond to the semi-major axis and / or semi-minor axis of an error ellipse for a certain confidence level (e.g., the semi-major axis and semi-minor axis of a 95% confidence error ellipse).

[0098] For the purposes of this disclosure, the term "weight" may refer to a parameter within a neural network that transforms input data within a hidden layer of the network. A neural network may include a series of nodes or neurons. Within each node is a set of inputs, weights, and bias values. When an input enters a node, it may be multiplied by the weight value, and the resulting output is observed or passed to the next layer in the neural network. Typically, the weights of a neural network are contained in the hidden layers of the network. For example, a single node may take input data and multiply it by an assigned weight value, and then add a bias before passing the data to the next layer. The last layer of a neural network is also called an output layer. The output layer typically tunes the input from the hidden layer to produce a desired number within a specified range.

[0099] Based on the weights calculated for the reference UE set, the ML output for each reference UE can then be fused to obtain a weighted sum based on (ie, as a reference UE position (xr ) is used to estimate the target UE position (x t ). In some examples, the ML model 702 can also be trained to minimize a loss function, such as based on the loss in is the ML-based position estimate, and x t is the true position. In one example, the loss L used to train the ML model 702 can be based on the mean squared error: In another example, if the similarity is interpreted as a parameter of a distribution, the loss L can be based on the log likelihood.In another example, the ML model 702 can be further trained / tuned / retrained based on measurements from a reference UE set and / or a target UE (eg, for a public cell).

[0100] In another aspect of the present disclosure, a location estimate for a target device (e.g., target device 506) may be configured as a function of a reference UE location (e.g., reference UE 504) and a cell location (e.g., neighboring cell 510), wherein the location of the target device may be estimated based at least in part on the locations of one or more reference UEs and the locations of one or more cells, such as Figure 5 shown.

[0101] Figure 8 800 is a diagram illustrating an example of an ML model capable of receiving inputs from a target UE and a plurality of reference UEs and providing weights for the inputs from each of the plurality of reference UEs in accordance with various aspects of the present disclosure. For a target UE(t) (e.g., target device 506), the ML framework may utilize a cell set (C t ), where each cell in the cell set with a known location can be represented by c (e.g., c∈C t ). Similarly, the reference UE set can be represented by R t , and each UE with a known position in the reference UE set can be represented by r (e.g., r∈R t ) to indicate, for example, combining Figure 7 as described.

[0102] As shown at 810, the first ML model 802 can be used to infer the set of cells (C t ), where each ML model 802 may receive features associated with a reference cell set from a target UE. t,r ) as input. Then, the ML model 802 can be based on W t,c =NN(features t,c ),c∈C tA weight (w t,c For example, if there are ten reference cells (C t =10), then there may be cells assigned to c1, c2, c3, ..., c 10 The ten weights Wc1, Wc2, Wc3, ..., Wc 10 The characteristics may include scanning information of the target UE, such as scanning / measurements performed by the target UE for each of the reference cells.

[0103] Similarly, as shown at 820, the second ML model 804 can be used to infer the similarity between each UE pair in the plurality of UE pairs (t, r), such as combining Figure 7 For example, the second ML model 804 may receive one or more defined features from each of the reference UE set and the target UE set. t,r ), such as scanning information of one or more cells from the target UE and the reference UE. The features may include RSRP of at least one cell or one common cell, coverage area of ​​at least one cell or one common cell, channel response of at least one cell or one common cell (e.g., the channel response may include at least one of the following: TA, RSRQ, RSSI, RSSNR and / or CQI), device characteristics of the target UE or each reference UE in the reference UE set (e.g., chipset, antenna, device type, etc.), location of each reference UE in the reference UE set, location uncertainty for the location of each reference UE in the reference UE set (which may also be referred to as geo-tag uncertainty in some examples), or a combination thereof. Then, the second ML model 804 may be based on W t,r =NN(features t,r ),r∈R t A weight (w t,r For example, if there are ten reference UEs (R t =10), then there may be UEs r1, r2, r3, ..., r assigned to the reference UEs r1, r2, r3, ..., r 10 The ten weights Wr1, Wr2, Wr3, ..., Wr 10 The first ML model 802 and / or the second ML model 804 may be implemented at a server (eg, server 502, a positioning server, a crowdsourcing server, a LMF, etc.) or a network node (eg, a base station or a component of a base station).

[0104] In one example, the first ML model 802 and / or the second ML model 804 may be able to identify at least one common cell between the target UE and the reference UE set, wherein the output of the ML model may include a similarity score between the UE and the reference UE set. The at least one public cell may be a single public cell, wherein the first ML model 802 and / or the second ML model 804 may identify the at least one public cell based on the ID of the single public cell. In another example, the at least one public cell may be a plurality of public cells, wherein the first ML model 802 and / or the second ML model 804 may identify the at least one public cell based on the IDs of the plurality of public cells. The at least one public cell may be a serving cell or a non-serving cell across a plurality of frequency bands of the target UE. In another example, the at least one public cell may share at least one feature, which may include a measurement of the at least one public cell, a UE type, an environmental condition, a cell characteristic associated with the at least one public cell, or a combination thereof.

[0105] After obtaining the reference UE set and the cell weights, the target UE (x t ) can be obtained by weighting The outputs from the first ML model 802 and the second ML model 804 are fused to estimate (i.e., as the reference UE position (x r ) and cell location (x c ) is a function of the position estimate of the target UE. In some examples, the first ML model 802 and / or the second ML model 804 may also be trained to minimize the loss In another example, the first ML model 802 and / or the second ML model 804 may be further trained / tuned / retrained based on measurements from a reference UE set and / or a target UE (eg, for a public cell).

[0106] In another aspect of the present disclosure, an ML model (e.g., ML models 702, 802, 804) may be configured to operate on a per-cell basis. For example, the ML model may infer a per-cell similarity between the target UE and each of the reference UEs, wherein the ML model may compare the similarity between the target UE and each of the reference UEs with respect to one cell (e.g., based on one or more features) and provide a weight for each reference UE. The ML model may then sum the similarities associated with the set of reference UEs based on the weights to obtain a similarity score: In some examples, one or more features may include scanning information of the target UE and the reference UE set from a particular cell (c), and the location of the reference UE relative to the cell (c). Additionally or alternatively, the ML model may also be configured to infer per-cell dissimilarity based on cells that are not common between the reference UE set and the target UE.

[0107] In another example, the ML model (e.g., ML models 702, 802, 804) may operate on a cross-cell basis. For example, the ML model may use summary statistics across cells as input, such as the mean and standard deviation of per-cell features (e.g., RSRP measurements). In one example, the summary statistics may include only cells seen / detected by the reference UE and the target UE. In another example, the summary statistics may include statistics across non-public cells. A non-public cell between a reference UE and a target UE may refer to a cell that can be seen / detected / scanned by either the reference UE or the target UE but not by both.

[0108] As combined Figure 7 and Figure 8 As described, the output from the ML model (e.g., ML models 702, 802, 804) can be based on a weighted sum Such as (for target UE position estimation as a function of reference UE position) or (in ) (for position estimation of the target UE as a function of the reference UE position and the cell position). Thus, the weighted sum may include reference UEs, cells, or both, based on criteria such as the number of reference UEs, the number of cells reported by each reference UE and / or by the target UE, the number of common cells, or a combination thereof.

[0109] In another example, the ML model may be configured to include only a subset of the reference UEs and cells in the weighted sum. For example, if there are ten (10) reference UEs in the reference UE set, the ML model may select only five (5) reference UEs from the reference UE set for computing the weighted sum. In one example, a similarity threshold may be configured for the similarities reported by the ML model, where the similarity threshold may be used by the ML model to determine which UEs / cells to include for computing the weighted sum (e.g., reference UEs and / or cells with similarities above the similarity threshold are included for computing the weighted sum, and reference UEs and / or cells with similarities below the similarity threshold are excluded from computing the weighted sum, etc.). In another instance, if a coarse position estimate of the target UE is available (which may be based on, for example, a combination of Figure 4If the target UE is located at a position close to the target UE (e.g., within a defined distance of the coarse position estimate of the target UE), the ML model may use the coarse position estimate of the target UE to select reference UEs and / or cells for calculating the weighted sum. For example, the ML model may select reference UEs and / or cells that are near the target UE (e.g., within a defined distance of the coarse position estimate of the target UE).

[0110] In another example, the fusion of ML outputs can be based on likelihood fusion, where the weights determined for one or more reference UEs and / or cells can be interpreted as parameters of a probability distribution. For example, the standard deviation corresponding to a Gaussian probability density function (PDF) around the location of each reference UE. The location likelihood of the target device can then be obtained by fusing the likelihood obtained from each of the reference UEs. In another instance, the fusion of ML outputs can be based on ML-based fusion, where an ML model can be trained to fuse information from one or more reference UEs and / or cells. In one example, the loss L that can be used to train the ML model can be based on a mean squared error: Alternatively, if the similarity is interpreted as a parameter of a distribution, the loss L that can be used to train the ML model can be based on the log-likelihood.

[0111] In another aspect of the present disclosure, a target UE (e.g., target UE 506) may signal a set of criteria / indications to a server (e.g., server 502) for the server to determine the type of ML model to be used and / or the type of fusion. For example, the target UE may signal its capabilities for cell scanning / measurement to the server, and in response, the server may configure at least one ML model (e.g., ML models 702, 802, 804) suitable for reasoning the location of the target UE based on the capabilities of the target UE. In another example, the target UE may specifically indicate to the server the ML models it supports, and the server may configure the corresponding ML model to reason about the location of the target UE. In some examples, the fusion of ML outputs for reference UEs and / or cells may occur across operators and across multiple frequency bands. In another example, a server (e.g., server 502) may send a configuration for the target UE to configure the target UE to measure at least one cell. In response, the target UE may measure / scan at least one cell based on the configuration, and the target UE may send the measurement / scan for at least one cell back to the server.

[0112] By utilizing reference UE positions and / or cell positions, the similarity learning framework described herein can achieve both universal positioning and local positioning of the target device. For example, by averaging the cell positions, a physically based (universal) mapping from RSRP to the range between the target UE and the reference cell can be obtained. Similarly, by averaging the reference UE positions, a local mapping corresponding to the environmental conditions (e.g., terrain, obstacles, etc.) around the target UE can also be obtained. Therefore, the various aspects presented herein can achieve more accurate positioning for target UEs (such as IoT devices with low power specifications).

[0113] Fig. 9 900 is a flow chart of a method of wireless communication. The method may be performed by a network entity (e.g., base station 102; server 502; ML models 702, 802, 804; network entity 1102). The method may enable the network entity to determine the location of the UE based on crowdsourcing and via at least one type of AI / ML framework.

[0114] At 906, the network entity may receive from the UE a first measurement set associated with at least one cell, such as in conjunction with Figure 5 , Figure 7 and Figure 8 For example, Figure 5 As shown in 506, the server 502 may receive a scan / measurement set associated with one or more neighboring cells 510 from the target device 506. The reception of the first measurement set may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0115] At 908, the network entity may perform, via at least one ML model, a position estimation of the UE based on at least one of a first set of measurements associated with at least one cell, a second set of measurements for each reference UE in a set of reference UEs, or a position of each reference UE in the set of reference UEs, wherein the UE and the set of reference UEs include at least one common cell, wherein the at least one ML model is capable of identifying at least one common cell between the UE and the set of reference UEs, and wherein an output of the at least one ML model includes a similarity score between the UE and the set of reference UEs, such as a combination of Figure 5 , Figure 7 and Figure 8 For example, as described in conjunction with Figure 5As described, the server 502 may perform a position estimation for the target device 506 via an ML model (e.g., ML models 702, 802, 804, etc.) based on measurements associated with one or more neighboring cells 510, measurements for each reference UE in a reference UE set, or a position of each reference UE in a reference UE set, wherein the target device and the reference UE set may include at least one common cell. The position estimation for the UE may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0116] In one example, at 902, the network entity may receive an indication of criteria associated with the UE from the UE, and the network entity may select an ML model and a fusion type for the ML model for performing position estimation for the UE based on the indication, such as in combination with Figure 5 , Figure 7 and Figure 8 The receipt of an indication of criteria associated with the UE and / or the selection of an ML model and a fusion type for the ML model may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0117] In another example, at 904, the network entity may send a configuration for the UE to configure the UE to measure at least one cell, and the network entity may receive a first measurement set associated with the at least one cell in response to the configuration, such as in conjunction with Figure 5 , Figure 7 and Figure 8 The sending of the configuration and / or the receiving of the first measurement set associated with at least one cell may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0118] In another example, at 910, the network entity may train an ML model using one or more measurements from a reference UE set for at least one common cell, such as in conjunction with Figure 5 , Figure 7 and Figure 8 The training of ML models can be done by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0119] In another example, the position estimate for the UE is also based on the position of at least one cell.

[0120] In another example, the first measurement set or the second measurement set includes at least one of: RSRP for at least one cell, coverage area for at least one cell, channel response for at least one cell, device characteristics of a UE or each reference UE in a reference UE set, location of each reference UE in a reference UE set, or location uncertainty for the location of each reference UE in a reference UE set. In such examples, the channel response includes at least one of TA, RSRQ, RSSI, RSSNR, and / or CQI. In another example, at least one ML model includes a first ML model and a second ML model, the first ML model being configured to infer a first set of weights for a first measurement set associated with at least one cell, and the second ML model being configured to infer a second set of weights for a second measurement set for each reference UE in a reference UE set, such as in combination with Figure 8 In such examples, the position estimation of the UE is based on fusing the output of a first ML model based on a first set of weights and a second ML model based on a second set of weights.

[0121] In another example, the set of outputs from the ML model is fused based on a weighted sum associated with a reference UE set, at least one cell, at least one public cell, or a combination thereof. In such examples, the weighted sum is based on the number of reference UE sets, the number of cells reported by each reference UE in the reference UE set, the number of cells reported by the UE, the number of at least one public cell.

[0122] In another example, the ML model is capable of identifying at least one common cell between the UE and a reference set of UEs, and wherein an output of the ML model comprises a similarity score between the UE and the reference set of UEs. In such examples, the at least one public cell is a single public cell, and wherein the ML model identifies the at least one public cell based on an ID of the single public cell, or the at least one public cell is a plurality of public cells, and wherein the ML model identifies the at least one public cell based on IDs of the plurality of public cells.

[0123] In another example, at least one cell for the UE is a serving cell or a non-serving cell across multiple frequency bands.

[0124] In another example, at least one public cell is associated with at least one characteristic, the at least one characteristic comprising one or more of: measurements for the at least one public cell, UE type, environmental conditions, cell characteristics associated with the at least one public cell, or a combination thereof.

[0125] Fig.101000 is a flow chart of a method of wireless communication. The method may be performed by a network entity (e.g., base station 102; server 502; ML models 702, 802, 804; network entity 1102). The method may enable the network entity to determine the location of the UE based on crowdsourcing and via at least one type of AI / ML framework.

[0126] At 1006, the network entity may receive from the UE a first measurement set associated with at least one cell, such as in conjunction with Figure 5 , Figure 7 and Figure 8 For example, Figure 5 As shown in 506, the server 502 may receive a scan / measurement set associated with one or more neighboring cells 510 from the target device 506. The reception of the first measurement set may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0127] At 1008, the network entity may perform, via at least one ML model, a position estimation of the UE based on at least one of a first set of measurements associated with at least one cell, a second set of measurements for each reference UE in a set of reference UEs, or a position of each reference UE in the set of reference UEs, wherein the UE and the set of reference UEs include at least one common cell, wherein the at least one ML model is capable of identifying at least one common cell between the UE and the set of reference UEs, and wherein an output of the at least one ML model includes a similarity score between the UE and the set of reference UEs, such as a combination of Figure 5 , Figure 7 and Figure 8 For example, as described in conjunction with Figure 5 As described, the server 502 may perform a position estimation for the target device 506 via an ML model (e.g., ML models 702, 802, 804, etc.) based on measurements associated with one or more neighboring cells 510, measurements for each reference UE in a reference UE set, or a position of each reference UE in a reference UE set, wherein the target device and the reference UE set may include at least one common cell. The position estimation for the UE may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0128] In one example, the network entity may receive an indication of criteria associated with the UE from the UE, and the network entity may select an ML model and a fusion type for the ML model for performing position estimation for the UE based on the indication, such as in combination with Figure 5 , Figure 7 and Figure 8The receipt of an indication of criteria associated with the UE and / or the selection of an ML model and a fusion type for the ML model may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0129] In another example, the network entity may send a configuration for the UE to configure the UE to measure at least one cell, and the network entity may receive a first measurement set associated with the at least one cell in response to the configuration, such as in conjunction with Figure 5 , Figure 7 and Figure 8 The sending of the configuration and / or the receiving of the first measurement set associated with at least one cell may be performed by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0130] In another example, the network entity may train an ML model using one or more measurements from a reference UE set for at least one common cell, such as in combination with Figure 5 , Figure 7 and Figure 8 The training of ML models can be done by, for example Fig.11 The crowdsourcing positioning component 199 and / or the transceiver 1146 of the network entity 1102 may be executed.

[0131] In another example, the position estimate for the UE is also based on the position of at least one cell.

[0132] In another example, the first measurement set or the second measurement set includes at least one of the following: RSRP for at least one cell, coverage area for at least one cell, channel response for at least one cell, device characteristics of the UE or each reference UE in the reference UE set, location of each reference UE in the reference UE set, or location uncertainty for the location of each reference UE in the reference UE set. In such examples, the channel response includes at least one of TA, RSRQ, RSSI, RSSNR, and / or CQI.

[0133] In another example, the at least one ML model includes a first ML model and a second ML model, the first ML model is configured to infer a first set of weights for a first set of measurements associated with at least one cell, and the second ML model is configured to infer a second set of weights for a second set of measurements for each reference UE in the set of reference UEs, such as in combination with Figure 8 In such examples, the position estimation of the UE is based on fusing the output of a first ML model based on a first set of weights and a second ML model based on a second set of weights.

[0134] In another example, the set of outputs from the ML model is fused based on a weighted sum associated with a reference UE set, at least one cell, at least one public cell, or a combination thereof. In such examples, the weighted sum is based on the number of reference UE sets, the number of cells reported by each reference UE in the reference UE set, the number of cells reported by the UE, the number of at least one public cell.

[0135] In another example, the ML model is capable of identifying at least one common cell between the UE and a reference set of UEs, and wherein an output of the ML model comprises a similarity score between the UE and the reference set of UEs. In such examples, the at least one public cell is a single public cell, and wherein the ML model identifies the at least one public cell based on an ID of the single public cell, or the at least one public cell is a plurality of public cells, and wherein the ML model identifies the at least one public cell based on IDs of the plurality of public cells.

[0136] In another example, at least one cell for the UE is a serving cell or a non-serving cell across multiple frequency bands.

[0137] In another example, at least one public cell is associated with at least one feature, the at least one feature comprising one or more of: measurements for the at least one public cell, UE type, environmental conditions, cell characteristics associated with the at least one public cell, or a combination thereof.

[0138] Fig.111100 is a diagram illustrating an example of a hardware implementation for a network entity 1102. The network entity 1102 may be a BS, a component of a BS, or may implement BS functionality. The network entity 1102 may include at least one of a CU 1110, a DU 1130, or a RU 1140. For example, depending on the layer functionality processed by the crowdsourced positioning component 199, the network entity 1102 may include a CU 1110; both a CU 1110 and a DU 1130; each of the CU 1110, the DU 1130, and the RU 1140; the DU 1130; both a DU 1130 and a RU 1140; or a RU 1140. The CU 1110 may include a CU processor 1112. The CU processor 1112 may include an on-chip memory 1112'. In some aspects, the CU 1110 may also include an additional memory module 1114 and a communication interface 1118. CU 1110 communicates with DU 1130 via a mid-range link such as an F1 interface. DU 1130 may include a DU processor 1132. DU processor 1132 may include on-chip memory 1132'. In some aspects, DU 1130 may also include an additional memory module 1134 and a communication interface 1138. DU 1130 communicates with RU 1140 via a forward link. RU 1140 may include a RU processor 1142. RU processor 1142 may include on-chip memory 1142'. In some aspects, RU 1140 may also include an additional memory module 1144, one or more transceivers 1146, an antenna 1180, and a communication interface 1148. RU 1140 communicates with UE 104. On-chip memory 1112', 1132', 1142' and additional memory modules 1114, 1134, 1144 may all be considered computer-readable media / memory. Each computer readable medium / memory may be non-transitory. Each of processors 1112, 1132, 1142 is responsible for general processing, which includes executing software stored on the computer readable medium / memory. The software, when executed by the corresponding processor, causes the processor to perform the various functions described above. The computer readable medium / memory may also be used to store data manipulated by the processor when executing the software.

[0139] As discussed above, the crowd-sourced positioning component 199 is configured to receive a first set of measurements associated with at least one cell from the UE. The crowd-sourced positioning component 199 may also be configured to perform a position estimate of the UE via at least one ML model based on at least one of the first set of measurements associated with the at least one cell, a second set of measurements for each reference UE in a reference UE set, or a position of each reference UE in a reference UE set, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying at least one common cell between the UE and the reference UE set, and wherein the output of the at least one ML model includes a similarity score between the UE and the reference UE set. The crowd-sourced positioning component 199 may be within one or more processors of one or more of the CU 1110, the DU 1130, and the RU 1140. The crowd-sourced positioning component 199 may be one or more hardware components specifically configured to perform the stated process / algorithm, implemented by one or more processors configured to perform the stated process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. The network entity 1102 may include various components configured for various functions. In one configuration, the network entity 1102 includes means for receiving a first measurement set associated with at least one cell from the UE. The network entity 1102 may also include means for performing a position estimation of the UE via at least one ML model based on at least one of the first measurement set associated with the at least one cell, a second measurement set for each reference UE in a reference UE set, or a position of each reference UE in the reference UE set, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying at least one common cell between the UE and the reference UE set, and wherein an output of the at least one ML model includes a similarity score between the UE and the reference UE set.

[0140] In one configuration, the network entity 1102 may also include means for receiving, from the UE, an indication of criteria associated with the UE, and means for selecting, based on the indication, an ML model and a fusion type for the ML model for performing position estimation for the UE.

[0141] In another configuration, the network entity 1102 may also include means for sending a configuration for the UE to configure the UE to measure at least one cell, and means for receiving a first measurement set associated with the at least one cell in response to the configuration.

[0142] In another configuration, the network entity 1102 may also include means for training the ML model using one or more measurements from the reference UE set for at least one common cell.

[0143] In another configuration, the position estimate for the UE is further based on the position of at least one cell.

[0144] In another configuration, the first measurement set or the second measurement set includes at least one of the following: RSRP for at least one cell, coverage area for at least one cell, channel response for at least one cell, device characteristics of the UE or each reference UE in the reference UE set, location of each reference UE in the reference UE set, or location uncertainty for the location of each reference UE in the reference UE set. In such a configuration, the channel response includes at least one of TA, RSRQ, RSSI, RSSNR and / or CQI. In another configuration, at least one ML model includes a first ML model and a second ML model, the first ML model is configured to infer a first set of weights for a first measurement set associated with at least one cell, and the second ML model is configured to infer a second set of weights for a second measurement set for each reference UE in the reference UE set. In such a configuration, the location estimation of the UE is based on fusing the output of the first ML model based on the first set of weights and the output of the second ML model based on the second set of weights.

[0145] In another configuration, the set of outputs from the ML model is fused based on a weighted sum associated with a reference UE set, at least one cell, at least one public cell, or a combination thereof. In such a configuration, the weighted sum is based on the number of reference UE sets, the number of cells reported by each reference UE in the reference UE set, the number of cells reported by the UE, the number of at least one public cell.

[0146] In another configuration, the ML model is capable of identifying at least one common cell between the UE and a reference set of UEs, and wherein an output of the ML model comprises a similarity score between the UE and the reference set of UEs. In such configurations, the at least one public cell is a single public cell, and wherein the ML model identifies the at least one public cell based on an ID of the single public cell, or the at least one public cell is a plurality of public cells, and wherein the ML model identifies the at least one public cell based on IDs of the plurality of public cells.

[0147] In another configuration, at least one cell for the UE is a serving cell or a non-serving cell across multiple frequency bands.

[0148] In another configuration, at least one public cell is associated with at least one characteristic, the at least one characteristic comprising one or more of: measurements for the at least one public cell, UE type, environmental conditions, cell characteristics associated with the at least one public cell, or a combination thereof.

[0149] The means may be the crowdsourcing positioning component 199 of the network entity 1102 configured to perform the functions recited by the means. As described above, the network entity 1102 may include the TX processor 316, the RX processor 370, and the controller / processor 375. Thus, in one configuration, the means may be the TX processor 316, the RX processor 370, and / or the controller / processor 375 configured to perform the functions recited by the means.

[0150] It is understood that the specific order or hierarchy of the blocks in the disclosed process / flowchart is an illustration of an exemplary method. Based on design preferences, it is understood that the specific order or hierarchy of the blocks in the process / flowchart can be rearranged. In addition, some blocks can be combined or omitted. The accompanying method claims provide the elements of the various blocks in a sample order and are not limited to the specific order or hierarchy provided.

[0151] The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects. Therefore, the claims are not limited to the aspects described herein, but conform to the full scope consistent with the language claims. Unless otherwise stated, reference to an element in the singular form does not mean "one and only one", but "one or more". Terms such as "if", "when ..." and "while" do not imply a direct temporal relationship or reaction. That is, these phrases (e.g., "when ...") do not mean immediate action in response to the occurrence of an action or during the occurrence of an action, but only mean that if the condition is met, then an action will occur, but the specific or immediate time constraint of the action occurrence is not required. The word "exemplary" is used herein to mean "used as an example, instance or illustration". Any aspect described herein as "exemplary" need not be interpreted as being preferred or advantageous over other aspects. Unless otherwise specifically stated, the term "some" refers to one or more. Combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, wherein any such combination may contain one or more members of A, B, or C. A set should be interpreted as a set of elements, wherein the number of elements is one or more. Thus, for a set of X, X will include one or more elements. If a first device receives data from or sends data to a second device, the data may be received / sent directly between the first device and the second device, or indirectly between the first device and the second device through a set of devices. All structural and functional equivalents of the elements of the various aspects described throughout the present disclosure, which are known or will be known later to those of ordinary skill in the art, are expressly incorporated herein by reference, and are covered by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly mentioned in the claims. Words such as "module", "mechanism", "element", "device" are not substitutes for the word "unit". Therefore, no claim element is to be interpreted as a unit plus function unless the phrase "unit for..." is explicitly used to record the element.

[0152] As used herein, the phrase "based on" should not be interpreted as a reference to a closed set of information, one or more conditions, one or more factors, etc. In other words, the phrase "based on A" (where "A" can be information, conditions, factors, etc.) should be interpreted as "based at least on A" unless specifically stated differently.

[0153] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein, but are not limited thereto.

[0154] Aspect 1 is a method of wireless communication at a network entity, comprising: receiving a first measurement set associated with at least one cell from a UE; and performing a position estimation of the UE via at least one machine learning (ML) model based on the first measurement set associated with the at least one cell, a second measurement set for each reference UE in a reference UE set, or at least one of the positions of each reference UE in the reference UE set, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying the at least one common cell between the UE and the reference UE set, and wherein an output of the at least one ML model includes a similarity score between the UE and the reference UE set.

[0155] Aspect 2 is a method according to aspect 1, wherein the position estimate for the UE is also based on the position of the at least one cell.

[0156] Aspect 3 is a method according to Aspect 1 or Aspect 2, wherein the first measurement set or the second measurement set includes at least one of the following items: RSRP for the at least one cell, coverage area for the at least one cell, channel response for the at least one cell, device characteristics of the UE or each reference UE in the reference UE set, the position of each reference UE in the reference UE set, or position uncertainty for the position of each reference UE in the reference UE set.

[0157] Aspect 4 is a method according to aspect 3, wherein the channel response includes at least one of TA, RSRQ, RSSI, RSSNR and / or CQI.

[0158] Aspect 5 is a method according to any one of Aspects 1 to 4, wherein the set of outputs from the at least one ML model is fused based on a weighted sum associated with the reference UE set, the at least one cell, the at least one common cell, or a combination thereof.

[0159] Aspect 6 is a method according to aspect 5, wherein the weighted sum is based on the number of the reference UE set, the number of cells reported by each reference UE in the reference UE set, the number of cells reported by the UE, and the number of the at least one public cell.

[0160] Aspect 7 is a method according to any one of Aspects 1 to 6, further comprising: receiving an indication of criteria associated with the UE from the UE; and selecting the at least one ML model and a fusion type for the at least one ML model based on the indication for performing the position estimation of the UE.

[0161] Aspect 8 is a method according to any one of Aspects 1 to 7, wherein the at least one ML model includes a first ML model and a second ML model, the first ML model is configured to infer a first set of weights for the first measurement set associated with the at least one cell, and the second ML model is configured to infer a second set of weights for the second measurement set for each reference UE in the reference UE set.

[0162] Aspect 9 is a method according to aspect 8, wherein the position estimation of the UE is based on fusing the output of the first ML model based on the first set of weights and the second ML model based on the second set of weights.

[0163] Aspect 10 is a method according to any one of aspects 1 to 9, wherein the at least one public cell is a single public cell, and wherein the ML model identifies the at least one public cell based on an ID of the single public cell.

[0164] Aspect 11 is a method according to any one of aspects 1 to 10, wherein the at least one public cell is a plurality of public cells, and wherein the ML model identifies the at least one public cell based on IDs of the plurality of public cells.

[0165] Aspect 12 is a method according to any one of aspects 1 to 11, further comprising: training the at least one ML model using one or more measurements from the reference UE set for the at least one common cell.

[0166] Aspect 13 is a method according to any one of aspects 1 to 12, wherein the at least one cell for the UE is a serving cell or a non-serving cell across multiple frequency bands.

[0167] Aspect 14 is a method according to any one of aspects 1 to 13, further comprising: sending a configuration for the UE to configure the UE to measure the at least one cell; and receiving a first measurement set associated with the at least one cell in response to the configuration.

[0168] Aspect 15 is a method according to any one of Aspects 1 to 14, wherein the at least one public cell is associated with at least one feature, and the at least one feature includes one or more of the following: measurements for the at least one public cell, UE type, environmental conditions, cell characteristics associated with the at least one public cell, or a combination thereof.

[0169] Aspect 16 is an apparatus for wireless communication at a first UE, comprising: a memory; and at least one processor coupled to the memory, and based at least in part on information stored in the memory, the at least one processor is configured to implement any of Aspects 1 to 15.

[0170] Aspect 17 is an apparatus according to aspect 16, further comprising at least one of a transceiver or an antenna coupled to the at least one processor, wherein the at least one processor is configured to receive the first measurement set via at least one of the transceiver or the antenna.

[0171] Aspect 18 is an apparatus for wireless communication, comprising means for implementing any one of aspects 1 to 15.

[0172] Aspect 19 is a computer-readable medium (eg, non-transitory computer-readable medium) storing computer-executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 1 to 15.

Claims

1. An apparatus for wireless communication at a network entity, comprising: Memory; at least one processor coupled to the memory and based at least in part on information stored in the memory, the at least one processor being configured to: receiving, from a user equipment (UE), a first measurement set associated with at least one cell; and Performing a position estimation of the UE based on at least one of the first measurement set associated with the at least one cell, a second measurement set for each reference UE in a reference UE set, or a position of each reference UE in the reference UE set via at least one machine learning (ML) model, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying the at least one common cell between the UE and the reference UE set, and wherein an output of the at least one ML model includes a similarity score between the UE and the reference UE set.

2. The device according to claim 1, wherein: The position estimate for the UE is also based on the location of the at least one cell.

3. The device according to claim 1, wherein: The first measurement set or the second measurement set includes at least one of the following: a reference signal received power (RSRP) for the at least one cell, For the coverage area of ​​the at least one cell, a channel response for the at least one cell, equipment characteristics of the UE or each reference UE in the set of reference UEs, The position of each reference UE in the reference UE set, or A position uncertainty for the position of each reference UE in the set of reference UEs.

4. The device according to claim 3, wherein: The channel response includes at least one of the following: timing advance (TA), reference signal received quality (RSRQ), received signal strength indicator (RSSI), reference signal signal to noise ratio (RSSNR), or channel quality indicator (CQI).

5. The device according to claim 1, wherein: The set of outputs from the at least one ML model is fused based on a weighted sum associated with the reference UE set, the at least one cell, the at least one common cell, or a combination thereof.

6. The device according to claim 5, wherein: The weighted sum is based on the number of the reference UE set, the number of cells reported by each reference UE in the reference UE set, the number of cells reported by the UE, and the number of the at least one common cell.

7. The device according to claim 1, wherein: The at least one processor is further configured to: receiving, from the UE, an indication of a criterion associated with the UE; and The at least one ML model and a fusion type for the at least one ML model are selected based on the indication for use in performing the position estimation for the UE.

8. The device according to claim 1, wherein: The at least one ML model includes a first ML model and a second ML model, the first ML model is configured to infer a first set of weights for the first measurement set associated with the at least one cell, and the second ML model is configured to infer a second set of weights for the second measurement set for each reference UE in the set of reference UEs.

9. The device according to claim 8, wherein: The position estimate for the UE is based on fusing the output of the first ML model based on the first set of weights and the second ML model based on the second set of weights.

10. The device according to claim 1, wherein: The at least one public cell is a single public cell, and wherein the ML model identifies the at least one public cell based on an identifier (ID) of the single public cell.

11. The device according to claim 1, wherein: The at least one public cell is a plurality of public cells, and wherein the ML model identifies the at least one public cell based on identifiers (IDs) of the plurality of public cells.

12. The device according to claim 1, wherein: The at least one processor is further configured to: The at least one ML model is trained using one or more measurements from the reference UE set for the at least one common cell.

13. The device according to claim 1, wherein: The at least one cell for the UE is a serving cell or a non-serving cell across multiple frequency bands.

14. The device according to claim 1, wherein: The at least one processor is further configured to: sending a configuration for the UE to configure the UE to measure the at least one cell; and The first measurement set associated with the at least one cell is received in response to the configuration.

15. The device according to claim 1, wherein: The at least one common cell is associated with at least one characteristic, the at least one characteristic comprising one or more of the following: measurements on the at least one public cell, UE type, Environmental conditions, a cell characteristic associated with the at least one public cell, or Its combination.

16. The apparatus of claim 1, further comprising at least one of a transceiver or an antenna coupled to the at least one processor, wherein: The at least one processor is configured to receive the first measurement set via at least one of the transceiver or the antenna.

17. A method of wireless communication at a network entity, comprising: receiving, from a user equipment (UE), a first measurement set associated with at least one cell; as well as Performing a position estimation of the UE based on at least one of the first measurement set associated with the at least one cell, a second measurement set for each reference UE in a reference UE set, or a position of each reference UE in the reference UE set via at least one machine learning (ML) model, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying the at least one common cell between the UE and the reference UE set, and wherein an output of the at least one ML model includes a similarity score between the UE and the reference UE set.

18. The method according to claim 17, wherein: The position estimate for the UE is also based on the position of the at least one cell.

19. The method according to claim 17, wherein: The first measurement set or the second measurement set includes at least one of the following: a reference signal received power (RSRP) for the at least one cell, For the coverage area of ​​the at least one cell, a channel response for the at least one cell, equipment characteristics of the UE or each reference UE in the set of reference UEs, The position of each reference UE in the reference UE set, or A position uncertainty for the position of each reference UE in the set of reference UEs.

20. The method according to claim 19, wherein: The channel response includes at least one of the following: timing advance (TA), reference signal received quality (RSRQ), received signal strength indicator (RSSI), reference signal signal to noise ratio (RSSNR), or channel quality indicator (CQI).

21. The method according to claim 17, wherein: The set of outputs from the at least one ML model is fused based on a weighted sum associated with the reference set of UEs, the at least one cell, the at least one common cell, or a combination thereof.

22. The method according to claim 21, wherein: The weighted sum is based on the number of the reference UE set, the number of cells reported by each reference UE in the reference UE set, the number of cells reported by the UE, and the number of the at least one common cell.

23. The method of claim 17, further comprising: receiving, from the UE, an indication of a criterion associated with the UE; as well as The at least one ML model and a fusion type for the at least one ML model are selected based on the indication for use in performing position estimation for the UE.

24. The method of claim 17, wherein: The at least one ML model includes a first ML model and a second ML model, the first ML model is configured to infer a first set of weights for the first measurement set associated with the at least one cell, and the second ML model is configured to infer a second set of weights for the second measurement set for each reference UE in the set of reference UEs.

25. The method according to claim 24, wherein: The position estimation for the UE is based on fusing the output of the first ML model based on the first set of weights and the second ML model based on the second set of weights.

26. The method according to claim 25, wherein: The at least one public cell is a single public cell or a plurality of public cells, and wherein the at least one ML model identifies the at least one public cell based on an identifier (ID) of the single public cell or the plurality of public cells.

27. The method of claim 17, further comprising: The at least one ML model is trained using one or more measurements from the reference UE set for the at least one common cell.

28. The method of claim 17, further comprising: sending a configuration for the UE to configure the UE to measure the at least one cell; as well as The first measurement set associated with the at least one cell is received in response to the configuration.

29. An apparatus for wireless communication at a network entity, comprising: means for receiving, from a user equipment (UE), a first measurement set associated with at least one cell; as well as A unit for performing a position estimation of the UE based on at least one of the first measurement set associated with the at least one cell, a second measurement set for each reference UE in a reference UE set, or a position of each reference UE in the reference UE set via at least one machine learning (ML) model, wherein the UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying the at least one common cell between the UE and the reference UE set, and wherein an output of the at least one ML model includes a similarity score between the UE and the reference UE set.

30. A computer readable medium storing computer executable code at a network entity, the code, when executed by a processor, causes the processor to: receiving, from a user equipment (UE), a first measurement set associated with at least one cell; and performing, via at least one machine learning (ML) model, a position estimation of the UE based on at least one of the first measurement set associated with the at least one cell, a second measurement set for each reference UE in a set of reference UEs, or a position of each reference UE in the set of reference UEs, wherein The UE and the reference UE set include at least one common cell, wherein the at least one ML model is capable of identifying the at least one common cell between the UE and the reference UE set, and wherein an output of the at least one ML model includes a similarity score between the UE and the reference UE set.

Images