WO2025156505A1

WO2025156505A1 - Systems and methods for performing downlink and uplink artificial intelligence/machine learning positioning

Info

Publication number: WO2025156505A1
Application number: PCT/CN2024/092283
Authority: WO
Inventors: Cong Wang; Chuangxin JIANG; Mengzhen LI; Junfeng Zhang; Yu Pan; Xingguang WEI; Zhaohua Lu
Original assignee: ZTE Corp
Current assignee: ZTE Corp
Priority date: 2024-05-10
Filing date: 2024-05-10
Publication date: 2025-07-31
Anticipated expiration: 2026-11-10

Abstract

Presented are systems and methods for performing downlink and uplink artificial intelligence/machine learning positioning. A first network entity can send a request/message for positioning to a second network entity. The first network entity can receive measurement information from the second network entity. The first network entity or the second network entity can compare first information with second information for model monitoring and/or metric calculation. The first network entity can receive a configuration optionally for monitoring from the second network entity. The first network entity can send positioning-related information to the second network entity. The first network entity can send a report, including a capability of the first network entity for a first process and/or a second process, to the second network entity.

Description

SYSTEMS AND METHODS FOR PERFORMING DOWNLINK AND UPLINK ARTIFICIAL INTELLIGENCE/MACHINE LEARNING POSITIONING

TECHNICAL FIELD

The disclosure relates generally to wireless communications, including but not limited to systems and methods for performing downlink and uplink artificial intelligence/machine learning positioning.

BACKGROUND

Coverage is a key consideration in cellular network deployments. With the rise of interconnected devices, there is a growing focus on effective device communication. The current 3GPP standards, spanning from 3G to 5G and beyond, focus on the importance of seamless communication among various devices, from smart home devices to wearable devices. In industrial settings, the complexity of tasks often requires collaboration. This calls for several cooperative operational management systems, with the aim of creating workgroups and managing different types of devices to complete the required tasks.

SUMMARY

The example embodiments disclosed herein are directed to solving the issues relating to one or multiple of the problems presented in the prior art, as well as providing additional features that will become readily apparent by reference to the following detailed description when taken in conjunction with the accompany drawings. In accordance with various embodiments, example systems, methods, devices and computer program products are disclosed herein. It is understood, however, that these embodiments are presented by way of example and are not limiting, and it will be apparent to those of ordinary skill in the art who read the present disclosure that various modifications to the disclosed embodiments can be made while remaining within the scope of this disclosure.

At least one aspect is directed to a system, method, apparatus, or a computer-readable medium. A first network entity (e.g., UE/gNB/TRP) can send/transmit/provide a request/message for positioning to a second network entity (LMF/gNB/TRP/PRU/other UEs) . In certain implementations, the request/message can include at least one of the following: channel measurement information of a DL PRS transmitted by a TRP/gNB; channel measurement information of an UL SRS transmitted by a UE/PRU; one or more reference times optionally associated with channel measurement information, model ID, an ID; and/or one or more TRP IDs/TRP ID lists optionally associated with (channel) measurement information. In certain implementations, the request/message can include model input/measurement information and/or output/label information for the positioning.

In certain implementations, the first network entity can be configured by the second network entity with TRP/gNB information. In certain implementations, the TRP/gNB information can include at least one of the following: a number N indicating that the first network entity is expected to perform and/or report channel measurement information of N TRP/gNBs; one or more TRP IDs and/or TRP/gNB ID lists indicating that the first network entity is expected to perform and/or report channel measurement information of a configured TRP/gNB; one or more reference TRPs, where one of the reference TRPs can be configured for a first positioning method and another of the reference TRPs can be configured for a second positioning method; and/or one or more indicators for a reference TRP indicating whether the reference TRP can be applied to at least one of the first positioning method or the second positioning method.

In certain implementations, the first positioning method can include a legacy positioning method, and the second positioning method can include an AI/ML-assisted positioning method. In certain implementations, the TRP/gNB information can be configured for the first network entity to report the channel measurement information.

In certain implementations, the first network entity can send/transmit/provide TRP/gNB information to the second network entity. In certain implementations, the TRP information can include at least one of the following: one or more TRP IDs or TRP ID lists associated with channel measurement information corresponding to a model input; one or more reference TRP IDs; an entrance index optionally associated with a reference TRP; and/or an indicator configured for indicating the reference TRP. In certain implementations, the first network entity can send/transmit/provide association information and/or reference time for different models to the second network entity. In some implementations, the association information can include an association between a model/association ID and the reference TRP. In some implementations, the association information can include the association/map between a model ID/association and reference time.

In certain implementations, a first network entity (e.g., LMF/UE/gNB) can compare first information with second information for model monitoring and/or metric calculation. In certain implementations, a second network entity can compare first information with second information for model monitoring and/or metric calculation. In certain implementations, each of the first information and the second information can include at least one of the following: UE/PRU’s location information; timing and/or distance information; or RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value. In certain implementations, the first information can be derived based on one of the following positioning methods: RAT-dependent positioning, DL-TDOA/DL-AOD/Multi-RTT/E-CID/UL-AOA/UL-TDOA positioning, GNSS, or PRU information. In certain implementations, the second information can be derived based on an AI/ML model.

In certain implementations, the first network entity can receive/obtain/acquire information from a second network entity. In some implementations, the information can include at least one of the following: a PRS resource ID; a PRS resource set ID; a TRP ID/dl-PRS-ID; an ID of a reference TRP, an ID of a measure TRP, and/or a UE ID; a slot index and/or a subframe number and/or an OFDM symbol index of a received DL PRS/UL SRS; a UE/PRU ID;an SRS resource ID; a T_UE-TX/T_gNB-TX/reference time of RTT/RSTD/RTOA, and/or a soft LOS/NLOS indicator; an inference output/measurement report including one or more of RTT, RSTD, RTOA, angle information, power information, or a hard LOS/NLOS indicator, or a soft LOS/NLOS indicator; or an indicator indicating reported RTT/RSTD/RTOA LOS/NLOS indicator is for model monitoring; and/or one or more timing/distance difference thresholds.

In certain implementations, the first network entity can receive/obtain/acquire an expected information from the second network entity. In some implementations, the expected information can include at least one of the following: RTT, RSTD, RTOA, hard and/or soft LOS/NLOS indicator, ground truth label. In certain implementations, the expected information can be based on a reference time provided by the second network entity. In some implementations, the expected information can be associated with the ID of the reference TRP, the ID of the measure TRP, and/or the UE ID.

In certain implementations, the first network entity can send/transmit/provide to a second network entity a request for the first network entity to provide a message. In some implementations, the message can include at least one of the following: assistance information of one or more UEs/TRPs; a UE/TRP/gNB ID; a UE/TRP pair ID; or a label of an expected RTT, RSTD, RTOA, a soft LOS/NLOS indicator, a hard LOS/NLOS indicator, and/or a ground truth label. In certain implementations, the request can include at least one of the following: a type of the request; a reference TRP; a measure TRP; a UE ID; a required time; and/or an expected response time.

In certain implementations, the first network entity can receive/obtain/acquire from the second network entity at least one of the following: location information of the reference TRP; a distance between the second network entity and the reference TRP; a propagation delay/time between the second network entity and the reference TRP; timing information between the second network entity and the reference TRP; and/or a UE ID, a PRU ID, a TRP ID, a gNB ID, or a reference TRP ID.

In certain implementations, a first network entity can receive/obtain/acquire measurement information, including (channel) measurement information of other UE/PRU/TRP, from a second network entity. In some implementations, the channel measurement information can be optionally associated with one or more of the following: a timestamp, a quality indicator, a timing error group, or scenario information. In certain implementations, the first network entity can send/transmit/provide location information of the other UE/PRU or the RTOA/RTT of gNB/TRP to the second network. In some implementations, the location information/RTOA/RTT can be optionally based on the (channel) measurement information. In certain implementations, the location information/RTOA/RTT can be derived using an AI/ML model. In certain implementations, the location information/RTOA/RTT can be associated with one or more of the following: a PRU ID, a UE ID, the timestamp, the quality indicator, and/or the timing error group.

In certain implementations, the first network entity can send/transmit/provide inference results, location information, accuracy, recommended monitoring behavior, or a monitoring metric of a model to the second network entity. In certain implementations, the first network entity can receive/obtain/acquire location/measurement information of the other UE/PRU from the second network entity. In some implementations, the location/measurement information can include at least one of the following: an RSTD; a UE Rx-Tx time difference; RSRP; RSRPP; AOD; LOS/NLOS indicator; and/or AOA.

In certain implementations, a first network entity can receive/obtain/acquire a configuration optionally for monitoring from a second network entity. In some implementations, the monitoring configuration can include a mapping relationship between a behavior and a metric, accuracy, or reliability. In certain implementations, the behavior can include at least one of the following: a fallback to a legacy/RAT-dependent positioning method; a deactivated model; model switching; and/or model fine-tuning. In certain implementations, the metric can include at least one of the following: positioning accuracy/reliability; accuracy/reliability on power/angle/timing information; accuracy/reliability on LOS/NLOS indicator, location/distance/power/angle/timing and/or LOS/NLOS indicator difference between inference output the ground truth label.

In certain implementations, the configuration can be associated with time and/or window information. In certain implementations, the applicable time and/or window information can include at least one of the following: a starting position of the window; a duration of the window; and/or a period and an offset of the window. In certain implementations, the configuration can be associated with area range information. In certain implementations, the area range information can include at least one of the following: a validity area; a coordinate range; or a cell, TRP, or gNB ID list. In certain implementations, the configuration can be associated with model information. In certain implementations, the model information can include at least one of the following: a model ID list; an AI/ML-based positioning method; an AI/ML positioning entity; and/or an applicable scenario.

In certain implementations, a first network entity can send/transmit/provide positioning-related information to a second network entity. In some implementations, the first network entity can be a model monitoring metric calculation entity. In some implementations, the second network entity can be a model monitoring entity. In certain implementations, the positioning-related information can include at least one of the following: an inference output; a difference between the inference output and a ground truth label; a positioning/inference accuracy/reliability of a model; or a number/ratio of model output that satisfies an accuracy requirement; and/or a suggested monitoring behavior. In certain implementations, the first network entity can receive/obtain/acquire from the second network entity at least one of the following: a fallback to a legacy/RAT-dependent positioning method; a deactivated model; model switching; and/or model fine-tuning.

In certain implementations, a first network entity can send/transmit/provide a report including a capability of the first network entity for a first process and/or a second process to a second network entity. In certain implementations, the first network entity can send/transmit/provide to the second network entity another report including one or more PRS processing capabilities per positioning frequency layer and/or per frequency combination, and/or per CC, and/or per band combination, and/or per CC combination for the first process and/or the second process. In certain implementations, the one or more PRS processing capabilities can include at least one of the following: a number of DL PRS resources that the second network entity can process in a slot; a duration N of DL-PRS symbols in units of ms that the second network entity can process every T for measurement gap, without measurement gap, and/or for PRS processing window; and/or a UE capability for an inference time optionally associated with a duration of DL-PRS symbols, a type of channel measurement, or a measurement size. In certain implementations, the first process can be applicable for RSTD, RTT, RSRP, and/or RSRPP. In some implementations, the second process can be applicable for channel measurement and, optionally, to derive CIR/PDP/DP and/or sample-based measurement and/or path-based measurement.

The system of the technical solution disclosed herein can support AI/ML based enhancements in wireless communication systems, improving network performance and positioning accuracy using trained datasets, according to at least one of the following example configurations (e.g., features or solutions) :

● Example configuration 1: Direct AI/ML Positioning.

● Example configuration 2: AI/ML Assisted Positioning.

BRIEF DESCRIPTION OF THE DRAWINGS

Various example embodiments of the present solution are described in detail below with reference to the following figures or drawings. The drawings are provided for purposes of illustration only and merely depict example embodiments of the present solution to facilitate the reader’s understanding of the present solution. Therefore, the drawings should not be considered limiting of the breadth, scope, or applicability of the present solution. It should be noted that for clarity and ease of illustration, these drawings are not necessarily drawn to scale.

FIG. 1 illustrates an example cellular communication network in which techniques disclosed herein may be implemented, in accordance with an embodiment of the present disclosure;

FIG. 2 illustrates a block diagram of an example base station and a user equipment device, in accordance with some embodiments of the present disclosure;

FIG. 3 illustrates an example configuration of RAT-dependent/legacy positioning, in accordance with some embodiments of the present disclosure;

FIG. 4 illustrates an example configuration for determining model input for an AI/ML assisted model for RTT, in accordance with some embodiments of the present disclosure;

FIG. 5 illustrates another example configuration for determining model input for an AI/ML assisted model for RTT, in accordance with some embodiments of the present disclosure;

FIG. 6 illustrates an example configuration for determining model input for an AI/ML assisted model for DL-TDOA, in accordance with some embodiments of the present disclosure;

FIG. 7 illustrates another example configuration for determining model input for an AI/ML assisted model for DL-TDOA, in accordance with some embodiments of the present disclosure;

FIG. 8 illustrates another example configuration for determining model input for an AI/ML assisted model for DL-TDOA, in accordance with some embodiments of the present disclosure;

FIG. 9 illustrates an example configuration for determining model input for an AI/ML assisted model for UL-RTOA, in accordance with some embodiments of the present disclosure;

FIG. 10 illustrates another example configuration for determining model input for an AI/ML assisted model for UL-RTOA, in accordance with some embodiments of the present disclosure;

FIG. 11 illustrates another example configuration for determining model input for an AI/ML assisted model for UL-RTOA, in accordance with some embodiments of the present disclosure;

FIG. 12 illustrates an example configuration for performing location estimation of a target UE, in accordance with some embodiments of the present disclosure;

FIG. 13 illustrates another example configuration for performing location estimation of a target UE, in accordance with some embodiments of the present disclosure;

FIG. 14 illustrates an example configuration for configuring one or more windows, in accordance with some embodiments of the present disclosure;

FIG. 15 illustrates an example configuration for performing downlink positioning, in accordance with some embodiments of the present disclosure;

FIG. 16 illustrates an example configuration for performing model monitoring or monitoring metric calculation, in accordance with some embodiments of the present disclosure;

FIG. 17 illustrates an example configuration for performing uplink positioning, in accordance with some embodiments of the present disclosure;

FIG. 18 illustrates another example configuration for performing model monitoring or monitoring metric calculation, in accordance with some embodiments of the present disclosure;

FIG. 19 illustrates another example configuration for performing model monitoring or monitoring metric calculation, in accordance with some embodiments of the present disclosure;

FIG. 20 illustrates a flow diagram of an example method for performing positioning requests and/or measurement information exchange, in accordance with an embodiment of the present disclosure;

FIG. 21 illustrates a flow diagram of an example method for performing model monitoring, in accordance with an embodiment of the present disclosure; and

FIG. 22 illustrates a flow diagram of an example method for performing capability reporting, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION

1. Mobile Communication Technology and Environment

FIG. 1 illustrates an example wireless communication network, and/or system, 100 in which techniques disclosed herein may be implemented, in accordance with an embodiment of the present disclosure. In the following discussion, the wireless communication network 100 may be any wireless network, such as a cellular network or a narrowband Internet of things (NB-IoT) network, and is herein referred to as “network 100. ” Such an example network 100 includes a base station 102 (hereinafter “BS 102” ; also referred to as wireless communication node) and a user equipment device 104 (hereinafter “UE 104” ; also referred to as wireless communication device) that can communicate with each other via a communication link 110 (e.g., a wireless communication channel) , and a cluster of cells 126, 130, 132, 134, 136, 138 and 140 overlaying a geographical area 101. In Figure 1, the BS 102 and UE 104 are contained within a respective geographic boundary of cell 126. Each of the other cells 130, 132, 134, 136, 138 and 140 may include at least one base station operating at its allocated bandwidth to provide adequate radio coverage to its intended users.

For example, the BS 102 may operate at an allocated channel transmission bandwidth to provide adequate coverage to the UE 104. The BS 102 and the UE 104 may communicate via a downlink radio frame 118, and an uplink radio frame 124 respectively. Each radio frame 118/124 may be further divided into sub-frames 120/127 which may include data symbols 122/128. In the present disclosure, the BS 102 and UE 104 are described herein as non-limiting examples of “communication nodes, ” generally, which can practice the methods disclosed herein. Such communication nodes may be capable of wireless and/or wired communications, in accordance with various embodiments of the present solution.

FIG. 2 illustrates a block diagram of an example wireless communication system 200 for transmitting and receiving wireless communication signals (e.g., OFDM/OFDMA signals) in accordance with some embodiments of the present solution. The system 200 may include components and elements configured to support known or conventional operating features that need not be described in detail herein. In one illustrative embodiment, system 200 can be used to communicate (e.g., transmit and receive) data symbols in a wireless communication environment such as the wireless communication environment 100 of Figure 1, as described above.

System 200 generally includes a base station 202 (hereinafter “BS 202” ) and a user equipment device 204 (hereinafter “UE 204” ) . The BS 202 includes a BS (base station) transceiver module 210, a BS antenna 212, a BS processor module 214, a BS memory module 216, and a network communication module 218, each module being coupled and interconnected with one another as necessary via a data communication bus 220. The UE 204 includes a UE (user equipment) transceiver module 230, a UE antenna 232, a UE memory module 234, and a UE processor module 236, each module being coupled and interconnected with one another as necessary via a data communication bus 240. The BS 202 communicates with the UE 204 via a communication channel 250, which can be any wireless channel or other medium suitable for transmission of data as described herein.

As would be understood by persons of ordinary skill in the art, system 200 may further include any number of modules other than the modules shown in Figure 2. Those skilled in the art will understand that the various illustrative blocks, modules, circuits, and processing logic described in connection with the embodiments disclosed herein may be implemented in hardware, computer-readable software, firmware, or any practical combination thereof. To clearly illustrate this interchangeability and compatibility of hardware, firmware, and software, various illustrative components, blocks, modules, circuits, and steps are described generally in terms of their functionality. Whether such functionality is implemented as hardware, firmware, or software can depend upon the particular application and design constraints imposed on the overall system. Those familiar with the concepts described herein may implement such functionality in a suitable manner for each particular application, but such implementation decisions should not be interpreted as limiting the scope of the present disclosure.

In accordance with some embodiments, the UE transceiver 230 may be referred to herein as an “uplink” transceiver 230 that includes a radio frequency (RF) transmitter and a RF receiver each comprising circuitry that is coupled to the antenna 232. A duplex switch (not shown) may alternatively couple the uplink transmitter or receiver to the uplink antenna in time duplex fashion. Similarly, in accordance with some embodiments, the BS transceiver 210 may be referred to herein as a “downlink” transceiver 210 that includes a RF transmitter and a RF receiver each comprising circuity that is coupled to the antenna 212. A downlink duplex switch may alternatively couple the downlink transmitter or receiver to the downlink antenna 212 in time duplex fashion. The operations of the two transceiver modules 210 and 230 may be coordinated in time such that the uplink receiver circuitry is coupled to the uplink antenna 232 for reception of transmissions over the wireless transmission link 250 at the same time that the downlink transmitter is coupled to the downlink antenna 212. Conversely, the operations of the two transceivers 210 and 230 may be coordinated in time such that the downlink receiver is coupled to the downlink antenna 212 for reception of transmissions over the wireless transmission link 250 at the same time that the uplink transmitter is coupled to the uplink antenna 232. In some embodiments, there is close time synchronization with a minimal guard time between changes in duplex direction.

The UE transceiver 230 and the base station transceiver 210 are configured to communicate via the wireless data communication link 250, and cooperate with a suitably configured RF antenna arrangement 212/232 that can support a particular wireless communication protocol and modulation scheme. In some illustrative embodiments, the UE transceiver 210 and the base station transceiver 210 are configured to support industry standards such as the Long Term Evolution (LTE) and emerging 5G standards, and the like. It is understood, however, that the present disclosure is not necessarily limited in application to a particular standard and associated protocols. Rather, the UE transceiver 230 and the base station transceiver 210 may be configured to support alternate, or additional, wireless data communication protocols, including future standards or variations thereof.

In accordance with various embodiments, the BS 202 may be an evolved node B (eNB) , a serving eNB, a target eNB, a femto station, or a pico station, for example. In some embodiments, the UE 204 may be embodied in various types of user devices such as a mobile phone, a smart phone, a personal digital assistant (PDA) , tablet, laptop computer, wearable computing device, etc. The processor modules 214 and 236 may be implemented, or realized, with a general purpose processor, a content addressable memory, a digital signal processor, an application specific integrated circuit, a field programmable gate array, any suitable programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, designed to perform the functions described herein. In this manner, a processor may be realized as a microprocessor, a controller, a microcontroller, a state machine, or the like. A processor may also be implemented as a combination of computing devices, e.g., a combination of a digital signal processor and a microprocessor, a plurality of microprocessors, one or multiple microprocessors in conjunction with a digital signal processor core, or any other such configuration.

Furthermore, the steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in firmware, in a software module executed by processor modules 214 and 236, respectively, or in any practical combination thereof. The memory modules 216 and 234 may be realized as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. In this regard, memory modules 216 and 234 may be coupled to the processor modules 210 and 230, respectively, such that the processors modules 210 and 230 can read information from, and write information to, memory modules 216 and 234, respectively. The memory modules 216 and 234 may also be integrated into their respective processor modules 210 and 230. In some embodiments, the memory modules 216 and 234 may each include a cache memory for storing temporary variables or other intermediate information during execution of instructions to be executed by processor modules 210 and 230, respectively. Memory modules 216 and 234 may also each include non-volatile memory for storing instructions to be executed by the processor modules 210 and 230, respectively.

The network communication module 218 generally represents the hardware, software, firmware, processing logic, and/or other components of the base station 202 that enable bi-directional communication between base station transceiver 210 and other network components and communication nodes configured to communicate with the base station 202. For example, network communication module 218 may be configured to support internet or WiMAX traffic. In a typical deployment, without limitation, network communication module 218 provides an 802.3 Ethernet interface such that base station transceiver 210 can communicate with a conventional Ethernet based computer network. In this manner, the network communication module 218 may include a physical interface for connection to the computer network (e.g., Mobile Switching Center (MSC) ) . The terms “configured for, ” “configured to” and conjugations thereof, as used herein with respect to a specified operation or function, refer to a device, component, circuit, structure, machine, signal, etc., that is physically constructed, programmed, formatted and/or arranged to perform the specified operation or function.

The Open Systems Interconnection (OSI) Model (referred to herein as, “open system interconnection model” ) is a conceptual and logical layout that defines network communication used by systems (e.g., wireless communication device, wireless communication node) open to interconnection and communication with other systems. The model is broken into seven subcomponents, or layers, each of which represents a conceptual collection of services provided to the layers above and below it. The OSI Model also defines a logical network and effectively describes computer packet transfer by using different layer protocols. The OSI Model may also be referred to as the seven-layer OSI Model or the seven-layer model. In some embodiments, a first layer may be a physical layer. In some embodiments, a second layer may be a Medium Access Control (MAC) layer. In some embodiments, a third layer may be a Radio Link Control (RLC) layer. In some embodiments, a fourth layer may be a Packet Data Convergence Protocol (PDCP) layer. In some embodiments, a fifth layer may be a Radio Resource Control (RRC) layer. In some embodiments, a sixth layer may be a Non-Access Stratum (NAS) layer or an Internet Protocol (IP) layer, and the seventh layer being the other layer.

Various example embodiments of the present solution are described below with reference to the accompanying figures to enable a person of ordinary skill in the art to make and use the present solution. As would be apparent to those of ordinary skill in the art, after reading the present disclosure, various changes or modifications to the examples described herein can be made without departing from the scope of the present solution. Thus, the present solution is not limited to the example embodiments and applications described and illustrated herein. Additionally, the specific order or hierarchy of steps in the methods disclosed herein are merely example approaches. Based upon design preferences, the specific order or hierarchy of steps of the disclosed methods or processes can be re-arranged while remaining within the scope of the present solution. Thus, those of ordinary skill in the art will understand that the methods and techniques disclosed herein present various steps or acts in a sample order, and the present solution is not limited to the specific order or hierarchy presented unless expressly stated otherwise.

2. Systems and Methods for Performing Downlink and Uplink Artificial Intelligence/Machine Learning Positioning

In a positioning session or process, a target UE (e.g., UE to be positioned) can receive the DL-PRS transmitted by a TRP and/or transmit the UL-SRS to a gNB. In certain implementations, UE and/or gNB can perform signal measurements, and the location of the target UE can be calculated/estimated based on the measurement results. In this regard, artificial intelligence/machine learning (AI/ML) can be used in wireless communication systems to improve network performance with a trained dataset. For example, in a positioning session or process, where the AI/ML model is located on the location management function (LMF) side, the UE/TRP can report the measurement results to the LMF.

In certain implementations, for AI/ML positioning, direct AI/ML positioning and/or AI/ML assisted positioning can be utilized. For direct AI/ML positioning, the AI/ML model output can be the UE location. For AI/ML assisted positioning, the AI/ML model output can be a new measurement and/or an enhancement of an existing measurement, for example, LOS/NLOS identification, timing and/or angle of measurement, or likelihood of measurement. In certain implementations, the reported information of AI/ML positioning for the UE/gNB side model can be RTT/RSTD/RTOA. In some implementations, the current signaling may not be clear enough for determining the model input and output for AI/ML assisted positioning. In some implementations, the detailed model monitoring behavior and exchange of required information may be unclear. In this regard, the technical solutions described herein provide solutions for supporting monitoring input and/or model monitoring of AI/ML positioning. In certain implementations, the technical solutions that require UE capability are described herein to support the RS process for AI/ML positioning.

In RAT-dependent/legacy positioning, multi-RTT can be supported, where gNB and/or UE report the Rx-Tx time difference (for example, the gNB reports the gNB Rx-Tx time difference and the UE reports the UE Rx-Tx time difference) to LMF. As shown in FIG. 3, the gNB Rx-Tx time difference can be T2 = T2_b-T2a, where T2_b is the time when gNB receives uplink (UL) sounding reference signal (SRS) and T2_a is the time when gNB transmits downlink (DL) positioning reference signal (PRS) . In certain implementations, the UE Rx-Tx time difference can be T1=T1_b-T1a, where T1a is the time when UE receives DL SRS and T1_b is the time when UE transmits UL PRS. In certain implementations, the LMF can calculate the propagation delay (PD) between UE and transmission reception point (TRP) , for example, PD =(T2-T1) /2. With several PD pairs and the location information of different TRPs, the location of UE can be calculated/determined. For AI/ML assisted positioning, the model output can be the UE Rx-Tx time difference (e.g., for the UE side model, case 2a) or the gNB Rx-Tx time difference (e.g., for the gNB side model, case 3a) . In certain implementations, the gNB and/or UE can report the Rx-Tx time difference to the LMF, where the reported values can be derived/obtained/determined using an AI/ML model.

In certain implementations, DL-TDOA/UL-RTOA can be supported, where gNB and/or UE report the RTOA and/or RSTD to the LMF. For DL-TDOA, the UE can report one or more sets of RSTD, which is the reference signal time difference between a measurement TRP and a reference TRP. For UL-RTOA, TRP can report RTOA, which is the relative time of arrival. The LMF can calculate/determine the location of UE based on the reported RSTD/RTOA values and/or the location information of different TRPs. For AI/ML assisted positioning, the model output can be the RSTD (e.g., for the UE side model, case 2a) or the RTOA (e.g., for the gNB side model, case 3a) . In certain implementations, the gNB and/or UE can report the RSTD/RTOA to the LMF, where the reported values can be derived/obtained/determined using an AI/ML model.

In some implementations, a first network entity is UE, and a second network entity is PRU/gNB/TRP/LMF/other UEs. In some implementations, a first network entity is gNB/TRP, and a second network entity is LMF. In some implementations, a first network entity is UE/gNB/LMF. In some implementations, a first network entity is UE, and a second network entity is LMF. In some implementations, a first network entity is LMF, and a second network entity is UE/gNB/TRP. In some implementations, UL-RTOA can be replaced by UL-TDOA.

In certain implementations/embodiments, for determining the model input for an AI/ML assisted model, several enhancements/configurations/implementations can be included. For example, in certain enhancements/configurations/implementations, the model input for the AI/ML assisted model (if the model output is UE/gNB Rx-Tx time difference) can be the (channel) measurement information of the DL PRS/UL SRS transmitted by one or more TRP (s) /gNB (s) /UE (s) . UE/TRP/gNB can send the information of model input to other entities, e.g., LMF/UE/TRP/gNB. As shown in FIG. 4, the model input M1/M2 can be the measurement information, and the model output can be T1_a/T2_b, which can be an absolute time or with respect to a reference time. In certain implementations, an additional post processing can be desired, for example, the UE/gNB is to calculate/determine the UE/gNB Rx-Tx time difference by subtracting the Tx time with AI/ML model output. For different UE/TRP pair (s) , the value of Tx time can be different.

In certain enhancements/configurations/implementations, as shown in FIG. 5, the model input for an AI/ML assisted model (if the model output is UE/gNB Rx-Tx time difference) can be the (channel) measurement information of the DL PRS/UL SRS transmitted by one or more TRP (s) /gNB (s) /UE (s) together with one or more Tx time (s) , where the Tx time for UE is T_UE-TX, the Tx time for gNB is T_gNB-TX. In certain implementations, the T_UE-TX/T_gNB-TX can be the UE/gNB transmit timing of uplink/downlink subframe #j that is closest in time to the subframe #i received from the TP/UE. In certain implementation, TRP (transmission-reception point) can be a TP (transmission point) . In certain implementations, the reference time of the (channel) measurement information can be the Tx time, for example, the (channel) measurement information can include the Tx time information. In some implementations, post processing may not be desired.

In certain implementations/embodiments, for determining the model input for an AI/ML assisted model, several enhancements/configurations/implementations can be included. In certain enhancements/configurations/implementations, the model input for the AI/ML assisted model (if the model output is RSTD) can be the (channel) measurement information of the DL PRS transmitted by one or more TRP (s) /gNB (s) and/or the information of the reference TRP. As shown in FIG. 6, the model input M1, M2…Mn can be the measurement information of DL PRS transmitted by TRP1, TRP2…TRPn, and the model output can be T1, T2…Tn, which can be the absolute time when UE received DL PRS or with respect to a reference time. In some implementations, additional post processing can be desired, for example, where the UE is to calculate/determine the RSTD difference by subtracting the received time of DL PRS transmitted by reference TRP (e.g., Tr as shown in the figure) from the AI/ML model output. For different reference TRP (s) , the value of Tr can be different.

In certain implementations, the model input for an AI/ML assisted model (if the model output is RSTD) can be the (channel) measurement information of the DL PRS transmitted by two TRP (s) /gNB (s) . As shown in FIG. 7, the model inputs M1 and M2 can be the measurement information of DL PRS transmitted by TRP1 and TRP2, and the model output can be the RSTD of TRP1 and TRP2. In some implementations, additional post processing may not be desired.

In some implementations, LMF can configure a number N to UE, where the number N indicates the UE is to perform and/or report the (channel) measurement information of N TRPs. In some implementations, LMF can configure one or more TRP IDs/TRP lists to UE, where the UE is expected to measure and/or report the (channel) measurement information of the configured TRP IDs. In some implementations, UE can report one or more TRP ID (s) (lists) , which can be associated with the (channel) measurement information corresponding to the model input (s) .

In certain implementations, the LMF can configure one or more reference TRP for positioning. For example, the reference TRP can be selected from the reported TRP ID. In some implementations, the LMF can configure two reference TRPs, where one reference TRP can be used for a first positioning method, and the other reference TRP can be used for a second positioning method. In some implementations, the LMF can configure an indicator for the reference TRP, indicating whether the reference TRP can be used for the first positioning method and/or the second positioning method. In some implementations, the first positioning method can be legacy positioning, e.g., DL-TDOA/UL-RTOA/Multi-RTT/AOD/GNSS/etc. In some implementations, the second positioning method can be AI/ML positioning.

In certain implementations, the UE can report one or more reference TRP ID (s) to LMF. For example, as shown in connection with FIG. 6, where there are multiple model input entrances, e.g., M1, M2…Mn, the UE can report the (entrance) index (es) to LMF. The entrance index (es) can be index of the reference TRP, i.e., UE measures/gets the measurement information of DL PRS transmitted by reference TRP (s) . In some implementations, the entrance index (es) can be associated with the reference TRP (s) . In certain implementations, the UE can report an indicator for reference TRP indication. In some implementations, the indicator can be a bitmap. For example, the bitmap “010101” indicates that indexes 2, 4, and 6 can be associated with the reference TRPs. The above implementations can be applicable for different use cases, i.e., LMF side model and/or UE side model and/or gNB side model.

In certain enhancements/configurations/implementations, the model input for AI/ML assisted model (if the model output is RSTD) can be the (channel) measurement information of the DL PRS transmitted by one or more TRP (s) /gNB (s) . As shown in FIG. 8, the model input M1 can be the measurement information of DL PRS transmitted by TRP1, and the model output from different model ID (s) can differ. As shown in FIG. 8, Model 1’s reference TRP is TRP A, and the model output is the RSTD of TRP1 and TRP A. Similarly, model 2’s reference TRP is TRP B, and the model output is the RSTD of TRP1 and TRP B. In certain implementations, the UE can report the association/map between the model ID and the reference TRP. In certain implementations, the UE can report the reference TRP for different models to the LMF. UE can send the information of model input to other entities, e.g., LMF/other UEs/TRP/gNB.

In certain implementations/embodiments, for UL-RTOA, the TRP reports RTOA with respect to a reference time, and the different selection of reference time can affect the reported value of RTOA. For determining the model input for an AI/ML assisted model, several enhancements can be included. In certain enhancements/configurations/implementations, the model input for an AI/ML assisted model (if the model output is RTOA) can be the (channel) measurement information of the UL SRS transmitted by one or more UE (s) . As shown in FIG. 9, the model inputs M1, M2…Mn can be the measurement information of UL SRS transmitted by UE1, UE2…UEn, and the model output can be T1, T2…Tn, which can be the absolute time when TRP receives UL SRS or with respect to a reference time. In some implementations, additional post processing may be desired, for example, where the TRP is to calculate/determine the RTOA by subtracting the reference time (T_ref) from the AI/ML model output.

In certain enhancements/configurations/implementations, the model input for an AI/ML assisted model can include one or more reference time information. As shown in FIG. 10, the model input M1 can be the measurement information of UL SRS transmitted by UE1 and a reference time, and the model output can be the RTOA of the time when TRP receives UL SRS transmitted by UE1. In some implementations, additional post processing may not be desired.

In certain enhancements/configurations/implementations, the model input for each AI/ML assisted model (if the model output is RTOA) can be the (channel) measurement information of the UL SRS transmitted by one UE. As shown in FIG. 11, the model input M1 can be the measurement information of UL SRS transmitted by UE1, and the model output of different model ID (s) can differ. As shown in FIG. 10, Model 1’s reference time can be Ref A, and the model output can be the RTOA of Ref A and the time when the UE1’s SRS is received. Similarly, model 2’s reference TRP can be Ref A, and the model output can be the RTOA between Ref A and the time when the UE1’s SRS is received by the TRP/gNB. In some implementations, the gNB can report the association/map between model ID and reference time. In some implementations, the gNB/TRP can report the reference time for different models to the LMF. In some implementations, the gNB/TRP can send the information of model input to other entities, e.g., LMF/UEs/TRP/other gNB.

In certain implementations/embodiments, for multi-RTT positioning, the location estimation for the target UE can desire multiple pairs of gNB/UE Rx-Tx time difference information. In certain implementations, for DL-TDOA/UL-RTOA positioning, the location estimation for the target UE can desire multiple RSTD/multiple RTOA information. In some implementations, where multiple models are used for a positioning process, model monitoring based on the location of the UE may not determine which model is unsatisfactory. In this regard, several model monitoring methods can be implemented.

In certain enhancements/configurations/implementations, the LMF can perform model monitoring or model monitoring metric calculation. For multi-RTT, the LMF can calculate/determine the location of the UE based on the received gNB/UE Rx-Tx time difference. As shown in FIG. 12, with the received gNB/UE Rx-Tx time difference reported by gNB and UE, the LMF can calculate/determine the distance or timing information for different UE/TRP pairs, and can estimate the location of the UE based on the calculated distance or timing information (or calculate UE’s location based on the received gNB/UE Rx-Tx time difference directly) . In certain implementations, the distance or timing information can be the distance/propagation delay/TOA between the UE and TRP pair. In some implementations, the UE can be replaced by the PRU. For DL-TDOA/UL-RTOA, the LMF can calculate/determine the location of the UE based on the received RSTD/RTOA report. As shown in FIG. 13, the LMF can calculate/determine the location of the UE based on the RSTD reported by the UE and/or the RTOA reported by the gNB.

In certain implementations, the LMF can perform hierarchical model monitoring, including one or more layers. In Layer 1, the LMF can compare the first location of UE/PRU with the second location of UE/PRU. In some implementations, the first location can be the location information derived by other positioning methods, e.g., RAT-dependent positioning, DL-TDOA/DL-AOD/Multi-RTT/E-CID/UL-AOA/UL-TDOA positioning, GNSS, or PRU information. In some implementations, the second location can be the location formation derived using the reported RTT/RSTD/TROA provided by UE/TRP with (AI/ML) model (inference) . In certain implementations, where the difference between the first location and the second location is small enough or within a first (pre-defined) threshold (which can be based on timing and/or distance threshold) , the model that performs model inference for RTT reporting in the associated/corresponding positioning procedure can be regarded as a satisfying model. In this regard, no extra model monitoring behavior may be desired. In certain implementations, Layer 2 model monitoring may be desired where the model output is RTT. In some implementations, Layer 3 model monitoring may be desired where the model output is RSTD/RTOA.

In Layer 2 (which, in some implementations, may not be applicable for DL-TDOA/UL-RTOA) , the LMF can compare the first timing and/or distance information with the second timing and/or distance information of a UE/TRP pair. In some implementations, the first timing and/or distance information can be derived using the location information of the PRU/UE/TRP, and/or measurement or current/legacy positioning methods. In some implementations, the second timing and/or distance information can be derived using the reported RTT provided by UE/TRP with (AI/ML) model (inference) . In certain implementations, where the difference between the first timing and/or distance and the second timing and/or distance is small enough or within a first (pre-defined) threshold (which can be based on timing and/or distance difference threshold) , the model that performs model inference for the associated/corresponding UE/TRP pair can be regarded as a satisfying model. In this regard, no extra model monitoring behavior may be desired. In certain implementations, Layer 3 model monitoring may be desired, depending on the implementation.

In Layer 3, the LMF can compare the first RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value with the second RTT RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value of a UE/TRP pair or a UE or a TRP. In some implementations, the first RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value can be derived using the location information of the PRU/UE/TRP, and/or measurement or current/legacy positioning methods. In some implementations, the second RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value can be provided by UE/TRP with (AI/ML) model (inference) . The monitoring metric can be the difference between the first RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value and the second RTT RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value. In certain implementations, where the difference between the first RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value and the second RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value is small enough or within a first (pre-defined) threshold (which can be based on timing and/or distance difference threshold) , the model that performs model inference for the associated/corresponding RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value can be regarded as a satisfying model. In this regard, no extra model monitoring behavior may be desired. In certain implementations, extra model monitoring behavior may be desired, depending on the implementation. In some implementations, where one model infers one or more RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator values, the monitoring metric can be the number/ratio of the second RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator values that satisfy a second (pre-defined) threshold (which can be based on the number/ratio of RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator inference output (s) ) . In some implementation, the first and/or the second (pre-defined) threshold (s) can be configured by LMF to UE/gNB/TRP or reported by UE/gNB/TRP to LMF.

In certain implementations, the LMF can perform model monitoring by comparing the location differences, timing and/or distance differences, and/or RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value differences. In this regard, the LMF can choose/select/utilize one or more of the following methods: the LMF can compare the first location of UE/PRU with the second location of UE/PRU; the LMF can compare the first timing and/or distance information with the second timing and/or distance information of a UE/TRP pair; the LMF can compare the first RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value with the second RTT RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value of a UE/TRP pair, a UE, or a TRP; and/or to support the LMF performs model monitoring, UE/TRP/gNB can send/transmit the T_UE-TX/T_gNB-TX/reference time of RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator to the LMF, where T_UE-TX/T_gNB-TX can be the UE/gNB transmit timing of uplink/downlink subframe #j that is closest in time to the subframe #i received from the TP/UE. In some implementations, the UE/TRP/gNB can send/transmit one or more of the following to LMF: PRS resource ID, PRS resource set ID, TRP ID/dl-PRS-ID, slot index, subframe number, and/or OFDM symbol index of the received DL PRS/UL SRS, UE/PRU ID, SRS resource ID, T_UE-TX/T_gNB-TX/reference time of RTT/RSTD/RTOA, and/or inference output/measurement report, including one or more of RTT/RSTD/RTOA/angle information/power information/LOS/NLOS indicator, an indicator (can be associated with the inference output/measurement report) , which indicates the reported RTT/RSTD/RTOA/LOS/NLOS indicator is for model monitoring.

In certain enhancements/configurations/implementations, the UE/TRP/gNB can perform the model monitoring or the model monitoring metric calculation. In some implementations, the UE/TRP/gNB can perform the model monitoring or the model monitoring metric calculation based on expected RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator. In certain implementations, the UE/TRP can calculate/determine the expected RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator/ground truth label based on assistance information. In this regard, the UE/TRP/gNB can send a request to LMF, requesting that the LMF provide assistance information for one or more UE/TRP (s) , including one or more of the following: information type, indicating what kind of information is requested, such as location information, distance, timing information, etc.; and/or UE/TRP/gNB ID. In certain implementations, the LMF can send/transmit one or more of the following to UE, TRP, and/or gNB: location information of UE, PRU, TRP, gNB, and/or reference TRP; distance between the UE/PRU and TRP/gNB/reference TRP; propagation delay/time (of UL SRS/DL PRS) between UE/PRU and TRP/gNB/reference TRP; timing information between UE/PRU and TRP/gNB/reference TRP; and/or UE ID/PRU ID/TRP ID/gNB ID/reference TRP ID. In certain implementations, the UE/TRP/gNB can calculate/determine the expected RTT/RSTD/RTOA//hard and/or soft LOS/NLOS indicator/ground truth label (of a UE/TRP and/or pair of UE/TRP) based on the above information.

In certain implementations, the LMF can provide expected RTT/RSTD/RTOA/RSTD/RTOA/hard and/or soft LOS/NLOS indicator/ground truth label to UE/gNB/TRP. In this regard, the UE/TRP/gNB can send/transmit the T_UE-TX/T_gNB-TX/reference time of RTT/RSTD/RTOA, hard and/or soft LOS/NLOS indicator, and/or the ID (s) of reference TRP and measured TRP to LMF to request the expected RTT/RSTD/RTOA/RSTD/RTOA/hard and/or soft LOS/NLOS indicator/ground truth label. In response to receiving the data, the LMF can calculate the expected RTT RSTD/RTOA/RSTD/RTOA/hard and/or soft LOS/NLOS indicator/ground truth label based on the location information of UE/PRU/TRP/gNB. The LMF can send/transmit the expected RTT/RSTD/RTOA, and/or hard and/or soft LOS/NLOS indicator, and/or ground truth label to the UE/TRP/gNB. In certain implementations, the LMF can send the association information of the expected RTT/RSTD/RTOA, and/or hard and/or soft LOS/NLOS indicator, and/or ground truth label to the UE/TRP/gNB, including the reference TRP ID, measured TRP ID, and/or UE/PRU ID.

In certain implementations, UE/TRP/gNB can send/transmit/provide a request to LMF to request the label of expected RTT/RSTD/RTOA/soft LOS/NLOS indicator and/or the ground truth label, where the request includes one or more of: the type of request, reference TRP and/or measure TRP and/or UE ID, required time, expected response time.

In certain implementations, for multi-RTT, the ground truth labels/RTT of UE/TRP can be interdependent. In some implementations, the location of the UE can be calculated with {UE RTT1, TRP RTT1} , {UE RTT2, TRP RTT2} … {UE RTTn, TRP RTTn} . For the UE side model, the gNB can provide the gNB Rx-Tx time difference corresponding to the target UE to UE/LMF. For the gNB side model, the UE can provide the UE Rx-Tx time difference corresponding to the target UE to TRP/gNB/LMF.

In certain implementations/embodiments, in an AI/ML based positioning, the entities responsible for model monitoring can vary in different positioning use cases. For example, for the gNB/UE side model, the model monitoring entity and/or monitoring metric calculation entity can be gNB/UE or LMF. In certain implementations, the model monitoring entity and/or monitoring metric calculation entity can configure a time window and/or indicator for the model monitoring data provider to indicate the purpose of the window, such as whether the current time window is for model monitoring.

In certain implementations, the model monitoring entity and/or monitoring metric calculation entity (which can be UE/TRP/LMF) can configure one or more windows for UE/PRU/TRP, to allow measurement nodes to perform measurement and/or send data or measurement results to model monitoring entity and/or monitoring metric calculation entity for model monitoring/monitoring metric calculation, or for model inference nodes to upload inference results. In certain implementations, as shown in connection with FIG. 14, the configuration of the window can include at least one of the following: the starting position (time) of the window; the duration of the window; the period and offset of the window; a type of indicator that indicates the window is used for monitoring; an SRS/PRS resource (set) ID; and/or a TRP ID/UE ID/PRU ID. In certain implementations, configuring a measurement window can allow the data provider to measure and/or report data or measurement information for model monitoring or monitoring metric calculation inside and/or outside the window.

In certain implementations, the model monitoring and/or monitoring metric calculation entity can configure the requirements for data or measurement information, which can include at least one of the following: label/measurement; type of label/measurement; accuracy, confidence level, and/or quality requirements for label/measurement; source of label/measurement (PRU/GNSS/other) ; number of samples; and/or multi-path/phase/RSRP requirements.

In certain implementations, the UE/TRP/PRU can measure and/or report data or measurement information to the model monitoring and/or monitoring metric calculation entity for model monitoring inside and/or outside the window (based on the configured requirements) . The data or measurement information can include channel measurement results. In certain implementations, the data or measurement information can include at least one of the following: measurement information; label/inference output, where the label/inference output can be the location of UE/PRU or RSTD (including reference TRP and measurement TRP ID) , UE/GNB Rx Tx time difference (including TRP/UE ID) , and/or the label/inference output can include information such as RSRP/RSRPP/AOD/AOA; type of label/measurement; accuracy, confidence, and/or quality of label/measurement; a first indicator that indicates whether the associated/corresponding measurement/report is performed within the configured measurement/report window; and/or a second indicator that indicates whether the corresponding/associated measurements/reports meet/satisfy the data requirements configured by the model monitoring and/or monitoring metric calculation entity.

In certain implementations/embodiments, for downlink positioning, the node providing model monitoring data/measurement information can be PRU or UE with measurement results (such as GNSS or other legacy positioning methods) . FIG. 15 illustrates certain implementations where the LMF is the node performing model monitoring or monitoring metric calculation. In certain implementations, where the model is on the UE side, the LMF can send/forward the data/ (channel) measurement results of other UE/PRU to the UE. The UE, executing the AI/ML model, can perform model inference and send/transmit the inference results to the LMF for model monitoring or monitoring metric calculation. After the UE, executing the AI/ML model with the data/ (channel) measurement results of other UE/PRU sent/forwarded by LMF (as model input) , and UE completes model inference, the UE can send/transmit the inference results/accuracy (of UE and/or other UE/PRU) , recommended monitoring behavior, and/or monitoring metric of the model to the LMF (for model monitoring/for making monitoring behavior/decision) .

FIG. 16 illustrates certain implementations where the UE is the node performing model monitoring or monitoring metric calculation. In certain implementations, the LMF can send the location information, and/or ground truth label, and/or measurement information of other UE/PRU (used for model monitoring) to the UE. The location information can be the location of PRU/other UEs, and the measurement information can be: RSTD (time difference between receiving PRS between PRU/other UE and reference TRP and measurement TRP) ; UE Rx-Tx time difference (alternatively includes TRP/UE ID) ; and/or RSRP/RSRPP/AOD/AOA, etc. In some implementations, the ground truth label and/or measurement information in the LMF can be calculated based on location and time information, angle, and/or PRS configuration.

In certain implementations/embodiments, for UL positioning, the TRP can receive the SRS transmitted by PRU/UE and report the measurement results to the LMF. FIG. 17 illustrates certain implementations where the LMF is the node performing model monitoring and/or monitoring metric calculation. In certain implementations, where the LMF has the location of UE/PRU, the LMF can get the location information/label/measurement. In some implementations, where the LMF may not have the location of UE/PRU, the LMF can request the location information/label/measurement from UE/PRU.

FIG. 18 illustrates certain implementations where the gNB is the node executing model monitoring and/or monitoring metric calculation. In some implementations, the TRP can send/transmit the measurement results to LMF, where the measurement result can be used for model monitoring on the gNB side. In certain implementations, the LMF can send/transmit the label/measurement information to gNB, and/or LMF can forward the measurement information of other TRPs/gNBs to TRP/gNB. In some implementations, the label can be PRU/other UE’s location information. In some implementations, the measurement can be at least one of the following: UL-RTOA (uplink reception time) ; gNB Rx-Tx time difference (including TRP/UE ID) ; and/or RSRP/RSRPP/AOD/AOA, etc. In some implementations, the label and/or measurement information can be calculated/estimated based on location and time information, angle, and/or PRS configuration, etc.

In certain implementations/embodiments, the monitoring criteria for different nodes differ, maintaining the fairness of the AI/ML modes located at different entities may become challenging. In this regard, the LMF can configure the monitoring criteria for UE/gNB/TRP and/or the applicable time and location/distance scope. In certain implementations, the configuration can include the monitoring criteria indicating the mapping relationship/association between monitoring behavior and accuracy/reliability, where the behavior may include at least one of the following: a fallback to legacy/RAT-dependent positioning methods; a de-activate model; model switching; and/or model fine-tuning. In certain implementations, the monitoring metric may include at least one of the following: (Statistical/average) positioning accuracy/reliability, (Statistical/average) error/accuracy/reliability on power/angle/timing information, (Statistical/average) error/accuracy/reliability on LOS/NLOS indicator, location/distance/power/angle/timing and/or LOS/NLOS indicator difference between inference output the ground truth label. In some implementations, the ground truth label can be the expected/accurate location/distance/power/angle/timing and/or LOS/NLOS indicator information. In some implementations, the accuracy/error can be one or more of the following: mean absolute error, mean squared error, and mean absolute percentage error indicators, root mean squared error, mean absolute error, R-squared, root mean squared logarithmic error, etc.

In certain implementations, the configuration can include the applicable time and/area and/or window of the current monitoring criteria that can include at least one of the following: the starting position (time) of the window; the duration of the window; the period and offset of the window; the applicable area range (s) of the monitoring criteria; one or more validity area; one or more coordinate range; and/or one or more cell/TRP/gNB ID lists. In certain implementations, the configuration can include the applicable models and/or model types for the monitoring criteria that can include at least one of the following: a model ID list; AI/ML based positioning methods, such as direct AI/ML positioning model and/or AI/ML assisted positioning model; AI/ML positioning entity with UE side model, gNB side model, and/or LMF side model; and/or applicable scenarios, such as Inf-SH, Inf-DH, etc. In certain implementations, the configuration can include reliability, which provides a measure of how many positioning requests/inference outputs satisfy QoS/accuracy requirements. An example for the configuration of mapping relationship/association between monitoring behavior and monitoring metric/accuracy/reliability is as {model fine-tuning, reliability 80%～85%. This means when the reliability of a AI/ML model is 80%～85%, the entity is expected to perform model fine-tuning.

In certain implementations/embodiments, the model monitoring can include different nodes, for example, the model inference node, the monitoring metric calculation node, and/or the monitoring node. The different nodes can be located in one or more entities. For example, the model inference node of the UE side model can be the UE, the monitoring metric calculation node can be the UE, and/or the monitoring node can be the LMF. The following table lists several possible entities for model monitoring:

In certain implementations, as shown in connection with FIG. 19, there can be several ways for model monitoring, for example, on the NG-RAN side model. In this regard, the gNB can perform the model monitoring metric calculation and make monitoring decisions. In some implementations, the LMF can perform the model monitoring metric calculation, and the gNB can make monitoring decisions. In some implementations, the gNB can perform the model monitoring metric calculation, and the LMF can make monitoring decisions.

In certain implementations, the model monitoring metric calculation entity can send/transmit one or more of the following to the model monitoring entity: the inference output/results; the difference between the inference output/result and the ground truth label; the positioning/inference accuracy/reliability of the model; the number/ratio of model output that satisfy the accuracy/ (one or more pre-defined thresholds for location and/or measurement) requirement; and/or the suggested monitoring behavior. In certain implementations, the model monitoring entity can send/transmit monitoring behavior, which may include at least one of the following: a fallback to legacy/RAT-dependent positioning methods; a de-activate model; a model switching; and/or a model fine-tuning.

In certain implementations, the model monitoring entity can send/transmit an applicable time and/or window of the current monitoring behavior to model monitoring metric calculation entity. In certain implementations, the model monitoring metric calculation entity can send/transmit the applicable area range (s) of the monitoring behavior to model monitoring entity. In certain implementations, the model monitoring metric calculation entity can send/transmit the applicable models for the monitoring behavior to model monitoring metric calculation entity.

In certain implementations/embodiments, the UE can report one or more indicators that indicate that the UE capability is for the first process, for the second process, and/or for the first process and the second process to LMF. The indicators can include the UE capability applicable to the number of DL PRS that can process in a slot, e.g., maxNumOfDL-PRS-ResProcessedPerSlot, maxNumOfDL-PRS-ResProcessedPerSlot-RRC-Inactive; PRS processing capabilities; dl-PRS-BufferType, and/or dl-PRS-BufferType-RRC-Inactive; durationOfPRS-Processing; and/or prs-ProcessingCapabilityOutsideMGinPPW.

In certain implementations, to support the UE performing channel measurement, the UE can report one or more UE capabilities that are for a first process and/or a second process to LMF, where one UE capability is for the first process only, one UE capability is for the second process only, and/or one UE capability is for the first process and the second process. In certain implementations, a first process can be applicable for RSTD, RTT, RSRP, and/or RSRPP, and the second process can be applicable for channel measurement to derive CIR/PDP/DP, sample-based measurement, and/or path-based measurement. In certain implementations, a second process can be applicable for AI/ML positioning.

In certain implementations, a UE can report one (reference) UE capability to LMF for a first process, one or more differential/association UE capabilities for a second process, and/or a third process. In certain implementations, a UE can report one (reference) UE capability for a second process and/or a third process, and/or one or more differential/association UE capabilities for a second process and/or a third process. In some implementations, the differential/association UE capability can be reported with respect to the (reference) UE capability or reported as a differential value compared to the (reference) UE capability. In certain implementations, the third process can be applicable for inference, for example, the time between when UE receives the measurement and derives the output. In certain implementations, a UE can report one or more indicators indicating whether the UE capability is selected as the (reference) UE capability.

In certain implementations, the UE can report one or more UE capabilities to LMF for a second process and/or a third process, where each UE capability can be applicable for one or more of CIR/PDP/DP, sample-based measurement, and/or path-based measurement. For example, for the second process, the UE can report {N (, T) for CIR} , {N1 (, T1) for PDP} , {N2 (, T2) for DP} , {N3 (, T3) for sample-based measurement} , and/or {N4 (, T4) for path-based measurement} . In certain implementations, for UE capability, the number of DL PRS resources N that a UE can process in a slot is N≤N1≤N2. For UE capability (duration N of DL-PRS symbols in units of ms) , a UE can process every T ms with the same T value, N≤N1≤N2, or for the same N value, T≥T1≥T2. For a third process, the UE capability can be associated with the size/number/dimension of model input/measurement/the number of PRS resources/samples.

In certain implementations, the UE capability can be at least one of the following: the UE capability for the number of DL PRS resources that UE can process in a slot; the duration N (and/or N2) of DL-PRS symbols in units of ms a UE can process every T (and/or T2 ms) for measurement gap and/or without measurement gap and/or for PRS processing window; and the inference time a UE can desire/require for output. For example, the UE can report capability {R_N, R_T} for the required inference time, where the required inference time can be associated with the model input. R_T can be the time desired to get the inference output/UE’s location/timing information/power information/angle information of R_N DL PRS duration or R_N DL PRS resources/samples/instances.

In certain implementations, the current IE PRS-ProcessingCapabilityPerBand can be defined for a single positioning frequency layer on a certain band (for example, a target device supporting multiple positioning frequency layers can be expected to process one frequency layer at a time) . In certain implementations, the UE can report to the LMF one or more PRS processing capabilities per positioning frequency layer and/or per frequency combination, per CC and/or per band combination, and/or per CC combination for a first process and/or a second process and/or a third process.

Referring now to FIG. 20, which illustrates a flow diagram of a method 2000 for performing positioning requests and/or measurement information exchange. The method 2000 may be implemented using any of the components and devices detailed herein in conjunction with FIGS. 1–19. In an overview, the method 2000 may include a first network entity sending a request/message for positioning to a second network entity (STEP 2002) . The method may include the first network entity receiving measurement information from the second network entity (STEP 2004) .

In certain configurations, a first network entity (e.g., UE/gNB/TRP) can send/transmit/provide a request/message for positioning to a second network entity (LMF/gNB/TRP/PRU/other UEs) (STEP 2002) . In certain configurations, the request/message can include at least one of the following: channel measurement information of a DL PRS transmitted by a TRP/gNB; channel measurement information of an UL SRS transmitted by a UE/PRU; one or more reference times optionally associated with channel measurement information, model ID, an ID; and/or one or more TRP IDs/TRP ID lists optionally associated with (channel) measurement information. In certain configurations, the request/message can include model input/measurement information and/or output/label information for the positioning.

In certain configurations, the first network entity can be configured by the second network entity with TRP/gNB information. In certain configurations, the TRP/gNB information can include at least one of the following: a number N indicating that the first network entity is expected to perform and/or report channel measurement information of N TRP/gNBs; one or more TRP IDs and/or TRP/gNB ID lists indicating that the first network entity is expected to perform and/or report channel measurement information of a configured TRP/gNB; one or more reference TRPs, where one of the reference TRPs can be configured for a first positioning method and another of the reference TRPs can be configured for a second positioning method; and/or one or more indicators for a reference TRP indicating whether the reference TRP can be applied to at least one of the first positioning method or the second positioning method.

In certain configurations, the first positioning method can include a legacy positioning method, and the second positioning method can include an AI/ML-assisted positioning method. In certain configurations, the TRP/gNB information can be configured for the first network entity to report the channel measurement information.

In certain configurations, the first network entity can send/transmit/provide TRP/gNB information to the second network entity. In certain configurations, the TRP information can include at least one of the following: one or more TRP IDs or TRP ID lists associated with channel measurement information corresponding to a model input; one or more reference TRP IDs; an entrance index optionally associated with a reference TRP; and/or an indicator configured for indicating the reference TRP. In certain configurations, the first network entity can send/transmit/provide association information and/or reference time for different models to the second network entity. In some implementations, the association information can include an association between a model/association ID and the reference TRP. In some implementations, the association information can include the association/map between a model ID/association and reference time.

In certain configurations, a first network entity can receive/obtain/acquire measurement information, including (channel) measurement information of other UE/PRU/TRP, from a second network entity (STEP 2004) . In some implementations, the channel measurement information can be optionally associated with one or more of the following: a timestamp, a quality indicator, a timing error group, or scenario information. In certain configurations, the first network entity can send/transmit/provide location information of the other UE/PRU or the RTOA/RTT of gNB/TRP to the second network. In some implementations, the location information/RTOA/RTT can be optionally based on the (channel) measurement information. In certain configurations, the location information/RTOA/RTT can be derived using an AI/ML model. In certain configurations, the location information/RTOA/RTT can be associated with one or more of the following: a PRU ID, a UE ID, the timestamp, the quality indicator, and/or the timing error group.

In certain configurations, the first network entity can send/transmit/provide inference results, location information, accuracy, recommended monitoring behavior, or a monitoring metric of a model to the second network entity. In certain configurations, the first network entity can receive/obtain/acquire location/measurement information of the other UE/PRU from the second network entity. In some implementations, the location/measurement information can include at least one of the following: an RSTD; a UE Rx-Tx time difference; RSRP; RSRPP; AOD; LOS/NLOS indicator; and/or AOA.

Referring now to FIG. 21, which illustrates a flow diagram of a method 2100 for performing model monitoring. The method 2100 may be implemented using any of the components and devices detailed herein in conjunction with FIGS. 1–19. In an overview, the method 2100 may include a first network entity or a second network entity comparing first information with second information for model monitoring (STEP 2102) . The method may include the first network entity receiving a configuration optionally for monitoring from a second network entity (STEP 2104) . The method may include the first network entity sending positioning-related information to the second network entity (STEP 2106) .

In certain configurations, a first network entity (e.g., LMF/UE/gNB) or a second network entity can compare first information with second information for model monitoring and/or metric calculation (STEP 2102) . In certain configurations, each of the first information and the second information can include at least one of the following: UE/PRU’s location information; timing and/or distance information; or RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value. In certain configurations, the first information can be derived based on one of the following positioning methods: RAT-dependent positioning, DL-TDOA/DL-AOD/Multi-RTT/E-CID/UL-AOA/UL-TDOA positioning, GNSS, or PRU information. In certain implementations, the second information can be derived based on an AI/ML model.

In certain configurations, the first network entity can receive/obtain/acquire information from a second network entity. In some implementations, the information can include at least one of the following: a PRS resource ID; a PRS resource set ID; a TRP ID/dl-PRS-ID; an ID of a reference TRP, an ID of a measure TRP, and/or a UE ID; a slot index and/or a subframe number and/or an OFDM symbol index of a received DL PRS/UL SRS; a UE/PRU ID;an SRS resource ID; a T_UE-TX/T_gNB-TX/reference time of RTT/RSTD/RTOA, and/or a soft LOS/NLOS indicator; an inference output/measurement report including one or more of RTT, RSTD, RTOA, angle information, power information, or a hard LOS/NLOS indicator, or a soft LOS/NLOS indicator; or an indicator indicating reported RTT/RSTD/RTOA LOS/NLOS indicator is for model monitoring; and/or one or more timing/distance difference thresholds.

In certain configurations, the first network entity can receive/obtain/acquire an expected information from the second network entity. In some implementations, the expected information can include at least one of the following: RTT, RSTD, RTOA, hard and/or soft LOS/NLOS indicator, ground truth label. In certain configurations, the expected information can be based on a reference time provided by the second network entity. In some implementations, the expected information can be associated with the ID of the reference TRP, the ID of the measure TRP, and/or the UE ID.

In certain configurations, the first network entity can send/transmit/provide to a second network entity a request for the first network entity to provide a message. In some implementations, the message can include at least one of the following: assistance information of one or more UEs/TRPs; a UE/TRP/gNB ID; a UE/TRP pair ID; or a label of an expected RTT, RSTD, RTOA, a soft LOS/NLOS indicator, a hard LOS/NLOS indicator, and/or a ground truth label. In certain configurations, the request can include at least one of the following: a type of the request; a reference TRP; a measure TRP; a UE ID; a required time; and/or an expected response time.

In certain configurations, the first network entity can receive/obtain/acquire from the second network entity at least one of the following: location information of the reference TRP; a distance between the second network entity and the reference TRP; a propagation delay/time between the second network entity and the reference TRP; timing information between the second network entity and the reference TRP; and/or a UE ID, a PRU ID, a TRP ID, a gNB ID, or a reference TRP ID.

In certain configurations, a first network entity can receive/obtain/acquire a configuration optionally for monitoring from a second network entity (STEP 2104) . In some implementations, the monitoring configuration can include a mapping relationship between a behavior and a metric, accuracy, or reliability. In certain configurations, the behavior can include at least one of the following: a fallback to a legacy/RAT-dependent positioning method; a deactivated model; model switching; and/or model fine-tuning. In certain configurations, the metric can include at least one of the following: positioning accuracy/reliability; accuracy/reliability on power/angle/timing information; accuracy/reliability on LOS/NLOS indicator, location/distance/power/angle/timing and/or LOS/NLOS indicator difference between inference output the ground truth label.

In certain configurations, the configuration can be associated with time and/or window information. In certain implementations, the applicable time and/or window information can include at least one of the following: a starting position of the window; a duration of the window; and/or a period and an offset of the window. In certain configurations, the configuration can be associated with area range information. In certain implementations, the area range information can include at least one of the following: a validity area; a coordinate range; or a cell, TRP, or gNB ID list. In certain configurations, the configuration can be associated with model information. In certain implementations, the model information can include at least one of the following: a model ID list; an AI/ML-based positioning method; an AI/ML positioning entity; and/or an applicable scenario.

In certain configurations, a first network entity can send/transmit/provide positioning-related information to a second network entity (STEP 2106) . In some implementations, the first network entity can be a model monitoring metric calculation entity. In some implementations, the second network entity can be a model monitoring entity. In certain configurations, the positioning-related information can include at least one of the following: an inference output; a difference between the inference output and a ground truth label; a positioning/inference accuracy/reliability of a model; or a number/ratio of model output that satisfies an accuracy requirement; and/or a suggested monitoring behavior. In certain configurations, the first network entity can receive/obtain/acquire from the second network entity at least one of the following: a fallback to a legacy/RAT-dependent positioning method; a deactivated model; model switching; and/or model fine-tuning.

Referring now to FIG. 22, which illustrates a flow diagram of a method 2200 for performing capability reporting. The method 2200 may be implemented using any of the components and devices detailed herein in conjunction with FIGS. 1–19. In an overview, the method 2200 may include a first network entity sending a report, including a capability of the first network entity for a first process and/or a second process, to a second network entity (STEP 2202) .

In certain configurations, a first network entity can send/transmit/provide a report including a capability of the first network entity for a first process and/or a second process to a second network entity (STEP 2202) . In certain configurations, the first network entity can send/transmit/provide to the second network entity another report including one or more PRS processing capabilities per positioning frequency layer and/or per frequency combination, and/or per CC, and/or per band combination, and/or per CC combination for the first process and/or the second process. In certain configurations, the one or more PRS processing capabilities can include at least one of the following: a number of DL PRS resources that the second network entity can process in a slot; a duration N of DL-PRS symbols in units of ms that the second network entity can process every T for measurement gap, without measurement gap, and/or for PRS processing window; and/or a UE capability for an inference time optionally associated with a duration of DL-PRS symbols, a type of channel measurement, or a measurement size. In certain configurations, the first process can be applicable for RSTD, RTT, RSRP, and/or RSRPP. In some implementations, the second process can be applicable for channel measurement and, optionally, to derive CIR/PDP/DP and/or sample-based measurement and/or path-based measurement.

While various embodiments/implementations of the present solution have been described above, it should be understood that they have been presented by way of example only, and not by way of limitation. Likewise, the various diagrams may depict an example architecture or configuration, which are provided to enable persons of ordinary skill in the art to understand example features and functions of the present solution. Such persons would understand, however, that the solution is not restricted to the illustrated example architectures or configurations but can be implemented using a variety of alternative architectures and configurations. Additionally, as would be understood by persons of ordinary skill in the art, one or multiple features of one embodiment/implementation can be combined with one or multiple features of another embodiment/implementation described herein. Thus, the breadth and scope of the present disclosure should not be limited by any of the above-described illustrative embodiments.

It is also understood that any reference to an element herein using a designation such as “first, ” “second, ” and so forth does not generally limit the quantity or order of those elements. Rather, these designations can be used herein as a convenient means of distinguishing between two or more elements or instances of an element. Thus, a reference to first and second elements does not mean that only two elements can be employed, or that the first element must precede the second element in some manner.

Additionally, a person having ordinary skill in the art would understand that information and signals can be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, and symbols, which may be referenced in the above description, can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

A person of ordinary skill in the art would further appreciate that any of the various illustrative logical blocks, modules, processors, means, circuits, methods and functions described in connection with the aspects disclosed herein can be implemented by electronic hardware (e.g., a digital implementation, an analog implementation, or a combination of the two) , firmware, various forms of program or design code incorporating instructions (which can be referred to herein, for convenience, as “software” or a “software module) , or any combination of these techniques. To clearly illustrate this interchangeability of hardware, firmware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware, firmware or software, or a combination of these techniques, depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in various ways for each particular application, but such implementation decisions do not cause a departure from the scope of the present disclosure.

Furthermore, a person of ordinary skill in the art would understand that various illustrative logical blocks, modules, devices, components, and circuits described herein can be implemented within or performed by an integrated circuit (IC) that can include a general purpose processor, a digital signal processor (DSP) , an application specific integrated circuit (ASIC) , a field programmable gate array (FPGA) or other programmable logic device, or any combination thereof. The logical blocks, modules, and circuits can further include antennas and/or transceivers to communicate with various components within the network or within the device. A general purpose processor can be a microprocessor, but in the alternative, the processor can be any conventional processor, controller, or state machine. A processor can also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or multiple microprocessors in conjunction with a DSP core, or any other suitable configuration to perform the functions described herein.

If implemented in software, the functions can be stored as one or multiple instructions or code on a computer-readable medium. Thus, the steps of a method or algorithm disclosed herein can be implemented as software stored on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that can be enabled to transfer a computer program or code from one place to another. A storage media can be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer.

In this document, the term “module” as used herein, refers to software, firmware, hardware, and any combination of these elements for performing the associated functions described herein. Additionally, for purpose of discussion, the various modules are described as discrete modules; however, as would be apparent to one of ordinary skill in the art, two or more modules may be combined to form a single module that performs the associated functions according to embodiments of the present solution.

Additionally, memory or other storage, as well as communication components, may be employed in embodiments of the present solution. It will be appreciated that, for clarity purposes, the above description has described embodiments of the present solution with reference to different functional units and processors. However, it will be apparent that any suitable distribution of functionality between different functional units, processing logic elements or domains may be used without detracting from the present solution. For example, functionality illustrated to be performed by separate processing logic elements, or controllers, may be performed by the same processing logic element, or controller. Hence, references to specific functional units are only references to a suitable means for providing the described functionality, rather than indicative of a strict logical or physical structure or organization.

Various modifications to the embodiments described in this disclosure will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the scope of this disclosure. Thus, the disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the novel features and principles disclosed herein, as recited in the claims below.

Claims

A wireless communication method, comprising:

sending, by a first network entity to a second network entity, a request/message for positioning.
The wireless communication method of claim 1, wherein the request/message comprises at least one of: channel measurement information of a DL PRS transmitted by a TRP/gNB; channel measurement information of an UL SRS transmitted by a UE/PRU; one or more reference times optionally associated with channel measurement information, model ID, and/or an ID; or one or more TRP IDs/TRP ID lists optionally associated with (channel) measurement information.
The wireless communication method of claim 1, wherein the request/message includes model input/measurement information and/or output/label information for the positioning.
The wireless communication method of claim 1, wherein the first network entity is configured by the second network entity with TRP/gNB information.
The wireless communication method of claim 4, wherein the TRP/gNB information comprises at least one of: a number N indicating that the first network entity is expected to perform and/or report channel measurement information of N TRP/gNBs; one or more TRP IDs and/or TRP/gNB ID lists indicating that the first network entity is expected to perform and/or report channel measurement information of a configured TRP/gNB; one or more reference TRPs, wherein one of the reference TRPs is configured for a first positioning method and another of the reference TRPs is configured for a second positioning method; or one or more indicators for a reference TRP indicating whether the reference TRP can be applied to at least one of the first positioning method or the second positioning method.
The wireless communication method of claim 5, wherein the first positioning method includes a legacy positioning method, and the second positioning method includes an AI/ML-assisted positioning method.
The wireless communication method of claim 5, wherein the TRP/gNB information is configured for the first network entity to report the (channel) measurement information.
The wireless communication method of claim 1, further comprising:

sending, by the first network entity to the second network entity, TRP/gNB information.
The wireless communication method of claim 8, wherein the TRP information comprises at least one of: one or more TRP IDs or TRP ID lists associated with channel measurement information corresponding to a model input; one or more reference TRP IDs; an entrance index optionally associated with a reference TRP; or an indicator configured for indicating the reference TRP.
The wireless communication method of claim 1, further comprising:

sending, by the first network entity to the second network entity, association information and/or reference time for different models, wherein the association information includes an association between a model/association ID and the reference TRP, or the association information includes the association/map between a model ID/association and reference time.
A wireless communication method, comprising:

comparing, by a first network entity and/or a second network entity, first information with second information for model monitoring and/or metric calculation.
The wireless communication method of claim 11, wherein each of the first information and the second information includes at least one of: UE/PRU’s location information; timing and/or distance information; or RTT/RSTD/RTOA/hard and/or soft LOS/NLOS indicator value.
The wireless communication method of claim 11, wherein the first information is derived based on one of the following positioning methods: RAT-dependent positioning, DL-TDOA/DL-AOD/Multi-RTT/E-CID/UL-AOA/UL-TDOA positioning, GNSS, or PRU information, and wherein the second information is derived based on an AI/ML model.
The wireless communication method of claim 11 or 1, further comprising:

receiving, by the first network entity from a second network entity, information, wherein the information comprises at least one of: a PRS resource ID; a PRS resource set ID; a TRP ID/dl-PRS-ID; an ID of a reference TRP, an ID of a measure TRP, and/or a UE ID; a slot index and/or a subframe number and/or an OFDM symbol index of a received DL PRS/UL SRS; a UE/PRU ID; an SRS resource ID; a T_UE-TX/T_gNB-TX/reference time of RTT/RSTD/RTOA, and/or a soft LOS/NLOS indicator; an inference output/measurement report including one or more of RTT, RSTD, RTOA, angle information, power information, or a hard LOS/NLOS indicator, or a soft LOS/NLOS indicator; or an indicator indicating reported RTT/RSTD/RTOA LOS/NLOS indicator is for model monitoring; or one or more timing/distance difference thresholds.
The wireless communication method of claim 11 or 1, further comprising:

receiving, by the first network entity from the second network entity, an expected information;

wherein the expected information can be one or more of: RTT, RSTD, RTOA, hard and/or soft LOS/NLOS indicator, ground truth label.
The wireless communication method of claim 15, wherein the expected information is based on a reference time provided by the second network entity, or the expected information is associated with the ID of the reference TRP, the ID of the measure TRP, and/or the UE ID.
The wireless communication method of claim 11 or 1, further comprising:

sending, by the first network entity to a second network entity, a request for the first network entity to provide a message, wherein the message comprises at least one of: assistance information of one or more UEs/TRPs; a UE/TRP/gNB ID; a UE/TRP pair ID; or a label of an (expected) RTT/RSTD/RTOA, a soft LOS/NLOS indicator, a hard LOS/NLOS indicator, and/or a ground truth label.
The wireless communication method of claim 17, wherein the request comprises at least one of: a type of the request; a reference TRP; a measure TRP; a UE ID; a required time; or an expected response time.
The wireless communication method of claim 18, further comprising:

receiving, by the first network entity from the second network entity, at least one of the following information: location information of the reference TRP; a distance between the second network entity and the reference TRP; a propagation delay/time between the second network entity and the reference TRP; timing information between the second network entity and the reference TRP; or a UE ID, a PRU ID, a TRP ID, a gNB ID, or a reference TRP ID.
A wireless communication method, comprising:

receiving, by a first network entity from a second network entity, measurement information including (channel) measurement information of other UE/PRU/TRP;

wherein the (channel) measurement information is optionally associated with one or more of:a timestamp, a quality indicator, a timing error group, or scenario information.
The wireless communication method of claim 20, further comprising:

sending, by the first network entity to the second network entity, location information of the other UE/PRU or the RTOA/RTT of gNB/TRP;

wherein the location information/RTOA/RTT is optionally based on the (channel) measurement information.
The wireless communication method of claim 21, wherein the location information/RTOA/RTT is derived using an AI/ML model.
The wireless communication method of claim 21, wherein the location information/RTOA/RTT is associated with one or more of: a PRU ID, a TRP ID, a UE ID, the timestamp, the quality indicator, or the timing error group.
The wireless communication method of claim 20 or 1, further comprising:

sending, by the first network entity to the second network entity, inference results, the location information, accuracy, recommended monitoring behavior, or a monitoring metric of a model.
The wireless communication method of claim 20 or 1, further comprising:

receiving, by the first network entity from the second network entity, location/measurement information of the other UE/PRU;

wherein the location/measurement information comprises at least one of: an RSTD; a UE Rx-Tx time difference; RSRP; RSRPP; AOD; LOS/NLOS indicator; or AOA.
A wireless communication method, comprising:

receiving, by a first network entity from a second network entity, a configuration optionally for monitoring;

wherein the monitoring configuration comprises a mapping relationship between a behavior and a metric, accuracy, or reliability.
The wireless communication method of claim 26, wherein the behavior comprises at least one of: a fallback to a legacy/RAT-dependent positioning method; a deactivated model; model switching; or model fine-tuning.
The wireless communication method of claim 26, wherein the metric comprises at least one of: positioning accuracy/reliability; accuracy/reliability on power/angle/timing information, accuracy/reliability on LOS/NLOS indicator, location/distance/power/angle/timing and/or LOS/NLOS indicator difference between inference output the ground truth label.
The wireless communication method of claim 26, wherein the configuration is associated with time and/or window information, the applicable time and/or window information comprises at least one of: a starting position of the window; a duration of the window; a period and an offset of the window.
The wireless communication method of claim 26, wherein the configuration is associated with area range information, the area range information comprises at least one of: a validity area; a coordinate range; or a cell, TRP, or gNB ID list.
The wireless communication method of claim 26, wherein the configuration is associated with model information, the model information comprises at least one of: a model ID list; an AI/ML-based positioning method; an AI/ML positioning entity; or an applicable scenario.
A wireless communication method, comprising:

sending, by a first network entity to a second network entity, positioning-related information;

wherein the first network entity is a model monitoring metric calculation entity, and the second network entity is a model monitoring entity.
The wireless communication method of claim 32, wherein the positioning-related information comprises at least one of: an inference output; a difference between the inference output and a ground truth label; a positioning/inference accuracy/reliability of a model; or a number/ratio of model output that satisfies an accuracy requirement; or a suggested monitoring behavior.
The wireless communication method of claim 33, further comprising:

receiving, by the first network entity from the second network entity, at least one of: a fallback to a legacy/RAT-dependent positioning method; a deactivated model; model switching; or model fine-tuning.
A wireless communication method, comprising:

sending, by a first network entity to a second network entity, a report including a capability of the first network entity for a first process and/or a second process.
The wireless communication method of claim 35, further comprising:

sending, by the first network entity to the second network entity, another report including one or more PRS processing capabilities per positioning frequency layer and/or per frequency combination, and/or per CC, and/or per band combination, and/or per CC combination for the first process and/or the second process.
The wireless communication method of claim 36, wherein the one or more PRS processing capabilities include at least one of: a number of DL PRS resources that the second network entity can process in a slot; a duration N of DL-PRS symbols in units of ms that the second network entity can process every T for measurement gap, without measurement gap, and/or for PRS processing window; or a UE capability for an inference time optionally associated with a duration of DL-PRS symbols, a type of channel measurement, or a measurement size.
The wireless communication method of claim 35 or 36, wherein the first process is applicable for RSTD, RTT, RSRP, RSRPP, and the second process is applicable for channel measurement and optionally to derive CIR/PDP/DP and/or sample-based measurement and/or path-based measurement.
A wireless communications apparatus comprising a processor and a memory, wherein the processor is configured to read code from the memory and implement a method recited in any of claims 1 to 38.
A computer program product comprising a computer-readable program medium code stored thereupon, the code, when executed by a processor, causing the processor to implement a method recited in any of claims 1 to 38.