Machine Learning for Positioning

Abstract

Various aspects of the present disclosure relate to methods, apparatuses, and systems that support machine learning for positioning. For instance, implementations provide for direct Artificial Intelligence (Al)-based positioning and Al-assisted positioning which can be leveraged to improve User Equipment (UE) location accuracy performance. In example implementations, for direct AI / Machine Learning (ML) positioning, techniques such as fingerprinting can be leveraged by AI / ML models to obtain enhanced location accuracies, such as via measurement and environmental data. Accordingly, the present disclosure provides techniques to configure direct AI / ML positioning assistance data as well as define measurements to perform AI / ML direct positioning. Further, the present disclosure provides techniques to configure reporting criteria for nodes and / or other entities performing AI / ML direct positioning measurements.

Description

1 / 125 Machine Learning for Positioning RELATED ORDERS

[001] This application claims priority over U.S. Provisional Application Serial No. 63 / 484,102, filed February 9, 2023, entitled “MACHINE LEARNING FOR POSITIONING”, and U.S. Provisional Application Serial No. 63 / 444,469, filed February 9, 2023, entitled “MACHINE LEARNING FOR POSITIONING”, the disclosures of which are incorporated herein by reference in their entirety. TECHNICAL FIELD

[002] This disclosure relates to wireless communications and, more specifically, to position determination in wireless communications. BACKGROUND

[003] A wireless communications system may include one or multiple network communication devices, such as base stations, which may also be known as eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. Each network communication device, such as a base station, may support wireless communications to one or multiple user communication devices, which may be known as user equipment (UE) or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices using wireless communication system features (e.g., timing features (e.g., symbols, slots, subframes, frames, or the like) or frequency features (e.g., subcarriers, carriers).In addition, the wireless communications system can support wireless communications through various radio access technologies, including third-generation (3G) radio access technology, fourth-generation (4G) radio access technology, fifth-generation (5G) radio access technology, among others. Petition 870260069606, dated 07 / 14 / 2026, page 7 / 134 2 / 125 suitable radio access technologies in addition to 5G (e.g., sixth generation (6G)).

[004] Some wireless communication systems provide ways to determine the position of a device (e.g., UE), such as the geographic position of a UE. However, current implementations for UE positioning may be inaccurate. SUMMARY

[005] This disclosure relates to methods, devices, and systems that support machine learning for positioning. For example, the implementations provide direct AI / ML-based positioning and AI / ML-assisted positioning, which can be leveraged to improve EU location accuracy performance. In example implementations, for direct AI / ML positioning, techniques such as fingerprinting can be leveraged by AI / ML models to achieve enhanced location accuracies, such as through environmental and measurement data. Consequently, this disclosure provides techniques for configuring direct AI / ML positioning assistance data, as well as defining measurements to perform direct AI / ML positioning. Furthermore, this disclosure provides techniques for configuring reporting criteria for us and / or other entities that perform direct AI / ML positioning measurements.

[006] Thus, by using the techniques described, a more precise positioning of the UEs can be obtained and the use of system resources to determine the UE position can be reduced.

[007] Some implementations of the methods and devices described herein may additionally include transmitting one or more machine learning positioning report requests including a machine learning report configuration. Petition 870260069606, dated 07 / 14 / 2026, page 8 / 134 3 / 125 of machine and one or more common reporting criteria; receive one or more machine learning positioning reports; process one or more machine learning positioning reports using a machine learning model; and generate, based at least in part on the output of the machine learning model, an estimated location of a user device (UD).

[008] Some implementations of the methods and devices described herein may additionally include: where the machine learning reporting configuration includes one or more direct machine learning reporting configurations or assisted machine learning reporting configurations; where the method is performed by a device including a configuration entity, and where the configuration entity includes at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE;including additionally transmitting one or more machine learning positioning report requests from a first device to one or more second devices, and receiving one or more machine learning positioning reports from the one or more second devices, and where the one or more second devices include at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE or a target UE.

[009] Some implementations of the methods and devices described herein may additionally include: where one or more common reporting criteria include one or more types of fingerprint, a type of true-field reference location, a time-domain reporting type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, Petition 870260069606, dated 07 / 14 / 2026, page 9 / 134 4 / 125 an indication of digital printing environment, an indication of digital printing quality, or an indication of label quality; wherein for at least one machine learning positioning report request, one or more common reporting criteria are configured to be one or more of the following: increased, removed, updated, enabled, or disabled; including additionally broadcasting one or more common reporting criteria via positioning system information broadcast signaling; wherein the machine learning reporting configuration includes an indication to report machine learning positioning measurement correlation between different sets of measurements.

[010] Some implementations of the methods and devices described herein may additionally include: where the machine learning positioning measurement correlation includes one or more spatial domain correlations or temporal domain correlations; where one or more machine learning positioning reports include one or more machine learning positioning measurements or machine learning positioning location information; where the machine learning report configuration includes an indication to report path loss at different locations, including a true-field reference location; where the machine learning report configuration includes an indication to average the machine learning positioning measurements across a configured number of measurements and report the average as part of one or more machine learning positioning reports;where the machine learning report configuration includes an indication to determine a similarity score in a location configured to determine one; Petition 870260069606, dated 07 / 14 / 2026, page 10 / 134 5 / 125 ideal mapping between a fingerprint measurement and an estimated location of a target UE.

[011] Some implementations of the methods and devices described herein may additionally include receiving one or more requests for machine learning positioning reports, including a machine learning reporting configuration and one or more common reporting criteria; generating one or more machine learning positioning reports based, at least in part, on the machine learning reporting configuration and one or more common reporting criteria; and transmitting one or more machine learning positioning reports.

[012] Some implementations of the methods and devices described herein may additionally include: where the method is performed by a device including one or more of a user equipment (UE), an anchor UE or a target UE; where the method is performed by a device including a configuration entity, and where the configuration entity includes at least one of a location server, a next-generation radio access network (NG-RAN) or a positioning reference unit (PRU).

[013] Some implementations of the methods and devices described herein may additionally include transmitting one or more machine learning positioning report requests, including a machine learning reporting configuration and one or more common reporting criteria; receiving one or more machine learning positioning reports; generating, based at least in part on one or more machine learning positioning reports, a machine learning positioning training dataset; and training a positioning machine learning model using the machine learning positioning training dataset. Petition 870260069606, dated 07 / 14 / 2026, page 11 / 134 6 / 125 to generate a trained positioning machine learning model.

[014] Some implementations of the methods and devices described herein may additionally include receiving one or more additional machine learning positioning reports; inserting at least a portion of one or more additional machine learning positioning reports into the trained positioning machine learning model; and estimating a position of a target user equipment (UE) based at least in part on the output of the trained positioning machine learning model; including additionally: receiving a request for machine learning positioning training data for positioning; and transmitting, based at least in part on the request, the machine learning positioning training dataset; including additionally: receiving a request for a trained positioning machine learning model;and transmit, based at least in part on the request, at least a portion of the trained positioning machine learning model. BRIEF DESCRIPTION OF THE DRAWINGS

[015] FIG. 1 illustrates an example of a wireless communications system that supports machine learning for positioning in accordance with aspects of the present disclosure.

[016] FIG. 2 illustrates a system in which positioning reference signals can be used to obtain positioning measurements.

[017] FIG. 3 illustrates a scenario for multicellular RTT placement.

[018] FIGS. 4a and 4b illustrate portions of an LPP message. RequestLocationInformation.

[019] FIGS. 5a and 5b illustrate portions of an LPP message. ProvideLocationInformation. Petition 870260069606, dated 07 / 14 / 2026, page 12 / 134 7 / 125

[020] FIG. 6 illustrates a system for RAN intelligence based on machine learning.

[021] FIG. 7 illustrates an example scenario that supports machine learning for positioning in accordance with aspects of this disclosure.

[022] FIG. 8 illustrates an example scenario that supports machine learning for positioning in accordance with aspects of the present disclosure.

[023] FIG. 9 illustrates a message that supports machine learning for positioning in accordance with aspects of the present disclosure.

[024] FIGS. 10a and 10b illustrate different parts of a message that supports machine learning for positioning in accordance with aspects of the present disclosure.

[025] FIG. 11 illustrates a message that supports machine learning for positioning in accordance with aspects of the present disclosure.

[026] FIG. 12 illustrates a message that supports machine learning for positioning in accordance with aspects of the present disclosure.

[027] FIG. 13 illustrates scenarios that support machine learning for positioning according to aspects of this disclosure.

[028] FIGS. 14a and 14b illustrate scenarios that support machine learning for positioning according to aspects of this disclosure.

[029] FIG. 15 illustrates a scenario that supports machine learning for positioning according to aspects of the present disclosure.

[030] FIG. 16 illustrates a scenario that supports machine learning for positioning according to aspects of the present disclosure. Petition 870260069606, dated 07 / 14 / 2026, page 13 / 134 8 / 125

[031] FIG. 17 illustrates a scenario that supports machine learning for positioning in accordance with aspects of this disclosure.

[032] FIGS. 18 and 19 illustrate example block diagrams of devices that support machine learning for positioning according to aspects of the present disclosure.

[033] FIGS. 20 to 25 illustrate flowcharts of methods that support machine learning for positioning in accordance with aspects of this disclosure. DETAILED DESCRIPTION

[034] In wireless communication systems, techniques are used to estimate a position (e.g., location) of a UE, such as a geographic position of the UE and / or a relative network location of the UE. For example, some systems use beam-based attempts to estimate the UE location, such as in commercial and regulatory scenarios (e.g., emergency). However, current position determination techniques can be inaccurate and result in inaccurate indications of the UE location.

[035] Consequently, this disclosure provides techniques that support machine learning for positioning. For example, the implementations provide AI-based direct positioning and AI-assisted positioning, which can be leveraged to improve UE location accuracy performance, such as within a 3GPP-defined positioning framework. For example, for direct AI / ML positioning, techniques such as fingerprinting can be leveraged by AI / ML models to achieve enhanced location accuracies, such as through environmental and measurement data. Consequently, this disclosure provides techniques for setting up direct AI / ML positioning assistance data, as well as defining measurements to perform direct AI / ML positioning. Furthermore, this disclosure provides Petition 870260069606, dated 07 / 14 / 2026, page 14 / 134 9 / 125 techniques for setting up reporting criteria for us and / or other entities that perform direct AI / ML positioning measurements.

[036] Thus, by using the techniques described, a more precise positioning of the UEs can be obtained by taking advantage of large amounts of radio data and other related data, and the use of system resources to determine the UE position can be reduced.

[037] Aspects of this disclosure are described in the context of a wireless communications system. Aspects of this disclosure are further illustrated and described with reference to device diagrams and flowcharts.

[038] FIG. 1 illustrates an example of a wireless communications system 100 that supports machine learning for positioning according to aspects of the present disclosure. The wireless communications system 100 may include one or more network entities 102, one or more UEs 104, a core network 106, and a packet data network 108. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a 5G network, such as an NR network. In other implementations, the 100 wireless communications system may be a combination of a 4G network and a 5G network, or other suitable radio access technology, including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20.The 100 wireless communications system can support radio access technologies in addition to 5G. Furthermore, the 100 wireless communications system can support technologies such as Time Division Multiple Access (TDMA) and Time Division Multiple Access. Petition 870260069606, dated 07 / 14 / 2026, page 15 / 134 10 / 125 frequency (FDMA) or code division multiple access (CDMA), etc.

[039] One or more network entities 102 may be dispersed over a geographical region to form the wireless communications system 100. One or more of the network entities 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a radio access network (RAN), a base transceiver station, an access point, a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. A network entity 102 and a UE 104 may communicate via a communication link 110, which may be a wireless or wired connection. For example, a network entity 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) via a Uu interface.

[040] A network entity 102 may provide a geographic coverage area 112 for which the network entity 102 may support services (e.g., voice, video, packet data, messaging, broadcast, etc.) for one or more UEs 104 within the geographic coverage area 112. For example, a network entity 102 and a UE 104 may support wireless communication of service-related signals (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or more radio access technologies. In some implementations, a network entity 102 may be mobile, for example, a satellite associated with a non-terrestrial network. In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas 112 may be associated with different network entities 102.The information and signals described here can be represented using any of a variety of different technologies and techniques. For example, data, instructions, etc. Petition 870260069606, dated 07 / 14 / 2026, page 16 / 134 11 / 125 commands, information, signals, bits, symbols, and chips that may be referenced throughout the description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[041] One or more UEs 104 may be dispersed across a geographic region of the wireless communications system 100. A UE 104 may include or be referred to as a mobile device, a wireless device, a remote device, a remote unit, a handheld device, or a subscriber device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine-type communication (MTC) device, among other examples. In some implementations, a UE 104 may be stationary in the wireless communications system 100. In some other implementations, a UE 104 may be mobile in the wireless communications system 100.

[042] One or more UEs 104 may be devices of different forms or have different capabilities. Some examples of UEs 104 are illustrated in FIG. 1. A UE 104 may be able to communicate with various types of devices, such as network entities 102, other UEs 104, or network equipment (e.g., the core network 106, the packet data network 108, a relay device, an integrated access and backhaul (IAB) node, or other network equipment), as shown in Figure 1. Additionally, or alternatively, a UE 104 may support communication with other network entities 102 or UEs 104, which may act as relays in the wireless communication system 100. Petition 870260069606, dated 07 / 14 / 2026, page 17 / 134 12 / 125

[043] A UE 104 may also be able to support wireless communication directly with other UEs 104 via a communication link 114. For example, a UE 104 may support wireless communication directly with another UE 104 via a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, V2X deployments, or V2X cellular deployments, the communication link 114 may be referred to as a side link. For example, a UE 104 may support wireless communication directly with another UE 104 via a PC5 interface.

[044] A network entity 102 can support communications with the core network 106, or with another network entity 102, or both. For example, a network entity 102 can interact with the core network 106 through one or more backhaul links. 116 (for example, through an S1, N2, N2 interface or other network). Network entities 102 can communicate with each other through backhaul links 116 (for example, through an X2, Xn interface or other network). In some implementations, network entities 102 can communicate with each other directly (for example, between network entities 102). In some other implementations, network entities 102 can communicate with each other indirectly (for example, through the core network 106). In some implementations, one or more network entities 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC can communicate with one or more UEs 104 through one or more other access network transmission entities, which may be called radio heads, smart radio heads, or transmit-receive points (TRPs).

[045] In some implementations, a 102 network entity can be configured in a disaggregated architecture, which can be configured to use a protocol stack distributed physically or logically between two or more entities. Petition 870260069606, dated 07 / 14 / 2026, page 18 / 134 13 / 125 network 102, such as an Integrated Access Backhaul (IAB) network, an Open RAN (O-RAN) (e.g., an O-RAN Alliance-sponsored network configuration), or a Virtualized RAN (vRAN) (e.g., a Cloud RAN (C-RAN)). For example, a 102 network entity may include one or more central units (CU), a distributed unit (DU), a radio unit (RU), an Intelligent RAN Controller (RIC) (e.g., a Near Real-Time RIC (RT RIC)), a Time RIC Not Real (RIC Not in RT)), a Service Management and Orchestration (SMO) system, or any combination thereof.

[046] A RU may also be called a radio head, intelligent radio head, remote radio head (RRH), remote radio unit (RRU), or transmit and receive point (TRP). One or more components of the 102 network entities in a disaggregated RAN architecture may be colocated, or one or more components of the 102 network entities may be located in distributed locations (e.g., separate physical locations). In some implementations, one or more network entities 102 of a disaggregated RAN architecture can be implemented as virtual units (for example, a virtual CU (VCU), a virtual DU (VDU), a virtual RU (VRU)).

[047] The division of functionality between a CU, a DU, and a RU can be flexible and can support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, radio frequency functions, and any combinations thereof) are performed in a CU, a DU, or an RU. For example, a functional division of a protocol stack can be employed between a CU and a DU so that the CU can support one or more layers of the protocol stack and the DU can support one or more different layers of the protocol stack. In some implementations, the CU can host higher protocol layer functionality and signaling (e.g., a layer 3 (L3), Petition 870260069606, dated 07 / 14 / 2026, p. 19 / 134 14 / 125 a layer 2 (L2)) (e.g., Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), Packet Data Convergence Protocol (PDCP)). The CU can be connected to one or more DUs or RUs, and one or more DUs or RUs can host lower protocol layers, such as a layer 1 (L1) (e.g., physical layer (PHY)) or an L2 (e.g., radio link control layer (RLC), medium access control layer (MAC)) functionality and signaling, and each can be at least partially controlled by the CU.

[048] Additionally, or alternatively, a functional split of the protocol stack can be employed between a DU and a RU so that the DU can support one or more layers of the protocol stack and the RU can support one or more different layers of the protocol stack. The DU can support one or multiple different cells (for example, through one or more RUs). In some implementations, a functional split between a CU and a DU, or between a DU and an RU, can be within a protocol layer (for example, some functions for a protocol layer can be performed by one of a CU, a DU, or an RU, while other protocol layer functions are performed by a different CU, DU, or RU).

[049] A CU can be further functionally divided into CU control plane (CU-CP) and CU user plane (CU-UP) functions. A CU can be connected to one or more DUs via a midhaul communication link (e.g., F1, F1-c, F1-u), and a DU can be connected to one or more RUs via a fronthaul communication link (e.g., open fronthaul interface (FH)). In some implementations, a midhaul communication link or a fronthaul communication link can be implemented according to an interface (e.g., a channel) between layers of a protocol stack supported by respective network entities 102 that are communicating via such communication links. Petition 870260069606, dated 07 / 14 / 2026, p. 20 / 134 15 / 125

[050] The 106 core network can support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The 106 core network can be an evolved packet core (EPC) or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), mobility and access management functions (AMF)) and a user plane entity that routes packets or interconnects external networks (e.g., a service gateway (S-GW), a location management function (LMF), which is a control plane entity that manages location-related services, a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)).In some implementations, the control plane entity may manage non-access stratum (NAS) functions such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for one or more UEs 104 served by one or more network entities 102 associated with the core network 106.

[051] The core network 106 can communicate with the packet data network 108 through one or more backhaul links 116 (for example, through an S1, N2, N2 interface or other network). The packet data network 108 may include an application server 118. In some implementations, one or more UEs 104 can communicate with the application server 118. A UE 104 can establish a session (for example, a PDU session or similar) with the core network 106 through a network entity 102. The core network 106 can route traffic (for example, control information, data and the like) between the UE 104 and the application server 118 using the established session (for example, the established PDU session). The PDU session can be an example of a logical connection between the UE 104 and the network. Petition 870260069606, dated 07 / 14 / 2026, page 21 / 134 16 / 125 core 106 (for example, one or more network functions of the core 106 network).

[052] In the wireless communication system 100, network entities 102 and UEs 104 can use resources of the wireless communication system 100 (e.g., timing resources (e.g., symbols, slots, subframes, frames, or similar) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, network entities 102 and Network entities (UEs) 104 can support different resource structures. For example, network entities 102 and UEs 104 can support different frame structures. In some implementations, such as 4G, network entities 102 and UEs 104 may support a single frame structure. In some other implementations, such as 5G and other suitable radio access technologies, network entities 102 and UEs 104 may support multiple frame structures (e.g., multiple frame structures). Network entities 102 and UEs 104 can support multiple frame structures based on one or more numerologies.

[053] One or more numerologies may be supported in the 100 wireless communications system, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., μ=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. The first numerology (e.g., μ=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., μ=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., μ=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or a prefix Petition 870260069606, dated 07 / 14 / 2026, page 22 / 134 17 / 125 extended cyclic. A fourth numerology (e.g., μ=3) can be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., μ=4) can be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[054] A time interval of a resource (for example, a communication resource) can be organized according to frames (also called radio frames). Each frame can have a duration, for example, a duration of 10 milliseconds (ms). In some implementations, each frame can include multiple subframes. For example, each frame can include 10 subframes, and each subframe can have a duration, for example, a duration of 1 ms. In some implementations, each frame can have the same duration. In some implementations, each subframe of a frame can have the same duration.

[055] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) can be organized according to slots. For example, a subframe might include a number (e.g., quantity) of slots. Each slot might include a number (e.g., quantity) of symbols (e.g., orthogonal frequency division multiplexing (OFDM) symbols). In some implementations, the number (e.g., quantity) of slots for a subframe might depend on a numerology. For a normal cyclic prefix, a slot might include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot might include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix might depend on a numerology.It should be understood that the reference to a first numerology (e.g., μ=0) is associated with a first subcarrier spacing. Petition 870260069606, dated 07 / 14 / 2026, p. 23 / 134 18 / 125 (e.g., 15 kHz) can be used interchangeably between subframes and slots.

[056] In the 100 wireless communications system, an electromagnetic (EM) spectrum can be divided, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the 100 wireless communications system can support one or multiple operating frequency bands, such as frequency band designations FR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz) and FR5 (114.25 GHz - 300 GHz). In some implementations, network entities 102 and UEs 104 can perform wireless communications in one or more of the operating frequency bands. In some implementations, FR1 can be used by network entities 102 and UEs 104, among other equipment or devices, for cellular communications traffic (e.g., control information, data).In some implementations, FR2 can be used by network entities 102 and UEs 104, among other equipment or devices for short-range, high-data-rate capabilities.

[057] FR1 can be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 can be associated with a first numerology (e.g., μ=0), which includes a subcarrier spacing of 15 kHz; a second numerology (e.g., μ=1), which includes a subcarrier spacing of 30 kHz; and a third numerology (e.g., μ=2), which includes a subcarrier spacing of 60 kHz. FR2 can be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 can be associated with a third numerology (e.g., μ=2), which includes a subcarrier spacing of 60 kHz; and a fourth numerology (e.g., μ=3), which includes a subcarrier spacing of 120 kHz. Petition 870260069606, dated 07 / 14 / 2026, p. 24 / 134 19 / 125

[058] According to machine learning implementations for positioning, a network entity 102 transmits an ML positioning configuration to a UE 104. The ML positioning configuration 120, for example, includes various information and / or parameters so that UE 104 measures various positioning information, generates positioning measurements, and / or processes positioning measurements. Thus, based at least in part on the ML positioning configuration 120, UE 104 performs ML positioning measurements 122, in order to measure and process various attributes of the wireless signal detected in UE 104. UE 104 generates an ML positioning response 124 based at least in part on the ML positioning measurements 122 and / or the ML positioning configuration 120 and transmits the ML positioning response to network entity 102.In implementations, the ML 124 positioning response may include an estimated position (e.g., location) of UE 104, and / or network entity 102 may use ML techniques to process the ML positioning response to estimate a position of UE 104.

[059] In some wireless communication systems, NR positioning based on Uu NR signals and autonomous architecture (SA) (e.g., beam-based transmissions) are specified. Target use cases include commercial and regulatory (emergency services) scenarios. Performance parameters include the following [Technical Report (TR) 38.855]: Table 1 Positioning Error Indoor Outdoor Horizontal positioning < 3m for 80% of UEs < 10m for 80% of UEs Vertical positioning < 3m for 80% of UEs < 3m for 80% of UEs

[060] In addition, some systems specify positioning performance parameters for commercial and IIoT use cases as follows [TR 38.857]: Table 2 Commercial IloT Positioning Error (< 1 m) for 90% of horizontal UEs (< 0.2 m) for 90% of UEs; Petition 870260069606, dated 07 / 14 / 2026, page 25 / 134 20 / 125 Vertical positioning (< 3 m) for 90% of UEs (< 1 m) for 90% of UEs Physical layer latency for UE position estimation (<10 ms) (<10 ms) End-to-end latency for UE position estimation (<100 ms) (< 100 ms, on the order of 10 ms is desired)

[061] At least some of the supported positioning techniques are listed in Table 3 [TS38.305]: Table 3 EU-Based Method EU-Assisted, LMF-Based NG-RAN Node Assisted SUPL A-GNSS Yes Yes No Yes (EU-based and EU-assisted) OTDOA Note 1, Note 2 No Yes No Yes (EU-assisted) E-CID Note 4 No Yes Yes Yes for EU-UTRA (EU-assisted) Sensor Yes Yes No No WLAN Yes Yes No Yes Bluetooth No Yes No No TBS Note 5 Yes Yes No Yes (MBS) DL-TDOA Yes Yes No No DL-AoD Yes Yes No No Multi-RTT No Yes Yes No NR E-CID No Yes FFS No UL-TDOA No No Yes No UL-AoA No No Yes No NOTE 1: This includes Terrestrial Beacon System (TBS) positioning based on PRS signals. NOTE 2: In this version of the specification, only LTE-based OTDOA is supported. NOTE 3: Empty. NOTE 4: This includes the Cell-ID for the NR method. NOTE 5: This version of the specification is only for TBS positioning based on Metropolitan Beacon System (MBS) signals. NOTE 6: Empty

[062] Separate positioning techniques, as indicated in Table 3, can currently be configured and implemented based on the requirements of LMF and UE capabilities. The transmission of Positioning Reference Signals (PRS) allows the UE to perform UE positioning-related measurements to enable the calculation of a UE location estimate and are configured by Transmission and Reception Point (TRP), where a TRP can transmit one or more beams. Petition 870260069606, dated 07 / 14 / 2026, page 26 / 134 21 / 125

[063] FIG. 2 illustrates a 200 system in which positioning reference signals can be used to obtain positioning measurements. For example, the PRS can be transmitted by different base stations (service and neighboring) using narrow beams in FR1 and FR2, which is relatively different when compared to LTE, where the PRS was transmitted throughout the cell. The PRS can be locally associated with a PRS Resource Identifier (ID) and a Resource Set ID for a base station (TRP). Similarly, UE positioning measurements, such as Reference Signal Time Difference (RSTD) and PRS RSRP measurements, are made between beams (e.g., between a different pair of downlink (DL) PRS resources or DL ​​PRS resource sets) as opposed to different cells, as was the case in LTE. Furthermore, there are additional UL positioning methods for the network to explore in order to calculate the target UE location.

[064] Table 4 and Table 5 show the reference signal for the measurement mapping required for each of the RAT-dependent positioning techniques supported on UE and gNB, respectively. RAT-dependent positioning techniques involve the 3GPP RAT and core network entities to perform UE position estimation, which are differentiated from RAT-independent positioning techniques that rely on GNSS, Inertial Measurement Unit (IMU) sensor, WLAN, and Bluetooth technologies to perform target device (UE) positioning. Table 4: UE measurements to enable RAT-dependent positioning techniques DL / UL Reference Signals UE Measurements To facilitate support for the following positioning techniques DL PRS Release 16 DL RSTD DL-TDOA DL PRS Release 16 DL PRS RSRP DL-TDOA, DL-AoD, Multi-RTT DL PRS Release 16 / SRS Release 16 for UE Time Difference Rx-Tx Multi-RTT positioning Petition 870260069606, dated 07 / 14 / 2026, p. 27 / 134 22 / 125 Release 15 SSB / CSIRS for Radio Resource Management (RRM) SS-RSRP (RSRP for RRM), SS-RSRQ (for RRM), CSI-RSRP (for RRM), CSI-RSRQ (for RRM), SS-RSRP (for RRM) E-CID Table 5: gNB measurements to enable RAT-dependent positioning techniques Reference Signals for DL / UL gNB Measurements To facilitate support for the following positioning techniques: SRS Release 16 for UL positioning RTOA UL-TDOA SRS Release 16 for UL positioning SRS-RSRP UL-TDOA, UL-AoA, Multi-RTT SRS Release 16 for DL ​​positioning PRS Release 16 gNB Time Difference RxTx Multi-RTT SRS Release 16 for AoA and ZoA positioning UL-AoA, Multi-RTT

[065] The following RAT-dependent positioning techniques can be supported [TS38. 305]:

[066] Downlink Time Difference of Arrival (DL-TDOA) positioning methods use the DL Reference Signal Time Difference (RSTD) (and optionally the DL Reference Signal Received Power PRS (RSRP)) of downlink signals received from multiple TPs, in the UE. The UE measures the DL RSTD (and optionally DL PRS RSRP) of the received signals using assistance data received from the positioning server, and the resulting measurements are used along with other configuration information to locate the UE relative to neighboring TPs.

[067] DL AoD positioning methods utilize the DL PRS RSRP measured from downlink signals received from multiple TPs, in the UE. The UE measures the DL PRS RSRP of the received signals using assistance data received from the positioning server, and the resulting measurements are used along with other configuration information to locate the UE relative to neighboring TPs.

[068] FIG. 3 illustrates a 300 scenario for multi-cell round-trip time (RTT) positioning. The methods of Petition 870260069606, dated 07 / 14 / 2026, page 28 / 134 23 / 125 Multi-Round Time of Travel (RTT) positioning uses UE Rx-Tx and DL PRS RSRP measurements of downlink signals received from multiple TRPs, measured by the UE, and gNB Rx-Tx and Uplink (UL) Sounding Reference Signal (SRS)-RSRP measurements on multiple TRPs of uplink signals transmitted from the UE. The UE measures the UE Rx-Tx measurements (and optionally DL PRS RSRP of the received signals) using assistance data received from the positioning server, and the TRPs measure the gNB Rx-Tx measurements (and optionally UL SRS-RSRP of the received signals) using assistance data received from the positioning server. The measurements are used to determine the RTT at the positioning server, which is used to estimate the UE's location.

[069] In an Enhanced Cell Identifier (E-CID) positioning method, the position of a UE is estimated with knowledge of its ng-eNB, gNB, and service cell and is based on LTE signals. Information about the ng-eNB, gNB, and service cell can be obtained by paging, logging, or other methods. E-CID NR positioning refers to techniques that use additional UE measurements and / or NR radio capabilities and other measurements to improve UE location estimation using NR signals. Although E-CID NR positioning may utilize some of the same measurements as the measurement control system in the RRC protocol, the UE is generally not expected to make additional measurements for the sole purpose of positioning; for example, positioning procedures do not provide a measurement configuration or measurement control message, and the UE reports the measurements it has available rather than being required to perform additional measurement actions.

[070] UL TDOA positioning methods use UL TDOA (and optionally UL SRS-RSRP) at multiple receiving points (RPs) of uplink signals transmitted to Petition 870260069606, dated 07 / 14 / 2026, p. 29 / 134 24 / 125 from the UE. The RPs measure the UL TDOA (and optionally UL SRSRSRP) of the received signals using assistance data received from the positioning server, and the resulting measurements are used along with other configuration information to estimate the UE's location.

[071] The UL AoA positioning method makes use of the measured azimuth and arrival zenith in multiple RPs of uplink signals transmitted from the UE. The RPs measure AAoA and Z-AoA of the received signals using assistance data received from the positioning server, and the resulting measurements are used along with other configuration information to estimate the UE's location.

[072] RAT-independent positioning techniques can also be implemented, including [TS38.305]:

[073] Network-Assisted Global Navigation Satellite System (GNSS) Methods: These methods make use of UEs equipped with radio receivers capable of receiving GNSS signals. In the 3GPP specifications, the term GNSS encompasses both global and regional / augmentation satellite navigation systems. Examples of global satellite navigation systems include the Global Positioning System (GPS), the Modernized GPS, Galileo, GLONASS, and the BeiDou Satellite Navigation System (BDS). Regional satellite navigation systems include the Near-Zenith Satellite System (QZSS), while some augmentation systems are classified under the generic term Space-Based Augmentation Systems (SBAS) and provide regional augmentation services. In this concept, different GNSSs (e.g., GPS, Galileo, etc.) can be used separately or in combination to determine the location of a UE.

[074] Barometric pressure sensor positioning: The barometric pressure sensor method uses barometric sensors to determine the vertical component of the UE's position. The UE measures the barometric pressure, optionally aided by Petition 870260069606, dated 07 / 14 / 2026, page 30 / 134 25 / 125 assistance data, to calculate the vertical component of its location or to send measurements to the positioning server for position calculation. This method can be combined with other positioning methods to determine the 3D position of the UE.

[075] Wireless Local Area Network (WLAN) Positioning: The WLAN positioning method uses WLAN measurements (access point (AP) identifiers and optionally other measurements) and databases to determine the UE's location. The UE measures signals received from WLAN access points, optionally aided by assist data, to send measurements to the positioning server for position calculation. Using the measurement results and a reference database, the UE's location is calculated. Alternatively, the UE uses WLAN measurements and optionally WLAN AP assist data provided by the positioning server to determine its location.

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

[077] TBS Positioning: A TBS consists of a network of terrestrial transmitters, broadcasting signals solely for positioning purposes. The current types of TBS positioning signals are MBS (Metropolitan Beacon System) and PRS (Technical Specification (TS) 36.211 [4]) signals. The The EU measures received TBS signals, optionally aided by assistance data, to calculate your location or to Petition 870260069606, dated 07 / 14 / 2026, page 31 / 134 26 / 125 send measurements to the positioning server for position calculation.

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

[079] FIGS. 4a and 4b illustrate portions of an LPP RequestLocationInformation 400 message. The RequestLocationInformation 400 message body in an LPP message can be used by the location server to request positioning measurements or a position estimate of the target device.

[080] FIGS. 5a and 5b illustrate portions of an LPP ProvideLocationInformation 500 message. The ProvideLocationInformation 500 message body in an LPP message can be used by the target device to provide positioning measurements or position estimates to the location server.

[081] For RAT-dependent positioning measurements, different DL measurements, including DL PRS-RSRP, DL RSTD, and UE Rx-Tx Difference Time, used for the supported RAT-dependent positioning techniques, are shown in Table 6 below. For example, the following measurement settings are specified [TS38.215]: • a) 4 pairs of DL RSTD measurements can be performed per cell pair. Each measurement is performed between a different pair of DL PRS Features / Feature Sets with a single reference timer. Petition 870260069606, dated 07 / 14 / 2026, page 32 / 134 27 / 125 • b) 8 DL PRS RSRP measurements can be performed on different DL PRS features of the same cell. Table 6: DL measurements required for DL-based positioning methods [TS38.215] Received DL PRS Reference Signal Power (DL PRS-RSRP) Definition Received DL PRS Reference Signal Power (DL PRS-RSRP) is defined as the linear average over the power contributions (in [W]) of the feature elements carrying DL PRS reference signals configured for RSRP measurements within the considered measurement frequency bandwidth. For frequency band 1, the reference point for DL ​​PRS-RSRP should be the UE antenna connector. For frequency band 2, DL PRS-RSRP should be measured based on the combined signal of antenna elements corresponding to a given receiver branch. For frequency bands 1 and 2, if receiver diversity is in use by the UE, the reported DL PRS-RSRP value should not be less than the corresponding DL PRS-RSRP of any of the individual receiver branches.Applicable to intra-frequency RRC_CONNECTED, inter-frequency RRC_CONNECTED DL Reference Signal Time Difference (DL RSTD) Definition The DL Reference Signal Time Difference (DL RSTD) is the relative DL timing difference between positioning node j and reference positioning node i, defined as TSubframeRxj — TSubframeRxi, where: TSubframeRxj is the time at which the UE receives the start of a subframe from positioning node j. TSubframeRxi is the time at which the UE receives the corresponding start of a subframe from the positioning node i that is closest in time to the subframe received from positioning node j. Multiple DL PRS features can be used to determine the start of a subframe from a positioning node. For frequency band 1, the reference point for the DL RSTD should be the UE antenna connector.For frequency band 2, the reference point for DL ​​RSTD should be the UE antenna. Applicable for intrafrequency RRC_CONNECTED and interfrequency RRC_CONNECTED. UE Rx - Tx Time Difference Definition: The UE Rx - Tx time difference is defined as TUE-RX - TUE-TX. Where: TUE-RX is the timing received by the UE of the downlink subframe #ia from a positioning node, defined by the first path detected in time. TUE-TX is the UE transmission timing of the uplink subframe #j that is closest in time to the subframe #i received from the positioning node. Multiple DL PRS features can be used to determine the start of a subframe from the first arrival path of the positioning node. For frequency band 1, the reference point for TUE-RX measurement should be the UE's Rx antenna connector, and the reference point for TUE-TX measurement should be the UE's Tx antenna connector.For frequency band 2, the reference point. Petition 870260069606, dated 07 / 14 / 2026, p. 33 / 134 28 / 125 For TUE-RX measurement, the reference point should be the UE antenna's Rx, and for TUE-TX measurement, the reference point should be the UE antenna's Tx. Applicable intra-frequency RRC CONNECTED to inter-frequency RRC CONNECTED DL PRS RSRPP (Reference Signal Received Path Power) Definition The DL PRS Reference Signal Received Path Power (DL PRS-RSRPP) is defined as the linear average power of the channel response at the i-th path delay of the feature elements carrying the DL PRS signal configured for measurement, where DL PRS-RSRPP for the 1st path delay is the power contribution corresponding to the first path detected in time. For frequency band 1, the reference point for DL ​​PRS-RSRPP should be the UE antenna connector. For frequency band 2, DL PRS-RSRPP should be measured based on the combined signal of antenna elements corresponding to a given receiver branch. Applicable to CONNECTED RRC, for INACTIVE RRC.

[082] FIG. 6 illustrates a 600 system for intelligence of RAN based on machine learning. In the 600 system, Data Collection is a function that provides input data for Model Training and Model Inference functions. AI / ML algorithm-specific data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) cannot be performed in the Data Collection function. Examples of input data might include measurements of UEs or different network entities, Actor feedback, and output from an AI / ML model. Training Data: Data required as input for the AI / ML model training function. Inference Data: Data required as input for the AI / ML Model Inference function.

[083] Model training is a function that performs ML model training, validation, and testing, which can generate model performance metrics as part of the model testing procedure. The Model Training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on Training Data provided by a Data Collection function. Petition 870260069606, dated 07 / 14 / 2026, page 34 / 134 29 / 125

[084] Model Deployment / Update: Used to initially deploy a trained, validated, and tested AI / ML model to the Model Inference function or to deliver an updated model to the Model Inference function.

[085] Model Inference is a function that provides AI / ML model inference output (e.g., predictions or decisions). The Model Inference function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on Inference Data delivered by a Data Collection function, if necessary.

[086] Output: The AI / ML model inference output produced by a model inference function.

[087] Model Performance Feedback: Applied if certain information derived from the Model Inference function is suitable for improving the AI / ML model trained in the Model Training function. Actor feedback or feedback from other network entities (via the Data Collection function) may be required in the Model Inference function to create Model Performance Feedback.

[088] An actor is a function that receives output from the Model Inference function and triggers or performs corresponding actions. The actor can trigger actions directed at other entities or at itself.

[089] Feedback: Information that can be used to derive training data or inference or performance feedback.

[090] Thus, this disclosure provides solutions that support machine learning for positioning. For example, AI-based direct positioning and AI-assisted positioning methods can be leveraged to improve the location accuracy performance of a UE. In direct AI / ML positioning scenarios, techniques such as Petition 870260069606, dated 07 / 14 / 2026, page 35 / 134 30 / 125 fingerprints can be leveraged by AI / ML models to achieve enhanced location accuracies using environmental and measurement data. This disclosure describes techniques for configuring direct AI / ML positioning assistance data, as well as defining measurements to perform direct AI / ML positioning. Additionally, this disclosure describes techniques for configuring reporting criteria for devices, nodes, and / or entities that perform direct AI / ML positioning measurements.

[091] Regarding the aspects of this disclosure, implementations are described for: configuring a target UE, positioning reference unit (PRU) UE, side link (SL) UE, or NG-RAN node to perform direct AI / ML positioning measurements based on the transmission of the positioning reference signal to generate a training dataset; enabling a target UE, PRU UE, SL UE, or NG-RAN node to perform requested measurements for different scenarios, which may form part of the fingerprint based on the environment topology and AI / ML measurement parameters; enabling a target UE, PRU UE, NG-RAN node, configuration entity, SL UE, and / or location server to indicate AI / ML positioning assistance data or causes of measurement errors;To enable a reporting configuration structure for a target UE, PRU UE, SL UE, and / or NG-RAN node to receive the desired direct AI / ML positioning measurements, e.g., fingerprint information; to enable a plurality of common reporting criteria for AI / ML positioning measurements; to enable configuration and reporting of assistance information to accurately report AI / ML positioning measurements.

[092] Some notes on the implementations described in this disclosure: The different implementations are combinable with each other in various ways; a reference signal related to Petition 870260069606, dated 07 / 14 / 2026, page 36 / 134 31 / 125 positioning can be referred to as a reference signal used for positioning procedures and / or purposes to estimate the location of a target UE, for example, PRS, signal based on existing reference signals such as Channel State Information Reference Signal (CSI) (CSI-RS) or SRS, etc.A target UE can be referred to as a device and / or entity to be located and / or positioned; the term 'PRS' can refer to any signal, such as a reference signal, which may or may not be used primarily for positioning; a target UE can be referred to as a UE of interest whose position (e.g., absolute and / or relative) is to be obtained by the network and / or the UE itself; the terms AI and ML can be used interchangeably to refer to an intelligent software component or system, and AI can represent a subset and / or implementation of ML; a reference made to device position and / or location information can refer to an absolute 2D / 3D position, relative position with respect to another node and / or entity, varying in terms of distance, varying in terms of direction, and combinations thereof.

[093] The implementations disclosed here offer support for direct AI / ML positioning measurement and processing configuration. For example, fingerprinting is described, as when an AI / ML inference model can be deployed across different entities. Examples of such implementations include UE-based positioning with a UE-side ML mode, UE-assisted and / or LMF-based positioning with an LMF-side ML model, NG-RAN node-assisted positioning with an LMF-side ML model, etc.

[094] In implementations that include UE-based positioning, a target UE can request training datasets based on DL and SL reference signals (e.g., DL-PRS, SL-PRS, etc.) from various data sources, including measurements performed and collected internally on the UE. Petition 870260069606, dated 07 / 14 / 2026, page 37 / 134 32 / 125 target, other UEs, a location server, an NG-RAN node, PRU, network operation, administration and maintenance (OAM), tracking collection entities (TCE) and / or combinations thereof. Training datasets may include waypoints and / or reference locations, and fingerprint information and / or other positioning measurements may be sampled, measured and / or associated. Multiple entities and / or network nodes may be enabled with the following procedures to enable the configuration: • A target UE, anchor UE and / or PRU UE can transmit a request and receive a response including configuration for direct downlink (DL) AI / ML positioning assistance data (e.g., configuration), for example, fingerprinting with respect to a location server; • A target UE can transmit a request and receive training data (e.g., instead of configuration to perform measurement) or instructions to obtain training data from a second node, for example, a location server, an NG-RAN node, positioning reference units, network OAM, TCE, or combinations thereof; • Another node (for example, the location server, the NG-RAN node, and / or another node) can transmit a request to the target UE to receive training data that the target UE has collected and / or measured; • A location server can receive AI / ML positioning assistance data directly from DL (e.g., configuration), for example, for a radio frequency (RF) fingerprint request from a plurality of UEs, including the target UE and the PRU UE, and the location server can provide a configuration response; • One or more EUs, including an anchor EU and / or PRU EU, may receive a request for assistance data from Petition 870260069606, dated 07 / 14 / 2026, page 38 / 134 33 / 125 direct AI / ML positioning from SL (e.g., RF configuration and / or fingerprinting) and can provide an appropriate configuration response.

[095] In implementations that include UE-assisted positioning, a location server can request a plurality of training datasets based on DL and SL reference signals (e.g., DL-PRS, SL-PRS) from various data sources, including measurements collected internally on the location server, multiple UEs, other neighboring location servers, NG-RAN nodes, positioning reference units, and combinations thereof. These datasets may contain reference points and / or reference locations where fingerprint information can be sampled, measured, and / or associated. Various entities and / or network nodes can be enabled with the following functionality to allow such implementations: • The location server can transmit AI / ML positioning assistance (configuration) directly via downlink (DL) or sidelink (SL), for example, fingerprint data. • At least one or more UEs, including the target UE or the UE PRU, may receive a response / configuration for a direct AI / ML positioning configuration from DL and / or SL, for example, fingerprinting against a location server.

[096] FIG. 7 illustrates an example scenario 700 that supports machine learning for positioning according to aspects of the present disclosure. Scenario 700, for example, includes representations of the AI / ML configuration mechanisms directly from DL and SL, as discussed above, within a rectangular environment 702 (e.g., an internal factory environment) with length L and width W including reference points and 18 gNB / TRPs separated by an inter-gNB / TRP distance D. Petition 870260069606, dated 07 / 14 / 2026, page 39 / 134 34 / 125

[097] In scenario 700, LTE Positioning Protocol (LPP) signaling from DL 704 of a location server 706 to a target UE 708 and / or an anchor UE / PRU 710 can be used to transmit the various direct AI / ML positioning configurations, for example, using the LPP ProvideAssistanceData message or a new LPP ProvideMLAssistanceData message, while the Side Link Positioning Protocol (SLPP) or the new positioning protocol related to the exchange of SL positioning messages can be used for signaling 712 to provide the plurality of direct AI / ML positioning configurations from the PRU UE / anchor UE 710, for example, using the SLPP message. ProvideAssistanceData. Alternatively or additionally, an SL Positioning Server UE can provide direct AI / ML positioning configurations via SLPP or similar. Furthermore, the target UE 708 can configure surrounding UEs, PRU UEs, and / or SL Positioning Server UEs to perform direct AI / ML positioning measurements, e.g., fingerprinting based on locations / landmarks. For illustrative purposes, direct signaling is shown from location server 706. However, this signaling can be transparently routed via a service gNB to a UE.

[098] In implementations, a 710 anchor UE / UE PRU can configure other 710 anchor UE / UE PRUs to perform AI / ML positioning measurements. Additionally, an LMF can configure a first set of 710 anchor UE / UE PRUs to transmit SL PRS for a second set of PRU UEs / EUs anchor 710.

[099] In implementations such as those illustrated in scenario 700, the target UE 708, the PRU UEs / anchor UEs 710 and / or the location server 706 can request a plurality of AI / ML positioning assistance data directly from DL or SL, for example, using the LPP RequestAssistanceData message. Petition 870260069606, dated 07 / 14 / 2026, page 40 / 134 35 / 125 Alternatively or additionally, the target UE 708 may request a plurality of AI / ML positioning assistance data directly from a PRU UE / UE anchor 710 and / or an SL positioning server UE, such as using SLPP and / or the SL positioning protocol message RequestAssistanceData.

[100] In implementations that include NG-RAN assisted positioning, a localization server can request a plurality of training datasets based on UL reference signals (e.g., SRS for positioning) from various data sources, including neighboring gNBs, TRPs, nodes of NG-RAN, PRU TRPs, CUs, DUs, and / or combinations thereof. Training datasets may include reference points and / or reference locations corresponding to an NG-RAN node, CU locations, and / or DU locations, and fingerprint information may be sampled, measured, and / or associated. In implementations, multiple entities and / or network nodes may be subject to the following procedures: • An NG-RAN node including gNB and / or TRP can transmit a direct AI / ML positioning configuration from UL (e.g., fingerprint) to one or more UEs upon request from a location server. • UEs, including a target UE, may receive a response and / or configuration for direct AI / ML positioning configuration from a UL (e.g., fingerprint) relative to a location server. • A location server can transmit AI / ML positioning assistance directly from UL, for example, requesting fingerprint data for one or more NG-RAN nodes, including gNB, TRP, CUs, DUs, PRU and / or combinations thereof, and then receive a configuration response.

[101] FIG. 8 illustrates an example scenario 800 that supports machine learning for positioning according to aspects of the present disclosure. In scenario 800, in step 802, Petition 870260069606, dated 07 / 14 / 2026, page 41 / 134 36 / 125 a location server 804 triggers a configuration request to an NG-RAN node 806, for example, a service gNB and / or neighboring gNBs. Step 806, for example, involves NRPPa with direct AI / ML positioning configuration from UL, for example, fingerprinting of N reference locations.

[102] In step 808, the NG-RAN node 806 forwards a UL-RS configuration (e.g., SRS for positioning configuration) to a target UE 810 and / or anchor UE / PRU 812, in order to enable a UL transmission and a subsequent direct UL AI / ML measurement on a gNB / TRP. Step 808, for example, may involve RRC with direct UL AI / ML positioning configuration, e.g., fingerprinting of N reference locations.

[103] In implementations, the 804 location server can directly forward a UL-RS configuration via DL LPP signaling to perform a UL transmission and a measurement of Direct AI / ML from subsequent UL at NG-RAN node 806, for example, a gNB / TRP. In an alternative implementation, NG-RAN node 806 can be implemented as a CU and a DU, where location server 804 can signal the CU and the DU can perform UL-RS measurements at different locations and / or distributed reference points, for example, in an internal factory scenario as described above. For example, in step 814, location server 804 can transmit the direct AI / ML positioning configuration from UL, for example, fingerprinting of N reference locations.

[104] In implementations, the UE anchor / PRU 812 location can be used together with a gNB / TRP field truth reference location to construct a fingerprint including field truth reference location. In such implementations, the UE anchor / PRU 812 can signal a 2D and / or 3D location where the SRS is being transmitted to the configuration entity, for example, the NG-RAN 806 node and / or Petition 870260069606, dated 07 / 14 / 2026, page 42 / 134 37 / 125 the location server 804. In scenarios that include signaling location information to the location server 804, LPP signaling (e.g., ProvideLocationInformation message) can be used and / or scenarios that involve signaling location information to the NG-RAN node 806, RRC signaling can be used, e.g., LocationMeasurementIndication.

[105] Alternatively or additionally, the configuration entity may request that the anchor UE / PRU 812 transmit UL SRS or SL PRS at certain predefined locations. These predefined locations may be included in the direct AI / ML configurations along with positioning reference signal configurations.

[106] In implementations, one type of NG-RAN node (e.g., PRU gNB / TRP) can also transmit SRS to other NG-RAN nodes, UEs, and / or devices. NG-RAN nodes that receive the SRS can perform direct AI / ML positioning measurements for direct AI / ML position estimation purposes. Thus, NG-RAN nodes that are capable of transmitting and receiving SRS, such as a PRU TRP, can support this type of measurement. In implementations, a new reference signal can also be supported between NG-RAN nodes for direct AI / ML position estimation purposes and can be transmitted, for example, via the Xn interface and / or via another wireless transmission medium. In implementations, the configuration methods discussed above can be combined to allow the use of direct AI / ML positioning measurements from DL, SL, and / or UL individually and in combination.

[107] In implementations, configurations such as those flagged as described above can be used to enable direct AI / ML position estimation, for example, using fingerprinting methods. The content of the configuration, for Petition 870260069606, dated 07 / 14 / 2026, page 43 / 134 Example 38 / 125 is considered in accordance with the implementations described above and as discussed below.

[108] In UE-based positioning scenarios, such as with a UE-side model, a target UE can create a plurality of fingerprint training datasets based on measurements performed, data, measurements received, and / or data from other network entities, e.g., location servers, other UEs, PRUs, and so on. The target UE can initiate a request to the location server for settings related to direct AI / ML measurements from DL or SL (e.g., fingerprint measurements) and / or request UL-RS transmission configuration related to direct AI / ML positioning. An example configuration is discussed below.

[109] FIG. 9 illustrates a 900 message that supports machine learning for positioning in accordance with aspects of the present disclosure. The 900 message, for example, represents an NR-Direct-AI-MLAssistanceData information element that can be used by a target device to request AI / ML positioning assistance data directly from a location server and / or a configuration entity, e.g., SL positioning server UE, anchor UE, etc.

[110] Table 7 below provides examples of field descriptions for message 900. Table 7 Field Descriptions NR-Direct-AI-ML-ReguestAssistanceData nr-PhysCellID This field specifies the physical NR cell identity of the target device's current primary cell. nr-AdType This field indicates the requested assistance data or DL ​​positioning configuration. dl-prs refers to the requested DL-PRS configuration for direct AI / ML measurement, posCalc means the requested assistance data is nr-PositionCalculationAssistance for EU-based positioning, nr-Training-Type This field indicates whether the requested Direct AI / ML configuration is used for online / offline training. Petition 870260069606, dated 07 / 14 / 2026, page 44 / 134 39 / 125 Field Descriptions NR-Dia:ect-AI-ML-ReqaestAssistaziceData nr-on-demand-DL-PRS-Regues t This field indicates the on-demand DL-PRS requested for direct AI / ML placement. In one implementation, this may apply to UE-initiated on-demand PRS. This field may be included when the dlprs or sl-prs bit in nr-AdType is set to '1' or '2'. nr-Learning-Method This field indicates the type of learning method employed for the requested assistance data. This is represented by a sequence of bits, with a value of one in the bit position meaning that the specific assistance data was requested; a value of zero means that it was not requested. - Bit 0 indicates whether supervised learning model(s) are employed on the target device. - Bit 1 indicates whether semi-supervised learning model(s) are employed on the target device. - Bit 2 indicates whether unsupervised learning model(s) are employed on the target device nr-PosCalcAssistanceReqaest This field indicates the Position Calculation Assistance Data requested to perform direct AI / ML positioning. This is represented by a bit sequence, with a value of one in the bit position meaning that the specific assistance data is requested; a value of zero means it is not requested. - Bit 0 indicates whether the nr-TRP-Locationlnfo field in the NR-PositionCalculationAssistance information element (IE) is requested or not; Bit 1 indicates whether the nr-DL-PRS-Beamlnfo field in IE NRPositionCalculationAssistance is requested or not; Bit 2 indicates whether the nr-RTD-Info field in IE NRPositionCalculationAssistance is requested or not; Bit 3 indicates whether the nr-TRP-BeamAntennalnfo field in IE NRPositionCalculationAssistance is requested or not; - Bit 4 indicates whether the nr-DL-PRS-Expected-LOS-NLOS-Assistance field in IE NRPositionCalculationAssistance is requested or not. Bit 5 indicates whether or not the fingerprint truth-of-field reference points / locations are requested. This field can only be present if the 'posCalc' bit in nr-AdType is set to the value '1'. pre-configured-AI-ML-AssistanceDataRequ.est This field, if present, indicates that the target device requests pre-configured assistance data for direct AI / ML positioning with area validity.

[111] In implementations, message 900 may include direct AI / ML positioning assistance data, assisted AI / ML positioning, or a combination thereof. Assisted AI / ML positioning measurements may be defined as measurements that have been enhanced and / or optimized using AI / ML models, for example, RAT-dependent measurements such as RSTD, relative time of arrival (RTOA), RSRP, RSRPP, Rx-Tx, AoAs, AoDs, time difference, and so on.

[112] In implementations, with regard to EU-based positioning, as described above, a target EU can provide an index Petition 870260069606, dated 07 / 14 / 2026, page 45 / 134 40 / 125 or list of true-field reference locations, for example, absolute and / or relative locations. Examples of true-field reference locations are defined below.

[113] In implementations such as those involving UE-based positioning (e.g., with a UE side model and / or UE-assisted positioning with an LMF side model), a localization server can transmit direct AI / ML positioning assistance data. Alternatively or additionally, the localization server can transmit assisted AI / ML positioning assistance data to one or more target devices, PRU UEs, anchor UEs, SL positioning server UEs, etc., to perform direct AI / ML and / or assisted AI / ML measurements to be used as training data input. A target UE, for example, can receive from the localization server a plurality of settings related to direct AI / ML measurements of DL or SL, e.g., fingerprint measurements and / or UL-RS transmission configuration related to direct AI / ML positioning.

[114] FIGS. 10a and 10b illustrate different parts of a 1000 message that supports machine learning for positioning according to aspects of the present disclosure. The 1000 message, for example, represents an NR-DirectAI-ML-ProvidesAssistanceData message.

[115] Table 8 below provides examples of field descriptions for message 1000. Table 8 Field Descriptions NR-Dii:ect-AI-ML-Pi:o~videAssista.nceDa.ta dl-PRS-ID or sl-PRS-ID This field is used in conjunction with a DL-PRS Resource Set ID and a DL-PRS Resource ID or an SL-PRS Resource Set ID and an SL-PRS Resource ID to uniquely identify a DL-PRS Resource or an SL-PRS Resource. This ID can be associated with multiple DL-PRS Resource Sets associated with a single TRP or multiple SL-PRS Resource Sets associated with a single SL transmission point. Each SL or TRP transmission point must be associated with only one ID. Petition 870260069606, dated 07 / 14 / 2026, p. 46 / 134 41 / 125 NR-Dinect-AI-ML-PnovideAssistanceData nr-PhysCellID field descriptions This field specifies the physical cell identity of the TRP associated with nr-CellGlobalID. This field specifies the NR Global Cell Identifier (NCGI), the globally unique identity of a cell in the NR, of the associated TRP. The server should include this field if it considers it necessary to resolve ambiguity in the TRP indicated by nr-PhysCellID. nr-ARFCN This field specifies the Absolute Radio Frequency Channel Number (ARFCN) of the CD-SSB (cell-defining SSB) corresponding to nr-PhysCellID. associate-DL-PRS-ID This field specifies the dl-PRS-ID of the associated TRP from which the beam information is obtained. GND-referencePoint This field specifies a configured field truth reference point used to define the field truth location in the GNDReference-LocationlnfoList. GND-Refeience-LocationlnfoList This field provides an index or list of true field reference point locations for performing AI / ML DL or SL positioning measurements, based on the reception and measurement of DL-PRS or SL-PRS features. GND-Reference-Local ti on This field provides true-to-field reference locations for performing AI / ML DL or SL positioning measurements, e.g., fingerprinting, which is based on receiving and measuring DLPRS or SL-PRS features. These can be represented by an absolute location or a location relative to the GND-referencePoint or other UE / device. The absolute / relative location can be determined by offline position determination or by a defined location estimate using one of the geographic forms defined in TS23.032. This can be based on RAT-dependent location determination, e.g., DL-TDOA, Multi-RTT, DL-AoD, etc., or RAT-independent location determination, e.g., GNSS coordinates, Bluetooth, WiFi, etc. This can include 2D or 3D location estimates. GND-Reference-Location-Source It provides the source positioning technology used to determine the location estimate or the value of the location or true field reference point. GND-Refenence -measureioen. t Time This field provides the time during which the location or true field reference point is valid for performing direct AI / ML measurements. Time formats can be represented in terms of System Frame Number (SFN), UTC time, GNSS time, and so on. In other implementations, this time may be associated with the validity for performing assisted AI / ML measurements. In an alternative implementation, this may also be represented as a time window. AI-ML-assistanceDataValidityAnea This field provides the geospatial criteria for which the AI / ML positioning configuration must be valid. This may include a cell ID, TRP ID, beam ID, area list, tracking area, RAN notification area, zone ID, or any combination thereof.

[116] In implementations, the configuration information of DL-PRS described above can be used to enable a device (e.g., target UE, UE PRU, UE SL, etc.) to perform Petition 870260069606, dated 07 / 14 / 2026, page 47 / 134 42 / 125 AI / ML measurements directly at each of the configured true-to-field reference locations, as indicated above. This process can be performed during an offline phase, and the measurements and their respective locations can be signaled to the location server or stored in a single UE or multiple UEs.

[117] In implementations involving NG-RAN assisted positioning (e.g., with LMF side model), a localization server can transmit one or more requests for a plurality of direct AI / ML positioning assistance data in terms of available SRS and / or other UL-PRS configurations to multiple gNBs and / or TRPs. One or more gNBs and / or TRPs can determine the SRS configuration per target UE to perform AI / ML positioning related to SRS transmission, which can be configured per carrier. In implementations, the SRS configuration can be broadcast to multiple UEs for use in multiple cells, within a predefined positioning system information area, within an area with an associated validity in terms of time and / or area, and combinations thereof.

[118] In implementations, a gNB and / or TRP can configure a UE to perform SRS for positioning transmissions via RRC signaling using, for example, RRCReconfiguration message. The gNB and / or TRP can configure the UE to perform SRS for positioning transmissions in order to perform direct AI / ML positioning or assisted AI / ML positioning.

[119] In implementations, a target UE can confirm receipt of SRS for positioning configuration to perform direct AI / ML positioning and / or assisted AI / ML positioning measurements, along with other non-AI / ML time- or angle-based measurements. A location server (e.g., LMF) can request that a Petition 870260069606, dated 07 / 14 / 2026, page 48 / 134 43 / 125 or more gNBs and / or TRPs activate SRS for positioning configuration for transmission by the target UE. The gNB and / or TRP can activate SRS transmission to a UE by transmitting a DL MAC control element (CE) activation command to the target UE. The location server can additionally disable SRS transmission via the gNB, and the gNB can transmit a deactivation command using, for example, a DL MAC CE.

[120] In implementations, a location server can receive a plurality of available SRS or UL-PRS configurations to perform UL Direct AI / ML positioning. In an example scenario, a gNB can derive SRS and / or UL-PRS fingerprints for location estimates for multiple UEs.

[121] In implementations, lower-layer signaling with respect to LPP (e.g., RRC signaling, MAC CE, downlink control information (DCI) signaling, and combinations thereof) can be used to transmit direct AI / ML or assisted AI / ML configurations. In at least one implementation, RRC and / or LPP signaling can be used to add, modify, remove, update, enable, and / or disable one or more direct AI / ML UE placement configurations.

[122] The implementations allow for direct AI / ML measurement and processing procedures. For example, methods for performing direct AI / ML measurements are presented based on a type of AI / ML approach. In at least one implementation, fingerprint measurements may depend on Received Signal Strength (RSS) measurements, including RSRP, Received Reference Signal Quality (RSRQ), RSSI, or combinations thereof. In implementations, fingerprint measurements may include a combination of RSS, measurements based on Petition 870260069606, dated 07 / 14 / 2026, page 49 / 134 44 / 125 timing, and angle-based measurements to learn the location estimate of a UE.

[123] In implementations, a target UE, PRU UE, SL UE, etc., can be configured to measure the following measurements to build an RF fingerprint applicable to: • RAT-dependent measures: DL / SL RSTD (DL or SL based measurements) DL / SL PRS Time of Arrival (TOA) (DL or SL based measurements) DL / SL PRS RSRP (DL or SL based measurements) DL / SL PRS RSRPP (DL or SL based measurements) Rx-Tx UE Time Difference (DL or SL based measurements) Synchronization Signal (SS) RSRP (RSRP for RRM), SSRSRQ (for RRM), CSI-RSRP (for RRM), CSI-RSRQ (for RRM), SSRSRP (for RRM) (DL based measurements) DL / SL Carrier Phase Measurements (DL or SL based measurements) DL / SL Carrier Phase Difference Measurements (DL or SL based measurements) DL E-CID LTE E-CID Link Side Shared Channel RSRP Physical SL (PSSCH), DL PRS RSSI (Received Signal Strength Indicator), LTE Observed Time-of-Arrival Difference (OTDOA) measurements, RAT-independent measurements, and A-GNSS measurements, including common assistance data, which may be applicable to any GNSS constellation, e.g., Galileo, GPS, GLONASS.etc., generic assistance data for specific GNSS constellations or data from, Petition 870260069606, dated 07 / 14 / 2026, page 50 / 134 45 / 125 periodic GNSS assistance signals are used to provide GNSS control information periodically to the UE / device. Bluetooth RSS measurements including RSSI; WLAN (WiFi) measurements, including RTT and RSSI information; IMU sensor measurements, including gyroscope, accelerometer, and so on. Barometric sensor measurements

[124] In implementations, an NG-RAN, gNB / TRP, CU-DU, etc. node can be configured to measure the following measurements applicable to: • RAT-dependent measurements o UL-RTOA (UL-based measurement) o UL SRS RSRP (UL-based measurement) o UL SRS RSRPP (UL-based measurement) o gNB Rx-Tx time difference measurements (UL-based measurement) o UL-AoA (UL-based measurement) o UL carrier phase measurements (UL-based measurements) o UL carrier phase difference measurements (UL-based measurements) o UL NR E-CID o LTE E-CID

[125] Instances of the above measurements may constitute a plurality of fingerprint measurements, including part of a direct AI / ML positioning measurement of DL or UL at one or more true-field locations. The use of RAT-dependent and RAT-independent methods may assist in the derivation of hybrid fingerprints to increase the accuracy of direct AI / ML positioning methods.

[126] In implementations, a location server (e.g., LMF) can provision a direct AI / ML configuration. Petition 870260069606, dated 07 / 14 / 2026, page 51 / 134 46 / 125 and / or AI / ML-assisted measurement, such as based on a type of AI and / or machine learning model. These models may include the following and are not limited to one or more of the following combinations: • Supervised Learning Approaches: the k-NN cluster (nearest neighbor) This model classifies fingerprints according to the Euclidean distance between neighboring training data points and determines the K-neighbors that have the greatest proximity to the input fingerprints. Support Vector Machines (SVMs) This model is based on margin calculation, where the input fingerprint data is plotted in n-dimensional space with the n-1 hyperplane drawn to divide the training data into n classes, so that the distance between each class and the hyperplane is maximized. the Decision Tree The problem of classification or regression with respect to fingerprint matching can be solved using a decision tree-like structure. Rules are used to divide the training data into multiple labels, where labels are predicted for any new fingerprint data points through this decision tree. The Random Forest This model is a collection of multiple decision trees where the result of each tree provides a fingerprint classification or, in another implementation, the average prediction of all decision trees is in the output. This helps overcome the overfitting problem faced by autonomous decision trees. Artificial Neural Networks (ANNs) Based on backpropagation learning algorithms, a set of fingerprint input data is Petition 870260069606, dated 07 / 14 / 2026, page 52 / 134 47 / 125 transformed using a non-linear transfer function within intermediate units / nodes that make up a hidden layer, into a final location estimate output. These models can be robust against fingerprint data with limited noise or interference. • Unsupervised Approaches: K-means This model divides fingerprints into K unique, non-overlapping groups or clusters to characterize specific location points. Gaussian Mixture Models (GMM) GMM is a probabilistic model that can be used to estimate the distribution of RF fingerprints in different locations, including true-field reference locations as well as unknown locations. The GMM can be trained using collected RF fingerprints and can then be used to determine the most likely location for a given set of RF fingerprints. • Supervised and Unsupervised Approaches: Bayesian Networks (BN) Business models (BMs) can be used to model the probabilistic relationships between RF fingerprints and environmental factors, such as radio channel parameters (e.g., channel state information - CSI), path loss, and fading parameters, for a given location. BMs can be trained using a configured training set of RF fingerprint BMs and environmental data to perform RF fingerprint localization. • Learning or Reinforcement Learning A learning algorithm based on trial-and-error methods, where decisions are based on so-called rewards or punishments, in which correct decisions are... Petition 870260069606, dated 07 / 14 / 2026, page 53 / 134 48 / 125 are rewarded, while incorrect decisions are penalized to improve model performance. Deep Learning Based on ANNs, which employ iterative weighting adjustment techniques between pairs of neurons / nodes, trained on large datasets of digital fingerprinting collected from the environment. Transfer Learning It leverages the model's ability to learn new features and subjects based on its own system knowledge, allowing for minimal changes to an already trained model. This can be leveraged to position AI / ML directly, for example, fingerprinting, to provide a scalable solution to avoid the large overhead of on-site fingerprint collection during initial local research, for example, during the offline phase.

[127] In implementations, a location server can explicitly indicate ML models for a target UE and / or PRU UE using UE-specific SLPP / LPP signaling, for example, SLPP / LPP ProvideAssistanceData messages. In implementations, models can be indicated using positioning system information broadcast messages, for example, new and / or existing posSIBs for multiple UEs.

[128] In implementations, a location server and / or configuration entity may receive a request from a target UE, PRU UE and / or SL UE for direct AI / ML positioning or assisted AI / ML positioning data, along with an indication of the models described above for which the measurements should be used as input data.

[129] In implementations, the ML models used to initiate a direct or assisted AI / ML placement session can be indicated via UE capability signaling. Petition 870260069606, dated 07 / 14 / 2026, p. 54 / 134 49 / 125 applicable (e.g., LPP ProvideCapabilities message) which may be based on a request from the location server and / or configuration entity, e.g., an LPP RequestCapabilities message.

[130] In implementations, a PRS RSSI measurement can be defined for AI / ML positioning purposes, including direct and assisted techniques. In implementations, PRS RSSI can be applied to positioning techniques unrelated to AI / ML. Furthermore, these measurements can be performed in the RRC_CONNECTED, RRC_INACTIVE, and RRC_IDLE states. PRS RSSI for downlink, sidelink, and uplink can be defined as follows in Table 9. Table 9: Definitions for measuring DL, SL and UL PRS RSSI DL PRS RSSI (Received Signal Strength Indicator) Definition The DL PRS reference signal received path power (DL PRS-RSRPP) is defined as the linear average of the total received power (in [W]) observed on feature elements of a slot carrying the DL PRS signal configured for measurement. In other deployments, the power unit may include dBm or dB. For frequency band 1, the reference point for the DL PRS-RSSI should be the UE antenna connector. For frequency band 2, the DL PRS-RSSI should be measured based on the combined signal of antenna elements corresponding to a given receiver branch. Applicable to RRC_CONNECTED, RRC_INACTIVE, RRC_IDLE The above includes various operational states, which refer to the state of a User Equipment (UE) in terms of radio connection to the LTE / 5G network.The RRC state of a UE is determined by the network based on UE / device activity, including any power requirements and network requirements for radio resources. The UE transitions between different RRC states in response to network commands or as a result of changes in network conditions. Therefore, this measurement can be supported in the aforementioned operational states. SL PRS RSSI (Received Signal Strength Indicator) Definition The PRS Side Link Received Signal Strength Indicator (SL PRS RSSI) is defined as the linear average of the total received power (in [W]) observed in the subchannel configured in OFDM symbols of a slot configured for physical side link control channel (PSCCH) and PSSCH bearing SL PRS symbols, starting from the 2nd OFDM symbol. In other implementations, the power unit may include dBm or dB. For frequency band 1, the reference point for the SL PRS RSSI should be the UE antenna connector.For frequency band 2, the SL PRS RSSI should be measured based on the combined signal of the antenna elements corresponding to one. Petition 870260069606, dated 07 / 14 / 2026, p. 55 / 134 50 / 125 a specific receiver branch. For frequency bands 1 and 2, if receiver diversity is in use by the UE, the reported SL PRS RSSI value should not be less than the corresponding SL PRS RSSI of any of the individual receiver branches. Applicable to RRC_CONNECTED, RRC_INACTIVE, RRC_IDLE. The above includes several operational states, which refers to the state of a User Equipment (UE) in terms of radio connection to the LTE / 5G network. The RRC status of a UE is determined by the network based on the UE / device activity, including any power / energy requirements and network requirements for radio resources. The UE transitions between different RRC states in response to network commands or as a result of changes in network conditions. Therefore, this measurement can be supported in the operational states mentioned above.NOTE: Currently, no state is defined for SL communication and positioning; however, this applicability would extend to any future support of the above operational states for SL communication and positioning. UL SRS RSSI (Received Signal Strength Indicator) Definition The received power of the UL SRS reference signal (UL SRSRSRP) is defined as the linear average of the total received power (in [W]) observed on feature elements of a slot carrying sounding reference signals (SRS). In other implementations, the power unit may include dBm or dB. The UL SRS RSSI should be measured over the configured feature elements within a slot of the considered measurement frequency bandwidth at the configured measurement time occasions. In other implementations, the power unit may include dBm or dB.Applicable to RRC_CONNECTED, RRC_INACTIVE, RRC_IDLE. The above includes various operational states, which refer to the state of a User Equipment (UE) in terms of radio connection to the LTE / 5G network. The RRC state of a UE is determined by the network based on the UE / device's activity, including any power / energy requirements and the network's requirements for radio resources. The UE transitions between different RRC states in response to network commands or as a result of changes in network conditions. Therefore, this measurement can be supported in the aforementioned operational states.

[131] In implementations and according to the measurement definitions presented in Table 9, DL, SL, and UL PRS RSSI may include a feature or signature of a fingerprint that can be used to enable direct AI / ML positioning. Additionally, an SRS TOA or PRS measurement may be defined to act as an additional feature or signature for AI / ML positioning purposes, including direct and assisted techniques. In implementations, PRS TOA may be applicable to positioning techniques unrelated to AI / ML. Furthermore, these measurements may be performed in the RRC_CONNECTED states, Petition 870260069606, dated 07 / 14 / 2026, page 56 / 134 51 / 125 RRC_INACTIVE and RRC_IDLE. The PRS TOA for downlink, sidelink, and uplink (SRS) is defined as follows in Table 10. Table 10: Definitions of DL, SL and UL PRS TOA measurements DL PRS TOA (Time of Arrival) Definition: The DL PRS time of arrival is the measured arrival time from the start of the subframe containing received SL PRS at the Receiving Point (RP) j. It can also be defined as the reception time of the DL PRS at the receiver reference point. In one implementation, the reference point will be the UE / device antenna connector. Multiple DL PRS features can be used to determine the start of a subframe containing received DL PRS at an RP. Applicable to RRC_CONNECTED, RRC_INACTIVE, RRC_IDLE. The above includes several operational states, which refer to the state of a User Equipment (UE) in terms of radio connection to the LTE / 5G network. The RRC state of a UE is determined by the network based on the UE / device activity, including any power / energy requirements and the network requirements for radio resources.The UE transitions between different RRC states in response to network commands or as a result of changes in network conditions. Therefore, this measurement can be supported in the aforementioned operational states. SL PRS TOA (Time of Arrival) Definition The SL PRS time of arrival is the measured arrival time from the start of the subframe containing SL PRS received at the Receiving Point (RP) j. It can also be defined as the reception time of the SL PRS at the receiver reference point. In one implementation, the reference point will be the UE / device antenna connector. Multiple SL PRS features can be used to determine the start of a subframe containing SL PRS received at an RP. Applicable to RRC_CONNECTED, RRC_INACTIVE, RRC_IDLE. The above includes several operational states, which refers to the state of a User Equipment (UE) in terms of radio connection to the LTE / 5G network.The RRC state of a UE is determined by the network based on UE / device activity, including any power / energy requirements and network requirements for radio resources. The UE transitions between different RRC states in response to network commands or as a result of changes in network conditions. Therefore, this measurement can be supported in the aforementioned operational states. NOTE: Currently, no state is defined for SL communication and positioning; however, this applicability would extend to any future support of the above operational states for SL communication and positioning. UL SRS TOA (Time to Arrival) Definition The UL SRS time to arrival is the measured arrival time from the start of the subframe containing the received SRS at the Receiving Point (RP) j. It can also be defined as the reception time of the UL SRS at the receiver reference point.In one implementation, the reference point should be the receiving antenna connector of the base station, while in another implementation the reference point may be the central location of the antenna's radiation region. Petition 870260069606, dated 07 / 14 / 2026, page 57 / 134 52 / 125 Reception from the base station. In another implementation, the reference point may include the transceiver-receiver boundary array connector of a base station. Multiple SRS features can be used to determine the start of a subframe containing received SRS in a RP. Applicable to RRC_CONNECTED, RRC_INACTIVE, RRC_IDLE. The above includes several operational states, which refers to the state of a User Equipment (UE) in terms of radio connection to the LTE / 5G network. The RRC state of a UE is determined by the network based on UE / device activity, including any power / energy requirements and network requirements for radio resources. The UE transitions between different RRC states in response to network commands or as a result of changes in network conditions. Therefore, this measurement can be supported in the aforementioned operational states.

[132] In implementations, a target UE and / or PRU UE can be configured to measure DL PRS and / or SL PRS for AI / ML positioning, as in one or more of the following scenarios: • Configured with a Measurement Gap (MG) associated with the Gap Pattern ID, Measurement Gap Length (MGL), and Measurement Gap Repetition Period (MGRP), or a combination thereof. This MG can be pre-configured with an activation or deactivation command. • Configured without or outside of a measurement gap, in the case of the DL PRS being within a bandwidth portion (BWP) of an active DL with the same numerology as the active DL BWP. • Configured training measurement gap (T-MG), with predefined gap pattern ID, Measurement Gap Length (MGL) and Measurement Gap Repetition Period (TMGRP), T-MG start time, T-MG duration, T-MG end time, indicator showing whether measurements are based on offline or online training or a combination of both. In other implementations, a time duration provided by the measurement window or timer expiration may be used to indicate the start and end of a duration for performing measurements for online or offline training of an AI / ML positioning model.

[133] In implementations, for each DL / SL PRS received, a UE can be configured with a priority setting of Petition 870260069606, dated 07 / 14 / 2026, page 58 / 134 53 / 125 PRS resources are used to perform AI / ML and non-AI / ML positioning measurements. These resources may form a subset of resources, which may be part of the same or a different set of PRS resources. This priority signaled to the UE / devices may indicate the priority for performing measurements, which may build an additional training dataset or alternatively perform measurements for non-AI / ML positioning.

[134] Implementations also allow providing assistance data and / or causes of measurement errors. For example, a UE can indicate to a network and / or configuration entity that one or more measurements associated with a true-to-field location and / or fingerprint have an associated error cause. The error cause is, for example, not receiving the PRS configuration or the PRS configuration not having configuration parameters. For example, using implementations described above, LPP and / or SLPP signaling can be used to indicate error causes in the network. In addition, error causes can be initiated by the UE, for example, originating on the UE side. In implementations, error causes can be an indication initiated by the location server to the UE.

[135] FIG. 11 illustrates a 1100 message that supports machine learning for positioning in accordance with aspects of this disclosure. The 1100 message, for example, represents an IE that shows error causes supported by the location server and / or configuration entity, such as those that can be transmitted via LPP. For example, the 1100 message represents an NR-AI-ML-LocationServerErrorCauses IE that can be used by a location server to provide AI / ML assistance data error reasons to a target device. The 1100 message can also be used for SL configuration entities that provide such error causes to a UE and / or target device. Petition 870260069606, dated 07 / 14 / 2026, page 59 / 134 54 / 125

[136] FIG. 12 illustrates a 1200 message that supports machine learning for positioning in accordance with aspects of this disclosure. The 1200 message, for example, presents error causes supported by a target UE, which can be transmitted via LPP. The 1200 message, for example, represents an NR-AI-ML-TargetDeviceErrorCauses IE that can be used by the target UE to provide measurement error reasons for direct or AI / ML-assisted NR AI / ML to a location server. Such implementations may be applicable to the target SL device and / or UE, providing the above error causes to the SL configuration entities.

[137] In implementations, an NG-RAN node can signal an IE NR-AI-ML-NG-RANnodeErrorCauses, with one or more parameter combinations included in the IE NR-AI-ML-TargetDeviceErrorCauses described above. Error causes derived at the NG-RAN node (e.g., gNB and / or TRP) can be signaled to a location server via an NRPPa interface, for example, using the Error Indication message. Additionally, the following error causes can be signaled from the NG-RAN node side: • The target UE or PRU UE has been moved to another cell. • The requested AI / ML positioning measurement could not be provided in time. • The AI / ML training model is invalid and needs to be retrained. • The AI / ML inference model is invalid and needs to be reacquired.

[138] In the implementations, the positioning measurements, including the definitions contained in Table 9 and Table 10, may have an associated quality indicator showing the following: • Quality of the measurement performed based on RSS and timing parameters. Petition 870260069606, dated 07 / 14 / 2026, page 60 / 134 55 / 125 • Quality of the measurement performed in relation to similar measurements performed at surrounding true-field reference locations.

[139] The implementations described here also provide report configuration procedures. For example, implementations that allow the configuration of measurement reports and direct AI / ML positioning reports (e.g., fingerprints) are described, as in the following scenarios, where an AI / ML inference model can be deployed on the following entities to perform positioning: • UE-based positioning with UE-side model • UE-assisted / LMF-based positioning with LMF-side model • NG-RAN node-assisted positioning with LMF-side model

[140] The above scenarios are presented only as examples and the corresponding details can be extended beyond these example scenarios.

[141] In UE-based positioning scenarios, a target UE can request training datasets based on DL and SL reference signals (e.g., DL-PRS, SL-PRS, etc.) from various data sources, including measurements taken and collected internally on the target UE, on other UEs, on a location server, on an NG-RAN node, on a PRU, on the OAM, on the TCE, and / or combinations thereof. Additionally, training can be performed on the UE side, and a computed location estimate can be computed by the target UE device. In such implementations, a reporting configuration including reporting criteria and / or assistance information and associated measurement reports can be initiated from the target UE. Petition 870260069606, dated 07 / 14 / 2026, page 61 / 134 56 / 125

[142] Multiple network entities, UEs and / or nodes can be enabled with the following procedures to enable a reporting configuration, such as in scenarios where AI / ML model training is performed on the UE side.

[143] FIG. 13 illustrates 1300 scenarios that support machine learning for positioning according to aspects of the present disclosure. The 1300 scenarios, for example, include a 1300a scenario in which UE-side training can be performed with target UE inference with other UEs, and a 1300b scenario in which UE-side training can be performed with target UE inference with network entities.

[144] In scenarios 1300, in 1302, a target UE 1304 can request a plurality of direct AI / ML positioning measurements based on defined reporting criteria. For example, in scenario 1300a for signaling transport towards a UE, in 1304a the SL positioning protocol (SLPP) and / or other defined positioning protocol can be employed by a target UE 104a to request direct AI / ML positioning reports from UEs 104b, including measurement reporting criteria and / or assistance information. In 1300b and for network entities 102, such as a location server, in 1304b LPP signaling can be employed to request direct AI / ML positioning reports, including measurement reporting criteria and / or assistance information. In scenarios involving an NG-RAN node, RRC and / or related UL signaling, such as UL MAC CE, can be used.

[145] In addition to scenarios 1300, the respective network entities 102 and / or UEs 104 may provide responses 1306 to requests 1304 to provide measurements correlated to the reporting criteria and / or assistance information indicated in requests 1304. For example, UEs 104b may respond in 1306a via SLPP, and network entities may respond in 1306b via LPP and / or RRC. In scenarios for network entities 102 Petition 870260069606, dated 07 / 14 / 2026, page 62 / 134 57 / 125 reporting measurements, a location server can receive measurement reports from other UEs based on solicited or unsolicited requests (e.g., PRU UEs and / or other UEs) and report such measurements to the target UE 104a.

[146] In 1308, the target UE 104a can build a training dataset based on measurement reports from different sources and perform AI / ML model training. In implementations, the target UE 104a can perform inference using a trained ML model and based on new measurement data, repeating steps 1304a, 1304b and 1306a, 1306b to obtain new measurement data for processing through a trained ML model. In implementations, training and inference datasets can be requested at once, to avoid repeating 1304 and 1306 to train an ML model and then perform inference later.

[147] In implementations, ML model training can be performed on the network side (e.g., on the location server or on the NG-RAN node (e.g., gNB)) and / or other UE / device, e.g., anchor UE, PRU UE, UE SL, and so on. In such implementations, the network entity and / or UE / device can request a plurality of reporting criteria so that the desired measurements and assistance information are reported in a timely and accurate manner. These datasets may contain reference points or reference locations where fingerprint information or other positioning measurements are sampled, measured, or associated.

[148] FIGS. 14a and 14b illustrate 1400 scenarios that support machine learning for positioning according to aspects of the present disclosure. The 1400 scenarios, for example, include a 1400a scenario and a 1400c scenario where UE side training is performed with target UE inference, and a scenario Petition 870260069606, dated 07 / 14 / 2026, page 63 / 134 58 / 125 1400b where network-side training is performed with target UE inference.

[149] In scenarios 1400, in 1402 the respective network entities 102 and / or UEs 104 may request from target UE 104a a plurality of direct AI / ML positioning measurements based on certain defined reporting criteria. In terms of signaling transport to UEs 104, SLPP and / or a newly defined positioning protocol may be employed, while in the case of network entities 102, as a location server, LPP signaling may be employed, and in scenarios for an NG-RAN node, RRC or any related DL signaling, such as DL MAC CE, may be employed.

[150] In 1404, the target UE 104a can respond to received requests and provide the requested measurements according to the reporting criteria and / or assistance information. For network entities 102, the location server can, for example, receive measurement reports from other UEs based on solicited or unsolicited requests (e.g., PRU UEs, other UEs, etc.) and then report such measurements to the target UE 104a.

[151] In 1406, the other UEs 104b and / or network entities 102 can generate a training dataset based on measurement reports from different sources and perform AI / ML model training.

[152] In 1408 and according to the implementations, the other UEs 104b and / or network entities 102 can perform inferences based on new measurement data by repeating the procedures in 1402 and 1404. In implementations, the training and inference datasets can be requested at once, as an alternative to repeating 1402, 1404.

[153] In implementations, the various entities or network nodes can be enabled with the following procedures for Petition 870260069606, dated 07 / 14 / 2026, page 64 / 134 59 / 125 Enable a reporting configuration in scenarios where AI / ML model training is not performed on the EU side: • The target UE performing the training can transmit a direct AI / ML positioning report configuration to the network entity and / or other UEs / devices and receive a corresponding report for direct AI / ML positioning measurements from downlink (DL) or sidelink (SL), e.g., fingerprint measurements. In other implementations, UL positioning measurements can also be provided, such as in cases where the UE can train a model based on such UL measurements, e.g., fingerprints. • The network entity (e.g., location server and / or NG-RAN node) performing the training can transmit a direct AI / ML positioning report configuration to the target UE and receive a corresponding report for direct AI / ML positioning measurements from downlink (DL) or sidelink (SL), e.g., fingerprint measurements. • A UE / node (e.g., anchor UE, PRU UE, UE SL, etc.) performing the training can transmit a direct AI / ML positioning report configuration to the target UE and receive a corresponding report for direct AI / ML positioning measurements via downlink (DL) or sidelink (SL), e.g., fingerprint measurements.

[154] In UE-assisted positioning scenarios, a location server can request measurement training datasets based on DL and SL reference signals (e.g., DL-PRS, SL-PRS, etc.) from various data sources, including measurements collected internally on the location server, multiple UEs, other neighboring location servers, NG-RAN nodes, positioning reference units, and combinations thereof. Petition 870260069606, dated 07 / 14 / 2026, page 65 / 134 60 / 125

[155] FIG. 15 illustrates a scenario 1500 that supports machine learning for positioning according to aspects of the present disclosure. Scenario 1500, for example, represents implementations for report exchange when network-side training and network-side inference are performed. In scenario 1500, training and inference are performed on a network entity 102 (e.g., location server) and network entity 102 can employ the illustrated signaling mechanisms to signal the direct AI / ML positioning report configuration, as well as receive measurements from a UE 104, e.g., target UE, PRU UE, and so on.

[156] In 1502, the respective network entities 102 can request a plurality of direct AI / ML positioning measurements based on certain defined reporting criteria from a UE 104. In terms of signaling transport towards UEs 104 for 1502 requests, LPP signaling can be employed, while in scenarios for an NG-RAN node, RRC and / or related DL signaling, such as DL MAC CE, can be employed.

[157] In 1504, UE 104 may respond in kind to requests 1502 received from network entities 102 and provides, as part of the responses 1504, measurements in accordance with the reporting criteria and / or assistance information specified by the requests 1502.

[158] In 1506, network entity 102 constructs a training dataset based on measurement reports from different UEs 104 and performs AI / ML model training. In 1508, network entity 102 performs inference based on new measurement data, repeating steps 1502 and 1504. Alternatively, or additionally, training and inference datasets may be requested in a single attempt. Petition 870260069606, dated 07 / 14 / 2026, page 66 / 134 61 / 125

[159] FIG. 16 illustrates a 1600 scenario that supports machine learning for positioning in accordance with aspects of the present disclosure. The 1600 scenario, for example, represents implementations for request and response procedures for stored AI / ML training datasets based on reported AI / ML measurements. In the 1500 scenario, where training is performed on a UE 104 (e.g., PRU UE), the UE can employ the signaling illustrated as shown in the 1600 scenario and described below to receive an AI / ML training dataset to perform training on the UE 104.

[160] In 1602, network entity 102 may request a plurality of direct AI / ML positioning measurements based on defined reporting criteria from a UE 104. In terms of signaling transport from network entity 102 to the UE 104, LPP signaling can be employed and, in scenarios for an NG-RAN node, RRC and / or related DL signaling, such as DL MAC CE, can be employed.

[161] In 1604, UE 104 can respond to request 1602 from network entities and provide measurements according to the reporting criteria and / or assistance information specified in request 1602. In 1606, network entity 102 constructs the training dataset based on measurement reports from different UEs / source nodes and stores the AI / ML training dataset. The storage of the training dataset can be associated with additional validity criteria, such as temporal criteria (e.g., time window, validity time duration, timer expiration) and / or spatial criteria, e.g., geographic region ID, area ID, cell ID, tracking area ID, system information area ID, zone ID, AI-ML-DatasetValidityArea, or combinations thereof. Petition 870260069606, dated 07 / 14 / 2026, page 67 / 134 62 / 125

[162] In 1608, in scenarios where training is performed on the UE 104 side, a UE 104 can request the AI / ML training dataset, which is based in part on measurements provided from 1604. In 1610, network entity 102 can respond to the 1608 request with the AI / ML training dataset, which can be based on certain criteria, including the applicability of the training dataset to the UE 104 location, radio link quality, radio channel parameters, mobility pattern, orientation, and so on.

[163] In 1612, UE 104 performs training based on the training dataset received from network entity 102 and, in 1614, network entity 102 and / or UE 104 can perform inference to derive an estimated location of a target UE 104 based on the trained AI / ML model.

[164] In implementations, scenario 1600 may be applicable to scenarios where, if training is performed on an NGRAN node, the NG-RAN node may request and receive a constructed training dataset stored on a localization server (e.g., LMF) based in part on measurements that the NG-RAN node provided to the localization server, as described below with reference to FIG. 17.

[165] In implementations, model training can be performed on the UE side, where the signaling mechanisms in scenario 1300b can be used to signal the configuration of the direct AI / ML positioning report, as well as receive measurements from a network entity. One or more UEs 104 (e.g., a target UE) can provide a plurality of direct AI / ML measurements for inference on the network side.

[166] In implementations, several entities and / or network nodes can be enabled with the following procedures to enable a reporting configuration in scenarios where AI / ML model training and inference are performed in Petition 870260069606, dated 07 / 14 / 2026, page 68 / 134 63 / 125 network side. For example, the network entity (e.g., location server) can transmit a direct AI / ML positioning report configuration to UEs and receive a corresponding report for direct AI / ML positioning measurements from DL and / or SL, e.g., fingerprint measurements.

[167] In NG-RAN assisted positioning scenarios, a location server can request a plurality of direct AI / ML positioning measurements from UL based on UL reference signals (e.g., SRS) for positioning from multiple data sources, including neighboring gNBs / TRPs or NG-RAN nodes, PRU TRPs, CUs, DUs, or combinations thereof.

[168] FIG. 17 illustrates a scenario 1700 that supports machine learning for positioning according to aspects of the present disclosure. Scenario 1700, for example, represents the exchange of reports when LMF-side training is performed with LMF-side inference. In scenario 1700, where training and inference are performed on a location server 1702, the location server 1702 can employ the illustrated signaling mechanisms to signal the AI / ML positioning report directly from UL.

[169] In 1704, the location server 1702 can request a plurality of AI / ML positioning measurements directly from UL based on defined reporting criteria from an NGRAN node 1706, for example, a service gNB / TRP, neighboring gNB / TRP, PRU gNB, TRP, etc. In terms of signaling transport towards the NG-RAN node 1706, NRPPa signaling can be employed, for example, Positioning Measurement Request and Positioning Measurement Response messages.

[170] In 1708, NG-RAN node 1706 can respond to request(s) 1704 from location server 1702 and provide measurements according to the reporting criteria and / or assistance information as specified in request 1704. Petition 870260069606, dated 07 / 14 / 2026, page 69 / 134 64 / 125

[171] In 1710, the location server 1702 builds a training dataset based on measurement reports from different source NG-RAN nodes 1706 and performs the training of an AI / ML model.

[172] In 1712, the location server 1702 performs inference based on new measurement data, repeating steps 1704 and 1706. In one implementation, the training and inference datasets can be requested at once.

[173] In implementations where training is performed on NG-RAN node 1706, NG-RAN node 1706 can request and receive AI / ML positioning measurement reports directly from UL from location server 1702, for example, via NRPPa and / or other NG-RAN nodes, for example, via the Xn interface.

[174] In implementations, several network entities and / or nodes can be enabled with the following procedures: The location server 1702 can transmit a direct AI / ML positioning report configuration to a plurality of NG-RAN nodes 1706 and receive a corresponding report for direct AI / ML positioning measurements from UL, for example, fingerprint measurements.

[175] In additional or alternative implementations, training dataset construction and dataset training may not necessarily occur on the same entity and may occur on other separate entities or network nodes. For example, according to scenario 1400Error! Reference source not found., a UE PRU, anchor UE, and / or another UE may perform dataset construction or dataset training. Furthermore, and similar to scenario 1600, a service gNB / TRP, a neighboring gNB / TRP, or a gNB / TRP PRU may perform training dataset construction or dataset training. Additionally, training dataset construction and AI / ML model inference may also follow the same behavior, although they are not Petition 870260069606, dated 07 / 14 / 2026, page 70 / 134 65 / 125 necessarily performed at the same entity. Alternatively or additionally, the reporting setup methods discussed above can be combined in various ways, such as to utilize a plurality of direct AI / ML positioning measurements from DL, SL, and UL in one or more combinations.

[176] The implementations described here also provide several ML-related reporting criteria. For example, the settings for reporting criteria are detailed to support direct AI / ML position estimation, for example, using fingerprinting methods.

[177] In UE-based positioning scenarios (e.g., with UE side model), the target UE may request a plurality of direct AI / ML positioning measurements from DL or SL or other data needed for training or inference. A set of common reporting criteria can be defined for network entities or UE / devices that provide measurement reports for building datasets. Table 11: Common Reporting Criteria Parameter Description Fingerprint Type This Information Element (IE) describes the type of fingerprints to be reported. This implies that the fingerprint is generated at the measurement entity / node and then reported to the target UE. The fingerprint may comprise one or more combinations of the following RAT-dependent DL / SL positioning measurements: RSTD, UE time difference RxTx, ToA, RSS metrics such as PRS / SRS RSRP, RSRPP, RSSI, RSRQ or AoD, AoA- or RAT-independent measurements, e.g., A-GNSS, Bluetooth, WiFi, IMU sensor, etc. In an implementation, the reporting configuration entity may configure different measurements depending on the type of AI / ML model used, for example, for AI / ML model A, timing-based and RSS measurements may characterize a fingerprint, while for AI / ML model B, only RAT-independent measurements are used.In a different implementation, these fingerprints can be organized into a hierarchical request for different fingerprints, depending on the AI / ML model type. Reference / True-of-Field Location Type This IE describes the true-of-field reference location type, where each of the direct AI / ML fingerprints or positioning measurements were obtained as referenced in TS 23.052. Petition 870260069606, dated 07 / 14 / 2026, page 71 / 134 66 / 125 including Ellipsoid Point, Ellipsoid Point with Uncertainty Ellipse, Ellipsoid Point with Uncertainty Circle, Polygon, Ellipsoid Point with Altitude, Ellipsoid Point with Altitude and Uncertainty Ellipsoid, Ellipsoid Arc, High-Precision Ellipsoid Point with Uncertainty Ellipse, High-Precision Ellipsoid Point with Altitude and Uncertainty Ellipse, and so on. In different implementations, the field truth reference locations may correspond to 2D or 3D location points (including height / altitude). Immediate Reports This time-domain reporting IE indicates that immediate direct AI / ML reports, including fingerprint measurements, are requested based on available processed measurements. Periodic Reports This time-domain reporting IE indicates that periodic direct AI / ML reports, including fingerprint measurements, are requested based on available processed measurements.This may include other subfields, such as Report Quantity, indicating the number of Direct AI / ML measurement reports, Report Interval, indicating the periodicity or interval between Direct AI / ML measurement reports, or a combination thereof. In other implementations, periodic reports may be enabled and disabled if no report quantity is configured. Triggered Reports This time-domain reporting IE indicates that triggered periodic Direct AI / ML reports, including fingerprint measurements, are requested based on available processed measurements. This may include other subfields such as geographic area change, such as Cell ID, Zone ID, new location or field truth reference point, or a combination of these changes. Another subfield may include a validity time associated with how long the triggered report remains active or inactive.Pre-processed Measurements: This IE indicates whether the measurement should pre-process the measurement, for example, apply normalization to the measurement, and so on. This IE may be in the form of an indicator showing whether pre-processing should be applied or not. In one implementation, an additional subfield may include data cleaning, where the measurement entity is required to clean and prune measurements before reporting, for example, removing incorrect labels, incorrectly classified data. This could be implemented, for example, in the form of an indicator. In one implementation, the measurement entity may be required to remove measurement biases or imbalances in the reported measurement dataset through a subfield, for example, through a Bias or Sampling subfield. In one implementation, another subfield may include whether the measurement data requires normalization before reporting the plurality of direct AI / ML measurements.Digital Imprint Environment This IE indicates the type of environment in which direct AI / ML or digital imprint measurements should be reported, for example, environment. Petition 870260069606, dated 07 / 14 / 2026, page 72 / 134 67 / 125 Indoor / Outdoor / Semi-Indoor / Semi-Outdoor, Office, Factory. Additional subfields may include floor plan information, including number of rooms, room area, and height. Measurement Validity This IE indicates the validity period of direct AI / ML / fingerprint measurements to be reported. This may also apply to assisted AI / ML positioning measurements. Assisted AI / ML positioning measurements may be defined as measurements that have been enhanced and / or optimized using AI / ML models, for example, RAT-dependent measurements such as RSTD, RTOA, RSRP, RSRPP, Rx-Tx, AoAs, AoDs, time difference, and so on. UE Type This IE indicates the UE type configuration, including antenna information, form factor, dimensions, portable UE, CPE, and so on. In another implementation, this may indicate whether the UE can report only DL positioning measurements, only SL positioning measurements, or a combination thereof.In another implementation, the UE type may also indicate the UE function, for example, PRU UE, Normal UE, Anchor UE, Roadside Unit, SL Positioning Server UE, and so on. Number of fingerprint measurements reported per true-field reference location This IE indicates the number of direct AI / ML or fingerprint measurements to be reported by the measuring entity at a given true-field reference location. This may be signaled as a single value or minimum-maximum range within which measurements should be reported. In another implementation, an index of true-field reference locations may be mapped to an index of the number of measurements required at each location. Mobility This IE is used to report whether measurements are reported depending on the type of mobility pattern of the measuring entity, comprising static, low, medium, or high mobility patterns.An additional subfield may include horizontal / vertical velocity or acceleration parameters. Orientation This IE is used to report the orientation of the measurement entity in terms of the Local Coordinate System (LCS) or Global Coordinate System (GCS). This may extend to overall orientation or the orientation of antenna configurations relative to the measurement entity or relative to a global reference. Fingerprint / Measurement Quality This IE is used to report measurement confidence or actual measurement quality, depending on whether the measurement is timing-based, angular, or RSS metric. In another implementation, this field may be used to indicate the overall quality of a composite fingerprint of one or more measurements. Label Quality This IE is used to report the label quality of a direct AI / ML or assisted AI / ML measurement.Quality can be expressed as a confidence indicator, for example, a binary indicator where '0' refers to low-quality labels while '1' refers to high-quality labels, or as a smooth indicator showing the percentage of a label's quality, for example, 0%, 10%, 20%... 100%. Petition 870260069606, dated 07 / 14 / 2026, pp. 73 / 134 68 / 125 In another implementation, where a label comprises a true-to-the-field reference location, the label quality corresponds to the location estimate quality depending on the location source and the method used to derive the location, e.g., offline location input, RAT-dependent methods, RAT-independent methods, or a combination thereof. Fingerprint Quality Validity This IE is used to report the validity associated with a fingerprint quality and may comprise temporal validity criteria, e.g., time window, after the expiration of a timer, e.g., UTC time, GNSS time, etc. In another implementation, the validity associated with fingerprint quality may be associated with some spatial validity criteria, associated with the geographic region in which the fingerprint was measured, e.g., cell ID, area ID, zone ID, and so on.Label Quality Validity This IE is used to report the validity associated with a label quality and may include temporal validity criteria, e.g., time window, after expiration of a timer, specified time base, e.g., UTC time, GNSS time, etc. In another implementation, the validity associated with a label quality may be associated with some spatial validity criteria, associated with the geographic region in which the fingerprint was measured, e.g., cell ID, area ID, zone ID, and so on.

[178] For EU-assisted positioning scenarios, one or more common reporting criteria detailed in Table 11 may be signaled by a network entity, for example, location server, for reporting data types, for example, measurement data.

[179] For NG-RAN assisted positioning scenarios, one or more common reporting criteria detailed in Table 11 can be signaled by a network entity, for example, location server for an NG-RAN node, for example, gNB for reporting data types, for example, measurement data.

[180] In implementations, lower-layer signaling with respect to LPP (e.g., RRC signaling, MAC CE, DCI signaling, or a combination thereof) can be used to transmit direct AI / ML reporting criteria settings. In implementations, LPP or RRC signaling can be used to add, modify, remove, update, enable, and / or Petition 870260069606, dated 07 / 14 / 2026, page 74 / 134 69 / 125 disable one or more settings for direct EU AI / ML positioning reports.

[181] In the implementations, the reporting criteria indicated in Table 11 and the associated implementation details can be extended to assisted AI / ML positioning measurements for Cases A, B, and C, where positioning measurements are enhanced using one or more AI / ML models.

[182] In implementations, common reporting criteria can be transmitted via system information blocks (SIBs) or positioning system information blocks (posSIBs) to multiple UEs within a given geographic region, for example, based on the same cell ID, based on a system information area, based on the zone ID, or a combination thereof.

[183] ​​The implementations also allow the reporting of various assistance information related to direct AI / ML positioning measurements to assist in deriving a location estimate of the target UE. For example, this can be extended to scenarios where AI / ML assisted positioning measurements are being reported, where applicable.

[184] In implementations, a measurement entity (e.g., UE or NG-RAN node performing AI / ML positioning measurements) can be configured to report the positioning measurement correlation between different sets of measurements performed on the same measurement entity. This correlation metric, for example, may be subject to UE capability. In at least one implementation, the measurement entity may report via a top-layer parameter (e.g., LPP signaling) RSS-Correlation associated with a set of AI / ML positioning RSRP / RSSI measurements with each DL or SL PRS feature, e.g., DL feature ID. In scenarios for an NG-RAN node measurement, RSS-Correlation may be associated with different sets of UL RSS measurements with each Petition 870260069606, dated 07 / 14 / 2026, page 75 / 134 70 / 125 UL resource, for example, SRS resource ID. In extended implementations, the correlation metric can be applied to time-based measurements (e.g., RSTD, ToA, etc.) or angle-based measurements (e.g., AoA, AoD, etc.). The correlation measurement metric can be obtained by true-field reference location to accurately and fairly calculate the measurement correlation of multiple measurements made at the same true-field reference location.

[185] In implementations, positioning measurement correlation can be obtained from different UEs / devices at the same true-field reference location. Measurements may be based, at least in part, on UE / NG-RAN node vendor-specific variations and therefore there may be variations of the same positioning measurement at the same true-field reference location. In such implementations, the network entity or UE / device collecting the positioning measurements can correlate the different measurements received from different network nodes / UEs / devices. Correlation can also be performed in the time domain (e.g., using a (sliding) time window), in addition to the spatial domain, e.g., based on location. In implementations, measurement correlations between adjacent reference location points can also be configured, determined, and reported. [18 6] According to the implementations, a measurement entity (e.g., UE and / or NG-RAN node) performing AI / ML positioning measurements can be configured to report channel characteristics associated with a direct AI / ML positioning measurement, including whether the measurement is line-of-sight (LOS) or non-LOS (NLOS) based on a binary (e.g., hard decision) or soft indicator, link path loss, channel coefficients, or a combination thereof. Report Petition 870260069606, dated 07 / 14 / 2026, page 76 / 134 71 / 125 additional channel features associated with a measurement can increase the stability and reliability of a reported AI / ML positioning measurement, for example, an RSS measurement such as RSRP.

[187] In implementations, the difference in path loss between a direct AI / ML true-field reference location point (e.g., fingerprint measurement) and the measurement of a target UE can be used to derive a PRS / SRS RSS measurement as a function of the Tx and Rx antenna gains, path loss reference, path loss exponents, standard deviation of fading parameters, e.g., shadow fading at the true-field reference location point(s) and at the unknown target UE location. One or more of the above-mentioned parameters can be configured for reporting and reported to the requesting entity, e.g., UE / device or NG-RAN node or location server. In implementations, the measuring entity and / or the target UE can calculate the path losses and report them to the requesting entity along with the direct AI / ML positioning measurement.

[188] In implementations, the measurement entity (e.g., UE or NG-RAN node) that performs AI / ML positioning measurements can be configured to report the average measurement at each true-field reference location point in (NxMi) j sample points, where N is a configured sample of each measurement instance while M is the total number of measurements from each gNB / TRP instance in the case of DL positioning measurements at each jth true-field reference location, while in the case of UL measurements M is the total number of measurements collected from each ith ue. In implementations, additional statistical measures can be obtained on NxMi measurement points, including variance, standard deviation, probability distribution functions, distribution functions Petition 870260069606, dated 07 / 14 / 2026, page 77 / 134 72 / 125 cumulative and so on at each location / reference point. NxMi can also be configured using upper-layer signaling, such as LPP, RRC, SLPP, or a combination thereof.

[189] In implementations where the configured direct AI / ML positioning model includes k-NN in the supervised case or K-Means in the case of an unsupervised model, a network entity that uses inference to determine the location of a target UE based on a fingerprint dataset can use the following generalized distance formula according to Minkowski distance to derive the location of the target UE by processing the newly received measurements using: dMinkowski(x, y) = (Σ?= ilxí - yi |a)“ (1) where n is the total number of measurements received with a pair (x,y) of parameters, while a can be configurable depending on the distance algorithm used, for example, if a=1, then the Manhattan distance approach is used while if a=2 then the Euclidean distance approach is used. In other implementations, Hamming distance or cosine distance and cosine similarity can be used to determine the similarity between direct AI / ML multidimensional positioning data.

[190] In implementations where online measurements must be matched with fingerprint measurements at each true-field reference location / point, a similarity score based on the cumulative Manhattan distance in Eq. (1), where a=1, can be used to determine the target UE location, whereby the measurement entity is configured to report the minimum and maximum PRS / SRS RSS measurement from a total of Mi,j measurements where i refers to measurements originating from each ithgNB / TRP or UE at each jth true-field reference location. The similarity score at each true-field reference location (PRef-LoCatiOn) can be given by the following mathematical relationship, where: Petition 870260069606, dated 07 / 14 / 2026, p. 78 / 134 73 / 125 PREf Location THE') AI / ML \ \^M / ML_^M / MLrT-UE,minl + lri,maxrT-UE,maxD) (2) where ^^^L is the minimum fingerprint / PRS or SRS RSS positioning measurement of the i gNB / TRP or UE, while ^^^min is the minimum sample positioning measurement of the set of measurements provided by the target UE, P,^^ is the maximum measurement of i, f L^L& Fingerprint positioning / PRS or SRS RSS of the ith gNB / TRP or UE, while Pr-i^max is the maximum positioning measurement of the sample from the set of measurements provided by the target UE. The lowest value of PRef-LoCation(Í^) corresponds to the most probable location where the target UE may be located.

[191] In implementations, PRef-Location(D can be derived according to a predefined time window associated with a start time, window duration, end time and periodicity, in order to capture the variation of positioning measurements and therefore the similarity score over time.

[192] In the implementations, a first arrival path is considered so that the RSS measurements above are used as part of the fingerprint training dataset. In the implementations, the first arrival path and up to T additional configurable paths can be associated with a fingerprint RSS measurement and can be reported to the requesting network entity / node / UE.

[193] In implementations, the measurement entity (e.g., a UE, PRU UE, or SL UE) can be configured to indicate whether an RSS / fingerprint measurement (e.g., DL PRS RSRP) of a set of PRS features configured within the same feature set was measured with the same DL reception beam or even spatial filter for reception.

[194] In implementations, the measurement, training and / or inference entity can be configured to autocalibrate direct or assisted AI / ML positioning measurements. Petition 870260069606, dated 07 / 14 / 2026, page 79 / 134 74 / 125 based on providing certain parameters for inclusion in the training or inference dataset for a reference device, for example, a UE PRU. In at least one example, a linear calibration can be employed to direct the UE measurement to that of a reference device, such as a UE PRU, which can be represented as follows: pAI / ML _ppAI / MLrPRU-UE,i,j =OTPrT-UE,i,j + r-TP where ΐί·τ— / M\j denotes the average SRS / PRS positioning measurement of the target UE from the i gNB / TRP or UE at each jth true-field reference location, PpRuMLjEij denotes the average PRU UE PRS / SRS positioning measurement of the ith gNB / TRP or UE at each jth true-field reference location, while δTΡ and μTΡ are the linear calibration parameters for mapping the target UE's RSS measurements to the UE's PRU. This is especially useful if different network entities or UEs / devices are performing measurements from different vendors. The linear parameters, δTP and μTP, can be configured for the measurement entity via upper-layer signaling, e.g., LPP, NRPPa, SLPP, etc., to calibrate the measurements before reporting.The measurement, training, and / or inference entity may additionally receive a request to perform self-calibration of direct or assisted AI / ML positioning measurements. In another implementation, a nonlinear function may also be used to self-calibrate direct or assisted AI / ML positioning measurements with procedures similar to those described for linear self-calibration in terms of providing and reporting nonlinear self-calibration parameters.

[195] The RSS measurements mentioned in the implementations described here may include RSRP, RSRPP, RSSI, RSRQ values, which are associated with DL PRS, SL PRS or UL SRS. Petition 870260069606, dated 07 / 14 / 2026, pp. 80 / 134 75 / 125

[196] FIG. 18 illustrates an example of an 1800 block diagram of an 1802 device (e.g., an apparatus) that supports machine learning for positioning according to aspects of the present disclosure. The 1802 device may be an example of a 104 UE as described herein. The 1802 device may support wireless communication with one or more 102 network entities, 104 UEs, or any combination thereof. The 1802 device may include components for bidirectional communications, including components for transmitting and receiving communications, such as an 1804 processor, an 1806 memory, an 1808 transceiver, and an 1810 I / O controller. These components may be in electronic communication or otherwise coupled (e.g., operationally, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[197] The 1804 processor, the 1806 memory, the 1808 transceiver, or various combinations thereof or various components thereof may be examples of means for carrying out various aspects of the present disclosure as described in this document. For example, the 1804 processor, the 1806 memory, the 1808 transceiver, or various combinations or components thereof may support a method for carrying out one or more of the operations described in this document.

[198] In some implementations, the 1804 processor, the 1806 memory, the 1808 transceiver, or various combinations or components thereof may be implemented in hardware (for example, in a communications management circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, discrete hardware components, or any combination thereof. Petition 870260069606, dated 07 / 14 / 2026, page 81 / 134 76 / 125 itself configured as or otherwise supporting a means to perform the functions described in this disclosure. In some implementations, the 1804 processor and the 1806 memory coupled to the 1804 processor may be configured to perform one or more of the functions described herein (for example, executing instructions stored in 1806 memory by the 1804 processor). In the context of UE 104, for example, the transceiver 1808 and the coupled processor 1804 coupled to transceiver 1808 are configured to cause UE 104 to perform the various operations described and / or combinations thereof.

[199] For example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples disclosed herein. For example, the 1804 processor and / or the 1808 transceiver may be configured as and / or otherwise support a means of receiving machine learning positioning configuration requests; and transmitting, based at least in part on the machine learning positioning configuration requests, machine learning positioning configuration responses that include positioning reference signal configurations to be measured at respective reference locations and with one or more associated validity criteria.

[200] In addition, in some implementations, the processor is configured to have the device receive machine learning positioning configuration requests from one or more network nodes or user equipment (UE) and transmit machine learning positioning configuration responses to the one or more network nodes or to the UE; the reference locations include one or more true-of-field reference locations; the machine learning positioning configuration responses include artificial intelligence configuration for the positioning reference signal settings; the processor is configured to Petition 870260069606, dated 07 / 14 / 2026, page 82 / 134 77 / 125 cause the device to transmit one or more machine learning positioning configuration responses independent of a machine learning positioning configuration request; the machine learning positioning configuration responses include one or more direct machine learning configurations or assisted machine learning configurations; the direct machine learning configuration includes configuration to perform radio frequency fingerprinting.

[201] In addition, in some implementations, machine learning positioning configuration requests include a request for one or more training types, a field truth location request, a machine learning method, a machine learning on-demand positioning reference signal request, or pre-configured machine learning assistance data; positioning reference signal configurations include one or more positioning reference signal features, feature sets, transmit / receive points, or positioning frequency layer to be measured at each reference location; the one or more associated validity criteria include one or more temporal criteria or spatial criteria; temporal criteria include a measurement time defined by one or more time bases;One or more time bases include at least one system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time; one or more associated validity criteria include a spatial criterion that refers to an indication of a geographic region, and the spatial criteria include one or more area identifiers, cell identifiers, or zone identifiers.

[202] In addition, in some implementations, the positioning reference signal settings include one or more Petition 870260069606, dated 07 / 14 / 2026, page 83 / 134 78 / 125 indications of one or more uplink radio access technology dependent measurements, downlink radio access technology dependent measurements, or sidelink radio access technology dependent measurements to be performed; the positioning reference signal configurations include one or more indications of one or more downlink radio access technology independent measurements or sidelink radio access technology independent measurements to be performed;The machine learning positioning configuration responses additionally include one or more configurations belonging to at least one of the following: a k-nearest neighbors (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, Bayesian networks, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; the apparatus includes at least one of the following: a location server, a next-generation radio access network (NGRAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE.

[203] In addition, in some implementations, the positioning reference signal settings include a received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink; and the received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink is defined as including a linear average of a total received power observed in feature elements of a slot that carry the positioning reference signal configured for measurement; the positioning reference signal settings include a positioning reference signal arrival time measurement for one or more of the following downlink, uplink, or sidelink; Petition 870260069606, dated 07 / 14 / 2026, page 84 / 134 79 / 125 and the measurement of the arrival time of a positioning reference signal for one or more of a downlink, uplink, or sidelink is defined as including the reception time of a positioning reference signal at a receiver reference point; the positioning reference signal settings include an indication that a location server is allowed to transmit an error cause related to an incorrect configuration of a positioning reference signal; the positioning reference signal settings include an indication that a target user equipment (UE) is allowed to transmit an error cause related to an error in one or more of a reception, a machine learning positioning configuration response, or a measurement error related to a machine learning positioning measurement.

[204] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means of transmitting a machine learning positioning configuration request; receiving a machine learning positioning configuration response that includes a positioning reference signal configuration to be measured at one or more respective reference locations and with one or more associated validity criteria; and performing, based at least in part on the positioning reference signal configuration, one or more machine learning position measurements.

[205] In addition, in some implementations, the processor and transceiver are configured to cause the device to do one or more of the following: receive the positioning configuration response Petition 870260069606, dated 07 / 14 / 2026, page 85 / 134 80 / 125 machine learning in response to a machine learning positioning configuration request; or receive the machine learning positioning configuration response independent of the machine learning positioning configuration request; the processor is configured to have the device input one or more machine learning position measurements into a machine learning model and receive an output from the machine learning model; the processor is configured to have the device generate an estimated device location based, at least in part, on the output of the machine learning model; the device includes one or more of a target user equipment (UE), a positioning reference unit (PRU), or an anchor UE.

[206] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means to transmit a configuration request to set up reference signals for machine learning positioning measurements; receive a configuration response including reference signal configuration; and transmit, based at least in part on the reference signal configuration, a reference signal transmission enablement command.

[207] In addition, in some implementations, the reference signals include one or more probing reference signals or positioning reference signals; the processor is configured to make the device transmit a reference signal transmission disable command; the device includes a location server, and in which the processor is configured to make the device transmit the reference signal transmission enable command for one or more Petition 870260069606, dated 07 / 14 / 2026, page 86 / 134 81 / 125 other devices that are configured to transmit the reference signals.

[208] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means to transmit one or more machine learning positioning report requests including a machine learning report configuration and one or more common reporting criteria; receive one or more machine learning positioning reports; process one or more machine learning positioning reports by means of a machine learning model; and generate, based at least in part on the output of the machine learning model, an estimated location of a user device (UD).

[209] In addition, in some implementations, the machine learning reporting configuration includes one or more direct machine learning reporting configurations or assisted machine learning reporting configurations; the device includes a configuration entity, and wherein the configuration entity includes at least one of a location server, a next-generation radio access network (NGRAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE; the processor is configured to have the device transmit one or more machine learning positioning report requests to one or more second devices, and to receive one or more machine learning positioning reports from the one or more second devices, and wherein the one or more second devices include at least one of a location server, a next-generation radio access network (NGRAN), a unit of Petition 870260069606, dated 07 / 14 / 2026, page 87 / 134 82 / 125 Positioning Reference Unit (PRU), a UE, an anchor UE, or a target UE.

[210] In addition, in some implementations, one or more common reporting criteria include one or more of a fingerprint type, a true-of-field reference location type, a time-domain reporting type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprint environment indication, a fingerprint quality indication, or a label quality indication; for at least one machine learning positioning report request, one or more common reporting criteria are configured to be one or more of the following: augmented, removed, updated, enabled, or disabled; the processor is configured to have the device broadcast one or more common reporting criteria via positioning system information broadcast signaling;The machine learning reporting configuration includes an option to report the correlation of machine learning positioning measurements between different sets of measurements.

[211] In addition, in some implementations, the machine learning positioning measurement correlation includes one or more spatial domain correlations or temporal domain correlations; the machine learning positioning reports include one or more machine learning positioning measurements or machine learning positioning location information; the machine learning report configuration includes an indication to report path loss at different locations, including a true-field reference location; the machine learning report configuration includes an indication to average the measurements of Petition 870260069606, dated 07 / 14 / 2026, page 88 / 134 83 / 125 machine learning positioning across a configured number of measurements and reporting the average as part of one or more machine learning positioning reports; the machine learning report configuration includes an indication to determine a similarity score at a configured location to determine an ideal mapping between a fingerprint measurement and an estimated location of a target UE.

[212] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured to, or otherwise, support a means of receiving one or more machine learning positioning report requests, including a machine learning report configuration and one or more common reporting criteria; generating one or more machine learning positioning reports based at least in part on the machine learning report configuration and one or more common reporting criteria; and transmitting one or more machine learning positioning reports.

[213] In addition, in some implementations, the device includes one or more user equipment (UE), an anchor UE or a target UE; the device includes a configuration entity, and wherein the configuration entity includes at least one location server, a next-generation radio access network (NG-RAN) or a positioning reference unit (PRU).

[214] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means Petition 870260069606, dated 07 / 14 / 2026, page 89 / 134 84 / 125 to transmit one or more machine learning positioning report requests, including a machine learning reporting configuration and one or more common reporting criteria; receive one or more machine learning positioning reports; generate, based at least in part on one or more machine learning positioning reports, a machine learning positioning training dataset; and train a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model.

[215] In addition, in some implementations, the processor and transceiver are configured to make the device receive one or more additional machine learning positioning reports; insert at least a portion of one or more additional machine learning positioning reports into the trained positioning machine learning model; and estimate a position of a target user equipment (UE) based, at least in part, on the output of the trained positioning machine learning model; the processor is configured to make the device: receive a request for machine learning positioning training data for positioning; and transmit, based, at least in part, on the request, the machine learning positioning training dataset; the processor is configured to make the device: receive a request for a trained positioning machine learning model;and transmit, based at least in part on the request, at least a portion of the trained positioning machine learning model.

[216] In a further example, the 1804 processor and / or the 1808 transceiver can support wireless communication in Petition 870260069606, dated 07 / 14 / 2026, pp. 90 / 134 85 / 125 device 1802 according to examples as disclosed herein. Processor 1804 and / or transceiver 1808, for example, may be configured as or otherwise support a means of receiving machine learning positioning configuration requests; and transmitting, based at least in part on the machine learning positioning configuration requests, machine learning positioning configuration responses that include positioning reference signal configurations to be measured at respective reference locations and with one or more associated validity criteria.

[217] In addition, in some implementations, the 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means of receiving machine learning positioning configuration requests from one or more network nodes or user equipment (UE) and transmitting machine learning positioning configuration responses to the one or more network nodes or to the UE; reference locations include one or more true-field reference locations; machine learning positioning configuration responses include artificial intelligence configuration for the positioning reference signal settings; transmitting one or more machine learning positioning configuration responses independent of a machine learning positioning configuration request;Machine learning positioning configuration responses include one or more direct machine learning configurations or assisted machine learning configurations; the direct machine learning configuration includes configuration to perform radio frequency fingerprinting.

[218] In addition, in some implementations, machine learning positioning configuration requests Petition 870260069606, dated 07 / 14 / 2026, pp. 91 / 134 86 / 125 includes a request for one or more training types, a request for true-to-field location, a machine learning method, a request for on-demand machine learning positioning reference signal, or pre-configured machine learning assistance data; the positioning reference signal configurations include one or more positioning reference signal features, feature sets, transmit / receive points, or positioning frequency layer to be measured at each reference location; the one or more associated validity criteria include one or more temporal criteria or spatial criteria; the temporal criteria include a measurement time defined by one or more time bases; the one or more time bases include at least one system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time;One or more associated validity criteria include a spatial criterion that refers to an indication of a geographic region, and the spatial criteria include one or more area identifiers, a cell identifier, or a zone identifier.

[219] In addition, in some implementations, the positioning reference signal settings include one or more indications of one or more uplink radio access technology-dependent measurements, downlink radio access technology-dependent measurements, or sidelink radio access technology-dependent measurements to be performed; the positioning reference signal settings include one or more indications of one or more downlink radio access technology-independent measurements or sidelink radio access technology-independent measurements to be performed; the machine learning positioning configuration responses additionally include one or more settings belonging to at least Petition 870260069606, dated 07 / 14 / 2026, pp. 92 / 134 87 / 125 minus one of the following: a k-nearest neighbor (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, Bayesian networks, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; the method is performed by an apparatus including at least one of the following: a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE.

[220] In addition, in some implementations, the positioning reference signal settings include a received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink; and the received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink is defined as including a linear average of a total received power observed in feature elements of a slot that carry the positioning reference signal configured for measurement; the positioning reference signal settings include a positioning reference signal arrival time measurement for one or more of the following downlink, uplink, or sidelink;and the measurement of arrival time of a positioning reference signal for one or more of the following links: downlink, uplink, or sidelink is defined as including the reception time of a positioning reference signal at a receiver reference point; the positioning reference signal settings include an indication that a location server is permitted to transmit an error cause related to an incorrect positioning reference signal setting; the positioning reference signal settings include; Petition 870260069606, dated 07 / 14 / 2026, pp. 93 / 134 88 / 125 is an indication that a target user equipment (UE) is permitted to transmit an error cause related to an error in one or more of a reception, a machine learning positioning configuration response, or a measurement error related to a machine learning positioning measurement.

[221] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means of transmitting a machine learning positioning configuration request; receiving a machine learning positioning configuration response that includes a positioning reference signal configuration to be measured at one or more respective reference locations and with one or more associated validity criteria; and performing, based at least in part on the positioning reference signal configuration, one or more machine learning position measurements.

[222] In addition, in some implementations, the 1804 processor and / or the 1808 transceiver, for example, may be configured to or otherwise support a means for one or more of: receiving the machine learning positioning configuration response in response to the machine learning positioning configuration request; or receiving the machine learning positioning configuration response independent of the machine learning positioning configuration request; inputting one or more machine learning position measurements into a machine learning model and receiving an output from the machine learning model; generating an estimated device location based, at least in part, on the model output. Petition 870260069606, dated 07 / 14 / 2026, pp. 94 / 134 89 / 125 machine learning; the method is performed by a device that includes one or more target user equipment (UE), a positioning reference unit (PRU), or an anchor UE.

[223] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means to transmit a configuration request to set up reference signals for machine learning positioning measurements; receive a configuration response including reference signal configuration; and transmit, based at least in part on the reference signal configuration, a reference signal transmission enablement command.

[224] In addition, in some implementations, the reference signals include one or more of the sounding reference signals or positioning reference signals; transmit a reference signal transmission deactivation command; the method is performed by a device that includes a location server, and in which the method additionally includes transmitting the reference signal transmission activation command to one or more other devices that are configured to transmit the reference signals.

[225] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means to transmit one or more machine learning positioning report requests including a machine learning report configuration and one or more common reporting criteria; receive one or more machine learning positioning reports; process one or more Petition 870260069606, dated 07 / 14 / 2026, pp. 95 / 134 90 / 125 machine learning positioning reports via a machine learning model; and generate, based at least in part on the output of the machine learning model, an estimated location of a user device (UD).

[226] In addition, in some implementations, the machine learning reporting configuration includes one or more direct machine learning reporting configurations or assisted machine learning reporting configurations; wherein the method is performed by an appliance including a configuration entity, and wherein the configuration entity includes at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE or a target UE;including additionally transmitting one or more machine learning positioning report requests from a first device to one or more second devices, and receiving one or more machine learning positioning reports from the one or more second devices, and where the one or more second devices include at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE or a target UE.

[227] In addition, in some implementations, one or more common reporting criteria include one or more of a fingerprint type, a true-of-field reference location type, a time-domain reporting type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprint environment indication, a fingerprint quality indication, or a label quality indication; wherein for at least one machine learning positioning reporting request, one or more of the common reporting criteria are configured to be one or more of Petition 870260069606, dated 07 / 14 / 2026, pp. 96 / 134 91 / 125 increased, removed, updated, activated or deactivated; including additionally broadcasting one or more common reporting criteria via positioning system information broadcast signaling; wherein the machine learning reporting configuration includes an indication to report the machine learning positioning measurement correlation between different sets of measurements.

[228] In addition, in some implementations, the machine learning positioning measurement correlation includes one or more spatial domain correlations or temporal domain correlations; wherein one or more machine learning positioning reports include one or more machine learning positioning measurements or machine learning positioning location information; wherein the machine learning report configuration includes an indication to report path loss at different locations, including a true-to-ground reference location; wherein the machine learning report configuration includes an indication to average the machine learning positioning measurements across a configured number of measurements and report the average as part of one or more machine learning positioning reports;where the machine learning report configuration includes an indication to determine a similarity score at a configured location to determine an ideal mapping between a fingerprint measurement and an estimated location of a target UE.

[229] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein. The 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means Petition 870260069606, dated 07 / 14 / 2026, pp. 97 / 134 92 / 125 to receive one or more requests for machine learning placement reports, including a machine learning report configuration and one or more common reporting criteria; generate one or more machine learning placement reports based, at least in part, on the machine learning report configuration and one or more common reporting criteria; and transmit one or more machine learning placement reports.

[230] In addition, in some implementations, the method is performed by a device including one or more of a user device (UD), an anchor UD or a target UD; wherein the method is performed by a device including a configuration entity, and wherein the configuration entity includes at least one of a location server, a next-generation radio access network (NG-RAN) or a positioning reference unit (PRU).

[231] In a further example, the 1804 processor and / or the 1808 transceiver may support wireless communication on the 1802 device according to examples as disclosed herein.The 1804 processor and / or the 1808 transceiver, for example, may be configured to, or otherwise, support a means of transmitting one or more machine learning positioning report requests, including a machine learning report configuration and one or more common reporting criteria; receiving one or more machine learning positioning reports; generating, based at least in part on one or more machine learning positioning reports, a machine learning positioning training dataset; and training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model. Petition 870260069606, dated 07 / 14 / 2026, pp. 98 / 134 93 / 125

[232] In addition, in some implementations, the 1804 processor and / or the 1808 transceiver, for example, may be configured as or otherwise support a means of receiving one or more additional machine learning positioning reports; inserting at least a portion of one or more additional machine learning positioning reports into the trained positioning machine learning model; and estimating a position of a target user equipment (UE) based at least in part on the output of the trained positioning machine learning model; including additionally: receiving a request for machine learning positioning training data for positioning; and transmitting, based at least in part on the request, the machine learning positioning training dataset; including additionally: receiving a request for a trained positioning machine learning model;and transmit, based at least in part on the request, at least a portion of the trained positioning machine learning model.

[233] The 1804 processor may include an intelligent hardware device (for example, a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some implementations, the 1804 processor may be configured to operate a memory array using a memory controller. In some other implementations, a memory controller may be integrated into the 1804 processor. The 1804 processor may be configured to execute computer-readable instructions stored in a memory (for example, the 1806 memory) to enable the 1802 device to perform various functions of the present disclosure. Petition 870260069606, dated 07 / 14 / 2026, pp. 99 / 134 94 / 125

[234] 1806 memory may include random access memory (RAM) and read-only memory (ROM). 1806 memory may store computer-readable and computer-executable code, including instructions that, when executed by the 1804 processor, cause the 1802 device to perform various functions described herein. The code may be stored in a non-transient, computer-readable medium, such as system memory or other types of memory. In some implementations, the code may not be directly executable by the 1804 processor, but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some implementations, 1806 memory may include, among other things, a basic I / O system (BIOS) that may control basic hardware or software operation, such as interaction with peripheral components or devices.

[235] The 1810 I / O controller can manage input and output signals for the 1802 device. The 1810 I / O controller can also manage peripherals not integrated into the M02 device. In some implementations, the 1810 I / O controller may represent a physical connection or port for an external peripheral. In some implementations, the 1810 I / O controller may utilize an operating system such as iOS®, ANDROID®, MS-DOS®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. In some implementations, the 1810 I / O controller may be implemented as part of a processor, such as the 1406 processor. In some implementations, a user may interact with the 1802 device through the 1810 I / O controller or through hardware components controlled by the 1810 I / O controller.

[236] In some implementations, the 1802 device may include a single 1812 antenna. However, in some other implementations, the 1802 device may have more than one 1812 antenna (e.g., multiple antennas), including multiple Petition 870260069606, dated 07 / 14 / 2026, pp. 100 / 134 95 / 125 antenna panels or antenna arrays, which may be capable of simultaneously transmitting or receiving multiple wireless transmissions. The 1808 transceiver may communicate bidirectionally, via one or more 1812 antennas, wired or wireless links, as described herein. For example, the 1808 transceiver may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The 1808 transceiver may also include a modem to modulate packets, to provide modulated packets to one or more 1812 antennas for transmission, and to demodulate packets received from one or more 1812 antennas.

[237] FIG. 19 illustrates an example of a 1900 block diagram of a 1902 device (e.g., an apparatus) that supports machine learning for positioning according to aspects of the present disclosure. The 1902 device may be an example of a 102 network entity as described herein. The 1902 device may support wireless communication with one or more 102 network entities, 104 UEs, or any combination thereof. The 1902 device may include components for bidirectional communications, including components for transmitting and receiving communications, such as a 1904 processor, a 1906 memory, a 1908 transceiver, and a 1910 I / O controller. These components may be in electronic communication or otherwise coupled (e.g., operationally, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[238] The 1904 processor, the 1906 memory, the 1908 transceiver, or various combinations thereof or various components thereof may be examples of means for carrying out various aspects of the present disclosure as described in this document. For example, the 1904 processor, the 1906 memory, the 1908 transceiver, or various combinations or components thereof may support Petition 870260069606, dated 07 / 14 / 2026, pp. 101 / 134 96 / 125 a method for performing one or more of the operations described in this document.

[239] In some implementations, the 1904 processor, the 1906 memory, the 1908 transceiver, or various combinations or components thereof may be implemented in hardware (for example, in a communications management circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting a means for performing the functions described in this disclosure. In some implementations, the 1904 processor and the 1906 memory coupled to the 1904 processor may be configured to perform one or more of the functions described herein (for example, executing, by the 1904 processor, instructions stored in the 1906 memory).In the context of network entity 102, for example, transceiver 1908 and processor 1904 coupled to transceiver 1908 are configured to cause network entity 102 to perform the various operations described and / or combinations thereof.

[240] For example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples disclosed herein. For example, the 1904 processor and / or the 1908 transceiver may be configured as and / or otherwise support a means of receiving machine learning positioning configuration requests; and transmitting, based at least in part on the machine learning positioning configuration requests, machine learning positioning configuration responses that include positioning reference signal configurations. Petition 870260069606, dated 07 / 14 / 2026, pp. 102 / 134 97 / 125 to be measured at their respective reference locations and with one or more associated validity criteria.

[241] In addition, in some implementations, the processor is configured to have the device receive machine learning positioning configuration requests from one or more network nodes or user equipment (UE) and transmit machine learning positioning configuration responses to the one or more network nodes or to the UE; reference locations include one or more true-of-field reference locations; machine learning positioning configuration responses include artificial intelligence configuration for the positioning reference signal settings; the processor is configured to have the device transmit one or more machine learning positioning configuration responses independent of a machine learning positioning configuration request;Machine learning positioning configuration responses include one or more direct machine learning configurations or assisted machine learning configurations; the direct machine learning configuration includes configuration to perform radio frequency fingerprinting.

[242] In addition, in some implementations, machine learning positioning configuration requests include a request for one or more training types, a field truth location request, a machine learning method, a machine learning on-demand positioning reference signal request, or pre-configured machine learning assistance data; positioning reference signal configurations include one or more positioning reference signal features, feature sets, transmit / receive points, or positioning frequency layer to be Petition 870260069606, dated 07 / 14 / 2026, pp. 103 / 134 98 / 125 measured at each reference location; one or more associated validity criteria include one or more temporal criteria or spatial criteria; temporal criteria include a measurement time defined by one or more time bases; one or more time bases include at least one system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time; one or more associated validity criteria include a spatial criterion that refers to an indication of a geographic region, and spatial criteria include one or more area identifiers, cell identifiers, or zone identifiers.

[243] In addition, in some implementations, the positioning reference signal settings include one or more indications of one or more uplink radio access technology dependent measurements, downlink radio access technology dependent measurements, or sidelink radio access technology dependent measurements to be performed; the positioning reference signal settings include one or more indications of one or more downlink radio access technology independent measurements or sidelink radio access technology independent measurements to be performed;The machine learning positioning configuration responses additionally include one or more configurations belonging to at least one of the following: a k-nearest neighbors (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, Bayesian networks, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; the apparatus includes at least one of the following: a location server, a next-generation radio access network (NGRAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE. Petition 870260069606, dated 07 / 14 / 2026, pp. 104 / 134 99 / 125

[244] In addition, in some implementations, the positioning reference signal settings include a received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink; and the received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink is defined as including a linear average of a total received power observed in feature elements of a slot that carry the positioning reference signal configured for measurement; the positioning reference signal settings include a positioning reference signal arrival time measurement for one or more of the following downlink, uplink, or sidelink;and the measurement of arrival time of a positioning reference signal for one or more of a downlink, uplink, or sidelink is defined as including the reception time of a positioning reference signal at a receiver reference point; the positioning reference signal settings include an indication that a location server is allowed to transmit an error cause related to an incorrect configuration of a positioning reference signal; the positioning reference signal settings include an indication that a target user equipment (UE) is allowed to transmit an error cause related to an error in one or more of a reception, a machine learning positioning configuration response, or a measurement error related to a machine learning positioning measurement.

[245] In a further example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples as disclosed herein. The 1904 processor and / or the 1908 transceiver, for example, Petition 870260069606, dated 07 / 14 / 2026, pp. 105 / 134 100 / 125 can be configured as or otherwise support a means to transmit a machine learning positioning configuration request; receive a machine learning positioning configuration response that includes a positioning reference signal configuration to be measured at one or more respective reference locations and with one or more associated validity criteria; and perform, based at least in part on the positioning reference signal configuration, one or more machine learning position measurements.

[246] In addition, in some implementations, the processor and transceiver are configured to cause the device to do one or more of the following: receive the machine learning positioning configuration response in response to the machine learning positioning configuration request; or receive the machine learning positioning configuration response independent of the machine learning positioning configuration request; the processor is configured to cause the device to input one or more machine learning position measurements into a machine learning model and receive an output from the machine learning model; the processor is configured to cause the device to generate an estimated location of the device based, at least in part, on the output of the machine learning model;The device includes one or more target user equipment (SU), a positioning reference unit (PRU), or an anchor SU.

[247] In a further example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples as disclosed herein. The 1904 processor and / or the 1908 transceiver, for example, may be configured as or otherwise support a means of transmitting a configuration request to configure Petition 870260069606, dated 07 / 14 / 2026, pp. 106 / 134 101 / 125 reference signals for machine learning positioning measurements; receive a configuration response including reference signal configuration; and transmit, based at least in part on the reference signal configuration, a reference signal transmission activation command.

[248] In addition, in some implementations, the reference signals include one or more probing reference signals or positioning reference signals; the processor is configured to make the device transmit a reference signal transmission disable command; the device includes a location server, and in which the processor is configured to make the device transmit the reference signal transmission enable command to one or more other devices that are configured to transmit the reference signals.

[249] In a further example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples as disclosed herein. The 1904 processor and / or the 1908 transceiver, for example, may be configured as or otherwise support a means to transmit one or more machine learning positioning report requests including a machine learning report configuration and one or more common reporting criteria; receive one or more machine learning positioning reports; process one or more machine learning positioning reports by means of a machine learning model; and generate, based at least in part on the output of the machine learning model, an estimated location of a user device (UD).

[250] In addition, in some implementations, the machine learning reporting configuration includes one or more direct machine learning reporting configurations or assisted machine learning reporting configurations; Petition 870260069606, dated 07 / 14 / 2026, pp. 107 / 134 102 / 125 the device includes a configuration entity, and wherein the configuration entity includes at least one of a location server, a next-generation radio access network (NGRAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE; the processor is configured to cause the device to transmit one or more machine learning positioning report requests to one or more second devices, and to receive one or more machine learning positioning reports from the one or more second devices, and wherein the one or more second devices include at least one of a location server, a next-generation radio access network (NGRAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

[251] In addition, in some implementations, one or more common reporting criteria include one or more of a fingerprint type, a true-of-field reference location type, a time-domain reporting type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprint environment indication, a fingerprint quality indication, or a label quality indication; for at least one machine learning positioning report request, one or more common reporting criteria are configured to be one or more of the following: augmented, removed, updated, enabled, or disabled; the processor is configured to have the device broadcast one or more common reporting criteria via positioning system information broadcast signaling;The machine learning reporting configuration includes an option to report the correlation of machine learning positioning measurements between different sets of measurements. Petition 870260069606, dated 07 / 14 / 2026, pp. 108 / 134 103 / 125

[252] In addition, in some implementations, the machine learning positioning measurement correlation includes one or more spatial domain correlations or temporal domain correlations; the one or more machine learning positioning reports include one or more machine learning positioning measurements or machine learning positioning location information; the machine learning report configuration includes an indication to report path loss at different locations, including a true-to-ground reference location; the machine learning report configuration includes an indication to average the machine learning positioning measurements across a configured number of measurements and report the average as part of the one or more machine learning positioning reports;The machine learning report configuration includes an option to determine a similarity score at a configured location to determine an ideal mapping between a fingerprint measurement and an estimated location of a target UE.

[253] In a further example, processor 1904 and / or transceiver 1908 may support wireless communication on device 1902 according to examples as disclosed herein. Processor 1904 and / or transceiver 1908, for example, may be configured to, or otherwise, support a means of receiving one or more machine learning positioning report requests, including a machine learning report configuration and one or more common reporting criteria; generating one or more machine learning positioning reports based at least in part on the machine learning report configuration and one or more common reporting criteria; and transmitting one or more machine learning positioning reports. Petition 870260069606, dated 07 / 14 / 2026, pp. 109 / 134 104 / 125

[254] In addition, in some implementations, the device includes one or more user equipment (UE), an anchor UE or a target UE; the device includes a configuration entity, and wherein the configuration entity includes at least one location server, a next-generation radio access network (NG-RAN) or a positioning reference unit (PRU).

[255] In a further example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples as disclosed herein.Processor 1904 and / or transceiver 1908, for example, may be configured to, or otherwise, support a means of transmitting one or more machine learning positioning report requests, including a machine learning report configuration and one or more common reporting criteria; receiving one or more machine learning positioning reports; generating, based at least in part on one or more machine learning positioning reports, a machine learning positioning training dataset; and training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model.

[256] In addition, in some implementations, the processor and transceiver are configured to have the device receive one or more additional machine learning positioning reports; insert at least a portion of one or more additional machine learning positioning reports into the trained positioning machine learning model; and estimate a position of a target user device (UD) based, at least in part, on the output of the trained positioning machine learning model; the processor Petition 870260069606, dated 07 / 14 / 2026, pp. 110 / 134 105 / 125 is configured to make the device: receive a request for machine learning positioning training data for positioning; and transmit, based at least in part on the request, the machine learning positioning training dataset; the processor is configured to make the device: receive a request for a trained positioning machine learning model; and transmit, based at least in part on the request, at least a portion of the trained positioning machine learning model.

[257] In a further example, processor 1904 and / or transceiver 1908 may support wireless communication on device 1902 according to examples as disclosed herein. Processor 1904 and / or transceiver 1908, for example, may be configured as or otherwise support a means of receiving machine learning positioning configuration requests; and transmitting, based at least in part on the machine learning positioning configuration requests, machine learning positioning configuration responses that include positioning reference signal configurations to be measured at respective reference locations and with one or more associated validity criteria.

[258] In addition, in some implementations, the 1904 processor and / or the 1908 transceiver, for example, may be configured as or otherwise support a means of receiving machine learning positioning configuration requests from one or more network nodes or user equipment (UE) and transmitting the machine learning positioning configuration responses to the one or more network nodes or to the EU; reference locations include one or more true-to-field reference locations; machine learning positioning configuration responses include Petition 870260069606, dated 07 / 14 / 2026, pp. 111 / 134 106 / 125 artificial intelligence configuration for positioning reference signal settings; transmit one or more independent machine learning positioning configuration responses from a machine learning positioning configuration request; machine learning positioning configuration responses include one or more direct machine learning settings or assisted machine learning settings; direct machine learning setting includes setting to perform radio frequency fingerprinting.

[259] In addition, in some implementations, machine learning positioning configuration requests include a request for one or more training types, a field truth location request, a machine learning method, a machine learning on-demand positioning reference signal request, or pre-configured machine learning assistance data; positioning reference signal configurations include one or more positioning reference signal features, feature sets, transmit / receive points, or positioning frequency layer to be measured at each reference location; the one or more associated validity criteria include one or more temporal criteria or spatial criteria; temporal criteria include a measurement time defined by one or more time bases;One or more time bases include at least one system frame number, Coordinated Universal Time (UTC), or Global Navigation Satellite System (GNSS) time; one or more associated validity criteria include a spatial criterion that refers to an indication of a geographic region, and the spatial criteria include one or more area identifiers, cell identifiers, or zone identifiers. Petition 870260069606, dated 07 / 14 / 2026, pp. 112 / 134 107 / 125

[260] In addition, in some implementations, the positioning reference signal settings include one or more indications of one or more uplink radio access technology dependent measurements, downlink radio access technology dependent measurements, or sidelink radio access technology dependent measurements to be performed; the positioning reference signal settings include one or more indications of one or more downlink radio access technology independent measurements or sidelink radio access technology independent measurements to be performed;The machine learning positioning configuration responses additionally include one or more configurations belonging to at least one of the following: a k-nearest neighbors (k-NN) algorithm, a support vector machine, a decision tree, a random forest, a Gaussian mixture model, Bayesian networks, an artificial neural network, K-means, reinforcement learning, deep learning, or transfer learning; the method is performed by an apparatus including at least one of the following: a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a user equipment (UE), an anchor UE, or a target UE.

[261] In addition, in some implementations, the positioning reference signal settings include a received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink; and the received signal strength indicator measurement for one or more of the following downlink, uplink, or sidelink is defined as including a linear average of a total received power observed in feature elements of a slot that carry the positioning reference signal configured for measurement; the signal settings of Petition 870260069606, dated 07 / 14 / 2026, pages 113 / 134 108 / 125 positioning references include a measurement of the arrival time of a positioning reference signal for one or more of the following links: downlink, uplink, or sidelink; and the measurement of the arrival time of a positioning reference signal for one or more of the following links: downlink, uplink, or sidelink is defined as including the reception time of a positioning reference signal at a receiver reference point; the positioning reference signal settings include an indication that a location server is permitted to transmit an error cause related to an incorrect configuration of a positioning reference signal setting;Positioning reference signal settings include an indication that a target user equipment (UE) is permitted to transmit an error cause related to an error in one or more receptions, a machine learning positioning configuration response, or a measurement error related to a machine learning positioning measurement.

[262] In a further example, processor 1904 and / or transceiver 1908 may support wireless communication on device 1902 according to examples as disclosed herein. Processor 1904 and / or transceiver 1908, for example, may be configured as or otherwise support a means of transmitting a machine learning positioning configuration request; receiving a machine learning positioning configuration response that includes a positioning reference signal configuration to be measured at one or more respective reference locations and with one or more associated validity criteria; and performing, based at least in part on the positioning reference signal configuration, one or more machine learning position measurements. Petition 870260069606, dated 07 / 14 / 2026, pages 114 / 134 109 / 125

[263] In addition, in some implementations, the 1904 processor and / or the 1908 transceiver, for example, may be configured as or otherwise support a means for one or more of: receiving the machine learning positioning configuration response in response to the machine learning positioning configuration request; or receiving the machine learning positioning configuration response independent of the machine learning positioning configuration request; inputting one or more machine learning position measurements into a machine learning model and receiving an output from the machine learning model; generating an estimated device location based, at least in part, on the output of the machine learning model; the method is performed by a device that includes one or more of a target user equipment (UE), a positioning reference unit (PRU), or an anchor UE.

[264] In a further example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples as disclosed herein. The 1904 processor and / or the 1908 transceiver, for example, may be configured as or otherwise support a means to transmit a configuration request to set up reference signals for machine learning positioning measurements; receive a configuration response including reference signal configuration; and transmit, based at least in part on the reference signal configuration, a reference signal transmission enablement command.

[265] In addition, in some implementations, the reference signals include one or more probing reference signals or positioning reference signals; transmit a reference signal transmission disable command; the method is performed by an apparatus that includes a location server, and in which the method additionally includes transmitting Petition 870260069606, dated 07 / 14 / 2026, pages 115 / 134 110 / 125 is the command to activate the transmission of a reference signal to one or more other devices that are configured to transmit reference signals.

[266] In a further example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples as disclosed herein. The 1904 processor and / or the 1908 transceiver, for example, may be configured as or otherwise support a means to transmit one or more machine learning positioning report requests including a machine learning report configuration and one or more common reporting criteria; receive one or more machine learning positioning reports; process one or more machine learning positioning reports by means of a machine learning model; and generate, based at least in part on the output of the machine learning model, an estimated location of a user device (UD).

[267] In addition, in some implementations, the machine learning reporting configuration includes one or more direct machine learning reporting configurations or assisted machine learning reporting configurations; wherein the method is performed by an appliance including a configuration entity, and wherein the configuration entity includes at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE or a target UE; including additionally transmitting one or more machine learning positioning report requests from a first appliance to one or more second appliances, and receiving one or more machine learning positioning reports from the one or more second appliances, and wherein the one or more second appliances include at least one of a location server, a next-generation radio access network Petition 870260069606, dated 07 / 14 / 2026, pages 116 / 134 111 / 125 next-generation radio (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

[268] In addition, in some implementations, one or more common reporting criteria include one or more of a fingerprint type, a true-of-field reference location type, a time-domain reporting type, a measurement preprocessing, a measurement validity, a UE type, a mobility indication, an orientation indication, a fingerprint environment indication, a fingerprint quality indication, or a label quality indication; wherein for at least one machine learning positioning report request, one or more common reporting criteria are configured to be one or more of the augmented, removed, updated, enabled, or disabled; including additionally broadcasting one or more common reporting criteria via positioning system information broadcast signaling;where the machine learning reporting configuration includes an indication to report the correlation of machine learning positioning measurements between different sets of measurements.

[269] In addition, in some implementations, the machine learning positioning measurement correlation includes one or more spatial domain correlations or temporal domain correlations; wherein one or more machine learning positioning reports include one or more machine learning positioning measurements or machine learning positioning location information; wherein the machine learning report configuration includes an indication to report path loss at different locations, including a true-field reference location; wherein the machine learning report configuration includes an indication to calculate the average. Petition 870260069606, dated 07 / 14 / 2026, pp. 117 / 134 112 / 125 of the machine learning positioning measurements across a configured number of measurements and report the average as part of one or more machine learning positioning reports; wherein the machine learning report configuration includes an indication to determine a similarity score at a configured location to determine an optimal mapping between a fingerprint measurement and an estimated location of a target UE.

[270] In a further example, processor 1904 and / or transceiver 1908 may support wireless communication on device 1902 according to examples as disclosed herein. Processor 1904 and / or transceiver 1908, for example, may be configured to, or otherwise, support a means of receiving one or more machine learning positioning report requests, including a machine learning report configuration and one or more common reporting criteria; generating one or more machine learning positioning reports based at least in part on the machine learning report configuration and one or more common reporting criteria; and transmitting one or more machine learning positioning reports.

[271] In addition, in some implementations, the method is performed by a device including one or more of a user device (UD), an anchor UD or a target UD; wherein the method is performed by a device including a configuration entity, and wherein the configuration entity includes at least one of a location server, a next-generation radio access network (NG-RAN) or a positioning reference unit (PRU).

[272] In a further example, the 1904 processor and / or the 1908 transceiver may support wireless communication on the 1902 device according to examples as disclosed herein. The 1904 processor and / or the 1908 transceiver, for example, Petition 870260069606, dated 07 / 14 / 2026, pages 118 / 134 113 / 125 can be configured as or otherwise support a means to transmit one or more machine learning positioning report requests, including a machine learning reporting configuration and one or more common reporting criteria; receive one or more machine learning positioning reports; generate, based at least in part on one or more machine learning positioning reports, a machine learning positioning training dataset; and train a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model.

[273] In addition, in some implementations, the 1904 processor and / or the 1908 transceiver, for example, may be configured as or otherwise support a means of receiving one or more additional machine learning positioning reports; inserting at least a portion of one or more additional machine learning positioning reports into the trained positioning machine learning model; and estimating a position of a target user equipment (UE) based at least in part on the output of the trained positioning machine learning model; including additionally: receiving a request for machine learning positioning training data for positioning; and transmitting, based at least in part on the request, the machine learning positioning training dataset; including additionally: receiving a request for a trained positioning machine learning model;and transmit, based at least in part on the request, at least a portion of the trained positioning machine learning model. Petition 870260069606, dated 07 / 14 / 2026, pp. 119 / 134 114 / 125

[274] The 1904 processor may include an intelligent hardware device (for example, a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some implementations, the 1904 processor may be configured to operate a memory array using a memory controller. In some other implementations, a memory controller may be integrated into the 1904 processor. The 1904 processor may be configured to execute computer-readable instructions stored in a memory (for example, the 1906 memory) to enable the 1902 device to perform various functions of the present disclosure.

[275] 1906 memory may include random access memory (RAM) and read-only memory (ROM). 1906 memory may store computer-readable and computer-executable code, including instructions that, when executed by the 1904 processor, cause the 1902 device to perform various functions described herein. The code may be stored in a non-transient, computer-readable medium, such as system memory or other types of memory. In some implementations, the code may not be directly executable by the 1904 processor, but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some implementations, 1906 memory may include, among other things, a basic I / O system (BIOS) that may control basic hardware or software operation, such as interaction with peripheral components or devices.

[276] The 1910 I / O controller can manage input and output signals for the 1902 device. The 1910 I / O controller can also manage peripherals not integrated into the M02 device. In some implementations, the 1910 I / O controller may represent a physical connection or port for a Petition 870260069606, dated 07 / 14 / 2026, pages 120 / 134 115 / 125 external peripheral. In some implementations, the 1910 I / O controller may use an operating system such as iOS®, ANDROID®, MS-DOS®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. In some implementations, the 1910 I / O controller may be implemented as part of a processor, such as the 1406 processor. In some implementations, a user may interact with the 1902 device through the 1910 I / O controller or through hardware components controlled by the 1910 I / O controller.

[277] In some implementations, the 1902 device may include a single 1912 antenna. However, in some other implementations, the 1902 device may have more than one 1912 antenna (e.g., multiple antennas), including multiple antenna panels or antenna arrays, which may be capable of simultaneously transmitting or receiving multiple wireless transmissions. The 1908 transceiver may communicate bidirectionally, via one or more 1912 antennas, wired or wireless links, as described herein. For example, the 1908 transceiver may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The 1908 transceiver may also include a modem to modulate the packets, to provide the modulated packets to one or more 1912 antennas for transmission, and to demodulate packets received from one or more 1912 antennas.

[278] FIG. 20 illustrates a 2000 message that supports machine learning for positioning in accordance with aspects of this disclosure. The operations of method 2000 can be implemented by a device or its components as described in this document. For example, the operations of method 2000 can be performed by a network entity 102 and / or a UE 104, as described with reference to FIGS. 1 to 19. In some implementations, the device can execute a set of instructions to control the function elements of Petition 870260069606, dated 07 / 14 / 2026, pages 121 / 134 116 / 125 device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[279] In 2002, the method may include receiving machine learning positioning configuration requests. The 2002 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2002 operations may be performed by a device as described with reference to FIG. 1.

[280] In 2004, the method may include transmitting, based at least in part on machine learning positioning configuration requests, machine learning positioning configuration responses comprising positioning reference signal configurations to be measured at respective reference locations and with one or more associated validity criteria. The 2004 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2004 operations may be performed by a device as described with reference to FIG. 1.

[281] FIG. 21 illustrates a 2100 message that supports machine learning for positioning according to aspects of this disclosure. The operations of method 2100 can be implemented by a device or its components as described in this document. For example, the operations of method 2100 can be performed by a network entity 102 and / or a UE 104, as described with reference to FIGS. 1 to 19. In some implementations, the device may execute a set of instructions to control the device's function elements to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware. Petition 870260069606, dated 07 / 14 / 2026, pages 122 / 134 117 / 125

[282] In 2102, the method may include transmitting a machine learning positioning configuration request. The 2102 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2102 operations may be performed by a device as described with reference to FIG. 1.

[283] In 2104, the method may include receiving a machine learning positioning configuration response comprising a positioning reference signal configuration to be measured at one or more respective reference locations and with one or more associated validity criteria. The 2104 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2104 operations may be performed by a device as described with reference to FIG. 1.

[284] In 2106, the method may include performing, based at least in part on the positioning reference signal configuration, one or more machine learning position measurements. The 2106 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2106 operations may be performed by a device as described with reference to FIG. 1.

[285] FIG. 22 illustrates a 2200 message that supports machine learning for positioning in accordance with aspects of this disclosure. The operations of method 2200 can be implemented by a device or its components as described in this document. For example, the operations of method 2200 can be performed by a network entity 102 and / or a UE 104, as described with reference to FIGS. 1 to 19. In some implementations, the device can perform a Petition 870260069606, dated 07 / 14 / 2026, pages 123 / 134 118 / 125 instruction set to control the device's function elements to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[286] In 2202, the method may include transmitting a configuration request to set up reference signals for machine learning positioning measurements. The 2202 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2202 operations may be performed by a device as described with reference to FIG. 1.

[287] In 2204, the method may include receiving a configuration response comprising reference signal configuration. The 2204 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2204 operations may be performed by a device as described with reference to FIG. 1.

[288] In 2206, the method may include the transmission, based at least in part on the reference signal configuration, of a reference signal transmission activation command. The 2206 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2206 operations may be performed by a device as described with reference to FIG. 1.

[289] FIG. 23 illustrates a 2300 message that supports machine learning for positioning in accordance with aspects of this disclosure. The operations of method 2300 can be implemented by a device or its components as described in this document. For example, the operations of method 2300 can be performed by a network entity 102 and / or a UE 104, as described with reference to FIGS. 1 to 19. In some implementations, the device can perform a Petition 870260069606, dated 07 / 14 / 2026, pages 124 / 134 119 / 125 instruction set to control the device's function elements to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[290] In 2302, the method may include transmitting one or more machine learning positioning report requests comprising a machine learning report configuration and one or more common reporting criteria. The 2302 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2302 operations may be performed by a device as described with reference to FIG. 1.

[291] In 2304, the method may include receiving one or more machine learning positioning reports. The 2304 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2304 operations may be performed by a device as described with reference to FIG. 1.

[292] In 2306, the method may include processing one or more machine learning positioning reports by means of a machine learning model. The 2306 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2306 operations may be performed by a device as described with reference to FIG. 1.

[293] In 2308, the method may include generating, based at least in part on the output of the machine learning model, an estimated location of a user device (UD). The 2308 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2308 operations may be performed by a device as described with reference to FIG. 1. Petition 870260069606, dated 07 / 14 / 2026, pages 125 / 134 120 / 125

[294] FIG. 24 illustrates a 2400 message that supports machine learning for positioning according to aspects of this disclosure. The operations of method 2400 can be implemented by a device or its components as described in this document. For example, the operations of method 2400 can be performed by a network entity 102 and / or a UE 104, as described with reference to FIGS. 1 to 19. In some implementations, the device may execute a set of instructions to control the device's function elements to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[295] In 2402, the method may include receiving one or more machine learning positioning report requests comprising a machine learning reporting configuration and one or more common reporting criteria. The 2402 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2402 operations may be performed by a device as described with reference to FIG. 1.

[296] In 2404, the method may include generating one or more machine learning positioning reports based, at least in part, on the machine learning reporting configuration and one or more common reporting criteria. The 2404 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2404 operations may be performed by a device as described with reference to FIG. 1.

[297] In 2406, the method may include transmitting one or more machine learning positioning reports. 2406 operations may be performed according to examples as described in this document. In some implementations, Petition 870260069606, dated 07 / 14 / 2026, pages 126 / 134 121 / 125 aspects of the 2406 operations can be performed by a device as described with reference to FIG. 1.

[298] FIG. 25 illustrates a 2500 message that supports machine learning for positioning according to aspects of this disclosure. The operations of method 2500 can be implemented by a device or its components as described in this document. For example, the operations of method 2500 can be performed by a network entity 102 and / or a UE 104, as described with reference to FIGS. 1 to 19. In some implementations, the device may execute a set of instructions to control the device's function elements to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[299] In 2502, the method may include transmitting one or more machine learning positioning report requests comprising a machine learning report configuration and one or more common reporting criteria. The 2502 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2502 operations may be performed by a device as described with reference to FIG. 1.

[300] In 2504, the method may include receiving one or more machine learning positioning reports. The 2504 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2504 operations may be performed by a device as described with reference to FIG. 1.

[301] In 2506, the method may include generating, based at least in part on one or more machine learning positioning reports, a machine learning positioning training dataset. The operations of Petition 870260069606, dated 07 / 14 / 2026, pages 127 / 134 122 / 125 2506 operations can be performed according to examples as described in this document. In some implementations, aspects of the 2506 operations can be performed by a device as described with reference to FIG. 1.

[302] In 2508, the method may include training a positioning machine learning model using the machine learning positioning training dataset to generate a trained positioning machine learning model. The 2508 operations may be performed according to examples as described in this document. In some implementations, aspects of the 2508 operations may be performed by a device as described with reference to FIG. 1.

[303] It should be noted that the methods described here describe possible implementations and that the operations and steps may be rearranged or modified in other ways and that other implementations are possible. Furthermore, aspects of two or more methods may be combined.

[304] The various illustrative blocks and components described in connection with the disclosure herein may be implemented or realized with a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration). Petition 870260069606, dated 07 / 14 / 2026, pages 128 / 134 123 / 125

[305] The functions described herein may be implemented in hardware, processor-executed software, firmware, or any combination thereof. If implemented in processor-executed software, the functions may be stored or transmitted as one or more instructions or code in a computer-readable medium. Other examples and implementations are within the scope of the disclosure and appended claims. For example, due to the nature of software, the functions described herein may be implemented using processor-executed software, hardware, firmware, wiring, or combinations thereof. The resources that implement functions may also be physically located in multiple locations, including being distributed so that parts of the functions are implemented in different physical locations.

[306] Computer-readable media include non-transient computer storage media and communication media, including any means that facilitate the transfer of a computer program from one place to another. A non-transient storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transient computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disc (CD) ROM or other optical disc storage, magnetic disc storage or other magnetic storage devices, or any other non-transient medium that can be used to transport or store desired program code media in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor.

[307] Any connection can be properly termed a computer-readable medium. For example, if the software is Petition 870260069606, dated 07 / 14 / 2026, pages 129 / 134 124 / 125 transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of computer-readable media. Disk and disc, as used herein, include CD, laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc, where discs generally reproduce data magnetically, while disks reproduce data optically with lasers. Combinations of the above are also included in the scope of computer-readable media.

[308] As used in this document, including in the claims, or as used in a list of items (for example, a list of items preceded by a phrase such as at least one of or one or more of or one or both of) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (for example, A and B and C). Furthermore, as used in this document, the phrase "based on" should not be interpreted as referring to a closed set of conditions. For example, an example step that is described as being based on condition A may be based on condition A and condition B without departing from the scope of this disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same way as the phrase "based at least in part on". Furthermore, as used herein, including in the claims, a set may include one or more elements.

[309] The terms transmit, receive or communicate, when referring to a network entity, may refer to any part of a network entity (for example, a station). Petition 870260069606, dated 07 / 14 / 2026, pp. 130 / 134 A 125 / 125 base network (one CU, one DU, one RU) of a RAN communicating with another device (for example, directly or through one or more other network entities).

[310] The description presented here, in connection with the accompanying drawings, describes example configurations and does not represent all examples that may be implemented or that are within the scope of the claims. The term example used in this document means serving as an example, occurrence, or illustration and not preferred or advantageous in relation to other examples. The detailed description includes specific details for the purpose of providing an understanding of the techniques described. These techniques, however, can be practiced without these specific details. In some cases, known structures and devices are shown in block diagram form to avoid obscuring the concepts of the example described.

[311] The description here is provided to enable a person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person skilled in the art, and the generic principles set forth herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described in this document, but should be given the broader scope consistent with the principles and new features disclosed in this document. Petition 870260069606, dated 07 / 14 / 2026, pages 131 / 134

Claims

1 / 5 CLAIMS 1. Device, characterized in that it comprises: a processor; and a memory coupled to the processor, the processor configured to make the device: transmit one or more machine learning positioning report requests comprising a machine learning report configuration and one or more common reporting criteria; receive one or more machine learning positioning reports; process the one or more machine learning positioning reports by means of a machine learning model; and generate, based at least in part on the output of the machine learning model, an estimated location of a user device (UD).

2. Device according to claim 1, characterized in that the machine learning reporting configuration comprises one or more direct machine learning reporting configurations or assisted machine learning reporting configurations.

3. Apparatus, according to claim 1, characterized in that the apparatus comprises a configuration entity, and in that the configuration entity comprises at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

4. Device according to claim 1, characterized in that the processor is configured to make the device: Petition 870250069432, dated 06 / 08 / 2025, page 197 / 209 2 / 5 transmit one or more machine learning positioning report requests to one or more second devices; receive one or more machine learning positioning reports from one or more second devices, and wherein the one or more second devices comprise at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

5. Device according to claim 1, characterized in that the processor is configured to enable the device to broadcast one or more common reporting criteria by means of positioning system information broadcast signaling.

6. Device according to claim 1, characterized in that one or more machine learning positioning reports comprise one or more machine learning positioning measurements or machine learning positioning location information.

7. Device, characterized in that it comprises: a processor; and a memory coupled to the processor, the processor configured to make the device: receive one or more machine learning positioning report requests comprising a machine learning report configuration and one or more common reporting criteria; generate one or more machine learning positioning reports based, at least in part, on the machine learning report configuration and one or more common reporting criteria; and transmit one or more machine learning positioning reports.

8. Apparatus, according to claim 7, characterized in that the apparatus comprises one or more user equipment (UE), an anchor UE, or a target UE.

9. Apparatus according to claim 7, characterized in that the apparatus comprises a configuration entity, and in that the configuration entity comprises at least one of a location server, a next-generation radio access network (NG-RAN), or a positioning reference unit (PRU).

10. Method for wireless communication, the method characterized in that it comprises: transmitting one or more machine learning positioning report requests comprising a machine learning report configuration and one or more common reporting criteria; receiving one or more machine learning positioning reports; processing the one or more machine learning positioning reports by means of a machine learning model; and generating, based at least in part on the output of the machine learning model, an estimated location of a user device (UD).

11. A method according to claim 10, characterized in that the machine learning report configuration comprises one or more direct machine learning report configurations or assisted machine learning report configurations.

12. Method, according to claim 10, characterized in that the method is carried out by a configuration entity, and wherein the configuration entity comprises at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

13. A method according to claim 10, characterized in that it further comprises: transmitting one or more machine learning positioning report requests to one or more second devices; and receiving one or more machine learning positioning reports from the one or more second devices, wherein the one or more second devices comprise at least one of a location server, a next-generation radio access network (NG-RAN), a positioning reference unit (PRU), a UE, an anchor UE, or a target UE.

14. Method, according to claim 10, characterized in that one or more machine learning positioning reports comprise one or more machine learning positioning measurements or machine learning positioning location information.

15. Method for wireless communication, the method characterized in that it comprises: receiving one or more machine learning positioning report requests comprising a machine learning report configuration and one or more common reporting criteria; generating one or more machine learning positioning reports based, at least in part, on the machine learning report configuration and one or more common reporting criteria; and transmitting one or more machine learning positioning reports.

Images