Portions of artificial intelligence or machine learning models

Abstract

Some examples of the techniques described herein may enable offloading some model computation to one or more other devices by splitting an AI / ML model for positioning. For instance, the other device may handle one or more offloaded computations. In some approaches, the other device may relay offloaded computations to a network entity. In some aspects, a framework for AI / ML model splitting and potential splitting options may include signaling aspects (e.g., capability indications or configurations, among other examples). One or more of the techniques described herein may be utilized for AI / ML-based sensing (where model output may include one or more sensing key performance indicators (KPIs), such as range information, Doppler information, velocity information, angle information, or positioning information related to a passive object or target). For instance, one or more sensing nodes may offload one or more computations to a sensing server.

Description

Qualcomm Ref. No. 2405199WO1PORTIONS OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING MODELSCROSS REFERENCE

[0001] The present Application for Patent claims priority to Greece Patent Application No. 20240100771 by HIRZALLAH et al., entitled “PORTIONS OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING MODELS,” filed November 1, 2024, which is assigned to the assignee hereof, and expressly incorporated by reference in its entirety herein.FIELD OF TECHNOLOGY

[0002] The following relates to wireless communications, including portions of artificial intelligence or machine learning models.BACKGROUND

[0003] Wireless communications systems are widely deployed to provide various types of communication content such as voice, video, packet data, messaging, broadcast, and so on. These systems may be capable of supporting communication with multiple users by sharing the available system resources (e.g., time, frequency, and power). Examples of such multiple-access systems include fourth generation (4G) systems such as Long Term Evolution (LTE) systems, LTE- Advanced (LTE-A) systems, or LTE-A Pro systems, and fifth generation (5G) systems which may be referred to as New Radio (NR) systems. These systems may employ technologies such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM). A wireless multiple-access communications system may include one or more base stations, each supporting wireless communication for communication devices, which may be known as user equipment (UE).Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO2SUMMARY

[0004] The systems, methods, and devices of this disclosure each have several innovative aspects, no single one of which is solely responsible for the desirable attributes disclosed herein.

[0005] A method by a first device is described. The method may include transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an artificial intelligence or machine learning (AI / ML) model at the first device, where the AI / ML model is associated with a positioning procedure and generating first information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device.

[0006] A first device is described. The first device may include one or more memories storing processor executable code, and one or more processors coupled with the one or more memories. The one or more processors may individually or collectively be operable to execute the code to cause the first device to transmit capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure and generate first information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device.

[0007] Another first device is described. The first device may include means for transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure and means for generating first information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model, the one or more portionsAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO3 of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device.

[0008] A non-transitory computer-readable medium storing code is described. The code may include instructions executable by one or more processors to transmit capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure and generate first information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device.

[0009] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting, to a second device, the first information associated with the position of the object.

[0010] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for receiving a reference signal, where the one or more measurements may be of the reference signal.

[0011] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining the one or more measurements via one or more sensors, the one or more measurements including a range measurement, a Doppler measurement, a velocity measurement, an angle measurement, or a position measurement associated with the object.

[0012] In some examples of the method, first devices, and non-transitory computer- readable medium described herein, the AI / ML model includes the first portion and a second portion, the first portion includes one or more first nodes, one or more first layers, one or more first residual blocks, one or more first attention mechanism stages, aAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO4 first portion of a graph structure, or a combination thereof, and the second portion includes one or more second nodes, one or more second layers, one or more second residual blocks, one or more second attention mechanism stages, a second portion of a graph structure, or a combination thereof.

[0013] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining, from a second device, model information indicating the AI / ML model or the first portion of the AI / ML model, where the second device may be a wireless device or a network entity.

[0014] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining, from a second device, an indication of the one or more portions of the AI / ML model.

[0015] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting, to a second device, model information indicating the AI / ML model or a second portion of the AI / ML model, where the second device may be a wireless device or a network entity.

[0016] In some examples of the method, first devices, and non-transitory computer- readable medium described herein, the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

[0017] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for communicating an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and a second portion of the AI / ML model, where the location of the split may be associated with a layer of the AI / ML model, anAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO5 attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.

[0018] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting an indication of a reason for portioning the AI / ML model, where the reason may be associated with a memory limit, a processing limit, a battery level, or a combination thereof.

[0019] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining configuration information that indicates one or more candidate devices for offloading processing associated with a second portion of the AI / ML model, where the second device may be one of the one or more candidate devices.

[0020] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining configuration information that indicates one or more locations to split the AI / ML model, where the one or more portions of the AI / ML model may be associated with the one or more locations.

[0021] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining configuration information that indicates the first portion of the AI / ML model for generation of the first information.

[0022] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting an indication of the first portion of the AI / ML model or a second portion of the AI / ML model.

[0023] Some examples of the method, first devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining, from a second device, second information indicating an output of a second portion of the AI / ML model based on the first information and transmitting, to a network entity, the second information.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO6

[0024] In some examples of the method, first devices, and non-transitory computer- readable medium described herein, the second information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0025] In some examples of the method, first devices, and non-transitory computer- readable medium described herein, the first information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0026] A method by a second device is described. The method may include obtaining, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure and generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device.

[0027] A second device is described. The second device may include one or more memories storing processor executable code, and one or more processors coupled with the one or more memories. The one or more processors may individually or collectively be operable to execute the code to cause the second device to obtain, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure and generate second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device.

[0028] Another second device is described. The second device may include means for obtaining, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure and means forAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO7 generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device.

[0029] A non-transitory computer-readable medium storing code is described. The code may include instructions executable by one or more processors to obtain, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure and generate second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device.

[0030] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting the second information associated with the position of the object.

[0031] In some examples of the method, second devices, and non-transitory computer-readable medium described herein, the first portion includes one or more first nodes, one or more first layers, one or more first residual blocks, one or more first attention mechanism stages, a first portion of a graph structure, or a combination thereof and the second portion includes one or more second nodes, one or more second layers, one or more second residual blocks, one or more second attention mechanism stages, a second portion of a graph structure, or a combination thereof.

[0032] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting, to the first device, model information indicating the AI / ML model or the first portion of the AI / ML model, where the second device may be a wireless device or a network entity.

[0033] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting, to the first device, an indication of one or more portions of the AI / ML model.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO8

[0034] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining, from the first device, model information indicating the AI / ML model or a second portion of the AI / ML model, where the second device may be a wireless device or a network entity.

[0035] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting capability information of the second device that indicates a capability of the second device to process one or more portions of the AI / ML model at the second device, where the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

[0036] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for communicating an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and the second portion of the AI / ML model, where the location of the split may be associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.

[0037] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining an indication of a reason for portioning the AI / ML model, where the reason may be associated with a memory limit, a processing limit, a battery level, or a combination thereof.

[0038] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining configuration information that indicates one or more candidateAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO9 devices for offloading processing associated with a second portion of the AI / ML model, where the second device may be one or the one or more candidate devices.

[0039] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining configuration information that indicates one or more locations to split the AI / ML model, where one or more portions of the AI / ML model may be associated with the one or more locations.

[0040] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for obtaining configuration information that indicates the second portion of the AI / ML model to generate the second information.

[0041] Some examples of the method, second devices, and non-transitory computer- readable medium described herein may further include operations, features, means, or instructions for transmitting an indication of the second portion of the AI / ML model to a first wireless device or to a network entity.

[0042] In some examples of the method, second devices, and non-transitory computer-readable medium described herein, the second information indicating the output of the second portion of the AI / ML model may be transmitted to the first device or to a network entity.

[0043] In some examples of the method, second devices, and non-transitory computer-readable medium described herein, the second information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0044] A method by a network entity is described. The method may include obtaining capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure and obtaining first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second informationAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO10 is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model.

[0045] A network entity is described. The network entity may include one or more memories storing processor executable code, and one or more processors coupled with the one or more memories. The one or more processors may individually or collectively be operable to execute the code to cause the network entity to obtain capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure and obtain first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model.

[0046] Another network entity is described. The network entity may include means for obtaining capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure and means for obtaining first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model.

[0047] A non-transitory computer-readable medium storing code is described. The code may include instructions executable by one or more processors to obtain capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure and obtain first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML modelAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO11 including the first portion of the AI / ML model and the second portion of the AI / ML model.

[0048] In some examples of the method, network entities, and non-transitory computer-readable medium described herein, the method may include operations, features, means, or instructions for generating second information associated with the position of the object, where the second information may be an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the network entity.

[0049] In some examples of the method, network entities, and non-transitory computer-readable medium described herein, the method may include operations, features, means, or instructions for generating third information associated with the position of the object, where the third information may be an output of a third portion of the AI / ML model based on the second information input to the third portion of the AI / ML model at the network entity.

[0050] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for transmitting, to the first device or a second device, model information indicating the AI / ML model, the first portion of the AI / ML model, or the second portion of the AI / ML model.

[0051] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for transmitting, to the first device or a second device, an indication of the one or more portions of the AI / ML model.

[0052] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for obtaining, from the first device or a second device, model information indicating the AI / ML model, the first portion of the AI / ML model, or the second portion of the AI / ML model.

[0053] In some examples of the method, network entities, and non-transitory computer-readable medium described herein, the capability information indicates one orAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO12 more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

[0054] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for obtaining capability information of a second device that indicates a capability of the second device to process one or more portions of the AI / ML model at the second device, where the capability information of the second device indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

[0055] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for communicating an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and the second portion of the AI / ML model, where the location of the split may be associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.

[0056] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for obtaining an indication of a reason for portioning the AI / ML model, where the reason may be associated with a memory limit, a processing limit, a battery level, or a combination thereof.

[0057] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for transmitting configuration information that indicates one orAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO13 more candidate devices for offloading processing associated with the second portion of the AI / ML model.

[0058] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for transmitting configuration information that indicates one or more locations to split the AI / ML model, where the one or more portions of the AI / ML model may be associated with the one or more locations.

[0059] Some examples of the method, network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for transmitting, to the first device or a second device, configuration information that indicates the first portion of the AI / ML model or the second portion of the AI / ML model.

[0060] In some examples of the method, network entities, and non-transitory computer-readable medium described herein, the first information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object, or the second information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0061] Details of one or more implementations of the subject matter described in this disclosure are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will become apparent from the description, the drawings, and the claims. Note that the relative dimensions of the following figures may not be drawn to scale.BRIEF DESCRIPTION OF THE DRAWINGS

[0062] FIG. 1 shows an example of a wireless communications system that supports portions of artificial intelligence or machine learning (AI / ML) models in accordance with one or more aspects of the present disclosure.Attorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO14

[0063] FIG. 2 shows an example of a network structure that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0064] FIG. 3 shows an example of a network architecture that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0065] FIG. 4 shows an example of a wireless communications system that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0066] FIG. 5 shows examples of block diagrams that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0067] FIG. 6 shows an example of a process flow that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0068] FIG. 7 shows an example of a process flow that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0069] FIG. 8 shows an example of a process flow that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0070] FIGs. 9 and 10 show block diagrams of devices that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0071] FIG. 11 shows a block diagram of a communications manager that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0072] FIG. 12 shows a diagram of a system including a device that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0073] FIGs. 13 and 14 show block diagrams of devices that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0074] FIG. 15 shows a block diagram of a communications manager that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO15

[0075] FIG. 16 shows a diagram of a system including a device that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0076] FIGs. 17 through 22 show flowcharts illustrating methods that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0077] FIG. 23 shows examples of wireless communications systems that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0078] FIG. 24 shows an example of a node diagram that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0079] FIG. 25 A and 25B show examples of block diagrams that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0080] FIG. 26 shows examples of block diagrams that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.

[0081] FIG. 27 shows examples of sensing modes that support portions of AI / ML models in accordance with one or more aspects of the present disclosure.DETAILED DESCRIPTION

[0082] Some wireless communications systems may utilize one or more artificial intelligence or machine learning (AI / ML) models to perform one or more positioning or sensing procedures. AI / ML-based positioning or sensing may provide enhanced positioning accuracy in stringent non-line-of-sight (NLOS) conditions. In some examples, a user equipment (UE) may support one or more AI / ML models for positioning or sensing. Depending on an internal status (e.g., battery, memory, or processing status, among other examples) of the UE, the UE may be resource constrained, which may limit the ability of the UE to process all the computations of an AI / ML model. For instance, a smart phone and a smart watch may be included in a wireless communication system, where the smart watch may have lower capabilitiesAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO16 than the smart phone, and may be able or unable to run the whole AI / ML model for positioning or sensing depending on the internal status of the smart watch.

[0083] Some examples of the techniques described herein may enable offloading some model computation to one or more other devices (e.g., a neighboring device, a network entity, a location server, or a sensing server) by splitting an AI / ML model for positioning. For instance, the other device may handle one or more offloaded computations. In some approaches, the other device may relay offloaded computations to a network entity (e.g., location management function (LMF) or sensing management function (SnMF)). In some aspects, a framework for AI / ML model splitting and potential splitting options may include signaling aspects (e.g., capability indications or configurations, among other examples). One or more of the techniques described herein may be utilized for AI / ML-based sensing (where model output may include one or more sensing key performance indicators (KPIs), such as range information, Doppler information, velocity information, angle information, or positioning information related to a passive object or target). For instance, one or more sensing nodes may offload one or more computations to a sensing server.

[0084] Aspects of the disclosure are described in the context of wireless communications systems. Aspects of the disclosure are also described in the context of a wireless network structure. Aspects of the disclosure are further described in the context of a network architecture. Aspects of the disclosure are additionally described in the context of process flows. Aspects of the disclosure are further illustrated by and described with reference to apparatus diagrams, system diagrams, flowcharts, a node diagram, and block diagrams that relate to network control with associated identifiers for AI / ML-based positioning procedures.

[0085] FIG. 1 shows an example of a wireless communications system 100 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The wireless communications system 100 may include one or more devices, such as one or more network devices (e.g., network nodes 105), one or more UEs 115, and a core network 130. In some examples, the wireless communications system 100 may be a Long Term Evolution (LTE) network, an LTE- Advanced (LTE-A) network, an LTE-A Pro network, a New Radio (NR) network, or a network operating inAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO17 accordance with other systems and radio technologies, including future systems and radio technologies not explicitly mentioned herein.

[0086] The network nodes 105 may be dispersed throughout a geographic area to form the wireless communications system 100 and may include devices in different forms or having different capabilities. In various examples, a network node 105 may be referred to as a network element, a network entity, a mobility element, a radio access network (RAN) node, or network equipment, among other nomenclature. In some examples, network nodes 105 and UEs 115 may wirelessly communicate via communication link(s) 125 (e.g., a radio frequency (RF) access link). For example, a network node 105 may support a coverage area 110 (e.g., a geographic coverage area) over which the UEs 115 and the network node 105 may establish the communication link(s) 125. The coverage area 110 may be an example of a geographic area over which a network node 105 and a UE 115 may support the communication of signals according to one or more radio access technologies (RATs).

[0087] The UEs 115 may be dispersed throughout a coverage area 110 of the wireless communications system 100, and each UE 115 may be stationary, or mobile, or both at different times. The UEs 115 may be devices in different forms or have different capabilities. Some example UEs 115 are illustrated in FIG. 1. The UEs 115 described herein may be capable of supporting communications with various types of devices in the wireless communications system 100 (e.g., other wireless communication devices, including UEs 115 or network nodes 105), as shown in FIG. 1.

[0088] As described herein, a node of the wireless communications system 100, which may be referred to as a network entity or a wireless node, may be a network node 105 (e.g., any network node described herein), a UE 115 (e.g., any UE described herein), a network controller, an apparatus, a device, a computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, a node may be a UE 115. As another example, a node may be a network node 105. As another example, a first node may be configured to communicate with a second node or a third node. In one aspect of this example, the first node may be a UE 115, the second node may be a network node 105, and the third node may be another UE 115. In another aspect of this example, the first node may be a UE 115, the second node may be a network node 105, and the third nodeAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO18 may be another network node 105. In yet other aspects of this example, the first, second, and third nodes may be different relative to these examples. Similarly, reference to a UE 115, network node 105, apparatus, device, computing system, or the like may include disclosure of the UE 115, network node 105, apparatus, device, computing system, or the like being a node. For example, disclosure that a UE 115 is configured to receive information from a network node 105 also discloses that a first node is configured to receive information from a second node.

[0089] In some examples, network nodes 105 may communicate with a core network 130, or with one another, or both. For example, network nodes 105 may communicate with the core network 130 via wired or wireless backhaul communication link(s) 120 (e.g., in accordance with an SI, N2, N3, or other interface protocol). In some examples, network nodes 105 may communicate with one another via backhaul communication link(s) 120 (e.g., in accordance with an X2, Xn, or other interface protocol) either directly (e.g., directly between network nodes 105) or indirectly (e.g., via the core network 130). In some examples, network nodes 105 may communicate with one another via a midhaul communication link 162 (e.g., in accordance with a midhaul interface protocol) or a fronthaul communication link 168 (e.g., in accordance with a fronthaul interface protocol), or any combination thereof. The backhaul communication link(s) 120, midhaul communication links 162, or fronthaul communication links 168 may be or include one or more wired links (e.g., an electrical link, an optical fiber link) or one or more wireless links (e.g., a radio link, a wireless optical link), among other examples or various combinations thereof. A UE 115 may communicate with the core network 130 via a communication link 155.

[0090] One or more of the network nodes 105 or network equipment described herein may include or may be referred to as a base station 140 (e.g., a base transceiver station, a radio base station, an NR base station, an access point (AP), a radio transceiver, a NodeB, an eNodeB (eNB), a next-generation NodeB or giga-NodeB (either of which may be referred to as a gNB), a 5GNB, a next-generation eNB (ng- eNB), a Home NodeB, a Home eNodeB, or other suitable terminology). In some examples, a network node 105 (e.g., a base station 140) may be implemented in an aggregated (e.g., monolithic, standalone) base station architecture, which may be configured to utilize a protocol stack that is physically or logically integrated within oneAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO19 network node (e.g., a network node 105 or a single RAN node, such as a base station 140).

[0091] In some examples, a network node 105 may be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture), which may be configured to utilize a protocol stack that is physically or logically distributed among multiple network entities (e.g., network nodes 105), such as an integrated access and backhaul (IAB) network, an open RAN (O- RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN)). For example, a network node 105 may include one or more of a central unit (CU), such as a CU 160, a distributed unit (DU), such as a DU 165, a radio unit (RU), such as an RU 170, a RAN Intelligent Controller (RIC), such as an RIC 175 (e.g., a Near-Real Time RIC (Near-RT RIC), a Non-Real Time RIC (Non-RT RIC)), a Service Management and Orchestration (SMO) system, such as an SMO system 180, or any combination thereof. An RU 170 may also be referred to as a radio head, a smart radio head, a remote radio head (RRH), a remote radio unit (RRU), or a transmission-reception point (TRP). One or more components of the network nodes 105 in a disaggregated RAN architecture may be co-located, or one or more components of the network nodes 105 may be located in distributed locations (e.g., separate physical locations). In some examples, one or more of the network nodes 105 of a disaggregated RAN architecture may be implemented as virtual units (e.g., a virtual CU (VCU), a virtual DU (VDU), a virtual RU (VRU)).

[0092] The split of functionality between a CU 160, a DU 165, and an RU 170 is flexible and may support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, or any combinations thereof) are performed at a CU 160, a DU 165, or an RU 170. For example, a functional split of a protocol stack may be employed between a CU 160 and a DU 165 such that the CU 160 may support one or more layers of the protocol stack and the DU 165 may support one or more different layers of the protocol stack. In some examples, the CU 160 may host upper protocol layer (e.g., layer 3 (L3), layer 2 (L2)) functionality and signaling (e.g., Radio Resource Control (RRC), service data adaptation protocol (SDAP), Packet Data Convergence Protocol (PDCP)). The CU 160 (e.g., one or more CUs) may be connected to a DU 165 (e.g., one or more DUs) or anAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO20RU 170 (e.g., one or more RUs), or some combination thereof, and the DUs 165, RUs 170, or both may host lower protocol layers, such as layer 1 (LI) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, and may each be at least partially controlled by the CU 160. Additionally, or alternatively, a functional split of the protocol stack may be employed between a DU 165 and an RU 170 such that the DU 165 may support one or more layers of the protocol stack and the RU 170 may support one or more different layers of the protocol stack. The DU 165 may support one or multiple different cells (e.g., via one or multiple different RUs, such as an RU 170). In some cases, a functional split between a CU 160 and a DU 165 or between a DU 165 and an RU 170 may be within a protocol layer (e.g., some functions for a protocol layer may be performed by one of a CU 160, a DU 165, or an RU 170, while other functions of the protocol layer are performed by a different one of the CU 160, the DU 165, or the RU 170). A CU 160 may be functionally split further into CU control plane (CU-CP) and CU user plane (CU-UP) functions. A CU 160 may be connected to a DU 165 via a midhaul communication link 162 (e.g., Fl interface, Fl-c interface, or Fl-u, among other examples), and a DU 165 may be connected to an RU 170 via a fronthaul communication link 168 (e.g., open fronthaul (FH) interface). In some examples, a midhaul communication link 162 or a fronthaul communication link 168 may be implemented in accordance with an interface (e.g., a channel) between layers of a protocol stack supported by respective network entities (e.g., one or more of the network nodes 105) that are in communication via such communication links.

[0093] In some wireless communications systems (e.g., the wireless communications system 100), infrastructure and spectral resources for radio access may support wireless backhaul link capabilities to supplement wired backhaul connections, providing an IAB network architecture (e.g., to a core network 130). In some cases, in an IAB network, one or more of the network nodes 105 (e.g., network nodes 105 or IAB node(s) 104) may be partially controlled by each other. The IAB node(s) 104 may be referred to as a donor entity or an IAB donor. A DU 165 or an RU 170 may be partially controlled by a CU 160 associated with a network node 105 or base station 140 (such as a donor network node or a donor base station). The one or more donor entities (e.g., IAB donors) may be in communication with one or more additional devices (e.g., IABAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO21 node(s) 104) via supported access and backhaul links (e.g., backhaul communication link(s) 120). IAB node(s) 104 may include an IAB mobile termination (IAB-MT) controlled (e.g., scheduled) by one or more DUs (e.g., DUs 165) of a coupled IAB donor. An IAB-MT may be equipped with an independent set of antennas for relay of communications with UEs 115 or may share the same antennas (e.g., of an RU 170) of IAB node(s) 104 used for access via the DU 165 of the IAB node(s) 104 (e.g., referred to as virtual IAB-MT (vIAB-MT)). In some examples, the IAB node(s) 104 may include one or more DUs (e.g., DUs 165) that support communication links with additional entities (e.g., IAB node(s) 104, UEs 115) within the relay chain or configuration of the access network (e.g., downstream). In such cases, one or more components of the disaggregated RAN architecture (e.g., the IAB node(s) 104 or components of the IAB node(s) 104) may be configured to operate according to the techniques described herein.

[0094] For instance, an access network (AN) or RAN may include communications between access nodes (e.g., an IAB donor), IAB node(s) 104, and one or more UEs 115. The IAB donor may facilitate connection between the core network 130 and the AN (e.g., via a wired or wireless connection to the core network 130). That is, an IAB donor may refer to a RAN node with a wired or wireless connection to the core network 130. The IAB donor may include one or more of a CU 160, a DU 165, and an RU 170, in which case the CU 160 may communicate with the core network 130 via an interface (e.g., a backhaul link). The IAB donor and IAB node(s) 104 may communicate via an Fl interface according to a protocol that defines signaling messages (e.g., an Fl AP protocol). Additionally, or alternatively, the CU 160 may communicate with the core network 130 via an interface, which may be an example of a portion of a backhaul link, and may communicate with other CUs (e.g., including a CU 160 associated with an alternative IAB donor) via an Xn-C interface, which may be an example of another portion of a backhaul link.

[0095] IAB node(s) 104 may refer to RAN nodes that provide IAB functionality (e.g., access for UEs 115, wireless self-backhauling capabilities). A DU 165 may act as a distributed scheduling node towards child nodes associated with the IAB node(s) 104, and the IAB-MT may act as a scheduled node towards parent nodes associated with IAB node(s) 104. That is, an IAB donor may be referred to as a parent node in communication with one or more child nodes (e.g., an IAB donor may relayAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO 1 transmissions for UEs through other IAB node(s) 104). Additionally, or alternatively, IAB node(s) 104 may also be referred to as parent nodes or child nodes to other IAB node(s) 104, depending on the relay chain or configuration of the AN. The IAB-MT entity of IAB node(s) 104 may provide a Uu interface for a child IAB node (e.g., the IAB node(s) 104) to receive signaling from a parent IAB node (e.g., the IAB node(s) 104), and a DU interface (e.g., a DU 165) may provide a Uu interface for a parent IAB node to signal to a child IAB node or UE 115.

[0096] For example, IAB node(s) 104 may be referred to as parent nodes that support communications for child IAB nodes, or may be referred to as child IAB nodes associated with IAB donors, or both. An IAB donor may include a CU 160 with a wired or wireless connection (e.g., backhaul communication link(s) 120) to the core network 130 and may act as a parent node to IAB node(s) 104. For example, the DU 165 of an IAB donor may relay transmissions to UEs 115 through IAB node(s) 104, or may directly signal transmissions to a UE 115, or both. The CU 160 of the IAB donor may signal communication link establishment via an Fl interface to IAB node(s) 104, and the IAB node(s) 104 may schedule transmissions (e.g., transmissions to the UEs 115 relayed from the IAB donor) through one or more DUs (e.g., DUs 165). That is, data may be relayed to and from IAB node(s) 104 via signaling via an NR Uu interface to MT of IAB node(s) 104 (e.g., other IAB node(s)). Communications with IAB node(s) 104 may be scheduled by a DU 165 of the IAB donor or of IAB node(s) 104.

[0097] In the case of the techniques described herein applied in the context of a disaggregated RAN architecture, one or more components of the disaggregated RAN architecture may be configured to support testing as described herein. For example, some operations described as being performed by a UE 115 or a network node 105 (e.g., a base station 140) may additionally, or alternatively, be performed by one or more components of the disaggregated RAN architecture (e.g., components such as an IAB node, a DU 165, a CU 160, an RU 170, an RIC 175, an SMO system 180).

[0098] A UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable terminology, where the “device” may also be referred to as a unit, a station, a terminal, or a client, among other examples. A UE 115 may also include or may be referred to as a personal electronic device such as a cellular phone, a personal digitalAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO23 assistant (PDA), a tablet computer, a laptop computer, or a personal computer. In some examples, a UE 115 may include or be referred to as a wireless local loop (WLL) station, an Internet of Things (loT) device, an Internet of Everything (loE) device, or a machine type communications (MTC) device, among other examples, which may be implemented in various objects such as appliances, vehicles, or meters, among other examples.

[0099] The UEs 115 described herein may be able to communicate with various types of devices, such as UEs 115 that may sometimes operate as relays, as well as the network nodes 105 and the network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, among other examples, as shown in FIG. 1.

[0100] The UEs 115 and the network nodes 105 may wirelessly communicate with one another via the communication link(s) 125 (e.g., one or more access links) using resources associated with one or more carriers. The term “carrier” may refer to a set of RF spectrum resources having a defined PHY layer structure for supporting the communication link(s) 125. For example, a carrier used for the communication link(s) 125 may include a portion of an RF spectrum band (e.g., a bandwidth part (BWP)) that is operated according to one or more PHY layer channels for a given RAT (e.g., LTE, LTE-A, LTE-A Pro, NR). Each PHY layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling that coordinates operation for the carrier, user data, or other signaling. The wireless communications system 100 may support communication with a UE 115 using carrier aggregation or multi-carrier operation. A UE 115 may be configured with multiple downlink component carriers and one or more uplink component carriers according to a carrier aggregation configuration. Carrier aggregation may be used with both frequency division duplexing (FDD) and time division duplexing (TDD) component carriers. Communication between a network node 105 and other devices may refer to communication between the devices and any portion (e.g., entity, sub-entity) of a network node 105. For example, the terms “transmitting,” “receiving,” or “communicating,” when referring to a network node 105, may refer to any portion of a network node 105 (e.g., a base station 140, a CU 160, a DU 165, a RU 170) of a RAN communicating with another device (e.g., directly or via one or more other network entities, such as one or more of the network nodes 105).Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO24

[0101] In some examples, such as in a carrier aggregation configuration, a carrier may have acquisition signaling or control signaling that coordinates operations for other carriers. A carrier may be associated with a frequency channel (e.g., an evolved universal mobile telecommunication system terrestrial radio access (E-UTRA) absolute RF channel number (EARFCN)) and may be identified according to a channel raster for discovery by the UEs 115. A carrier may be operated in a standalone mode, in which case initial acquisition and connection may be conducted by the UEs 115 via the carrier, or the carrier may be operated in a non- standalone mode, in which case a connection is anchored using a different carrier (e.g., of the same or a different RAT).

[0102] The communication link(s) 125 of the wireless communications system 100 may include downlink transmissions (e.g., forward link transmissions) from a network node 105 to a UE 115, uplink transmissions (e.g., return link transmissions) from a UE 115 to a network node 105, or both, among other configurations of transmissions. Carriers may carry downlink or uplink communications (e.g., in an FDD mode) or may be configured to carry downlink and uplink communications (e.g., in a TDD mode).

[0103] A carrier may be associated with a particular bandwidth of the RF spectrum and, in some examples, the carrier bandwidth may be referred to as a “system bandwidth” of the carrier or the wireless communications system 100. For example, the carrier bandwidth may be one of a set of bandwidths for carriers of a particular RAT (e.g., 1.4, 3, 5, 10, 15, 20, 40, or 80 megahertz (MHz)). Devices of the wireless communications system 100 (e.g., the network nodes 105, the UEs 115, or both) may have hardware configurations that support communications using a particular carrier bandwidth or may be configurable to support communications using one of a set of carrier bandwidths. In some examples, the wireless communications system 100 may include network nodes 105 or UEs 115 that support concurrent communications using carriers associated with multiple carrier bandwidths. In some examples, each served UE 115 may be configured for operating using portions (e.g., a sub-band, a BWP) or all of a carrier bandwidth.

[0104] Signal waveforms transmitted via a carrier may be made up of multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM)). In a system employing MCM techniques, a resource element mayAttorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO25 refer to resources of one symbol period (e.g., a duration of one modulation symbol) and one subcarrier, in which case the symbol period and subcarrier spacing may be inversely related. The quantity of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both), such that a relatively higher quantity of resource elements (e.g., in a transmission duration) and a relatively higher order of a modulation scheme may correspond to a relatively higher rate of communication. A wireless communications resource may refer to a combination of an RF spectrum resource, a time resource, and a spatial resource (e.g., a spatial layer, a beam), and the use of multiple spatial resources may increase the data rate or data integrity for communications with a UE 115.

[0105] One or more numerologies for a carrier may be supported, and a numerology may include a subcarrier spacing (A ) and a cyclic prefix. A carrier may be divided into one or more BWPs having the same or different numerologies. In some examples, a UE 115 may be configured with multiple BWPs. In some examples, a single BWP for a carrier may be active at a given time and communications for the UE 115 may be restricted to one or more active BWPs.

[0106] The time intervals for the network nodes 105 or the UEs 115 may be expressed in multiples of a basic time unit which may, for example, refer to a sampling period of Ts= l / (A / max■ Ay) seconds, for which fmaxmay represent a supported subcarrier spacing, and Ay may represent a supported discrete Fourier transform (DFT) size. Time intervals of a communications resource may be organized according to radio frames each having a specified duration (e.g., 10 milliseconds (ms)). Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023).

[0107] Each frame may include multiple consecutively-numbered subframes or slots, and each subframe or slot may have the same duration. In some examples, a frame may be divided (e.g., in the time domain) into subframes, and each subframe may be further divided into a quantity of slots. Alternatively, each frame may include a variable quantity of slots, and the quantity of slots may depend on subcarrier spacing. Each slot may include a quantity of symbol periods (e.g., depending on the length of the cyclic prefix prepended to each symbol period). In some wireless communications systems,Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO26 such as the wireless communications system 100, a slot may further be divided into multiple mini-slots associated with one or more symbols. Excluding the cyclic prefix, each symbol period may be associated with one or more (e.g., Ay) sampling periods. The duration of a symbol period may depend on the subcarrier spacing or frequency band of operation.

[0108] A subframe, a slot, a mini-slot, or a symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communications system 100 and may be referred to as a transmission time interval (TTI). In some examples, the TTI duration (e.g., a quantity of symbol periods in a TTI) may be variable. Additionally, or alternatively, the smallest scheduling unit of the wireless communications system 100 may be dynamically selected (e.g., in bursts of shortened TTIs (sTTIs)).

[0109] Physical channels may be multiplexed for communication using a carrier according to various techniques. A physical control channel and a physical data channel may be multiplexed for signaling via a downlink carrier, for example, using one or more of time division multiplexing (TDM) techniques, frequency division multiplexing (FDM) techniques, or hybrid TDM-FDM techniques. A control region (e.g., a control resource set (CORESET)) for a physical control channel may be defined by a set of symbol periods and may extend across the system bandwidth or a subset of the system bandwidth of the carrier. One or more control regions (e.g., CORESETs) may be configured for a set of the UEs 115. For example, one or more of the UEs 115 may monitor or search control regions for control information according to one or more search space sets, and each search space set may include one or multiple control channel candidates in one or more aggregation levels arranged in a cascaded manner. An aggregation level for a control channel candidate may refer to an amount of control channel resources (e.g., control channel elements (CCEs)) associated with encoded information for a control information format having a given payload size. Search space sets may include common search space sets configured for sending control information to UEs 115 (e.g., one or more UEs) or may include UE-specific search space sets for sending control information to a UE 115 (e.g., a specific UE).

[0110] A network node 105 may provide communication coverage via one or more cells, for example a macro cell, a small cell, a hot spot, or other types of cells, or anyAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO27 combination thereof. The term “cell” may refer to a logical communication entity used for communication with a network node 105 (e.g., using a carrier) and may be associated with an identifier for distinguishing neighboring cells (e.g., a physical cell identifier (PCID), a virtual cell identifier (VCID)). In some examples, a cell also may refer to a coverage area 110 or a portion of a coverage area 110 (e.g., a sector) over which the logical communication entity operates. Such cells may range from smaller areas (e.g., a structure, a subset of structure) to larger areas depending on various factors such as the capabilities of the network node 105. For example, a cell may be or include a building, a subset of a building, or exterior spaces between or overlapping with coverage areas 110, among other examples.[OHl] A macro cell generally covers a relatively large geographic area (e.g., several kilometers in radius) and may allow unrestricted access by the UEs 115 with service subscriptions with the network provider supporting the macro cell. A small cell may be associated with a network node 105 operating with lower power (e.g., a base station 140 operating with lower power) relative to a macro cell, and a small cell may operate using the same or different (e.g., licensed, unlicensed) frequency bands as macro cells. Small cells may provide unrestricted access to the UEs 115 with service subscriptions with the network provider or may provide restricted access to the UEs 115 having an association with the small cell (e.g., the UEs 115 in a closed subscriber group (CSG), the UEs 115 associated with users in a home or office). A network node 105 may support one or more cells and may also support communications via the one or more cells using one or multiple component carriers.

[0112] In some examples, a carrier may support multiple cells, and different cells may be configured according to different protocol types (e.g., MTC, narrowband loT (NB-IoT), enhanced mobile broadband (eMBB)) that may provide access for different types of devices.

[0113] In some examples, a network node 105 (e.g., a base station 140, an RU 170) may be movable and therefore provide communication coverage for a moving coverage area, such as the coverage area 110. In some examples, coverage areas 110 (e.g., different coverage areas) associated with different technologies may overlap, but the coverage areas 110 (e.g., different coverage areas) may be supported by the same network node (e.g., a network node 105). In some other examples, overlapping coverageAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO28 areas, such as a coverage area 110, associated with different technologies may be supported by different network entities (e.g., the network nodes 105). The wireless communications system 100 may include, for example, a heterogeneous network in which different types of the network nodes 105 support communications for coverage areas 110 (e.g., different coverage areas) using the same or different RATs.

[0114] The wireless communications system 100 may support synchronous or asynchronous operation. For synchronous operation, network nodes 105 (e.g., base stations 140) may have similar frame timings, and transmissions from different network entities (e.g., different ones of the network nodes 105) may be approximately aligned in time. For asynchronous operation, network nodes 105 may have different frame timings, and transmissions from different network entities (e.g., different ones of network nodes 105) may, in some examples, not be aligned in time. The techniques described herein may be used for either synchronous or asynchronous operations.

[0115] Some UEs 115, such as MTC or loT devices, may be relatively low cost or low complexity devices and may provide for automated communication between machines (e.g., via Machine-to-Machine (M2M) communication). M2M communication or MTC may refer to data communication technologies that allow devices to communicate with one another or a network node 105 (e.g., a base station 140) without human intervention. In some examples, M2M communication or MTC may include communications from devices that integrate sensors or meters to measure or capture information and relay such information to a central server or application program that uses the information or presents the information to humans interacting with the application program. Some UEs 115 may be designed to collect information or enable automated behavior of machines or other devices. Examples of applications for MTC devices include smart metering, inventory monitoring, water level monitoring, equipment monitoring, healthcare monitoring, wildlife monitoring, weather and geological event monitoring, fleet management and tracking, remote security sensing, physical access control, and transaction-based business charging.

[0116] Some UEs 115 may be configured to employ operating modes that reduce power consumption, such as half-duplex communications (e.g., a mode that supports one-way communication via transmission or reception, but not transmission and reception concurrently). In some examples, half-duplex communications may beAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO29 performed at a reduced peak rate. Other power conservation techniques for the UEs 115 may include entering a power saving deep sleep mode when not engaging in active communications, operating using a limited bandwidth (e.g., according to narrowband communications), or a combination of these techniques. For example, some UEs 115 may be configured for operation using a narrowband protocol type that is associated with a defined portion or range (e.g., set of subcarriers or resource blocks (RBs)) within a carrier, within a guard-band of a carrier, or outside of a carrier.

[0117] The wireless communications system 100 may be configured to support ultra-reliable communications or low-latency communications, or various combinations thereof. For example, the wireless communications system 100 may be configured to support ultra-reliable low-latency communications (URLLC). The UEs 115 may be designed to support ultra-reliable, low-latency, or critical functions. Ultra-reliable communications may include private communication or group communication and may be supported by one or more services such as push-to-talk, video, or data. Support for ultra-reliable, low-latency functions may include prioritization of services, and such services may be used for public safety or general commercial applications. The terms ultra-reliable, low-latency, and ultra-reliable low-latency may be used interchangeably herein.

[0118] In some examples, a UE 115 may be configured to support communicating directly with other UEs (e.g., one or more of the UEs 115) via a device-to-device (D2D) communication link, such as a D2D communication link 135 (e.g., in accordance with a peer-to-peer (P2P), D2D, or sidelink protocol). In some examples, one or more UEs 115 of a group that are performing D2D communications may be within the coverage area 110 of a network node 105 (e.g., a base station 140, an RU 170), which may support aspects of such D2D communications being configured by (e.g., scheduled by) the network node 105. In some examples, one or more UEs 115 of such a group may be outside the coverage area 110 of a network node 105 or may be otherwise unable to or not configured to receive transmissions from a network node 105. In some examples, groups of the UEs 115 communicating via D2D communications may support a one-to- many (1 :M) system in which each UE 115 transmits to one or more of the UEs 115 in the group. In some examples, a network node 105 may facilitate the scheduling of resources for D2D communications. In some other examples, D2D communicationsAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO30 may be carried out between the UEs 115 without an involvement of a network node 105.

[0119] In some systems, a D2D communication link 135 may be an example of a communication channel, such as a sidelink communication channel, between vehicles (e.g., UEs 115). In some examples, vehicles may communicate using vehicle-to- everything (V2X) communications, vehicle-to-vehicle (V2V) communications, or some combination of these. A vehicle may signal information related to traffic conditions, signal scheduling, weather, safety, emergencies, or any other information relevant to a V2X system. In some examples, vehicles in a V2X system may communicate with roadside infrastructure, such as roadside units, or with the network via one or more network entities (e.g., network nodes 105, base stations 140, RUs 170) using vehicle-to- network (V2N) communications, or with both.

[0120] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an evolved packet core (EPC) or 5G core (5GC), which may include at least one control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management function (AMF)) and at least one user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). The control plane entity may manage non-access stratum (NAS) functions such as mobility, authentication, and bearer management for the UEs 115 served by the network nodes 105 (e.g., base stations 140) associated with the core network 130. User IP packets may be transferred through the user plane entity, which may provide IP address allocation as well as other functions. The user plane entity may be connected to IP services 150 for one or more network operators. The IP services 150 may include access to the Internet, Intranet(s), an IP Multimedia Subsystem (IMS), or a Packet-Switched Streaming Service.

[0121] The wireless communications system 100 may include an location server 185 (e.g., LMF). The location server 185 may provide positioning, location, or tracking functions. For instance, the location server 185 may participate in one or more positioning procedures to determine a location of (e.g., coordinates of, relativeAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO31 distance(s) to, or an address of) one or more of the UEs 115. Examples of positioning procedures may include one or more operations of assisted global navigation satellite system (A-GNSS), observed time difference of arrival (OTDOA), enhanced cell identifier (E-CID), sensor-based positioning, wireless local area network (WLAN)- based positioning, Bluetooth-based positioning, terrestrial beacon systems (TBS) positioning, downlink time difference of arrival (DL-TDOA), downlink angle of departure (DL-AOD), multi-round-trip time (Multi-RTT), New Radio enhanced cell identifier (NR E-CID), uplink time difference of arrival (UL-TDOA), and uplink angle of arrival (UL-AOA), among other examples. Some examples of the positioning procedures may be managed by, assisted by, or performed with the location server 185. For instance, measurements associated with reference signaling may be provided to the location server 185, which may estimate a location of a UE 115 based on the measurements. In some aspects, the location server 185 may track or store location information corresponding to one or more UEs 115. Some examples of the positioning procedures may be performed without the location server 185.

[0122] The location server 185 may be included in the core network 130 or may be separate from the core network 130. In some examples, a location server 185 may be a standalone device or may be included in (e.g., integrated with) a network node 105, a base station 140, a UE 115, a satellite 190, a server, or another device. For instance, the location server 185 may be (or may be included in) a secure user plane location (SUPL) location platform (SLP) device, a third-party server, or another device. The location server 185 may generally refer to a positioning device, a location device, a computing device, or a server, among other examples.

[0123] A UE 115 may communicate with the location server 185 directly or indirectly. For example, a UE 115 may communicate with the location server 185 via a network node 105 that is serving the UE 115 and via the core network 130.Additionally, or alternatively, a UE 115 may communicate with the location server 185 through another path (e.g., via an application server (not shown)) or via another network (e.g., via a WLAN AP), among other examples. Communication between a UE 115 and the location server 185 may be represented via an indirect connection (e.g., through a communication link 125, a network node 105, a communication link 155, a backhaulAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO32 communication link 120, or the core network 130) or as a direct connection, with one or more intervening nodes (if any) omitted for concision or convenience.

[0124] A satellite 190 may be an aerial or space vehicle with signaling capability. In some examples, the wireless communications system 100 may include or communicate with one or more satellites 190. The satellite(s) 190 may be included in one or more satellite positioning systems (e.g., GNSS(s)). A satellite positioning system may include any combination of one or more global or regional navigation satellites associated with one or more satellite positioning systems (e.g., global positioning system (GPS), global navigation satellite system (GLONASS), BeiDou navigation satellite system (BDS), or Galileo, among other examples). A satellite positioning system may include satellites 190 or other transmitters positioned to enable receivers (e.g., UEs 115) to determine a location on or above the Earth based on signals (e.g., the signals 195) received from the satellites 190. For instance, each satellite 190 may transmit a signal 195 marked with a repeating pseudo-random noise (PN) code of a set quantity of chips. In some cases, one or more transmitters located on ground-based control stations, network nodes 105, or UEs 115 may transmit signals for enabling a UE 115 to determine a location.

[0125] A UE 115 may include one or more receivers designed to receive the signal(s) 195 from the satellite(s) 190 for determining location information (e.g., a geographic location of the UE 115). For instance, the UE 115 may receive one or more signals 195 from the satellite(s) 190, which may be utilized to determine a location of the UE 115.

[0126] In a satellite positioning system, the use of signals 195 may be augmented with one or more satellite-based augmentation systems (SB AS) that may be associated with or enabled for use with one or more global or regional navigation satellite systems. An SB AS may provide integrity information, differential corrections, or other information for use in conjunction with a satellite positioning system. An SBAS may include one or more augmentation systems, such as the Wide Area Augmentation System (WAAS), the European Geostationary Navigation Overlay Service (EGNOS), the Multi-functional Satellite Augmentation System (MSAS), or the GPS Aided Geo Augmented Navigation (GAGAN) system, among other examples.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO33

[0127] In some aspects, the satellite(s) 190 may be included in one or more nonterrestrial networks (NTNs). In an NTN, a satellite 190 may communicate with one or more devices (e.g., network entities, ground stations, NTN gateways, or gateways) located on or above the Earth. For example, the satellite 190 may send or receive one or more communications 192 with a network node 105. In some aspects, the communication(s) 192 may include one or more signals relayed to or from a UE 115. Additionally, or alternatively, the satellite 190 may communicate with another terrestrial device that is connected to one or more elements of the wireless communications system 100. For instance, the satellite 190 may communicate with a ground station or NTN gateway, which may provide access to the wireless communications system 100 or one or more other entities (e.g., Internet web servers or one or more other user devices) external to the wireless communications system 100. In some examples, a UE 115 may receive communication signals 195 from the satellite 190 instead of, or in addition to, communication signals from a terrestrial network entity.

[0128] The wireless communications system 100 may operate using one or more frequency bands, which may be in the range of 300 megahertz (MHz) to 300 gigahertz (GHz). Generally, the region from 300 MHz to 3 GHz is known as the ultra-high frequency (UHF) region or decimeter band because the wavelengths range from approximately one decimeter to one meter in length. UHF waves may be blocked or redirected by buildings and environmental features, which may be referred to as clusters, but the waves may penetrate structures sufficiently for a macro cell to provide service to the UEs 115 located indoors. Communications using UHF waves may be associated with smaller antennas and shorter ranges (e.g., less than one hundred kilometers) compared to communications using the smaller frequencies and longer waves of the high frequency (HF) or very high frequency (VHF) portion of the spectrum below 300 MHz.

[0129] The wireless communications system 100 may also operate using a super high frequency (SHF) region, which may be in the range of 3 GHz to 30 GHz, also known as the centimeter band, or using an extremely high frequency (EHF) region of the spectrum (e.g., from 30 GHz to 300 GHz), also known as the millimeter band. In some examples, the wireless communications system 100 may support millimeter wave (mmW) communications between the UEs 115 and the network nodes 105 (e.g., baseAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO34 stations 140, RUs 170), and EHF antennas of the respective devices may be smaller and more closely spaced than UHF antennas. In some examples, such techniques may facilitate using antenna arrays within a device. The propagation of EHF transmissions, however, may be subject to even greater attenuation and shorter range than SHF or UHF transmissions. The techniques disclosed herein may be employed across transmissions that use one or more different frequency regions, and designated use of bands across these frequency regions may differ by country or regulating body.

[0130] The wireless communications system 100 may utilize licensed or unlicensed RF spectrum bands. For example, the wireless communications system 100 may employ License Assisted Access (LAA), LTE-Unlicensed (LTE-U) RAT, or NR technology using an unlicensed band such as the 5 GHz industrial, scientific, and medical (ISM) band. While operating using unlicensed RF spectrum bands, devices such as the network nodes 105 and the UEs 115 may employ carrier sensing for collision detection and avoidance. In some examples, operations using unlicensed bands may be based on a carrier aggregation configuration in conjunction with component carriers operating using a licensed band (e.g., LAA). Operations using unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, among other examples.

[0131] A network node 105 (e.g., a base station 140, an RU 170) or a UE 115 may be equipped with multiple antennas, which may be used to employ techniques such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communications, or beamforming. The antennas of a network node 105 or a UE 115 may be located within one or more antenna arrays or antenna panels, which may support MIMO operations or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly, such as an antenna tower. In some examples, antennas or antenna arrays associated with a network node 105 may be located at diverse geographic locations. A network node 105 may include an antenna array with a set of rows and columns of antenna ports that the network node 105 may use to support beamforming of communications with a UE 115. Likewise, a UE 115 may include one or more antenna arrays that may support various MIMO or beamforming operations. Additionally, or alternatively, an antenna panel may support RF beamforming for a signal transmitted via an antenna port.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO35

[0132] The network nodes 105 or the UEs 115 may use MIMO communications to exploit multipath signal propagation and increase spectral efficiency by transmitting or receiving multiple signals via different spatial layers. Such techniques may be referred to as spatial multiplexing. The multiple signals may, for example, be transmitted by the transmitting device via different antennas or different combinations of antennas. Likewise, the multiple signals may be received by the receiving device via different antennas or different combinations of antennas. Each of the multiple signals may be referred to as a separate spatial stream and may carry information associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers may be associated with different antenna ports used for channel measurement and reporting. MIMO techniques include single-user MIMO (SU-MIMO), for which multiple spatial layers are transmitted to the same receiving device, and multiple-user MIMO (MU-MIMO), for which multiple spatial layers are transmitted to multiple devices.

[0133] Beamforming, which may also be referred to as spatial filtering, directional transmission, or directional reception, is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a network node 105, a UE 115) to shape or steer an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining the signals communicated via antenna elements of an antenna array such that some signals propagating along particular orientations with respect to an antenna array experience constructive interference while others experience destructive interference. The adjustment of signals communicated via the antenna elements may include a transmitting device or a receiving device applying amplitude offsets, phase offsets, or both to signals carried via the antenna elements associated with the device. The adjustments associated with each of the antenna elements may be defined by a beamforming weight set associated with a particular orientation (e.g., with respect to the antenna array of the transmitting device or receiving device, or with respect to some other orientation).

[0134] A network node 105 or a UE 115 may use beam sweeping techniques as part of beamforming operations. For example, a network node 105 (e.g., a base station 140, an RU 170) may use multiple antennas or antenna arrays (e.g., antenna panels) toAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO36 conduct beamforming operations for directional communications with a UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be transmitted by a network node 105 multiple times along different directions. For example, the network node 105 may transmit a signal according to different beamforming weight sets associated with different directions of transmission. Transmissions along different beam directions may be used to identify (e.g., by a transmitting device, such as a network node 105, or by a receiving device, such as a UE 115) a beam direction for later transmission or reception by the network node 105.

[0135] Some signals, such as data signals associated with a particular receiving device, may be transmitted by a transmitting device (e.g., a network node 105 or a UE 115) along a single beam direction (e.g., a direction associated with the receiving device, such as another network node 105 or UE 115). In some examples, the beam direction associated with transmissions along a single beam direction may be determined based on a signal that was transmitted along one or more beam directions. For example, a UE 115 may receive one or more of the signals transmitted by the network node 105 along different directions and may report to the network node 105 an indication of the signal that the UE 115 received with a highest signal quality or an otherwise acceptable signal quality.

[0136] In some examples, transmissions by a device (e.g., by a network node 105 or a UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or beamforming to generate a combined beam for transmission (e.g., from a network node 105 to a UE 115). The UE 115 may report feedback that indicates precoding weights for one or more beam directions, and the feedback may correspond to a configured set of beams across a system bandwidth or one or more sub-bands. The network node 105 may transmit a reference signal (e.g., a cell-specific reference signal (CRS), a channel state information reference signal (CSI- RS)), which may be precoded or unprecoded. The UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., a multi-panel type codebook, a linear combination type codebook, a port selection type codebook). Although these techniques are described with reference to signals transmitted along one or more directions by a network node 105 (e.g., a baseAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO37 station 140, an RU 170), a UE 115 may employ similar techniques for transmitting signals multiple times along different directions (e.g., for identifying a beam direction for subsequent transmission or reception by the UE 115) or for transmitting a signal along a single direction (e.g., for transmitting data to a receiving device).

[0137] A receiving device (e.g., a UE 115) may perform reception operations in accordance with multiple receive configurations (e.g., directional listening) when receiving various signals from a transmitting device (e.g., a network node 105), such as synchronization signals, reference signals, beam selection signals, or other control signals. For example, a receiving device may perform reception in accordance with multiple receive directions by receiving via different antenna subarrays, by processing received signals according to different antenna subarrays, by receiving according to different receive beamforming weight sets (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of an antenna array, or by processing received signals according to different receive beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as “listening” according to different receive configurations or receive directions. In some examples, a receiving device may use a single receive configuration to receive along a single beam direction (e.g., when receiving a data signal). The single receive configuration may be aligned along a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have a highest signal strength, highest signal-to- noise ratio (SNR), or otherwise acceptable signal quality based on listening according to multiple beam directions).

[0138] The wireless communications system 100 may be a packet-based network that operates according to a layered protocol stack. In the user plane, communications at the bearer or PDCP layer may be IP -based. An RLC layer may perform packet segmentation and reassembly to communicate via logical channels. A MAC layer may perform priority handling and multiplexing of logical channels into transport channels. The MAC layer also may implement error detection techniques, error correction techniques, or both to support retransmissions to improve link efficiency. In the control plane, an RRC layer may provide establishment, configuration, and maintenance of an RRC connection between a UE 115 and a network node 105 or a core network 130Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO38 supporting radio bearers for user plane data. A PHY layer may map transport channels to physical channels.

[0139] The UEs 115 and the network nodes 105 may support retransmissions of data to increase the likelihood that data is received successfully. Hybrid automatic repeat request (HARQ) feedback is one technique for increasing the likelihood that data is received correctly via a communication link (e.g., the communication link(s) 125, a D2D communication link 135). HARQ may include a combination of error detection (e.g., using a cyclic redundancy check (CRC)), forward error correction (FEC), and retransmission (e.g., automatic repeat request (ARQ)). HARQ may improve throughput at the MAC layer in relatively poor radio conditions (e.g., low signal -to-noise conditions). In some examples, a device may support same-slot HARQ feedback, in which case the device may provide HARQ feedback in a specific slot for data received via a previous symbol in the slot. In some other examples, the device may provide HARQ feedback in a subsequent slot, or according to some other time interval.

[0140] Some wireless communications systems may utilize one or more AI / ML models to perform one or more positioning or sensing procedures. AI / ML-based positioning or sensing may provide enhanced positioning accuracy in stringent NLOS conditions. In some examples, a UE 115 may support one or more AI / ML models for positioning or sensing. Depending on an internal status (e.g., battery, memory, or processing status, among other examples) of the UE 115, the UE 115 may be resource constrained, which may limit the ability of the UE 115 to process all the computations of an AI / ML model. For instance, a smart phone and a smart watch may be included in a wireless communication system, where the smart watch may have lower capabilities than the smart phone, and may be able or unable to run the whole AI / ML model for positioning or sensing depending on the internal status of the smart watch.

[0141] Some examples of the techniques described herein may enable offloading some model computation to one or more other devices (e.g., a neighboring device, a network entity, a location server, or a sensing server) by splitting an AI / ML model for positioning. For instance, the other device may handle one or more offloaded computations. In some approaches, the other device may relay offloaded computations to a network entity (e.g., location server 185, LMF or SnMF). In some aspects, a framework for AI / ML model splitting and potential splitting options may includeAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO39 signaling aspects (e.g., capability indications or configurations, among other examples). One or more of the techniques described herein may be utilized for AI / ML-based sensing (where model output may include one or more sensing KPIs, such as range information, Doppler information, velocity information, angle information, or positioning information related to a passive object or target). For instance, one or more sensing nodes may offload one or more computations to a sensing server.

[0142] As used herein, the terms “Al,” “AI / ML,” “Al-based,” or “ML-based” may refer to Al or machine learning techniques. The term “Al model” may refer to one or more Al models (with or without machine learning) or to one or more machine learning models. As used herein, an Al model may be referred to as an “Al-based model,” an “ML model,” or an “ML-based model.”

[0143] FIG. 2 shows an example of a network structure 200 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The wireless network structure 200 may include a core network 130-a, a RAN 225, a UE 115-a, an LMF 265, an external device 230 (e.g., third-party device or server), or an SLP 235. In some examples, the wireless network structure 200 may be included in the wireless communications system 100 described with reference to FIG. 1. The core network 130-a may be an example of the core network 130, the UE 115-a may be an example of the UEs 115, or the LMF 265 may be an example of the location server 185, as described with reference to FIG. 1.

[0144] The core network 130-a may provide one or more control plane (C-plane) functions (e.g., UE registration, authentication, network access, or gateway selection, among other examples) or one or more user plane (U-plane) functions (e.g., UE gateway function, data network access, or IP routing, among other examples). One or more of the functions of the core network 130-a may be implemented in one or more devices (e.g., one or more electronic devices, computing devices, servers, among other examples) in hardware (e.g., circuitry) or a combination of hardware and instructions (e.g., a processor with instructions). The core network 130-a may be an EPC, 5GC, or a Next Generation Core (NGC), among other examples.

[0145] The core network 130-a may provide an AMF 210, a session management function (SMF) 220, or a user plane function (UPF) 215. The AMF 210 may provideAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO40 one or more C-plane functions, such as registration management, connection management, reachability management, mobility management, lawful interception, transport for session management (SM) messages between one or more UEs 115-a and the SMF 220, transparent proxy services for routing SM messages, access authentication and access authorization, transport for short message service (SMS) messages between the UE 115-a and the short message service function (SMSF) (not shown in FIG. 2), or security anchor functionality (SEAF) (not shown in FIG. 2), among other examples. In some aspects, the AMF 210 may interact with an authentication server function (AUSF) (not shown in FIG. 2) and the UE 115-a, and may receive an intermediate key established as a result of a UE 115-a authentication process. In a case of authentication based on a universal mobile telecommunications system (UMTS) subscriber identity module (USIM), the AMF 210 may retrieve security information from the AUSF. In some examples, the AMF 210 may provide a security context management (SCM) function. The SCM function may receive a key from the SEAF that may be utilized to derive access-network specific keys. The AMF 210 may provide location services management for regulatory services, transport for location services messages between the UE 115-a and an LMF 265, transport for location services messages between the RAN 225 and the LMF 265, evolved packet system (EPS) bearer identifier allocation for interworking with the EPS, or UE 115-a mobility event notification. In some approaches, the AMF 210 may support one or more functionalities for Third Generation Partnership Project (3 GPP) access networks or non-3GPP access networks.

[0146] The UPF 215 may provide one or more U-plane functions, such as acting as an anchor point for intra / inter-RAT mobility, acting as an external protocol data unit (PDU) session point of interconnection to a data network (not shown in FIG. 2), providing packet routing and forwarding, packet inspection, user plane policy rule enforcement (e.g., gating, redirection, or traffic steering), user plane collection (e.g., interception), traffic usage reporting, quality of service (QoS) handling for the U-plane (e.g., uplink or downlink rate enforcement, reflective QoS marking in the downlink), uplink traffic verification (e.g., service data flow (SDF) to QoS flow mapping), transport level packet marking in the uplink or downlink, downlink packet buffering, downlink data notification triggering, or sending or forwarding one or more indicationsAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO41 of an end of a transmission (e.g., “end markers”) to a source RAN node, among other examples. In some examples, the UPF 215 may support the transfer of location services messages over a U-plane between the UE 115-a and another device (e.g., the SLP 235 or the external device 230.

[0147] The SMF 220 may provide one or more functions, such as session management, UE IP address allocation and management, selection and control of user plane functions, configuration of traffic steering at the UPF 215 to route traffic to a destination, control (e.g., partial control) of policy enforcement or QoS, or downlink data notification. In some aspects, the SMF 220 may communicate with the AMF 210 over an N11 interface 240.

[0148] The RAN 225 may include one or more gNBs 255 or one or more ng-eNBs 260. The gNB(s) 255 or the ng-eNB(s) 260 may be examples of the network nodes 105 described with reference to FIG. 1. For instance, a next generation RAN (NG-RAN) may include one or more gNBs 255, or other examples of the RAN 225 may include one or more ng-eNBs 260 or gNBs 255.

[0149] The core network 130-a may communicate with the RAN 225 via a C-plane interface 245 (e.g., NG-C or N2 interface) or a U-plane interface 250 (e.g., NG-U or N3 interface). The C-plane interface 245 or the U-plane interface 250 may connect the gNB 255 or the ng-eNB 260 to the core network 130-a (e.g., to one or more control plane functions or one or more user plane functions). For instance, the C-plane interface 245 may connect the AMF 210 to one or more gNBs 255 or ng-eNBs 260 in the RAN 225, or the U-plane interface 250 may connect the UPF 215 to one or more gNBs 255 or ng- eNBs 260 in the RAN 225. The gNB(s) 255 or ng-eNB(s) 260 of the RAN 225 may communicate with each other via one or more backhaul communication links 120-a (e.g., Xn-C interface). The backhaul communication link(s) 120-a may be examples of the backhaul communication links 120 described with reference to FIG. 1. One or more of the gNBs 255 or ng-eNBs 260 may communicate with one or more UEs 115-a over one or more communication links 125-a (e.g., the Uu interface). The communication link(s) 125-a may be examples of the communication links 125 described with reference to FIG. 1.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO42

[0150] The LMF 265 may communicate with the core network 130-a to provide location functionality (e.g., to participate in one or more positioning procedures) for the UE(s) 115-a. The LMF 265 may be an example of the location server 185 described with reference to FIG. 1. The LMF 265 may be implemented as one or more devices (e.g., one or more servers, such as physically separate servers, one or more instruction sets on a single server, or instruction sets distributed across multiple physical servers, among other examples). The LMF 265 may support one or more location services for one or more UEs 115-a that may connect to the LMF 265 via the RAN 225, via the core network 130-a, or via another connection (e.g., the Internet). In some examples, the LMF 265 may communicate with a UE 115-a or another device via a C-plane connection (e.g., using one or more interfaces or protocols for signaling control information, or separate from voice or payload data). In some aspects, the LMF 265 may be integrated into a component of the core network 130-a or may be external to the core network 130-a (e.g., on an external device 230, such as an original equipment manufacturer (OEM) server or other server).

[0151] In some examples, the SLP 235 may provide location functionality (e.g., may participate in one or more positioning procedures) for the UE(s) 115-a. The SLP 235 may be an example of the location server 185 described with reference to FIG. 1. The SLP 235 may be implemented as one or more devices (e.g., one or more servers, such as physically separate servers, one or more instruction sets on a single server, or instruction sets distributed across multiple physical servers, among other examples). The SLP 235 may support one or more location services for one or more UEs 115-a that may connect to the SLP 235 via the RAN 225, via the core network 130-a, or via another connection (e.g., the Internet). In some examples, the SLP 235 may communicate with a UE 115-a or another device via a U-plane connection (e.g., using one or more interfaces or protocols for signaling voice or payload data, such as a transmission control protocol (TCP) or IP).

[0152] In some examples, the external device 230 may communicate with the LMF 265, the SLP 235, the core network 130-a (e.g., via the AMF 210 or the UPF 215), the RAN 225, or the UE 115-a to obtain location information (e.g., a location estimate) for the UE 115-a. The external device 230 may be referred to as a location services (LCS) client or an external client. The external device 230 may be implemented as one or moreAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO43 devices (e.g., one or more servers, such as physically separate servers, one or more instruction sets on a single server, or instruction sets distributed across multiple physical servers, among other examples). The external device 230 may support one or more location services for one or more UEs 115-a that may connect to the external device 230 via the RAN 225, via the core network 130-a, or via another connection (e.g., the Internet). In some examples,

[0153] In some approaches, the functionality of a gNB 255 may be divided between a CU 160-a, one or more DUs 165-a, or one or more RUs 170-a. The CU 160-a may be an example of the CU 160 described with reference to FIG. 1, the one or more DUs 165-a may be examples of the DU 165 described with reference to FIG. 1, or the one or more RUs 170-a may be examples of the RU 170 described with reference to FIG. 1. In some examples, the CU 160-a may provide one or more functions, such as transferring user data, mobility control, radio access network sharing, positioning, session management, or others, except for one or more functions allocated exclusively to the DU(s) 165-a. A DU 165-a may support one or more cells. The DUs 165-a may communicate with the CU 160-a via midhaul communication links 162-a (e.g., via the Fl interface). The midhaul communication links 162-a may be examples of the midhaul communication links 162 described with reference to FIG.l. The RUs 170-a may perform one or more functions such as power amplification, signal transmission, or signal reception. The RUs 170-a may communicate with the DUs 165-a via fronthaul communication links 168-a (e.g., via the Fx interface). The fronthaul communication links 168-a may be examples of the fronthaul communication links 168 described with reference to FIG. l. The UE 115-a may communicate with the gNB 255, RU 170-a, or ng-eNB 260 a via communication links 125-a. The communication links 125-a may be examples of the communication links 125 described with reference to FIG.l. The UE 115-a may communicate with the CU 160-a via the RRC, SDAP, and PDCP layers, with a DU 165-a via the RLC and MAC layers, or with an RU 170-a via the PHY layer.

[0154] FIG. 3 shows an example of a network architecture 300 (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The network architecture 300 may illustrate an example for implementing one or more aspects of the wireless communications system 100. The networkAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO44 architecture 300 may include one or more CUs 160-b that may communicate directly with a core network 130-b via a backhaul communication link 120-b, or indirectly with the core network 130-b through one or more disaggregated network nodes 105 (e.g., a Near-RT RIC 175-b via an E2 link, or a Non-RT RIC 175-a associated with an SMO 180-a (e.g., an SMO Framework), or both). A CU 160-b may communicate with one or more DUs 165-b via respective midhaul communication links 162-b (e.g., an Fl interface). The DUs 165-b may communicate with one or more RUs 170-b via respective fronthaul communication links 168-b. The RUs 170-b may be associated with respective coverage areas 110-a and may communicate with UEs 115-b via one or more communication links 125-b. In some implementations, a UE 115-b may be simultaneously served by multiple RUs 170-b.

[0155] Each of the network nodes 105 of the network architecture 300 (e.g., CUs 160-b, DUs 165-b, RUs 170-b, Non-RT RICs 175-a, Near-RT RICs 175-b, SMOs 180-a, Open Clouds (O-Clouds) 305, Open eNBs (O-eNBs) 310) may include one or more interfaces or may be coupled with one or more interfaces configured to receive or transmit signals (e.g., data, information) via a wired or wireless transmission medium. Each network node 105, or an associated processor (e.g., controller) providing instructions to an interface of the network node 105, may be configured to communicate with one or more of the other network nodes 105 via the transmission medium. For example, the network nodes 105 may include a wired interface configured to receive or transmit signals over a wired transmission medium to one or more of the other network nodes 105. Additionally, or alternatively, the network nodes 105 may include a wireless interface, which may include a receiver, a transmitter, or transceiver (e.g., an RF transceiver) configured to receive or transmit signals, or both, over a wireless transmission medium to one or more of the other network nodes 105.

[0156] In some examples, a CU 160-b may host one or more higher layer control functions. Such control functions may include RRC, PDCP, SDAP, or the like. Each control function may be implemented with an interface configured to communicate signals with other control functions hosted by the CU 160-b. A CU 160-b may be configured to handle user plane functionality (e.g., CU-UP), control plane functionality (e.g., CU-CP), or a combination thereof. In some examples, a CU 160-b may be logically split into one or more CU-UP units and one or more CU-CP units. A CU-UPAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO45 unit may communicate bidirectionally with the CU-CP unit via an interface, such as an El interface when implemented in an O-RAN configuration. A CU 160-b may be implemented to communicate with a DU 165-b, as necessary, for network control and signaling.

[0157] A DU 165-b may correspond to a logical unit that includes one or more functions (e.g., base station functions, RAN functions) to control the operation of one or more RUs 170-b. In some examples, a DU 165-b may host, at least partially, one or more of an RLC layer, a MAC layer, and one or more aspects of a PHY layer (e.g., a high PHY layer, such as modules for FEC encoding and decoding, scrambling, modulation and demodulation, or the like) depending, at least in part, on a functional split, such as those defined by the 3rd Generation Partnership Project (3GPP). In some examples, a DU 165-b may further host one or more low PHY layers. Each layer may be implemented with an interface configured to communicate signals with other layers hosted by the DU 165-b, or with control functions hosted by a CU 160-b.

[0158] In some examples, lower-layer functionality may be implemented by one or more RUs 170-b. For example, an RU 170-b, controlled by a DU 165-b, may correspond to a logical node that hosts RF processing functions, or low-PHY layer functions (e.g., performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, or the like), or both, based at least in part on the functional split, such as a lower-layer functional split. In such an architecture, an RU 170-b may be implemented to handle over the air (OTA) communication with one or more UEs 115-b. In some implementations, real-time and non-real-time aspects of control and user plane communication with the RU(s) 170-b may be controlled by the corresponding DU 165-b. In some examples, such a configuration may enable a DU 165-b and a CU 160-b to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0159] The SMO 180-a may be configured to support RAN deployment and provisioning of non-virtualized and virtualized network nodes 105. For non-virtualized network nodes 105, the SMO 180-a may be configured to support the deployment of dedicated physical resources for RAN coverage requirements which may be managed via an operations and maintenance interface (e.g., an 01 interface). For virtualized network nodes 105, the SMO 180-a may be configured to interact with a cloudAttorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO46 computing platform (e.g., an O-Cloud 305) to perform network node life cycle management (e.g., to instantiate virtualized network nodes 105) via a cloud computing platform interface (e.g., an 02 interface). Such virtualized network nodes 105 can include, but are not limited to, CUs 160-b, DUs 165-b, RUs 170-b, and Near-RT RICs 175-b. In some implementations, the SMO 180-a may communicate with components configured in accordance with a 4G RAN (e.g., via an 01 interface). Additionally, or alternatively, in some implementations, the SMO 180-a may communicate directly with one or more RUs 170-b via an 01 interface. The SMO 180-a also may include a Non- RT RIC 175-a configured to support functionality of the SMO 180-a.

[0160] The Non-RT RIC 175-a may be configured to include a logical function that enables non-real-time control and optimization of RAN elements and resources, artificial intelligence (Al) or machine learning (ML) workflows including model training and updates, or policy-based guidance of applications / features in the Near-RT RIC 175-b. The Non-RT RIC 175-a may be coupled with or communicate with (e.g., via an Al interface) the Near-RT RIC 175-b. The Near-RT RIC 175-b may be configured to include a logical function that enables near-real-time control and optimization of RAN elements and resources via data collection and actions over an interface (e.g., via an E2 interface) connecting one or more CUs 160-b, one or more DUs 165-b, or both, as well as an O-eNB 310, with the Near-RT RIC 175-b.

[0161] In some examples, to generate AI / ML models to be deployed in the Near-RT RIC 175-b, the Non-RT RIC 175-a may receive parameters or external enrichment information from external servers. Such information may be utilized by the Near-RT RIC 175-b and may be received at the SMO 180-a or the Non-RT RIC 175-a from nonnetwork data sources or from network functions. In some examples, the Non-RT RIC 175-a or the Near-RT RIC 175-b may be configured to tune RAN behavior or performance. For example, the Non-RT RIC 175-a may monitor long-term trends and patterns for performance and employ Al or ML models to perform corrective actions through the SMO 180-a (e.g., reconfiguration via 01) or via generation of RAN management policies (e.g., Al policies).

[0162] FIG. 4 shows an example of a wireless communications system 400 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The wireless communications system 400 may implement aspects ofAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO47 or may be implemented by aspects of the wireless communications system 100. For example, the wireless communications system 400 includes a first device 410, which may be an example of a UE 115, network node 105, RU 170, DU 165, or CU 160 described with reference to FIG. 1, a UE 115-a, gNB 255, RU 170-a, DU 165-a, CU 160-a, or ng-eNB 260 described with reference to FIG. 2, or a UE 115-b, RU 170-b, DU 165-b, or CU 160-b described with reference to FIG. 3. The wireless communications system 400 also includes one or more devices 420, each of which may be an example of a UE 115, network node 105, location server 185, RU 170, DU 165, or CU 160 described with reference to FIG. 1, a UE 115-a, LMF 265, external device 230, SLP 235, AMF 210, SMF 220, UPF 215, gNB 255, RU 170-a, DU 165-a, CU 160-a, or ng- eNB 260 described with reference to FIG. 2, or a UE 115-b, RU 170-b, DU 165-b, or CU 160-b described with reference to FIG. 3. In some examples, the one or more devices 420 may be an example of an SnMF.

[0163] The first device 410 may communicate with the one or more devices 420 using a link 425, which may be an example of a communication link 125, a backhaul communication link 120, or a communication link 155 described with reference to FIG. 1, a communication link 125-a, a backhaul communication link 120-a, a C-plane interface 245, or a U-plane interface 250 described with reference to FIG. 2, a communication link 125-b or a backhaul communication link 120-b described with reference to FIG. 3, or another link. The link 425 may include a uni-directional or bidirectional link that enables uplink, downlink, sidelink, device-to-device, or other communications. For example, the first device 410 may transmit one or more transmissions 415, such as control signals or data signals, to the one or more devices 420 using the link 425, or the one or more devices 420 may transmit one or more transmissions (not shown in FIG. 4), such as control signals or data signals, to the first device 410 using the link 425. The transmission(s) may include one or more uplink transmissions, downlink transmissions, sidelink transmissions, or other transmissions.

[0164] In some approaches, the first device 410 (e.g., a UE or network entity) may be capable of performing one or more positioning procedures to generate position information. A positioning procedure may be one or more operations for estimating or sensing a position of an object (e.g., a device such as the first device 410 or a UE, or a passive object that does not provide signals for positioning) or an object. As usedAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO48 herein, a “positioning procedure” may include one or more operations for sensing or estimating a position of an object.

[0165] For instance, a positioning procedure may include one or more operations of A-GNSS positioning, OTDOA positioning, E-CID positioning, sensor-based positioning (e.g., monostatic mode(s), bi-static mode(s), or multi-static mode(s)), WLAN-based positioning, Bluetooth-based positioning, TBS positioning, DL-TDOA positioning, DL- AOD positioning, Multi-RTT positioning, NR E-CID positioning, UL-TDOA positioning, or UL-AOA positioning, among other examples. Position information may include an estimated position (e.g., estimated location) or one or more measurements associated with a positioning procedure (e.g., AI / ML-based positioning procedure or non-AI / ML-based positioning procedure). For instance, position information may include a position or measurement determined based on one or more positioning procedures, such as A-GNSS positioning, OTDOA positioning, E-CID positioning, sensor-based positioning (e.g., monostatic mode(s), bi-static mode(s), or multi-static mode(s)), WLAN-based positioning, Bluetooth-based positioning, TBS positioning, DL-TDOA positioning, DL-AOD positioning, Multi-RTT positioning, NR E-CID positioning, UL-TDOA positioning, or UL-A positioning, among other examples. Examples of positioning procedures are described with reference to FIG. 23, FIG. 25 A, FIG. 25B, FIG. 26, or FIG. 27.

[0166] As used herein, the term “AI / ML-based positioning procedure” may refer to a positioning procedure performed with an Al model or ML model. An “AI / ML-based positioning procedure” may refer to direct AI / ML (D-AI / ML) positioning or sensing, or may refer to assisted AI / ML (A-AI / ML) positioning or sensing. An “AI / ML model” for positioning may refer generally to a physical AI / ML model, a logical AI / ML model, an AI / ML function, AI / ML functionality, or an AI / ML method, among other examples. The term “non-AI / ML-based positioning procedure” may refer to a positioning procedure performed without an Al model or ML model. AI / ML-based positioning procedures may improve positioning accuracy.

[0167] A non-AI / ML-based positioning procedure may include one or more positioning procedures where an AI / ML technique is not utilized to determine (e.g., infer or predict) a location or measurement. For instance, A-GNSS positioning, OTDOA positioning, E-CID positioning, sensor-based positioning, WLAN-based positioning,Attorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO49Bluetooth-based positioning, TBS positioning, DL-TDOA positioning, DL-AOD positioning, Multi-RTT positioning, NR E-CID positioning, UL-TDOA positioning, UL-AOA positioning, or other positioning or sensing performed without the use of an AI / ML technique or model may be examples of a non-AI / ML-based positioning procedure.

[0168] An AI / ML-based positioning procedure may include one or more positioning procedures where one or more AI / ML techniques (e.g., AI / ML model(s) or AI / ML function(s)) are utilized to determine (e.g., infer or predict) a position or measurement. In some examples, an Al model may be utilized to perform one or more operations of a positioning procedure (e.g., to infer or predict a measurement, value, quantity, or location). For instance, A-GNSS positioning, OTDOA positioning, E-CID positioning, sensor-based positioning (e.g., monostatic mode(s), bi-static mode(s), or multi-static mode(s)), WLAN-based positioning, Bluetooth-based positioning, TBS positioning, DL-TDOA positioning, DL-AOD positioning, Multi-RTT positioning, NR E-CID positioning, UL-TDOA positioning, UL-AOA positioning, or other positioning or sensing performed with the use of an AI / ML technique(s) or model(s) may be examples of an AI / ML-based positioning procedure. For instance, an Al model may be trained to model one or more operations of a positioning procedure. When the Al model is executed, for instance, a position or one or more measurements may be generated (e.g., inferred or predicted) without directly performing the one or more operations of the positioning procedure.

[0169] A position may be information or data indicating a point, area, or region where an object (e.g., the first device 410) is located. A location may be expressed as coordinates (e.g., latitude, longitude, or altitude of a geographic coordinate system (GCS), universal transverse mercator (UTM) coordinates, state plane coordinate system (SPCS) coordinates, or Earth-centered Earth-fixed (ECEF) coordinates, among other examples), an address, or a location relative to another location, among other examples.

[0170] A measurement may be measured, sensed, generated, calculated, inferred, or predicted based on one or more samples, sensor data, information, or characteristics of a reference signal. Examples of measurements may include signal strength, reference signal received power (RSRP), reference signal received path power (RSRPP), received signal strength indicator (RSSI), reference signal received quality (RSRQ), signal-to-Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO50 interference plus noise ratio (SINR), SNR, channel frequency response (CFR), channel impulse response (CIR), power delay profile (PDP), delay profile (DP), channel quality indicator (CQI), CSI, line-of-sight (LOS) indicator, time of arrival (TOA), angle of arrival (AO A), angle of departure (AOD), round-trip time (RTT), reference signal time difference (RSTD), time difference of arrival (TDOA), reference signal carrier phase (RSCP), reference signal carrier phase difference (RSCPD), reception-to-transmission (Rx-Tx) time difference, range, distance, image data, temperature data, or motion data, among other examples. In some examples, a measurement may be data or an indicator that indicates one or more of the aforementioned values.

[0171] In some examples, a network node may output (e.g., transmit), or the first device 410 may obtain (e.g., receive), a reference signal (not shown in FIG. 4). In some examples, the network node may be a positioning reference unit (PRU). The reference signal may be a signal (e.g., electromagnetic signal, RF signal) with one or more established characteristics (e.g., signaling pattern, strength, amplitude, magnitude, frequency, timing, modulation, phase, or data, among other examples). For instance, the first device 410 or the one or more devices 420 may store information indicating one or more of the characteristics of the reference signal, which may allow for comparison of one or more stored characteristics and one or more characteristics of the received reference signal. The reference signal (e.g., the comparison) may enable channel estimation (e.g., channel attenuation, phase, frequency shift, or Doppler effects, among other examples), positioning, or tracking. Examples of the reference signal may include a reference signal of a synchronization signal block (SSB), a CSLRS, a positioning reference signal (PRS), a sounding reference signal (SRS), a demodulation reference signal (DMRS), or a tracking reference signal (TRS), among other examples.

[0172] In some examples, the first device 410 may obtain, receive, sense, capture, or generate one or more measurements. For instance, the first device 410 may include, may communicate with, or may be coupled with one or more sensors to obtain one or more measurements. Examples of a sensor may include an image sensor(s), infrared (IR) sensor(s), light sensor(s), depth sensor(s) (e.g., LIDAR, stereoscopic camera(s), or time-of-flight (TOF) sensor(s)), microphone(s), or RF sensor(s), among other examples. Examples of one or more measurements may include a range map (e.g., depth map), Doppler map, space map, angle map, light spectrum data, pixel(s), image(s) (e.g., red-Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO51 green-blue-depth (RGBD) image(s)), audio signal(s), temperature map, TOF measurement(s), RF measurement(s), or other information (e.g., information regarding one or more objects).

[0173] The measurement s) may be processed to generate input (e.g., input data) to an AI / ML model or may be utilized by an AI / ML model to generate an inferred position or other measurements. Examples of input data, inferred measurements, and positions (e.g., locations) are provided with reference to FIG. 25 A and FIG. 25B. In some aspects, an indication of one or more measurements or positions (e.g., one or more inferred measurements or positions) may be communicated with (e.g., transmitted to or received from) the first device 410 or the one or more devices 420. For example, the first device 410 may output (e.g., transmit) or the one or more devices 420 may obtain (e.g., receive) an indication of one or more inferred measurements or positions based on the one or more processing operations associated with AI / ML. Some examples of the techniques described herein may be utilized for AI / ML-based positioning for sensing, for which position, range, velocity, or angle of an object (e.g., a passive object or device) may be an AI / ML model output.

[0174] In some examples, one or more AI / ML models or one or more portions of one or more AI / ML models may be stored or processed on the first device 410 (e.g., a UE or a network node) or on the one or more devices 420 (e.g., a UE, a network node, location server, or sensing server). Examples of locations where an AI / ML model may be stored or processed are provided with reference to FIG. 5 and FIG. 26. One or more of the techniques described herein may be utilized to split one or more AI / ML models, to operate one or more portions of one or more AI / ML models, or to communicate information generated from one or more portions of one or more AI / ML models.

[0175] As illustrated in the example of FIG. 4, the first device 410 may include (e.g., store or execute) a first portion 405 of one or more AI / ML models. The one or more devices 420 (e.g., second device(s), network entity(ies), network node(s), or UE(s), among other examples) may include (e.g., store or execute) one or more other portions 430 of one or more AI / ML models.

[0176] In some approaches, AI / ML model computation splitting options may include splitting AI / ML model computations into two or more portions (e.g., a firstAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO52 portion 405 and a second portion (e.g., portion(s) 430), or a first portion 405, a second portion (e.g., portion(s) 430), and a third portion (e.g., portion(s) 430). In some examples, an AI / ML model or AI / ML model computation may be split into two, three, or more portions. For instance, the first portion 405 may be executed at a UE, the second portion may be executed at another UE, network node, or network entity (e.g., LMF), or the third portion may be executed at a network node (e.g., LMF).

[0177] In some examples, the first device 410 and the one or more devices 420 may have varying capabilities (e.g., processing capabilities, available processing bandwidth, memory capacity, available memory capacity, communication bandwidth, or other varying capabilities). For instance, the wireless communications system 400 may include a first device 410 that may be a lower capability device, a second device (of the one or more devices 420, for instance) that may be a higher capability device, and a third device (e.g., a network entity, LMF, or SnMF, among other examples).

[0178] Some options for splitting an AI / ML model may include a first option, where an AI / ML model or AI / ML model processing is split between the first device 410 and a network entity (e.g., a device 420, LMF, or SnMF, among other examples). In the first option, the first device 410 may report first information generated from the first portion 405 (of an AI / ML model) to a network entity (e.g., LMF), and the network entity executes a second portion (e.g., portion 430) of the AI / ML model. In a second option, AI / ML model processing is split between the first device 410 and the second device (e.g., device 420), where the first device 410 generates first information from the first portion 405 of an AI / ML model and provides the first information to the second device, and the second device reports second information generated from a second portion of the AI / ML model to a network entity (e.g., LMF). In a third option, an AI / ML model is split into three portions (e.g., a first portion 405 at the first device, a second portion (e.g., one of the portions 430) at a second device, and a third portion (e.g., one of the portions 430) at a network entity (e.g., LMF), where the first device 410 generates first information from the first portion 405 of the AI / ML model and provides the first information to the second device, the second device reports second information generated from a second portion of the AI / ML model to the first device 410, the first device 410 provides the second information to the network entity, which may generates third information from a third portion of the AI / ML model. Other options may includeAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO53 other AI / ML model locations or communications (as shown in FIG. 5, for example). Table (1) provides some examples of the first option, the second option, and the third option.Table (1)

[0179] In some examples, the first device 410 may be a wireless device (e.g., UE, gNB, or network node, among other examples). The one or more devices 420 may include a second device (e.g., a second wireless device, UE, gNB, or network node, among other examples). Additionally, or alternatively, the one or more devices 420 may include a network entity (e.g., a location server, LMF, or SnMF, among other examples). The first device 410 may include an AI / ML model (for performing one or more AI / ML-based positioning procedures) or a first portion 405 of the AI / ML model. The second device (of the device(s) 420) may include the AI / ML model or a second portion (of the portion(s) 430) of the AI / ML model. Additionally, or alternatively, the network entity (of the device(s) 420) may include the AI / ML model, a second portion of the AI / ML model, or a third portion of the AI / ML model.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO54

[0180] The first device 410 may transmit, or the one or more devices 420 (e.g., a network entity) may obtain (e.g., receive), capability information 440 of the first device 410 that indicates a capability of the first device 410 to process one or more portions of an AI / ML model at the first device 410. The AI / ML model may be associated with a positioning procedure. In some approaches, a second device (of the device(s) 420) may additionally, or alternatively, communicate capability information (e.g., similar capability information).

[0181] In some examples, the capability information 440 indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model. For instance, the first device 410 (or a second device of the device(s) 420) may indicate one or more capabilities to perform AI / ML model computation splitting, a supported quantity (e.g., maximum quantity) of computations, or memory available to handle the model portion. In some aspects, the capability information may indicate whether model splitting is supported (e.g., {Yes, No}), a supported quantity of computations per portion (e.g., floating point operations per second (FLOPs) per portion {XI, X2, X3}), or a supported quantity of learnable parameters (e.g., weights) per portion.

[0182] In some approaches, the first device 410, a second device, or a network entity (of the device(s) 420) may communicate (e.g., output, transmit, obtain, or receive) capability information (e.g., capability information 440) via capability signaling, TRP information, uplink control information (UCI), an RRC message, a medium access control-control (MAC-CE) message, LTE positioning protocol (LPP) signaling, NR positioning protocol A (NRPPa) signaling, or sidelink LPP (SL-LPP) signaling, among other examples.

[0183] The first device 410 may generate first information associated with a position of an object. The first information may be an output (or may correspond to or represent an output, for instance) of the first portion 405 of the AI / ML model. The one or more portions of the AI / ML model may include the first portion 405 of the AI / ML model. In some examples, the output of the first portion 405 of the AI / ML model mayAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO55 be based on one or more measurements input to the first portion 405 of the AI / ML model at the first device 410.

[0184] In some examples, the first device 410 may receive a reference signal (from the second device or from a network node, for instance). The one or more measurements may be of the reference signal. For instance, the first device 410 may obtain one or more reference signal measurements, and may utilize the measurement(s) to obtain the first information (e.g., one or more first AI / ML positioning measurements) using the first portion 405 of the AI / ML model (for positioning, for example).

[0185] In some aspects, the one or more measurements may be a measurement s) from one or more sensors. For instance, the first device 410 may obtain the one or more measurements via one or more sensors, where the one or more measurements may include a range measurement, a Doppler measurement, a velocity measurement, an angle measurement, or a position measurement associated with the object. The measurement(s) may be input to the first portion 405 of the AI / ML model to generate the first information.

[0186] In some approaches, the first device 410 may transmit the first information associated with the position of the object to the second device (of the device(s) 420, for instance). The second device may obtain, from the first device 410, the first information associated with the position of the object. As described herein, the first information may be an output of the first portion 405 of the AI / ML model. Additionally, or alternatively, the first device 410 may transmit the first information associated with the position of the object to the network entity (of the device(s) 420, for instance).

[0187] In some examples, the second device (of the device(s) 420, for instance) may generate second information associated with the position of the object. The second information may be an output of a second portion (of the portion(s) 430, for instance) of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device. For example, the second device (e.g., second wireless device, UE, or network node, among other examples) may obtain the first information (e.g., first AI / ML positioning measurements) and may utilize the first information to obtain second information (e.g., second AI / ML positioning measurements) using a second portion of the AI / ML model (e.g., positioning model). InAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO56 some examples, the second information may indicate an estimated position of the object or one or more intermediate measurements related to a position of the object.

[0188] In some approaches, the second device (of the device(s) 420, for instance) may transmit the second information associated with the position of the object. For example, the second device may transmit, or the network entity (of the device(s) 420, for instance) may obtain (e.g., receive) the second information.

[0189] In some aspects, the network entity (of the device(s) 420, for instance), may obtain (e.g., receive) the first information or the second information associated with the position of the object. As described herein, the first information may be an output of a first portion of the AI / ML model or the second information may be an output of a second portion of the AI / ML model. The one or more portions of the AI / ML model may include the first portion of the AI / ML model and the second portion of the AI / ML model.

[0190] In some examples, the network entity (of the device(s) 420, for instance), may obtain (e.g., receive) the first information, and may generate the second information associated with the position of the object, where the second information may be an output of the second portion (of the portion(s) 430) of the AI / ML model based on the first information input to the second portion of the AI / ML model at the network entity. For instance, the network entity may obtain the first information (e.g., first AI / ML positioning measurements from the first device 410) and may utilize the first information to obtain the second information (e.g., second AI / ML positioning measurements) using a second portion of the AI / ML model (e.g., positioning model).

[0191] Additionally, or alternatively, the network entity (of the device(s) 420, for instance), may obtain (e.g., receive) the second information, and may generate third information associated with the position of the object. The third information may be an output of a third portion (of the portion(s) 430, for instance) of the AI / ML model based on the second information input to the third portion of the AI / ML model at the network entity. Accordingly, the network entity may utilize the obtained first information or second information (e.g., first or second AI / ML positioning measurements) to determine a position of the object (e.g., a position of the first device 410 or another object). Additionally, or alternatively, the network entity may utilize the obtained secondAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO57 information (e.g., second AI / ML positioning measurements) with a third portion (of the portion(s) 430, for instance) of the AI / ML model (e.g., positioning model executed at the network entity) to determine a position of the object (e.g., a position of the first device 410 or another object).

[0192] As described herein, model splitting may refer to splitting the data structure of an AI / ML model (e.g., positioning or sensing model) into portions or splitting processing of an AI / ML model into processing portions of the AI / ML model (e.g., positioning or sensing model). In some examples, the AI / ML model may include the first portion 405 and a second portion (of the portion(s) 430). The first portion 405 may include one or more first nodes, one or more first layers, one or more first residual blocks (e.g., resnet blocks), one or more first attention mechanism stages, a first portion of a graph structure, or a combination thereof. The second portion (of the portion(s) 430) may include one or more second nodes, one or more second layers, one or more second residual blocks, one or more second attention mechanism stages, a second portion of a graph structure, or a combination thereof.

[0193] In some approaches, an AI / ML model may have one or more potential splitting points (or options), for which computations may be performed in stages. For instance, an AI / ML model (or AI / ML model processing) may be split based on layers, resnet blocks, attention mechanism layers, or stages, among other examples. The first portion 405, second portion (of the portion(s) 430), a potential third portion (of the portion(s) 430) may be described with a set of stages. For example, each stage may be associated with (or include) one or more layers. A layer may be convolution-based, fully-connected, an attention mechanism. Additionally, or alternatively, a portion (e.g., the first portion 405 or each of the portion(s) 430) of an AI / ML model may be a portion of a connected graph based on the AI / ML model structure.

[0194] In some examples, the AI / ML model, one or more portions of the AI / ML model, one or more indications of the AI / ML model, or one or more indications of one or more portions of the AI / ML model may be communicated (e.g., output, transmitted, obtained, or received) between the first device 410 and the device(s) 420. In some aspects, the AI / ML model, a portion of the AI / ML model, or an indication of one or more portions of the AI / ML model may be provided or transferred from the first device 410 (e.g., first wireless device) to a second device (of the device(s) 420, for instance) orAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO58 to a network entity (of the device(s) 420, for instance). For example, the first device 410 may transmit, the second device (of the device(s) 420, for instance) may obtain (e.g., receive), or the network entity (of the device(s) 420, for instance) may obtain (e.g., receive) model information indicating the AI / ML model, the first portion 405 of the AI / ML model, a second portion (of the portion(s) 430, for instance), or another portion (of the portion(s) 430, for instance) of the AI / ML model. Additionally, or alternatively, the first device 410 may transmit, the second device (of the device(s) 420, for instance) may obtain (e.g., receive), or the network entity (of the device(s) 420, for instance) may obtain (e.g., receive) an indication of one or more portions of the AI / ML model (e.g., an indication of the first portion 405, a second portion (of the portion(s) 430, for instance), or one or more other portions 430).

[0195] In some approaches, the AI / ML model, a portion of the AI / ML model, or an indication of one or more portions of the AI / ML model may be provided or transferred from the second device (of the device(s) 420, for instance) to the first device 410 (e.g., first wireless device) or to a network entity (of the device(s) 420, for instance). For example, the second device (of the device(s) 420, for instance) may transmit, the first device 410 may obtain (e.g., receive), or the network entity (of the device(s) 420, for instance) may obtain (e.g., receive) model information indicating the AI / ML model, the first portion 405 of the AI / ML model, a second portion (of the portion(s) 430, for instance), or another portion (of the portion(s) 430, for instance) of the AI / ML model. Additionally, or alternatively, the second device (of the device(s) 420, for instance) may transmit, the first device 410 may obtain (e.g., receive), or the network entity (of the device(s) 420, for instance) may obtain (e.g., receive) an indication of one or more portions of the AI / ML model (e.g., an indication of the first portion 405, a second portion (of the portion(s) 430, for instance), or one or more other portions 430).

[0196] In some examples, the AI / ML model, a portion of the AI / ML model, or an indication of the one or more portions of the AI / ML model may be provided or transferred from the network entity (of the device(s) 420, for instance) to the first device 410 (e.g., first wireless device) or to the second device (of the device(s) 420, for instance). For example, the network entity (of the device(s) 420, for instance) may output (e.g., transmit), the first device 410 may obtain (e.g., receive), or the second device (of the device(s) 420, for instance) may obtain (e.g., receive) model informationAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO59 indicating the AI / ML model, the first portion 405 of the AI / ML model, a second portion (of the portion(s) 430, for instance), or another portion (of the portion(s) 430, for instance) of the AI / ML model. Additionally, or alternatively, the network entity (of the device(s) 420, for instance) may output (e.g., transmit), the first device 410 may obtain (e.g., receive), or the second device (of the device(s) 420, for instance) may obtain (e.g., receive) an indication of one or more portions of the AI / ML model (e.g., an indication of the first portion 405, a second portion (of the portion(s) 430, for instance), or one or more other portions 430).

[0197] In some aspects, the AI / ML model (or one or more portions of the AI / ML model) or an indication of the AI / ML model (or an indication of one or more portions of the AI / ML model) may be provided by (e.g., output from, transmitted from, obtain from, or received from) another entity (e.g., a core network entity, an operations, administration, and maintenance (0AM) entity, an 0-RAN entity, an OTT server, or a network data analytics function (NWDAF), among other examples) to the first device 410, to a second device, or to a network entity.

[0198] In some approaches, the first device 410, a second device (of the device(s) 420, for instance), or a network entity (of the device(s) 420, for instance) may communicate (e.g., output, transmit, obtain, or receive) an indication of a location of a split of the AI / ML model between the first portion 405 of the AI / ML model and a second portion (of the portion(s) 430, for instance) of the AI / ML model. The location of the split may be associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof. When the AI / ML model or a portion of an AI / ML model is provided, for example, a description of one or more potential splitting options of different portions may be indicated. The AI / ML model may be utilized for D-AI / ML positioning or A- AI / ML positioning.

[0199] In some aspects, the signaled splitting indication (e.g., from the first device 410 to a second device (of the device(s) 420), from the first device 410 to a network entity (of the device(s) 420, such as an LMF), or from the second device to the network entity) may include information on where split is located or where the split occurred (e.g., an index of a layer, stage, or block, among other examples). The informationAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO60 regarding where the split is located may enable a second device or network entity (e.g., LMF) to have information regarding the remaining computations to be performed.

[0200] In some approaches, the first device 410, the second device (of the device(s) 420, for instance), or the network entity (of the device(s) 420, for instance) may communicate (e.g., output, transmit, obtain, or receive) an indication of a reason for portioning (e.g., splitting) the AI / ML model. For example, the reason may be associated with a memory limit, a processing limit, a battery level, or a combination thereof. In some aspects, the reason of splitting may indicate that a memory limit is exceeded (or would be exceeded), that a processing limit of a central processing unit (CPU), graphics processing unit (GPU), or neural processing unit (NPU) is exceeded (or would be exceeded), or that less than a threshold quantity of battery power is remaining, among other examples.

[0201] In some approaches, configuration information related to AI / ML model splitting may be communicated. For instance, the first device 410, a second device (of the device(s) 420, for instance), or a network entity (of the device(s) 420, for instance), may communicate (e.g., output, transmit, obtain, or receive) configuration information indicating one or more potential splitting options or one or more candidate devices for offloading AI / ML model computation (for one or more split portions, for instance). Configuration information may be communicated via LPP signaling, NRPPa signaling, or SL-LPP signaling, among other examples.

[0202] In some aspects, the first device 410, a second device (of the device(s) 420, for instance), or a network entity (of the device(s) 420, for instance) may communicate (e.g., output, transmit, obtain, or receive) configuration information that indicates one or more locations to split the AI / ML model. The one or more portions of the AI / ML model may be associated with the one or more locations.

[0203] In some examples, the first device 410 (e.g., first wireless device) may receive, from a second device (e.g., a second wireless device of the device(s) 420), configuration information indicating the first portion 405 of the AI / ML model (e.g., positioning model) to be utilized for obtaining the first information (e.g., first AI / ML positioning measurements). Additionally, or alternatively, the first device 410 (e.g., first wireless device) may receive, from a network entity (of the device(s) 420, for instance),Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO61 configuration information indicating the first portion 405 of the AI / ML model (e.g., positioning model) to be utilized for obtaining the first information (e.g., first AI / ML positioning measurements). For instance, the first device 410 may obtain configuration information that indicates the first portion 405 of the AI / ML model for generation of the first information.

[0204] In some examples, a second device (e.g., a second wireless device of the device(s) 420) may receive, from the first device 410 (e.g., first wireless device), configuration information indicating a second portion (of the portions(s) 430, for instance) of the AI / ML model (e.g., positioning model) to be utilized for obtaining the second information (e.g., second AI / ML positioning measurements). Additionally, or alternatively, the second device (e.g., a second wireless device of the device(s) 420) may receive, from a network entity (of the device(s) 420, for instance), configuration information indicating the second portion of the AI / ML model (e.g., positioning model) to be utilized for obtaining the second information (e.g., second AI / ML positioning measurements). For instance, the second device (e.g., a second wireless device of the device(s) 420) may obtain configuration information that indicates the second portion (of the portion(s) 430, for instance) of the AI / ML model for generation of the second information.

[0205] In some examples, a network entity (of the device(s) 420, for instance) may output (e.g., transmit) configuration information to the first device 410 (e.g., first wireless device) or to a second device (e.g., a second wireless device of the device(s) 420), configuration information indicating the first portion 405 or a second portion (of the portions(s) 430, for instance) of the AI / ML model (e.g., positioning model) to be utilized for obtaining the first information (e.g., first AI / ML positioning measurements) or the second information (e.g., second AI / ML positioning measurements). Additionally, or alternatively, the network entity (of the device(s) 420, for instance) may obtain (e.g., receive), from the first device 410 or a second device (e.g., a second wireless device of the device(s) 420), configuration information indicating the first portion 405 or a second portion of the AI / ML model (e.g., positioning model) to be utilized for obtaining the first information or the second information (e.g., second AI / ML positioning measurements).Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO62

[0206] In some aspects, the first device 410, a second device (of the device(s) 420, for instance), or a network entity (of the device(s) 420, for instance) may communicate (e.g., output, transmit, obtain, or receive) configuration information that indicates one or more candidate devices for offloading processing associated with a second portion of the AI / ML model. For instance, the first device 410 or a second device (of the device(s) 420, for instance, may be one of the one or more candidate devices. In some approaches, the first device 410 may select or communicate with a second device (of the device(s) 420, for instance) based on the configuration information that indicates the second device as a candidate device for offloading processing.

[0207] In some approaches, the first device 410 may output (e.g., transmit) the first information to a second device (of the device(s) 420, for instance) or to a network entity (of the device(s) 420, for instance). For example, the first device 410 (e.g., first wireless device) may report, to the second device (e.g., second wireless device of the device(s) 420), the first information (e.g., first AI / ML positioning measurements). Additionally, or alternatively, the first device 410 may report, to the second device, an indication of the first portion 405 of the AI / ML positioning model utilized to obtain the first information (e.g., first AI / ML positioning measurements). In some aspects, the first device 410 (e.g., first wireless device) may report, to the network entity (e.g., network entity of the device(s) 420), the first information (e.g., first AI / ML positioning measurements). Additionally, or alternatively, the first device 410 may report, to the network entity, an indication of the first portion 405 of the AI / ML positioning model utilized to obtain the first information (e.g., first AI / ML positioning measurements).

[0208] In some aspects, the first device 410 (e.g., first wireless device) may obtain (e.g., receive), from a second device (of the device(s) 420, for instance), the second information indicating an output of the second portion (of the portion(s) 430) of the AI / ML model based on the first information (e.g., where the second information was generated by inputting the first information to the second portion of the AI / ML model). The first device 410 may output (e.g., transmit), to a network entity (of the device(s) 420), the second information. For example, the first device 410 (e.g., first wireless device) may report, to the network entity (e.g., network entity of the device(s) 420), the second information (e.g., second AI / ML positioning measurements). Additionally, or alternatively, the first device 410 may report, to the network entity, an indication of theAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO63 second portion (of the portion(s) 430, for instance) of the AI / ML positioning model utilized to obtain the second information (e.g., second AI / ML positioning measurements).

[0209] In some examples, a second device (of the device(s), for instance) may output (e.g., transmit) the second information indicating the output of the second portion (of the portion(s) 430, for instance) of the AI / ML model to the first device 410 or to a network entity (of the device(s) 420, for instance). For example, the second device (e.g., second wireless device of the device(s) 420) may report, to the first device 410 (e.g., first wireless device), the second information (e.g., second AI / ML positioning measurements). Additionally, or alternatively, the second device may report, to the first device 410, an indication of the second portion (of the portion(s) 430) of the AI / ML positioning model utilized to obtain the second information (e.g., second AI / ML positioning measurements). In some aspects, the second device (e.g., second wireless device of the device(s)) may report, to the network entity (e.g., network entity of the device(s) 420), the second information (e.g., second AI / ML positioning measurements). Additionally, or alternatively, the second device may report, to the network entity, an indication of the second portion (of the portion(s) 430) of the AI / ML positioning model utilized to obtain the second information (e.g., second AI / ML positioning measurements).

[0210] In some examples, the first information (e.g., first AI / ML positioning measurement(s) or output of the first portion 405 of the AI / ML model) may include a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object. For instance, the first AI / ML positioning measurement(s) may include a first latent representation of reference signal measurements corresponding to a location of an object (e.g., the first device 410 or a passive object). In some approaches, the first AI / ML positioning measurement s) may include first location information (e.g., coarse location information) corresponding to a location of an object (e.g., the first device 410 or a passive object). Additionally, or alternatively, the first AI / ML positioning measurement(s) may include one or more other measurements (e.g., an RSTD, RSTD relative difference, TOA, TOA relative difference, TOF, TOF relative difference, Rx-Tx time difference (of a UE or gNB, forAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO64 instance), an uplink or downlink RTOA, an uplink or downlink RTOA relative difference, an uplink or downlink RSRP, an uplink or downlink RSRPP, an uplink or downlink AOD, an uplink or downlink AO A, an uplink or downlink RSCP, or an uplink or downlink RSCPD, among other examples) corresponding to a location of the object (e.g., the first device 410 or a passive object).

[0211] In some examples, the second information may include a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object. In some aspects, the second information (e.g., second AI / ML positioning measurement(s) or output of the second portion of the AI / ML model) may include a latent representation of a reference signal measurement based on the first information obtained from the first device 410 (e.g., corresponding to the position of the object such as the first device 410, an indication of the position of the object, or at least one measurement corresponding to the position of the object). For instance, the second AI / ML positioning measurement s) may include a second latent representation of reference signal measurements based on the first information obtained from the first device 410 corresponding to a location of an object (e.g., the first device 410 or a passive object). In some approaches, the second AI / ML positioning measurement(s) may include second location information (e.g., fine location information) based on the first information obtained from the first device 410 corresponding to a location of an object (e.g., the first device 410 or a passive object). Additionally, or alternatively, the second AI / ML positioning measurement(s) may include one or more other measurements (e.g., an RSTD, RSTD relative difference, TOA, TOA relative difference, TOF, TOF relative difference, Rx-Tx time difference (of a UE or gNB, for instance), an uplink or downlink RTOA, an uplink or downlink RTOA relative difference, an uplink or downlink RSRP, an uplink or downlink RSRPP, an uplink or downlink AOD, an uplink or downlink AO A, an uplink or downlink RSCP, or an uplink or downlink RSCPD, among other examples) based on the first information obtained from the first device 410, where the second AI / ML positioning measurements may correspond to a location of the object (e.g., the first device 410 or a passive object). In some examples, the second information (e.g., second AI / ML positioning measurements) may be an enhancement to the first information (e.g., first AI / MLAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO65 positioning measurements). For instance, the second information may provide increased measurement or position accuracy relative to the first information (e.g., fine measurements versus coarse measurements).

[0212] In some aspects, one or more of the AI / ML-based positioning procedures, AI / ML model portions, or communications (e.g., signaling capability information, configuration information, first information, or second information, among other examples) described herein may be utilized for one or more sensing use cases. For instance, sensing may be performed to determine a position or motion of an object (e.g., a wireless device or other object). Examples of sensing use cases may include one or more of transportation, unmanned aerial vehicles (UAVs), smart cities, smart homes, smart factories, or health monitoring. For instance, a transportation use case may include intrusion detection on a highway, sensing assisted automotive maneuvering or navigation, smart parking, or other assistance, among other examples. A UAV use case may include UAV flight trajectory tracing or sensing for UAV intrusion detection, among other examples. A smart city use case may include rainfall monitoring, tourist spot traffic management, flooding awareness, weather forecasting, or public safety search and rescue, among other examples. A smart home use case may include intruder detection in a smart home, gesture recognition, or extended reality (XR) streaming, among other examples. A smart factory use case may include automated guided vehicle (AGV) detection and tracking in factories or inventory tracking, among other examples. A health monitoring use case may include monitoring vital signs and health related measures, sleep monitoring, or health monitoring, among other examples. Examples of sensing modes that may be employed in some examples of the techniques described herein are provided in FIG. 27.

[0213] In some examples, one or more of the AI / ML models described herein may correspond to one or more sensing KPIs (with equivalent A- AI / ML sensing or D-AI / ML sensing). Some examples of sensing KPIs may include an accuracy of positioning (e.g., horizontal or vertical), an accuracy of range or cross-range of target, an accuracy of AOA of a target (e.g., azimuth or elevation), an accuracy of velocity (e.g., horizontal or vertical), a sensing range or cross-range resolutions, a sensing velocity resolution, a sensing angle resolution, a sensing latency, a sensing refreshing rate, a receiverAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO66 operating characteristics (ROC) (e.g., misdetection or false alarm probabilities), a confidence interval or level of sensing, or target discrimination.

[0214] FIG. 5 shows examples of block diagrams 500 that support portions of AI / ML models in accordance with one or more aspects of the present disclosure. The block diagrams 500 illustrate examples of scenarios (e.g., a first scenario 505-a, a second scenario 505-b, a third scenario 505-c, a fourth scenario 505-d, and a fifth scenario 505-e) in which some of the techniques described herein may be utilized. One or more of the first devices 510-a, 510-b, 510-c, 510-d, 510-e illustrated in FIG. 5 may be examples of the first device 410 described with reference to FIG. 4. One or more of the second devices 520-b, 520-c, 520-d, 520-e illustrated in FIG. 5 may be examples of the device(s) 420 described with reference to FIG. 4. One or more of the network entities 530-a, 530-b, 530-c, 530-d, 530-e illustrated in FIG. 5 may be examples of the device(s) 420 described with reference to FIG. 4.

[0215] Each of the first devices 510-a, 510-b, 510-c, 510-d, 510-e may include a respective first portion 515-a, 515-b, 515-c, 515-d, 515-e of an AI / ML model. The first portions 515-a, 515-b, 515-c, 515-d, 515-e may be examples of the first portion 405 described with reference to FIG. 4. Each of the second devices 520-b, 520-c, 520-d, 520-e may include a respective second portion 525-b, 525-c, 525-d, 525-e of an AI / ML model. The second portions 525-b, 525-c, 525-d, 525-e may be examples of the portion(s) 430 described with reference to FIG. 4. Some of the network entities 530-a, 530-c, 530-e may include a respective second portion 525-a or third portion 535-c, 535-e of an AI / ML model. The second portion 525-a or third portions 535-c, 535-e may be examples of the portion(s) 430 described with reference to FIG. 4. The first information 540-a, 540-b, 540-c, 540-d, 540-e may be examples of the first information or position or measurement(s) described with reference to FIG. 4. The second information 545-c, 545-e or the position or measurement s) 550-b, 550-d may be examples of the second information or position or measurement(s) described with reference to FIG. 4.

[0216] In the first scenario 505-a, the first device 510-a includes a first portion 515-a of an AI / ML model and a network entity 530-a includes a second portion 525-a of the AI / ML model. In this example, the first device 510-a generates first information 540-a utilizing the first portion 515-a of the AI / ML model. The first information 540-aAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO67 is communicated to the network entity 530-a. The network entity 530-a may input the first information 540-a to the second portion 525-a of the AI / ML model to generate a position (e.g., position estimate) or measurement(s) of an object (e.g., the first device 510-a or another object) as described herein.

[0217] In the second scenario 505-b, the first device 510-b includes a first portion 515-b of an AI / ML model and the second device 520-b includes a second portion 525-b of the AI / ML model. In this example, the first device 510-b generates first information 540-b utilizing the first portion 515-b of the AI / ML model. The first information 540-b is communicated to the second device 520-b. The second device 520-b may input the first information 540-b to the second portion 525-b of the AI / ML model to generate a position or measurement(s) 550-b as described herein. The position or measurement(s) 550-b may be communicated to the network entity 530-b.

[0218] In the third scenario 505-c, the first device 510-c includes a first portion 515-c of an AI / ML model, the second device 520-c includes a second portion 525-c of the AI / ML model, and the network entity 530-c includes a third portion 535-c of the AI / ML model. In this example, the first device 510-c generates first information 540-c utilizing the first portion 515-c of the AI / ML model. The first information 540-c is communicated to the second device 520-c. The second device 520-c may input the first information 540-c to the second portion 525-c of the AI / ML model to generate second information 545-c as described herein. The second information 545-c may be communicated to the network entity 530-c. The network entity 530-c may input the second information 545-c to the third portion 535-c of the AI / ML model to generate a position (e.g., position estimate) or measurement(s) of an object (e.g., the first device 510-c or another object) as described herein.

[0219] In the fourth scenario 505-d, the first device 510-d includes a first portion 515-d of an AI / ML model and the second device 520-d includes a second portion 525-d of the AI / ML model. In this example, the first device 510-d generates first information 540-d utilizing the first portion 515-d of the AI / ML model. The first information 540-d is communicated to the second device 520-d. The second device 520-d may input the first information 540-d to the second portion 525-d of the AI / ML model to generate a position or measurement(s) 550-d as described herein. The position or measurement(s) 550-d may be communicated to the first device 510-d. The first device 510-d mayAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO68 communicate (e.g., relay) the position or measurement s) 555-d to the network entity 530-d.

[0220] In the fifth scenario 505-e, the first device 510-e includes a first portion 515-e of an AI / ML model and the second device 520-e includes a second portion 525-e of the AI / ML model. In this example, the first device 510-e generates first information 540-e utilizing the first portion 515-e of the AI / ML model. The first information 540-e is communicated to the second device 520-e. The second device 520-e may input the first information 540-e to the second portion 525-e of the AI / ML model to generate second information 545-e as described herein. The second information 545-e may be communicated to the first device 510-e. The first device 510-e may communicate (e.g., relay) the second information 560-e to the network entity 530-e. The network entity 530-e may input the second information 560-e to the third portion 535-e of the AI / ML model to generate a position (e.g., position estimate) or measurement s) of an object (e.g., the first device 510-e or another object) as described herein.

[0221] FIG. 6 shows an example of a process flow 600 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The process flow 600 may include a first device 410-a, which may be an example of a UE 115, UE 115-a, UE 115-b, or first device 410, as described herein. The process flow 600 may also include a second device 420-a, which may be an example of a UE 115, UE 115-a, UE 115-b, a network node 105, network entity, gNB 255, CU 160-a, DU 165-a, RU 165-a, TRP, location server 185, LMF 265, external device 230, SLP 235, SnMF, or one or more devices 420 as described herein. In some approaches, second device 420-a may communicate with the first device 410-a via one or more network nodes (e.g., base station(s), TRP(s), CU(s), DU(s), or RU(s), among other examples).

[0222] In the following description of the process flow 600, the communications between the first device 410-a and the second device 420-a may be transmitted in a different order than the example order shown, or the operations performed by the first device 410-a or the second device 420-a may be performed in different orders or at different times. One or more operations may be omitted from the process flow 600, or one or more other operations may be added to the process flow 600. Although some operations or signaling may be shown to occur at different times for discussionAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO69 purposes, these operations may actually occur at the same time or in overlapping time periods in some examples.

[0223] In some examples, the first device 410-a and the second device 420-a may communicate information (e.g., capability information, configuration information, position data, measurement data, or requests for location or measurements, among other examples) via a network node or independent of a network node. In some examples, the first device 410-a and a network node may communicate information (e.g., capability information, configuration information, position data, measurement data, or requests for location or measurements, among other examples), where the information may be relayed transparently via the network node, may be processed by the network node before communication to the second device 420-a or the first device 410-a, or may not be transmitted to the second device 420-a or the first device 410-a.

[0224] At 605, the first device 410-a may transmit capability information to the second device 420-a. For instance, the capability information may be transmitted to the second device 420-a as described with reference to FIG. 4. In some examples, the second device 420-a may output (e.g., transmit) configuration information to the first device 410-a based on (e.g., in accordance with) the capability information.

[0225] At 610, the first device 410-a may generate first information associated with a position of an object. For instance, the first device 410-a may execute a first portion of an AI / ML model to generate the first information as described with reference to FIG. 4 or FIG. 5.

[0226] At 615, the first device 410-a may output (e.g., transmit), to the second device 420-a, the first information. For instance, the second device 420-a may transmit the first information as described with reference to FIG. 4 or FIG. 5.

[0227] FIG. 7 shows an example of a process flow 700 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The process flow 700 may include a first device 410-b, which may be an example of a UE 115, UE 115-a, UE 115-b, or first device 410, as described herein. The process flow 700 may also include a second device 420-b, which may be an example of a UE 115, UE 115-a, UE 115-b, a network node 105, gNB 255, CU 160-a, DU 165-a, RU 165-a, TRP, or one or more devices 420 as described herein. The process flow 700 may also includeAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO70 a network entity 420-c, which may be an example of a network node 105, network entity, gNB 255, CU 160-a, DU 165-a, RU 165-a, TRP, location server 185, LMF 265, external device 230, SLP 235, SnMF, or one or more devices 420 as described herein. In some approaches, the first device 410-b, the second device 420-b, or the network entity 420-c may communicate via one or more network nodes (e.g., base station(s), TRP(s), CU(s), DU(s), or RU(s), among other examples).

[0228] In the following description of the process flow 700, the communications between the first device 410-b, the second device 420-b, or the network entity 420-c may be transmitted in a different order than the example order shown, or the operations performed by the first device 410-b, the second device 420-b, or the network entity 420-c may be performed in different orders or at different times. One or more operations may be omitted from the process flow 700, or one or more other operations may be added to the process flow 700. Although some operations or signaling may be shown to occur at different times for discussion purposes, these operations may actually occur at the same time or in overlapping time periods in some examples.

[0229] In some examples, the first device 410-b and the network entity 420-c may communicate information (e.g., capability information, configuration information, position data, measurement data, or requests for location or measurements, among other examples) via the second device 420-b or independent of the second device 420-b. In some examples, the first device 410-b and the second device 420-b may communicate information (e.g., capability information, configuration information, position data, measurement data, or requests for location or measurements, among other examples), where the information may be relayed transparently via the second device 420-b, may be processed by the second device 420-b before communication to the network entity 420-c or the first device 410-b, or may not be transmitted to the network entity 420-c or the first device 410-b.

[0230] At 705, the first device 410-b may transmit first information to the second device 420-b. For instance, the first information may be transmitted to the network entity 420-c as described with reference to FIG. 4 or FIG. 5.

[0231] At 710, the second device 420-b may generate second information associated with a position of an object. For instance, the second device 420-b execute a secondAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO71 portion an of AI / ML model based on the first information to generate the second information as described with reference to FIG. 4 or FIG. 5.

[0232] At 715, the second device 420-b may output (e.g., transmit), to the network entity 420-c, second information. For instance, the second device 420-b may transmit the second information to the network entity 420-c as described with reference to FIG. 4. In some examples, the second information may indicate that a position or measurements (e.g., inferred position or measurements) of the object (e.g., first device 410-b or another object).

[0233] FIG. 8 shows an example of a process flow 800 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The process flow 800 may include a first device 410-c, which may be an example of a UE 115, UE 115-a, UE 115-b, or first device 410, as described herein. The process flow 700 may also include a second device 420-d, which may be an example of a UE 115, UE 115-a, UE 115-b, a network node 105, gNB 255, CU 160-a, DU 165-a, RU 165-a, TRP, or one or more devices 420 as described herein. The process flow 700 may also include a network entity 420-e, which may be an example of a network node 105, network entity, gNB 255, CU 160-a, DU 165-a, RU 165-a, TRP, location server 185, LMF 265, external device 230, SLP 235, SnMF, or one or more devices 420 as described herein. In some approaches, the first device 410-c, the second device 420-d, or the network entity 420-e may communicate via one or more network nodes (e.g., base station(s), TRP(s), CU(s), DU(s), or RU(s), among other examples).

[0234] In the following description of the process flow 800, the communications between the first device 410-c, the second device 420-d, and the network entity 420-e may be transmitted in a different order than the example order shown, or the operations performed by the first device 410-c, the second device 420-d, or the network entity 420-e may be performed in different orders or at different times. One or more operations may be omitted from the process flow 800, or one or more other operations may be added to the process flow 800. Although some operations or signaling may be shown to occur at different times for discussion purposes, these operations may actually occur at the same time or in overlapping time periods in some examples.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO72

[0235] In some examples, the first device 410-c, the second device 420-d, and the network entity 420-e may communicate information (e.g., capability information, configuration information, position data, measurement data, or requests for location or measurements, among other examples) via a network node or independent of a network node. In some examples, the first device 410-c, the second device 420-d, the network entity 420-e, or a network node may communicate information (e.g., capability information, configuration information, position data, measurement data, or requests for location or measurements, among other examples), where the information may be relayed transparently via the network node, may be processed by the network node before communication to the network entity 420-e, to the second device 420-d, or to the first device 410-c, or may not be transmitted to the network entity 420-e, to the first device 410-c, or to the second device 420-d.

[0236] At 805, the first device 410-c may transmit capability information to the network entity 420-e. For instance, the capability information may be transmitted to the network entity 420-e as described with reference to FIG. 4. In some examples, the network entity 420-e may output (e.g., transmit) configuration information to the first device 410-c based on (e.g., in accordance with) the capability information.

[0237] At 810, the first device 410-c may transmit first information to the network entity 420-e. For instance, the first information may be transmitted to the network entity 420-e as described with reference to FIG. 4.

[0238] At 815, the second device 420-d may output (e.g., transmit), to the network entity 420-e, second information. For instance, the second device 420-d may transmit the second as described with reference to FIG. 4. In some examples, the network entity 420-e may execute a portion of an AI / ML model based on the first information or the second information to determine a position or measurement s) corresponding to a position of an object (e.g., the first device 410-c). In some aspects, the second information may be a position or measurement(s) corresponding to a position of an object (e.g., the first device 410-c).

[0239] FIG. 9 shows a block diagram 900 of a device 905 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The device 905 may be an example of aspects of a first device or a second device asAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO73 described herein. The device 905 may include a receiver 910, a transmitter 915, and a communications manager 920. The device 905, or one or more components of the device 905 (e.g., the receiver 910, the transmitter 915, the communications manager 920), may include at least one processor, which may be coupled with at least one memory, to, individually or collectively, support or enable the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses).

[0240] The receiver 910 may provide a means for receiving information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to portions of AI / ML models). Information may be passed on to other components of the device 905. The receiver 910 may utilize a single antenna or a set of multiple antennas.

[0241] The transmitter 915 may provide a means for transmitting signals generated by other components of the device 905. For example, the transmitter 915 may transmit information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to portions of AI / ML models). In some examples, the transmitter 915 may be co-located with a receiver 910 in a transceiver module. The transmitter 915 may utilize a single antenna or a set of multiple antennas.

[0242] The communications manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be examples of means for performing various aspects of portions of AI / ML models as described herein. For example, the communications manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be capable of performing one or more of the functions described herein.

[0243] In some examples, the communications manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry). The hardware may include at least one of a processor, a digital signal processor (DSP), a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field programmable gateAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO74 array (FPGA) or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure. In some examples, at least one processor and at least one memory coupled with the at least one processor may be configured to perform one or more of the functions described herein (e.g., by one or more processors, individually or collectively, executing instructions stored in the at least one memory).

[0244] Additionally, or alternatively, the communications manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be implemented in code (e.g., as communications management software or firmware) executed by at least one processor (e.g., referred to as a processor-executable code). If implemented in code executed by at least one processor, the functions of the communications manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be performed by a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices (e.g., configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure).

[0245] In some examples, the communications manager 920 may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 910, the transmitter 915, or both. For example, the communications manager 920 may receive information from the receiver 910, send information to the transmitter 915, or be integrated in combination with the receiver 910, the transmitter 915, or both to obtain information, output information, or perform various other operations as described herein.

[0246] For example, the communications manager 920 is capable of, configured to, or operable to support a means for transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The communications manager 920 is capable of, configured to, or operable to support a means for generating first information associated with a position of an object, where the first information is an output of a first portion of theAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO75AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device.

[0247] For example, the communications manager 920 is capable of, configured to, or operable to support a means for obtaining, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure. The communications manager 920 is capable of, configured to, or operable to support a means for generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device.

[0248] By including or configuring the communications manager 920 in accordance with examples as described herein, the device 905 (e.g., at least one processor controlling or otherwise coupled with the receiver 910, the transmitter 915, the communications manager 920, or a combination thereof) may support techniques for reduced processing, reduced power consumption, or more efficient utilization of communication resources.

[0249] FIG. 10 shows a block diagram 1000 of a device 1005 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The device 1005 may be an example of aspects of a device 905, a first device or a second device as described herein. The device 1005 may include a receiver 1010, a transmitter 1015, and a communications manager 1020. The device 1005, or one or more components of the device 1005 (e.g., the receiver 1010, the transmitter 1015, the communications manager 1020), may include at least one processor, which may be coupled with at least one memory, to support the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses).

[0250] The receiver 1010 may provide a means for receiving information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, informationAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO76 channels related to portions of AI / ML models). Information may be passed on to other components of the device 1005. The receiver 1010 may utilize a single antenna or a set of multiple antennas.

[0251] The transmitter 1015 may provide a means for transmitting signals generated by other components of the device 1005. For example, the transmitter 1015 may transmit information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to portions of AI / ML models). In some examples, the transmitter 1015 may be co-located with a receiver 1010 in a transceiver module. The transmitter 1015 may utilize a single antenna or a set of multiple antennas.

[0252] The device 1005, or various components thereof, may be an example of means for performing various aspects of portions of AI / ML models as described herein. For example, the communications manager 1020 may include a capability component 1025, a generation component 1030, an information component 1035, or any combination thereof. The communications manager 1020 may be an example of aspects of a communications manager 920 as described herein. In some examples, the communications manager 1020, or various components thereof, may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 1010, the transmitter 1015, or both. For example, the communications manager 1020 may receive information from the receiver 1010, send information to the transmitter 1015, or be integrated in combination with the receiver 1010, the transmitter 1015, or both to obtain information, output information, or perform various other operations as described herein.

[0253] The capability component 1025 is capable of, configured to, or operable to support a means for transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The generation component 1030 is capable of, configured to, or operable to support a means for generating first information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output ofAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO77 the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device.

[0254] The information component 1035 is capable of, configured to, or operable to support a means for obtaining, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure. The generation component 1030 is capable of, configured to, or operable to support a means for generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device.

[0255] FIG. 11 shows a block diagram 1100 of a communications manager 1120 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The communications manager 1120 may be an example of aspects of a communications manager 920, a communications manager 1020, or both, as described herein. The communications manager 1120, or various components thereof, may be an example of means for performing various aspects of portions of AI / ML models as described herein. For example, the communications manager 1120 may include a capability component 1125, a generation component 1130, an information component 1135, a reference signal component 1140, a measurement component 1145, a model component 1150, a configuration component 1155, or any combination thereof. Each of these components, or components or subcomponents thereof (e.g., one or more processors, one or more memories), may communicate, directly or indirectly, with one another (e.g., via one or more buses).

[0256] The capability component 1125 is capable of, configured to, or operable to support a means for transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The generation component 1130 is capable of, configured to, or operable to support a means for generating first information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output ofAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO78 the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device.

[0257] In some examples, the information component 1135 is capable of, configured to, or operable to support a means for transmitting, to a second device, the first information associated with the position of the object.

[0258] In some examples, the reference signal component 1140 is capable of, configured to, or operable to support a means for receiving a reference signal, where the one or more measurements are of the reference signal.

[0259] In some examples, the measurement component 1145 is capable of, configured to, or operable to support a means for obtaining the one or more measurements via one or more sensors, the one or more measurements including a range measurement, a Doppler measurement, a velocity measurement, an angle measurement, or a position measurement associated with the object.

[0260] In some examples, the AI / ML model includes the first portion and a second portion. In some examples, the first portion includes one or more first nodes, one or more first layers, one or more first residual blocks, one or more first attention mechanism stages, a first portion of a graph structure, or a combination thereof. In some examples, the second portion includes one or more second nodes, one or more second layers, one or more second residual blocks, one or more second attention mechanism stages, a second portion of a graph structure, or a combination thereof.

[0261] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for obtaining, from the second device, model information indicating the AI / ML model or the first portion of the AI / ML model, where the second device is a wireless device or a network entity.

[0262] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for obtaining, from the second device, an indication of the one or more portions of the AI / ML model.

[0263] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for transmitting, to the second device, model informationAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO79 indicating the AI / ML model or a second portion of the AI / ML model, where the second device is a wireless device or a network entity.

[0264] In some examples, the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

[0265] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for communicating an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and a second portion of the AI / ML model, where the location of the split is associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.

[0266] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for transmitting an indication of a reason for portioning the AI / ML model, where the reason is associated with a memory limit, a processing limit, a battery level, or a combination thereof.

[0267] In some examples, the configuration component 1155 is capable of, configured to, or operable to support a means for obtaining configuration information that indicates one or more candidate devices for offloading processing associated with a second portion of the AI / ML model, where the second device is one of the one or more candidate devices.

[0268] In some examples, the configuration component 1155 is capable of, configured to, or operable to support a means for obtaining configuration information that indicates one or more locations to split the AI / ML model, where the one or more portions of the AI / ML model are associated with the one or more locations.

[0269] In some examples, the configuration component 1155 is capable of, configured to, or operable to support a means for obtaining configuration informationAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO80 that indicates the first portion of the AI / ML model for generation of the first information.

[0270] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for transmitting an indication of the first portion of the AI / ML model or a second portion of the AI / ML model.

[0271] In some examples, the information component 1135 is capable of, configured to, or operable to support a means for obtaining, from the second device, second information indicating an output of a second portion of the AI / ML model based on the first information. In some examples, the information component 1135 is capable of, configured to, or operable to support a means for transmitting, to a network entity, the second information.

[0272] In some examples, the second information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0273] In some examples, the first information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0274] The information component 1135 is capable of, configured to, or operable to support a means for obtaining, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure. In some examples, the generation component 1130 is capable of, configured to, or operable to support a means for generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO81

[0275] In some examples, the information component 1135 is capable of, configured to, or operable to support a means for transmitting the second information associated with the position of the object.

[0276] In some examples, the first portion includes one or more first nodes, one or more first layers, one or more first residual blocks, one or more first attention mechanism stages, a first portion of a graph structure, or a combination thereof. In some examples, the second portion includes one or more second nodes, one or more second layers, one or more second residual blocks, one or more second attention mechanism stages, a second portion of a graph structure, or a combination thereof.

[0277] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for transmitting, to the first device, model information indicating the AI / ML model or the first portion of the AI / ML model, where the second device is a wireless device or a network entity.

[0278] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for transmitting, to the first device, an indication of one or more portions of the AI / ML model.

[0279] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for obtaining, from the first device, model information indicating the AI / ML model or a second portion of the AI / ML model, where the second device is a wireless device or a network entity.

[0280] In some examples, the capability component 1125 is capable of, configured to, or operable to support a means for transmitting capability information of the second device that indicates a capability of the second device to process one or more portions of the AI / ML model at the second device, where the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO82

[0281] In some examples, the reference signal component 1140 is capable of, configured to, or operable to support a means for communicating an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and the second portion of the AI / ML model, where the location of the split is associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.

[0282] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for obtaining an indication of a reason for portioning the AI / ML model, where the reason is associated with a memory limit, a processing limit, a battery level, or a combination thereof.

[0283] In some examples, the configuration component 1155 is capable of, configured to, or operable to support a means for obtaining configuration information that indicates one or more candidate devices for offloading processing associated with a second portion of the AI / ML model, where the second device is one or the one or more candidate devices.

[0284] In some examples, the configuration component 1155 is capable of, configured to, or operable to support a means for obtaining configuration information that indicates one or more locations to split the AI / ML model, where one or more portions of the AI / ML model are associated with the one or more locations.

[0285] In some examples, the configuration component 1155 is capable of, configured to, or operable to support a means for obtaining configuration information that indicates the second portion of the AI / ML model to generate the second information.

[0286] In some examples, the model component 1150 is capable of, configured to, or operable to support a means for transmitting an indication of the second portion of the AI / ML model to the first wireless device or to a network entity.

[0287] In some examples, the second information indicating the output of the second portion of the AI / ML model is transmitted to the first device or to a network entity.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO83

[0288] In some examples, the second information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0289] FIG. 12 shows a diagram of a system 1200 including a device 1205 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The device 1205 may be an example of or include components of a device 905, a device 1005, or a first device 410 as described herein. The device 1205 may include components for bi-directional voice and data communications including components for transmitting and receiving communications, such as a communications manager 1220, an I / O controller, such as an I / O controller 1210, one or more transceivers 1215, one or more antennas 1225, at least one memory 1230, code 1235, and at least one processor 1240. The device 1205 may include one or more sensors 1250. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., a bus 1245). The I / O controller 1210 may manage input and output signals for the device 1205. The I / O controller 1210 may also manage peripherals not integrated into the device 1205. In some cases, the I / O controller 1210 may represent a physical connection or port to an external peripheral. In some cases, the I / O controller 1210 may utilize an operating system such as iOS®, ANDROID®, MS-DOS®, MS- WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. Additionally, or alternatively, the I / O controller 1210 may represent or interact with a modem, a keyboard, a mouse, a touchscreen, or a similar device. In some cases, the I / O controller 1210 may be implemented as part of one or more processors, such as the at least one processor 1240. In some cases, a user may interact with the device 1205 via the I / O controller 1210 or via hardware components controlled by the I / O controller 1210.

[0290] In some cases, the device 1205 may include a single antenna. However, in some other cases, the device 1205 may have more than one antenna, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver(s) 1215 may communicate bi-directionally via the one or more antennas 1225 using wired or wireless links as described herein. For example, the transceiverAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO841215 may represent a wireless transceiver and may communicate bi-directionally with another wireless transceiver. The transceiver 1215 may also include a modem to modulate the packets, to provide the modulated packets to one or more antennas 1225 for transmission, and to demodulate packets received from the one or more antennas 1225. The transceiver 1215, or the transceiver 1215 and one or more antennas 1225, may be an example of a transmitter 915, a transmitter 1015, a receiver 910, a receiver 1010, or any combination thereof or component thereof, as described herein.

[0291] The one or more transceivers 1215 may include one or more wireless wide area network (WWAN) transceivers, one or more short-range wireless transceivers, or one or more satellite transceivers. The WWAN transceiver(s) may communicate with (e.g., transmit one or more signals to, or receive one or more signals from) one or more wireless communication networks, such as an NR network, an LTE network, or a GSM network, among other examples. The WWAN transceiver(s) may be connected to one or more of the antenna(s) 1225 for communicating with other devices, such as one or more UEs 115, network nodes 105, access points, base stations (e.g., eNBs, gNBs), or another device(s), via at least one RAT (e.g., NR, LTE, or GSM, among other examples) over a wireless communication medium (e.g., time or frequency resources of a frequency spectrum). The WWAN transceiver(s) may be configured for transmitting and encoding signals (e.g., messages, indications, or information, among other examples) or for receiving and decoding signals (e.g., messages, indications, information, or pilots, among other examples), in accordance with the RAT. For instance, the WWAN transceiver(s) may include one or more transmitters for transmitting and encoding signals, or one or more receivers for receiving and decoding signals.

[0292] The short-range wireless transceivers may be connected to one or more of the antenna(s) 1225 to communicate with (e.g., transmit one or more signals to, or receive one or more signals from) one or more network entities, such as one or more UEs 115, network nodes 105, access points, base stations, or another device(s), via at least one RAT (e.g, Wi-Fi, LTE Direct, BLUETOOTH®, ZIGBEE®, Z-WAVE®, PC5, dedicated short-range communications (DSRC), wireless access for vehicular environments (WAVE), near-field communication (NFC), or ultra-wideband (UWB), among other examples) over a wireless communication medium. The short-range wireless transceiver(s) may be configured for transmitting and encoding signals (e.g.,Attorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO85 messages, indications, or information, among other examples), or for receiving and decoding signals (e.g., messages, indications, information, or pilots, among other examples), in accordance with the RAT. For instance, the short-range wireless transceiver(s) may include one or more transmitters for transmitting and encoding signals, or one or more receivers for receiving and decoding signals. In some examples, the short-range wireless transceiver s) may be one or more Wi-Fi transceivers, BLUETOOTH® transceivers, ZIGBEE® transceivers, Z-WAVE® transceivers, NFC transceivers, UWB transceivers, vehi cl e-to- vehicle (V2V) transceivers, or vehicle-to- everything (V2X) transceivers, among other examples.

[0293] The satellite transceiver(s) may include one or more satellite signal receivers, or one or more satellite signal transmitters. In some cases, the device 1205 may be a terrestrial device that may communicate one or more satellites via the satellite transceiver(s). In other cases, device 1205 may be a satellite (or other non-terrestrial entity) that uses the satellite transceiver(s) to communicate with one or more terrestrial networks or other satellites.

[0294] The satellite signal receiver(s) may be connected to one or more of the antenna(s) 1225 for receiving or measuring satellite positioning or communication signals. In some examples, the satellite signal receiver(s) may include one or more satellite positioning system receivers, where the satellite positioning or communication signals may be GPS signals, GLONASS signals, Galileo signals, BeiDou signals, Indian Regional Navigation Satellite System (NAVIC), or Quasi-Zenith Satellite System (QZSS) signals, among other examples. In some examples, the satellite signal receiver(s) may include one or more NTN receivers, where the satellite positioning or communication signals may be communication signals (e.g., carrying control or user data) originating from a device or network. The satellite signal receiver(s) may include hardware or a combination of hardware and instructions for receiving and processing satellite positioning or communication signals. The satellite signal receiver(s) or the processor 1240 may perform calculations to determine a location of the device 1205, the UE 115, the network node 105, or another device using measurements obtained from one or more satellite signals.

[0295] The one or more satellite signal transmitters may be connected to one or more of the antennas 1225 for transmitting satellite positioning communication signals.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO86In some examples, the satellite signal transmitter(s) may be satellite positioning system transmitters, and the satellite positioning or communication signals may be GPS signals, GLONASS® signals, Galileo signals, BeiDou signals, NAVIC, or QZSS signals, among other examples. In some examples, the satellite signal transmitter(s) include one or more NTN transmitters, and the satellite positioning or communication signals may be communication signals (e.g., carrying control or user data). The satellite signal transmitter(s) may comprise hardware or a combination of hardware and instructions for transmitting satellite positioning or communication signals.

[0296] The device 1205 may include one or more sensors 1250 coupled with the one or more processors 1240 for obtaining sensor data (e.g., image data, RF data, motion data, orientation data, or audio data, among other examples). For example, the one or more sensors 1250 may sense or detect movement or orientation information. In some aspects, the movement or orientation information may be independent from motion data derived from signals received by the one or more WWAN transceivers, the one or more short-range wireless transceivers, or the satellite signal interface. In some examples, the sensor(s) 1250 may include an accelerometer (e.g., a micro-electrical mechanical systems (MEMS) device), a gyroscope, a geomagnetic sensor (e.g., a compass), an altimeter (e.g., a barometric pressure altimeter), or any other type of movement detection sensor. Additionally, or alternatively, the one or more sensors 1250 may include an image sensor, camera, microphone, light detector, or pressure sensor, among other examples. In some aspects, the sensor(s) 1250 may include a plurality of different types of devices, and the device 1205 (e.g., sensor(s) or 1250 processor(s) 1240) may combine the outputs of the different types of devices to provide motion information. For example, the sensor(s) 1250 may use a combination of a multi-axis accelerometer sensors, orientation sensors, or image sensors to provide the ability to compute positions in two-dimensional (2D) or three-dimensional (3D) coordinate systems.

[0297] The at least one memory 1230 may include RAM and ROM. The at least one memory 1230 may store computer-readable, computer-executable, or processorexecutable code, such as the code 1235. The code 1235 may include instructions that, when executed by the at least one processor 1240, cause the device 1205 to perform various functions described herein. The code 1235 may be stored in a non-transitoryAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO87 computer-readable medium such as system memory or another type of memory. In some cases, the code 1235 may not be directly executable by the at least one processor 1240 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some cases, the at least one memory 1230 may include, among other things, a BIOS which may control basic hardware or software operation such as the interaction with peripheral components or devices.

[0298] The at least one processor 1240 may include one or more intelligent hardware devices (e.g., one or more general-purpose processors, one or more DSPs, one or more CPUs, one or more graphics processing units (GPUs), one or more neural processing units (NPUs) (also referred to as neural network processors or deep learning processors (DLPs)), one or more microcontrollers, one or more ASICs, one or more FPGAs, one or more programmable logic devices, discrete gate or transistor logic, one or more discrete hardware components, or any combination thereof). In some cases, the at least one processor 1240 may be configured to operate a memory array using a memory controller. In some other cases, a memory controller may be integrated into the at least one processor 1240. The at least one processor 1240 may be configured to execute computer-readable instructions stored in a memory (e.g., the at least one memory 1230) to cause the device 1205 to perform various functions (e.g., functions or tasks supporting signaling for sample-based position estimation). For example, the device 1205 or a component of the device 1205 may include at least one processor 1240 and at least one memory 1230 coupled with or to the at least one processor 1240, the at least one processor 1240 and the at least one memory 1230 configured to perform various functions described herein.

[0299] In some examples, the at least one processor 1240 may include multiple processors and the at least one memory 1230 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions described herein. In some examples, the at least one processor 1240 may be a component of a processing system, which may refer to a system (such as a series) of machines, circuitry (including, for example, one or both of processor circuitry (which may include the at least one processor 1240) and memory circuitry (which may include the at least one memory 1230)), or components, that receives or obtains inputs andAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO88 processes the inputs to produce, generate, or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. For example, the at least one processor 1240 or a processing system including the at least one processor 1240 may be configured to, configurable to, or operable to cause the device 1205 to perform one or more of the functions described herein. Further, as described herein, being “configured to,” being “configurable to,” and being “operable to” may be used interchangeably and may be associated with a capability, when executing code 1235 (e.g., processor-executable code) stored in the at least one memory 1230 or otherwise, to perform one or more of the functions described herein.

[0300] For example, the communications manager 1220 is capable of, configured to, or operable to support a means for receiving a request that the wireless device is to report a set of one or more measurements. The communications manager 1220 is capable of, configured to, or operable to support a means for receiving a reference signal, where the wireless device generates the set of one or more measurements based on the reference signal, and where the set of one or more measurements is associated with a time period. The communications manager 1220 is capable of, configured to, or operable to support a means for transmitting a first indication of a reference time of the reference signal, where the first indication of the reference time of the reference signal is based on the set of one or more measurements of the reference signal associated with the time period. The communications manager 1220 is capable of, configured to, or operable to support a means for transmitting a second indication of a set of one or more signal samples that have a temporal association with the reference time of the reference signal, where individual ones of the set of one or more signal samples are distributed in accordance with a uniform spacing or a subsampled uniform spacing.

[0301] By including or configuring the communications manager 1220 in accordance with examples as described herein, the device 1205 may support techniques for enhanced positioning accuracy, improved communication reliability, reduced latency, reduced power consumption, more efficient utilization of communication resources, improved coordination between devices, longer battery life, or improved utilization of processing capability.

[0302] In some examples, the communications manager 1220 may be configured to perform various operations (e.g., receiving, monitoring, transmitting) using or otherwiseAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO89 in cooperation with the transceiver 1215, the one or more antennas 1225, or any combination thereof. Although the communications manager 1220 is illustrated as a separate component, in some examples, one or more functions described with reference to the communications manager 1220 may be supported by or performed by the at least one processor 1240, the at least one memory 1230, the code 1235, or any combination thereof. For example, the code 1235 may include instructions executable by the at least one processor 1240 to cause the device 1205 to perform various aspects of signaling for sample-based position estimation as described herein, or the at least one processor 1240 and the at least one memory 1230 may be otherwise configured to, individually or collectively, perform or support such operations.

[0303] FIG. 13 shows a block diagram 1300 of a device 1305 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The device 1305 may be an example of aspects of a network entity as described herein. The device 1305 may include a receiver 1310, a transmitter 1315, and a communications manager 1320. The device 1305, or one or more components of the device 1305 (e.g., the receiver 1310, the transmitter 1315, the communications manager 1320), may include at least one processor, which may be coupled with at least one memory, to, individually or collectively, support or enable the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses).

[0304] The receiver 1310 may provide a means for obtaining (e.g., receiving, determining, identifying) information such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack). Information may be passed on to other components of the device 1305. In some examples, the receiver 1310 may support obtaining information by receiving signals via one or more antennas. Additionally, or alternatively, the receiver 1310 may support obtaining information by receiving signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof.

[0305] The transmitter 1315 may provide a means for outputting (e.g., transmitting, providing, conveying, sending) information generated by other components of the device 1305. For example, the transmitter 1315 may output information such as userAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO90 data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack). In some examples, the transmitter 1315 may support outputting information by transmitting signals via one or more antennas. Additionally, or alternatively, the transmitter 1315 may support outputting information by transmitting signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1315 and the receiver 1310 may be co-located in a transceiver, which may include or be coupled with a modem.

[0306] The communications manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be examples of means for performing various aspects of portions of AI / ML models as described herein. For example, the communications manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be capable of performing one or more of the functions described herein.

[0307] In some examples, the communications manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry). The hardware may include at least one of a processor, a DSP, a CPU, an ASIC, an FPGA or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure. In some examples, at least one processor and at least one memory coupled with the at least one processor may be configured to perform one or more of the functions described herein (e.g., by one or more processors, individually or collectively, executing instructions stored in the at least one memory).

[0308] Additionally, or alternatively, the communications manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be implemented in code (e.g., as communications management software or firmware) executed by at least one processor (e.g., referred to as a processor-executable code). If implemented in code executed by at least one processor, the functions of theAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO91 communications manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be performed by a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices (e.g., configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure).

[0309] In some examples, the communications manager 1320 may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 1310, the transmitter 1315, or both. For example, the communications manager 1320 may receive information from the receiver 1310, send information to the transmitter 1315, or be integrated in combination with the receiver 1310, the transmitter 1315, or both to obtain information, output information, or perform various other operations as described herein.

[0310] For example, the communications manager 1320 is capable of, configured to, or operable to support a means for obtaining capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The communications manager 1320 is capable of, configured to, or operable to support a means for obtaining first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model.

[0311] By including or configuring the communications manager 1320 in accordance with examples as described herein, the device 1305 (e.g., at least one processor controlling or otherwise coupled with the receiver 1310, the transmitter 1315, the communications manager 1320, or a combination thereof) may support techniques for reduced processing, reduced power consumption, or more efficient utilization of communication resources.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO92

[0312] FIG. 14 shows a block diagram 1400 of a device 1405 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The device 1405 may be an example of aspects of a device 1305 or a network entity as described herein. The device 1405 may include a receiver 1410, a transmitter 1415, and a communications manager 1420. The device 1405, or one or more components of the device 1405 (e.g., the receiver 1410, the transmitter 1415, the communications manager 1420), may include at least one processor, which may be coupled with at least one memory, to support the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses).

[0313] The receiver 1410 may provide a means for obtaining (e.g., receiving, determining, identifying) information such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack). Information may be passed on to other components of the device 1405. In some examples, the receiver 1410 may support obtaining information by receiving signals via one or more antennas. Additionally, or alternatively, the receiver 1410 may support obtaining information by receiving signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof.

[0314] The transmitter 1415 may provide a means for outputting (e.g., transmitting, providing, conveying, sending) information generated by other components of the device 1405. For example, the transmitter 1415 may output information such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack). In some examples, the transmitter 1415 may support outputting information by transmitting signals via one or more antennas. Additionally, or alternatively, the transmitter 1415 may support outputting information by transmitting signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1415 and the receiver 1410 may be co-located in a transceiver, which may include or be coupled with a modem.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO93

[0315] The device 1405, or various components thereof, may be an example of means for performing various aspects of portions of AI / ML models as described herein. For example, the communications manager 1420 may include a capability manager 1425 an information manager 1430, or any combination thereof. The communications manager 1420 may be an example of aspects of a communications manager 1320 as described herein. In some examples, the communications manager 1420, or various components thereof, may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 1410, the transmitter 1415, or both. For example, the communications manager 1420 may receive information from the receiver 1410, send information to the transmitter 1415, or be integrated in combination with the receiver 1410, the transmitter 1415, or both to obtain information, output information, or perform various other operations as described herein.

[0316] The capability manager 1425 is capable of, configured to, or operable to support a means for obtaining capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The information manager 1430 is capable of, configured to, or operable to support a means for obtaining first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model.

[0317] FIG. 15 shows a block diagram 1500 of a communications manager 1520 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The communications manager 1520 may be an example of aspects of a communications manager 1320, a communications manager 1420, or both, as described herein. The communications manager 1520, or various components thereof, may be an example of means for performing various aspects of portions of AI / ML models as described herein. For example, the communications manager 1520 may include a capability manager 1525, an information manager 1530, a generation manager 1535, a model manager 1540, a configuration manager 1545, or any combinationAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO94 thereof. Each of these components, or components or subcomponents thereof (e.g., one or more processors, one or more memories), may communicate, directly or indirectly, with one another (e.g., via one or more buses). The communications may include communications within a protocol layer of a protocol stack, communications associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack, within a device, component, or virtualized component associated with a network entity, between devices, components, or virtualized components associated with a network entity), or any combination thereof.

[0318] The capability manager 1525 is capable of, configured to, or operable to support a means for obtaining capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The information manager 1530 is capable of, configured to, or operable to support a means for obtaining first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model.

[0319] In some examples, to support method, the generation manager 1535 is capable of, configured to, or operable to support a means for generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the network entity.

[0320] In some examples, to support method, the generation manager 1535 is capable of, configured to, or operable to support a means for generating third information associated with the position of the object, where the third information is an output of a third portion of the AI / ML model based on the second information input to the third portion of the AI / ML model at the network entity.

[0321] In some examples, the model manager 1540 is capable of, configured to, or operable to support a means for transmitting, to the first device or a second device,Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO95 model information indicating the AI / ML model, the first portion of the AI / ML model, or the second portion of the AI / ML model.

[0322] In some examples, the model manager 1540 is capable of, configured to, or operable to support a means for transmitting, to the first device or a second device, an indication of the one or more portions of the AI / ML model.

[0323] In some examples, the model manager 1540 is capable of, configured to, or operable to support a means for obtaining, from the first device or a second device, model information indicating the AI / ML model, the first portion of the AI / ML model, or the second portion of the AI / ML model.

[0324] In some examples, the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

[0325] In some examples, the capability manager 1525 is capable of, configured to, or operable to support a means for obtaining capability information of a second device that indicates a capability of the second device to process one or more portions of the AI / ML model at the second device, where the capability information of the second device indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

[0326] In some examples, the model manager 1540 is capable of, configured to, or operable to support a means for communicating an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and the second portion of the AI / ML model, where the location of the split is associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO96

[0327] In some examples, the model manager 1540 is capable of, configured to, or operable to support a means for obtaining an indication of a reason for portioning the AI / ML model, where the reason is associated with a memory limit, a processing limit, a battery level, or a combination thereof.

[0328] In some examples, the configuration manager 1545 is capable of, configured to, or operable to support a means for transmitting configuration information that indicates one or more candidate devices for offloading processing associated with the second portion of the AI / ML model.

[0329] In some examples, the configuration manager 1545 is capable of, configured to, or operable to support a means for transmitting configuration information that indicates one or more locations to split the AI / ML model, where the one or more portions of the AI / ML model are associated with the one or more locations.

[0330] In some examples, the configuration manager 1545 is capable of, configured to, or operable to support a means for transmitting, to the first device or a second device, configuration information that indicates the first portion of the AI / ML model or the second portion of the AI / ML model.

[0331] In some examples, the first information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object, or the second information includes a latent representation of a reference signal measurement corresponding to the position of the object, an indication of the position of the object, or at least one measurement corresponding to the position of the object.

[0332] FIG. 16 shows a diagram of a system 1600 including a device 1605 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The device 1605 may be an example of or include components of a device 1305, a device 1405, or one or more devices 420 as described herein. The device 1605 may include components for bi-directional voice and data communications including components for transmitting and receiving communications, such as a communications manager 1620, one or more transceivers 1610, one or more antennas 1615, at least one memory 1625, code 1630, and at least one processor 1635. TheseAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO97 components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., a bus 1640).

[0333] The transceiver 1610 may support bi-directional communications via wired links, wireless links, or both as described herein. In some examples, the transceiver 1610 may include a wired transceiver and may communicate bi-directionally with another wired transceiver. Additionally, or alternatively, in some examples, the transceiver 1610 may include a wireless transceiver and may communicate bidirectionally with another wireless transceiver. In some examples, the device 1605 may include one or more antennas 1615, which may be capable of transmitting or receiving wireless transmissions (e.g., concurrently). The transceiver 1610 may also include a modem to modulate signals, to provide the modulated signals for transmission (e.g., by one or more antennas 1615, by a wired transmitter), to receive modulated signals (e.g., from one or more antennas 1615, from a wired receiver), and to demodulate signals. In some implementations, the transceiver 1610 may include one or more interfaces, such as one or more interfaces coupled with the one or more antennas 1615 that are configured to support various receiving or obtaining operations, or one or more interfaces coupled with the one or more antennas 1615 that are configured to support various transmitting or outputting operations, or a combination thereof. In some implementations, the transceiver 1610 may include or be configured for coupling with one or more processors or one or more memory components that are operable to perform or support operations based on received or obtained information or signals, or to generate information or other signals for transmission or other outputting, or any combination thereof. In some implementations, the transceiver 1610, or the transceiver 1610 and the one or more antennas 1615, or the transceiver 1610 and the one or more antennas 1615 and one or more processors or one or more memory components (e.g., the at least one processor 1635, the at least one memory 1625, or both), may be included in a chip or chip assembly that is installed in the device 1605. In some examples, the transceiver 1610 may be operable to support communications via one or more communications links (e.g., communication link(s) 125, backhaul communication link(s) 120, a midhaul communication link 162, a fronthaul communication link 168).Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO98

[0334] The one or more transceivers 1610 may include one or more WWAN transceivers, one or more short-range wireless transceivers, or one or more satellite transceivers. The WWAN transceiver(s) may communicate with (e.g., transmit one or more signals to, or receive one or more signals from) one or more wireless devices, such as the network node 105 or the UE 115, among other examples. The WWAN transceiver(s) may be connected to one or more of the antenna(s) 1615 for communicating with other devices, such as one or more UEs 115, network nodes 105, access points, base stations (e.g., eNBs, gNBs), or another device(s), via at least one RAT (e.g., NR, LTE, or GSM, among other examples) over a wireless communication medium (e.g., time or frequency resources of a frequency spectrum). The WWAN transceiver(s) may be configured for transmitting and encoding signals (e.g., messages, indications, or information, among other examples) or for receiving and decoding signals (e.g., messages, indications, information, or pilots, among other examples), in accordance with the RAT. For instance, the WWAN transceiver(s) may include one or more transmitters for transmitting and encoding signals, or one or more receivers for receiving and decoding signals.

[0335] The short-range wireless transceivers may be connected to one or more of the antenna(s) 1615 to communicate with (e.g., transmit one or more signals to, or receive one or more signals from) one or more network entities, such as one or more UEs 115, network nodes 105, access points, base stations, or another device(s), via at least one RAT (e.g, Wi-Fi, LTE Direct, BLUETOOTH®, ZIGBEE®, Z-WAVE®, PC5, DSRC, WAVE, NFC, or UWB, among other examples) over a wireless communication medium. The short-range wireless transceiver(s) may be configured for transmitting and encoding signals (e.g, messages, indications, or information, among other examples), or for receiving and decoding signals (e.g, messages, indications, information, or pilots, among other examples), in accordance with the RAT. For instance, the short-range wireless transceiver(s) may include one or more transmitters for transmitting and encoding signals, or one or more receivers for receiving and decoding signals. In some examples, the short-range wireless transceiver(s) may be one or more Wi-Fi transceivers, BLUETOOTH® transceivers, ZIGBEE® transceivers, Z- WAVE® transceivers, NFC transceivers, UWB transceivers, V2V transceivers, or V2X transceivers, among other examples.Attorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO99

[0336] The satellite transceiver(s) may include one or more satellite signal receivers, or one or more satellite signal transmitters. In some cases, the device 1605 may be a terrestrial device that may communicate one or more satellites via the satellite transceiver(s). In other cases, device 1605 may be a satellite (or other non-terrestrial entity) that uses the satellite transceiver(s) to communicate with one or more terrestrial networks or other satellites.

[0337] The satellite signal receiver(s) may be connected to one or more of the antenna(s) 1615 for receiving or measuring satellite positioning or communication signals. In some examples, the satellite signal receiver(s) may include one or more satellite positioning system receivers, where the satellite positioning or communication signals may be GPS signals, GLONASS signals, Galileo signals, BeiDou signals, NAVIC, or QZSS signals, among other examples. In some examples, the satellite signal receiver(s) may include one or more NTN receivers, where the satellite positioning or communication signals may be communication signals (e.g., carrying control or user data) originating from a device or network. The satellite signal receiver(s) may include hardware or a combination of hardware and instructions for receiving and processing satellite positioning or communication signals. The satellite signal receiver(s) or the processor 1635 may perform calculations to determine a location of the device 1605, the UE 115, the network node 105, or another device using measurements obtained from one or more satellite signals.

[0338] The one or more satellite signal transmitters may be connected to one or more of the antennas 1615 for transmitting satellite positioning communication signals. In some examples, the satellite signal transmitter(s) may be satellite positioning system transmitters, and the satellite positioning or communication signals may be GPS signals, GLONASS® signals, Galileo signals, BeiDou signals, NAVIC, or QZSS signals, among other examples. In some examples, the satellite signal transmitter(s) include one or more NTN transmitters, and the satellite positioning or communication signals may be communication signals (e.g., carrying control or user data). The satellite signal transmitter(s) may comprise hardware or a combination of hardware and instructions for transmitting satellite positioning or communication signals.

[0339] The at least one memory 1625 may include RAM, ROM, or any combination thereof. The at least one memory 1625 may store computer-readable, computer-Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO100 executable, or processor-executable code, such as the code 1630. The code 1630 may include instructions that, when executed by one or more of the at least one processor 1635, cause the device 1605 to perform various functions described herein. The code 1630 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, the code 1630 may not be directly executable by a processor of the at least one processor 1635 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some cases, the at least one memory 1625 may include, among other things, a BIOS which may control basic hardware or software operation such as the interaction with peripheral components or devices. In some examples, the at least one processor 1635 may include multiple processors and the at least one memory 1625 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories which may, individually or collectively, be configured to perform various functions herein (for example, as part of a processing system).

[0340] The at least one processor 1635 may include one or more intelligent hardware devices (e.g., one or more general-purpose processors, one or more DSPs, one or more CPUs, one or more graphics processing units (GPUs), one or more neural processing units (NPUs) (also referred to as neural network processors or deep learning processors (DLPs)), one or more microcontrollers, one or more ASICs, one or more FPGAs, one or more programmable logic devices, discrete gate or transistor logic, one or more discrete hardware components, or any combination thereof). In some cases, the at least one processor 1635 may be configured to operate a memory array using a memory controller. In some other cases, a memory controller may be integrated into one or more of the at least one processor 1635. The at least one processor 1635 may be configured to execute computer-readable instructions stored in a memory (e.g., one or more of the at least one memory 1625) to cause the device 1605 to perform various functions (e.g., functions or tasks supporting signaling for sample-based position estimation). For example, the device 1605 or a component of the device 1605 may include at least one processor 1635 and at least one memory 1625 coupled with one or more of the at least one processor 1635, the at least one processor 1635 and the at least one memory 1625 configured to perform various functions described herein. The at least one processor 1635 may be an example of a cloud-computing platform (e.g., oneAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO101 or more physical nodes and supporting software such as operating systems, virtual machines, or container instances) that may host the functions (e.g., by executing code 1630) to perform the functions of the device 1605. The at least one processor 1635 may be any one or more suitable processors capable of executing scripts or instructions of one or more software programs stored in the device 1605 (such as within one or more of the at least one memory 1625).

[0341] In some examples, the at least one processor 1635 may include multiple processors and the at least one memory 1625 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein. In some examples, the at least one processor 1635 may be a component of a processing system, which may refer to a system (such as a series) of machines, circuitry (including, for example, one or both of processor circuitry (which may include the at least one processor 1635) and memory circuitry (which may include the at least one memory 1625)), or components, that receives or obtains inputs and processes the inputs to produce, generate, or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. For example, the at least one processor 1635 or a processing system including the at least one processor 1635 may be configured to, configurable to, or operable to cause the device 1605 to perform one or more of the functions described herein. Further, as described herein, being “configured to,” being “configurable to,” and being “operable to” may be used interchangeably and may be associated with a capability, when executing code stored in the at least one memory 1625 or otherwise, to perform one or more of the functions described herein.

[0342] In some examples, a bus 1640 may support communications of (e.g., within) a protocol layer of a protocol stack. In some examples, a bus 1640 may support communications associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack), which may include communications performed within a component of the device 1605, or between different components of the device 1605 that may be co-located or located in different locations (e.g., where the device 1605 may refer to a system in which one or more of the communications manager 1620, the transceiver 1610, the at least one memory 1625, the code 1630, and the at least oneAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO102 processor 1635 may be located in one of the different components or divided between different components).

[0343] In some examples, the communications manager 1620 may manage aspects of communications with a core network 130 (e.g., via one or more wired or wireless backhaul links). For example, the communications manager 1620 may manage the transfer of data communications for client devices, such as one or more UEs 115. In some examples, the communications manager 1620 may manage communications with one or more other network nodes 105, and may include a controller or scheduler for controlling communications with UEs 115 (e.g., in cooperation with the one or more other network devices). In some examples, the communications manager 1620 may support an X2 interface within an LTE / LTE-A wireless communications network technology to provide communication between network nodes 105.

[0344] For example, the communications manager 1620 is capable of, configured to, or operable to support a means for transmitting a request that a wireless device is to report a set of one or more measurements. The communications manager 1620 is capable of, configured to, or operable to support a means for obtaining a first indication of a reference time of a reference signal that is transmitted to the wireless device, where the first indication of the reference time of the reference signal is based on the set of one or more measurements of the reference signal associated with a time period. The communications manager 1620 is capable of, configured to, or operable to support a means for obtaining a second indication of a set of one or more signal samples that have a temporal association with the reference time of the reference signal, where individual ones of the set of one or more signal samples are distributed in accordance with a uniform spacing or a subsampled uniform spacing.

[0345] By including or configuring the communications manager 1620 in accordance with examples as described herein, the device 1605 may support techniques for increased positioning accuracy, improved communication reliability, reduced latency, improved user experience related to reduced processing, reduced power consumption, more efficient utilization of communication resources, improved coordination between devices, longer battery life, improved utilization of processing capability.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO103

[0346] In some examples, the communications manager 1620 may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the transceiver 1610, the one or more antennas 1615 (e.g., where applicable), or any combination thereof. Although the communications manager 1620 is illustrated as a separate component, in some examples, one or more functions described with reference to the communications manager 1620 may be supported by or performed by the transceiver 1610, one or more of the at least one processor 1635, one or more of the at least one memory 1625, the code 1630, or any combination thereof (for example, by a processing system including at least a portion of the at least one processor 1635, the at least one memory 1625, the code 1630, or any combination thereof). For example, the code 1630 may include instructions executable by one or more of the at least one processor 1635 to cause the device 1605 to perform various aspects of signaling for sample-based position estimation as described herein, or the at least one processor 1635 and the at least one memory 1625 may be otherwise configured to, individually or collectively, perform or support such operations.

[0347] FIG. 17 shows a flowchart illustrating a method 1700 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The operations of the method 1700 may be implemented by a device or its components as described herein. For example, the operations of the method 1700 may be performed by a device as described with reference to FIGs. 1 through 12. In some examples, a device may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[0348] At 1705, the method may include transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The operations of 1705 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1705 may be performed by a capability component 1125 as described with reference to FIG. 11.

[0349] At 1710, the method may include generating first information associated with a position of an object, where the first information is an output of a first portion ofAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO104 the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device. The operations of 1710 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1710 may be performed by a generation component 1130 as described with reference to FIG. 11.

[0350] FIG. 18 shows a flowchart illustrating a method 1800 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The operations of the method 1800 may be implemented by a device or its components as described herein. For example, the operations of the method 1800 may be performed by a device as described with reference to FIGs. 1 through 12. In some examples, a device may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[0351] At 1805, the method may include transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The operations of 1805 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1805 may be performed by a capability component 1125 as described with reference to FIG. 11.

[0352] At 1810, the method may include generating first information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based on one or more measurements input to the first portion of the AI / ML model at the first device. The operations of 1810 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1810 may be performed by a generation component 1130 as described with reference to FIG. 11.

[0353] At 1815, the method may include transmitting, to a second device, the first information associated with the position of the object. The operations of 1815 may be performed in accordance with examples as disclosed herein. In some examples, aspectsAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO105 of the operations of 1815 may be performed by an information component 1135 as described with reference to FIG. 11.

[0354] FIG. 19 shows a flowchart illustrating a method 1900 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The operations of the method 1900 may be implemented by a device or its components as described herein. For example, the operations of the method 1900 may be performed by a device as described with reference to FIGs. 1 through 12. In some examples, a device may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[0355] At 1905, the method may include obtaining, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure. The operations of 1905 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1905 may be performed by an information component 1135 as described with reference to FIG. 11.

[0356] At 1910, the method may include generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device. The operations of 1910 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1910 may be performed by a generation component 1130 as described with reference to FIG. 11.

[0357] FIG. 20 shows a flowchart illustrating a method 2000 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The operations of the method 2000 may be implemented by a device or its components as described herein. For example, the operations of the method 2000 may be performed by a device as described with reference to FIGs. 1 through 12. In some examples, a device may execute a set of instructions to control the functional elements of the device toAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO106 perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

[0358] At 2005, the method may include obtaining, from a first device, first information associated with a position of an object, where the first information is an output of a first portion of an AI / ML model, where the AI / ML model is associated with a positioning procedure. The operations of 2005 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2005 may be performed by an information component 1135 as described with reference to FIG. 11.

[0359] At 2010, the method may include generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the second device. The operations of 2010 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2010 may be performed by a generation component 1130 as described with reference to FIG. 11.

[0360] At 2015, the method may include transmitting the second information associated with the position of the object. The operations of 2015 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2015 may be performed by an information component 1135 as described with reference to FIG. 11.

[0361] FIG. 21 shows a flowchart illustrating a method 2100 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The operations of the method 2100 may be implemented by a network entity or its components as described herein. For example, the operations of the method 2100 may be performed by a network entity as described with reference to FIGs. 1 through 27 and 13 through 16. In some examples, a network entity may execute a set of instructions to control the functional elements of the network entity to perform the described functions. Additionally, or alternatively, the network entity may perform aspects of the described functions using special-purpose hardware.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO107

[0362] At 2105, the method may include obtaining capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The operations of 2105 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2105 may be performed by a capability manager 1525 as described with reference to FIG. 15.

[0363] At 2110, the method may include obtaining first information or second information associated with a position of an object, where the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model. The operations of 2110 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2110 may be performed by an information manager 1530 as described with reference to FIG. 15.

[0364] FIG. 22 shows a flowchart illustrating a method 2200 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. The operations of the method 2200 may be implemented by a network entity or its components as described herein. For example, the operations of the method 2200 may be performed by a network entity as described with reference to FIGs. 1 through 27 and 13 through 16. In some examples, a network entity may execute a set of instructions to control the functional elements of the network entity to perform the described functions. Additionally, or alternatively, the network entity may perform aspects of the described functions using special-purpose hardware.

[0365] At 2205, the method may include obtaining capability information of a first device that indicates a capability of the first device to process one or more portions of an AI / ML model at the first device, where the AI / ML model is associated with a positioning procedure. The operations of 2205 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2205 may be performed by a capability manager 1525 as described with reference to FIG. 15.

[0366] At 2210, the method may include obtaining first information or second information associated with a position of an object, where the first information is anAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO108 output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model. The operations of 2210 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2210 may be performed by an information manager 1530 as described with reference to FIG. 15.

[0367] At 2215, the method may include generating second information associated with the position of the object, where the second information is an output of a second portion of the AI / ML model based on the first information input to the second portion of the AI / ML model at the network entity. The operations of 2215 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 2215 may be performed by a generation manager 1535 as described with reference to FIG. 15.

[0368] FIG. 23 show examples of wireless communications systems 2300 that support portions of AI / ML models in accordance with one or more aspects of the present disclosure. Various positioning techniques are illustrated in the context of the wireless communications systems 2300. Some examples of the positioning procedures described herein may be performed in accordance with one or more aspects of the positioning techniques. While TRPs and UEs are provided in the examples illustrated in FIG. 23, other devices (e.g., network entities, base stations, RRHs, RUs, APs, wireless devices, or stations, among other examples) may be similarly utilized in other examples. The examples of positioning techniques include downlink-based positioning techniques, uplink-based positioning techniques, and downlink-and-uplink-based positioning techniques.

[0369] Examples of OTDOA or DL-TDOA 2305 are illustrated in FIG. 23. One or more of the OTDOA or DL-TDOA 2305 positioning techniques may be included in a downlink-based positioning procedure. In OTDOA or DL-TDOA 2305 positioning techniques, a UE may measure a difference between TOAs of reference signals (e.g., PRSs) received from one or more pairs of TRPs (e.g., TRP2 and TRP3). In some approaches, a difference in TOAs may be referred to as an RSTD or a TDOA measurement. A positioning device (e.g., the UE, a location server, an LMF, an SLP, orAttorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO109 another device) may utilize the differences in TOAs to determine (e.g., estimate) a location of the UE.

[0370] In some aspects, the UE may receive an identifier (ID) associated with a reference TRP (e.g., a serving base station) and one or more IDs associated with one or more non-reference TRPs in received data (e.g., assistance data). The UE may measure the difference of TOAs between the reference TRP and each of the non-reference TRPs to produce RSTDs or TDOAs. In some aspects, the UE may report an indication of the RSTDs or TDOAs to the positioning device (e.g., a location server, LMF, an SLP, or another device). Based on established locations of the base stations and the RSTD measurements, the positioning device (e.g., the UE for UE-based positioning or a location server for UE-assisted positioning) may estimate the UE’s location.

[0371] An example of UL-TDOA 2310 is illustrated in FIG. 23. One or more of theUL-TDOA 2310 positioning techniques may be included in an uplink-based positioning procedure. UL-TDOA 2310 may have some similarities to DL-TDOA 2305. The UL- TDOA 2310 positioning techniques may be based on uplink reference signals (e.g., SRS) transmitted from the UE to multiple TRPs. For example, the UE transmits one or more uplink reference signals that are measured by a reference TRP (e.g., TRP3) and non-reference TRPs (e.g., TRP1 and TRP2). Each TRP then reports the reception time (which may be referred to as a relative time of arrival (RTOA)) of the reference signal(s) to a positioning device (e.g., a location server, LMF, SLP, or UE) that has information about the locations and relative timing of the TRPs. Based on the reception- to-reception (Rx-Rx) time differences between the reported RTOA of the reference TRP and the reported RTOA of each non-reference TRP, the locations of the TRPs, and the corresponding timing offsets, the positioning device may estimate the location of the UE using TDOA.

[0372] An example of DL-AOD 2315 is illustrated in FIG. 23. One or more of theDL-AOD 2315 positioning techniques may be included in a downlink-based positioning procedure. In DL-AOD 2315, a UE may obtain received signal strength measurements corresponding to multiple downlink transmit beams for one or more TRPs (e.g., TRP1 and TRP2). In some approaches, the UE reports the measurements to a positioning device. The positioning device may use the signal strength measurements of the multiple downlink transmit beams to determine the angle(s) (e.g., AOD1 and AOD2)Attorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO110 between the UE and the transmitting TRP(s). The positioning device (e.g., location server, LMF, SLP, UE, or another device) may estimate the location of the UE based on the determined angle(s) and the established location(s) of the transmitting TRP(s).

[0373] An example of UL-AOA 2320 is illustrated in FIG. 23. One or more of the UL-AOA 2320 positioning techniques may be included in an uplink positioning procedure. In UL-AOA 2320, one or more TRPs (e.g., TRP1 and TRP2) measure the received signal strength of one or more uplink reference signals (e.g., SRSs) received from a UE on one or more uplink receive beams. In some aspects, the signal strength measurements may be reported to a positioning device. A positioning device (e.g., LFM, SLP, UE, or another device) may use the signal strength measurements and the angle(s) of the receive beam(s) to determine the angle(s) between the UE and the TRP(s). Based on the determined angle(s) and the established location(s) of the TRP(s), the positioning device may estimate the location of the UE.

[0374] Some positioning techniques or procedures may include a combination downlink-based and uplink-based positioning techniques. Examples of downlink-based and uplink-based positioning techniques may include E-CID positioning and multi- round-trip-time (RTT) positioning (which may be referred to as “multi-RTT” or “multicell RTT” when multiple cells are utilized).

[0375] In multi-RTT, a first device (e.g., a TRP or UE) may transmit a first RTT- related signal (e.g., a PRS or SRS) to a second device (e.g., the UE or TRP). The second device may transmit a second RTT-related signal (e.g., an SRS or PRS) back to the first device. Each device may measure a time difference between the TOA of the received RTT-related signal and the transmission time of the transmitted RTT-related signal. The time difference may be referred to as a reception-to-transmission (Rx-Tx) time difference. In some aspects, the Rx-Tx time difference measurement may be obtained or adjusted to include (e.g., include only) a time difference between nearest slot boundaries for the received and transmitted signals. The first device or the second device may send the corresponding Rx-Tx time difference measurements to a positioning device (e.g., a location server, LMF, SLP, UE, or other device), which may calculate a round trip propagation time (or RTT) between the two device based on the two Rx-Tx time difference measurements (e.g., as a sum of the two Rx-Tx time difference measurements). Additionally, or alternatively, one device may send a correspondingAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WOI l lRx-Tx time difference measurement to the other device, which may calculate the RTT. The distance between the two devices may be determined from the RTT and a signal speed (e.g., the speed of light).

[0376] An example of multi-cell RTT 2325 is illustrated in FIG. 23. One or more of the multi-RTT or multi-cell RTT techniques described may be included in an uplinkbased or downlink-based positioning procedure. In multi-cell RTT 2325, a first device (e.g., a UE or TRP) may perform an RTT positioning procedure with multiple second devices (e.g., multiple TRPs or UEs) to enable the location of the first device to be determined (e.g., using multilateration) based on distances to, and the established locations of, the second devices.

[0377] In some examples, RTT or multi-RTT techniques may be combined with one or more other positioning techniques (e.g., UL-AOA, DL-AOD, or other positioning techniques), to enhance location accuracy. Examples of combined DL-AOD and RTT 2330 positioning techniques are illustrated in FIG. 23.

[0378] E-CID positioning techniques (not shown in FIG. 23) may be based on radio resource management (RRM) measurements. In E-CID, a UE may obtain or report a serving cell ID, a timing advance (TA), identifiers of one or more detected neighbor TRPs, estimated timing of one or more detected neighbor TRPs, or a signal strength measurement of one or more detected neighbor TRPs. A positioning device (e.g., an LFM, SLP, UE, or another device) may utilize the serving cell ID, TA, identifiers, estimated timing, or signal strength measurements with one or more established locations of one or more TRPs to estimate the location of the UE.

[0379] In some approaches, a positioning device (e.g., location server, LMF, SLP, or another device) may provide assistance data to the UE. Assistance data is data to assist with one or more positioning operations (e.g., to detect one or more neighboring TRPs or to receive reference signaling). For instance, the assistance data may indicate IDs of the TRPs (e.g., IDs of one or more cells or TRPs corresponding to a network node) from which reference signals may be measured. In some examples, a positioning device may transmit assistance data or other information indicating one or more reference signal configuration parameters. The reference signal configuration parameter(s) may include or indicate a quantity of consecutive slots including PRS, aAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO112 periodicity of consecutive slots including PRS, a muting sequence, a frequency hopping sequence, a reference signal identifier, a reference signal bandwidth, or one or more other parameters applicable to a positioning technique or procedure. Additionally, or alternatively, the assistance data may be sent from one or more TRPs (e.g., in periodically broadcasted overhead messages, a scheduled message, a unicast message, or a multicast message, among other examples). In some examples, a UE may be able to detect one or more neighboring TRPs (e.g., network entities) without the use of assistance data.

[0380] For OTDOA positioning techniques or DL-TDOA positioning techniques, the assistance data may indicate an expected RSTD value and an associated uncertainty or search window around the expected RSTD. For example, an expected RSTD value may have an associated uncertainty or search window with a range of ±500 microseconds (ps). In another example, when any of the resources used for the positioning measurement(s) are in frequency range 1 (FR1), an expected RSTD value may have an associated uncertainty or search window with a range of ±32 ps. In another example, when all of the resources used for the positioning measurement s) are in frequency range 2 (FR2), an expected RSTD value may have an associated uncertainty or search window with a range of ±8 ps.

[0381] In some examples, a location may be referred to as a position estimate, location estimate, position, position fix, or fix, among other examples. A location may be geodetic and include coordinates (e.g., latitude, longitude, or altitude) or may be civic and include a street address, postal address, or another description of a location. In some aspects, a location may be defined relative to another location or may be defined in absolute terms (e.g., latitude, longitude, or altitude). A location may include an indication of error or uncertainty (e.g., by including an area or volume within which the location may be included with a specified or default level of confidence).

[0382] Various examples of sidelink positioning techniques are illustrated in FIG. 23. Sidelink positioning techniques may include positioning techniques that are based on sidelink communication (e.g., based exclusively on sidelink communication or based on sidelink communication jointly with other communication(s), such as Uu interface communication).Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO113

[0383] A first example of sidelink positioning 2335 is illustrated in FIG. 23. In the first example of sidelink positioning 2335, at least one peer UE with an established location may improve location estimation (e.g., Uu-based positioning, multi-cell RTT, DL-TDOA, or UL-TDOA, among other examples) for a target UE by providing an additional anchor (e.g., sidelink RTT (SL-RTT)).

[0384] A second example of sidelink positioning 2340 is illustrated in FIG. 23. In the second example of sidelink positioning 2340, different types (e.g., categories, classes, or capabilities) of UEs may be utilized. For example, first UEs and a second UE may be utilized. Relative to the second UE, the first UEs may have one or more increased capabilities, such as one or more additional sensors, a faster processor, greater memory capacity, one or more additional antenna elements, a higher transmit power capability, access to one or more additional frequency bands, or any combination thereof. In some aspects, the second UE may be a reduced capacity or “RedCap” UE. The second UE may be assisted by the first UEs to determine the location of the second UE. For instance, sidelink-based positioning or ranging procedures may be performed with the first UEs, which may enhance the location accuracy of the second UE.

[0385] A third example of sidelink positioning 2345 is illustrated in FIG. 23. The third example of sidelink positioning 2345 may be performed via one or more sidelink connections (e.g., via sidelink connections exclusively or jointly with one or more Uu- based connections). In the third example of sidelink positioning 2345, the UEs may perform peer-to-peer (P2P) positioning or ranging. Sidelink positioning may be helpful for out-of-coverage or public safety scenarios. For instance, the UEs may be out of coverage of a network and may determine a location or a relative distance and a relative position among the UEs using sidelink positioning techniques. In some examples, sidelink positioning may be performed by UEs in public safety scenarios (e.g., for police, firefighters, search-and-rescue, or paramedics, among other examples).

[0386] A fourth example of sidelink positioning 2350 is illustrated in FIG. 23. The fourth example of sidelink positioning 2350 may be performed via one or more sidelink connections (e.g., via sidelink connections exclusively or jointly with one or more Uu- based connections). In the fourth example of sidelink positioning 2350, one or more of the UEs may determine a location or a relative distance and a relative position using sidelink positioning techniques, such as SL-RTT. For instance, one or more of the UEsAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO114 may be out of coverage of a network and may determine a location or a relative distance and a relative position among the UEs using sidelink positioning techniques.

[0387] An example of relay positioning 2355 is illustrated in FIG. 23. In the example of relay positioning 2355, a relay UE (e.g., with an established location) may participate in the location estimation of a remote UE (without performing uplink reference signal transmission over the Uu interface, for instance). For example, the relay UE may receive a downlink PRS from a TRP and may relay an SL-PRS to the remote UE. In some cases, the remote UE may also receive another downlink PRS from the TRP. A positioning device (e.g., location server, LMF, SLP, UE, or other device) may utilize a downlink PRS measurement and an SL-PRS measurement with the established location of the relay UE to estimate the location of the remote UE.

[0388] An example of joint positioning 2360 is illustrated in FIG. 23. In the example of joint positioning 2360, multiple peer UEs (without established locations, for instance) may be located. In some approaches, multiple peer UEs may be jointly located in NLOS conditions by utilizing one or more constraints from one or more peer (e.g., neighboring or nearby) UEs. As illustrated in FIG. 23, RTT or TDOA techniques may be performed between TRP1 and each of the peer UEs, may be performed between TRP2 and each of the peer UEs, and may be performed between the peer UEs. In some examples, one or more of the peer UEs may report measurements from the RTT or TDOA technique(s) to a positioning device. The positioning device (e.g., location server, LMF, SLP, UE, or other device) may utilize the measurements from the RTT or TDOA technique(s) to estimate the locations of the peer UEs.

[0389] Some aspects of the techniques described herein may be performed in conjunction with one or more of the positioning techniques described with reference to FIG. 23. For instance, one or more samples of a reference signal (e.g., PRS, SRS, or other reference signal) may be measured or transmitted in accordance with one or more of the techniques described with reference to FIG. 4 for one or more of the positioning techniques. Some examples of the positioning techniques may be performed in one or more wireless communications systems 2300, such as LTE and NR, where NR may support sidelink communications.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO115

[0390] FIG. 24 shows an example of a node diagram 2400 that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. Al models are programmatic or algorithmic structures that simulate intelligent behavior. Machine learning models may be examples of Al models. Machine learning models are programmatic or algorithmic structures that may be trained to infer or predict an output based on an input. For example, a machine learning model may be trained using training input data and ground truth data.

[0391] Machine learning models may be categorized as unsupervised or supervised. Unsupervised learning may be utilized to draw inferences and find patterns from input data without references to labeled outcomes. Two examples of unsupervised learning models include clustering and dimensionality reduction. Clustering is an unsupervised technique that involves the grouping, or clustering, of data points. Clustering techniques may include k-means clustering, hierarchical clustering, mean shift clustering, and density-based clustering. Dimensionality reduction may be a procedure for reducing a quantity of random variables under consideration by obtaining a set of principal variables. Dimensionality reduction may reduce the dimension of a feature set or reduce a quantity of features). Some dimensionality reduction techniques may be categorized as feature elimination or feature extraction. One example of dimensionality reduction may be referred to as principal component analysis (PCA). PCA may involve projecting higher dimensional data (e.g., three dimensions) to a lower-dimensional space (e.g., two dimensions), which may result in a lower dimension of data (e.g., two dimensions instead of three dimensions) while maintaining one or more variables in the model.

[0392] Supervised learning involves learning a function that maps an input to an output based on associated inputs and outputs. For instance, supervised learning may be utilized to draw inferences and find patterns from input data based on labeled data (e.g., training input data with associated ground truth data). A supervised model may subcategorized as a regression or classification model. Regression models may provide continuous outputs. One example of a regression model is a linear regression, which may determine a line that fits (e.g., best fits) input data. Extensions of linear regression include multiple linear regression (e.g., finding a plane of best fit) and polynomial regression (e.g., finding a curve of best fit).Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO116

[0393] In classification models, the output may be discrete. One example of a classification model is logistic regression. Logistic regression may be similar to linear regression, but may be used to model a probability for a finite quantity of outcomes. For example, a logistic regression may be utilized such that the output values may be between 0 and 1. Another example of a classification model is a support vector machine. For two classes of data, for example, a support vector machine may determine a hyperplane or a boundary between the two classes of data that maximizes a margin between the two classes. For instance, many planes may separate two classes, while one plane may maximize the margin or distance between the classes. Another example of a classification model is Naive Bayes, which is based on Bayes Theorem.

[0394] Other examples of classification models include decision tree models, random forest models, and neural network models, where an output may be discrete. In a decision tree model, a tree structure is defined with multiple nodes. Decisions may be used to move from a root node at the top of the decision tree to a leaf node (e.g., a node without a child node) at the bottom of the decision tree. A higher quantity of nodes in the decision tree model may correlate with higher decision accuracy.

[0395] Random forest models may utilize ensemble learning techniques that build from decision tree models. Random forests involve creating multiple decision trees using bootstrapped datasets of the original data and randomly selecting a subset of variables at each tier of the decision tree. The model may select the mode of all of the predictions of each decision tree. By relying on a “majority wins” model, the risk of error from an individual tree may be reduced.

[0396] Another example of a machine learning model is a neural network (NN). A neural network may be a network of functional nodes. Neural networks may utilize one or more input variables to traverse the nodes and generate one or more output variables. For example, a neural network may utilize an input vector to generate an output vector.

[0397] The Al model illustrated in FIG. 24 is an example of a neural network. The neural network includes an input layer i that receives n (one or more) inputs (illustrated as “Input 1,” “Input 2,” and “Input n”), one or more hidden layers (illustrated as hidden layers “hl,” “h2,” and “h3”) for processing the inputs from the input layer, and an output layer o that provides m (one or more) outputs (labeled “Output 1” and “OutputAttorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO117 m”). While examples of quantities of inputs n, hidden layers h, and outputs m are illustrated in FIG. 24, same or different quantities of inputs, hidden layers, or outputs may be utilized in other examples. In some approaches, the hidden layers h may include linear function(s) or activation function(s) that the nodes (illustrated as circles) of each successive hidden layer process from the nodes of the previous hidden layer.

[0398] In some aspects, the Al model illustrated in FIG. 24 or another Al model may be trained in accordance with one or more training techniques. In some examples of the training techniques described herein, one or more Al models (e.g., implemented by one or more devices) may be trained based on training input data (e.g., measurements of reference signals to or from various UEs) and ground truth data (e.g., locations of the various UEs), thereby enabling later determination of an output (e.g., an inferred or prediction location or measurement) when an Al model is executed with runtime input data (e.g., from other UEs).

[0399] Ground truth data may be data representing a target output associated with training input data. Ground truth data may be generated or observed (e.g., empirical) data. In some examples, ground truth data may indicate one or more observed locations (e.g., coordinates or addresses, among other examples) corresponding to training input data. Examples of training input data may include reference signal data (e.g., measurements of a PRS, SRS, reference signal of an SSB, CSI-RS, DMRS, or TRS, among other examples), signal data (e.g., signal strength data, RSRP data, RSRPP data, RS SI data, RSRQ data, SINR data, or SNR data, among other examples), channel data (e.g., CIR data, PDP data, DP data, CQI data, CSI data, decoding failure rate, or retransmission request rate, among other examples), AOA data, AOD data, TDOA data, RTT data, TA data, sensor data (e.g., image data, RF data, motion data, orientation data, or audio data, among other examples), or identifier data (e.g., cell ID data or service set identifier (SSID) data, among other examples), among other examples.

[0400] In some examples, ground truth data may indicate one or more measurements or values (e.g., AOA measurements, AOD measurements, TDOA measurements, RTT measurements, line-of-sight (LOS) angle(s), or other values) corresponding to training input data. Examples of training input data may include reference signal data (e.g., measurements of a PRS, SRS, reference signal of an SSB, CSI-RS, DMRS, or TRS, among other examples), signal data (e.g., signal strength data,Attorney Docket No. PB0007GR.WO (114958.5250)Qualcomm Ref. No. 2405199WO118RSRP data, RS SI data, RSRQ data, SINR data, or SNR data, among other examples), channel data (e.g., CIR data, PDP data, DP data, CQI data, CSI data, decoding failure rate, or retransmission request rate, among other examples), TA data, sensor data (e.g., image data, RF data, motion data, orientation data, or audio data, among other examples), or identifier data (e.g., cell ID data or SSID data, among other examples), among other examples.

[0401] An Al model (e.g., the Al model illustrated in FIG. 24 or a machine learning model) may be trained by executing the Al model with the training data to produce an output, comparing the output with the ground truth data, and adjusting weights of the Al model to reduce a disparity between the output and the ground truth data. For example, one or more of the nodes or connections of the Al model may have an associated weight that may be adjusted to modify one or more of the outputs. In some approaches, a cost function may be utilized to compare the output with the ground truth data to indicate a cost (e.g., error or disparity). Adjustments to the weights that reduce the cost may be retained, advanced, or increased, while adjustments to the weights that increase the cost may be discarded, avoided, or decreased. Training procedures may be repeated or iterated to improve Al model performance.

[0402] Input data (e.g., runtime input data) may be provided to a trained Al model, which may infer or predict an output based on the input data. Some examples of Al models may be trained to infer or predict a location based on input data (e.g., reference signal data, signal data, channel data, AOA data, AOD data, TDOA data, RTT data, TA data, sensor data, or identifier data, among other examples). Some examples of Al models may be trained to infer or predict measurements or values (e.g., timing measurement(s), angle measurement s), AOA measurement(s), AOD measurement(s), TDOA measurement s), RTT measurements), LOS angle(s), or other values) based on input data.

[0403] Some examples of the techniques described herein may be performed in conjunction with one or more of the Al models described with reference to FIG. 24. For instance, an Al model may be split or executed in portions as described with reference to FIG. 4.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO119

[0404] FIG. 25A shows an example of a block diagram 2500-a that supports portions of AI / ML models in accordance with one or more aspects of the present disclosure. In some examples of the techniques described herein, a positioning device (e.g., location server, LMF, SnMF, SLP, UE, or other device) may utilize D- AI / ML positioning or sensing. In D-AI / ML positioning, one or more Al models 2510 (e.g., machine learning model(s) or D-AI / ML model(s)) may be trained to utilize input data 2505 to output (e.g., infer or predict) object data 2515 (e.g., location, velocity, range, position estimate, coordinates, or an address of an object). Examples of the input data 2505 may include reference signal data (e.g., measurements of a PRS, SRS, reference signal of an SSB, CSI-RS, DMRS, or TRS, among other examples), signal data (e.g., signal strength data, RSRP data, RSRPP data, RS SI data, RSRQ data, SINR data, or SNR data, among other examples), channel data (e.g., CFR data, CIR data, PDP data, DP data, CQI data, CSI data, decoding failure rate, or retransmission request rate, among other examples), AOA data, AOD data, TDOA data, RTT data, TA data, RSTD data, difference of RSTDs (diff-RSTD) data, RTOA data, difference of RTOAs (difif- RTOA) data, sensor data (e.g., range map data, Doppler map data, space map data, image data, RF data, motion data, orientation data, or audio data, among other examples), or identifier data (e.g., cell ID data or SSID data, among other examples), among other examples.

[0405] FIG. 25B shows a block diagram 2500-b that supports portions of AI / ML models in accordance with one or more as...

Claims

Qualcomm Ref. No. 2405199WO141CLAIMSWhat is claimed is:

1. A first device, comprising: one or more memories storing processor-executable code; and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the first device to: transmit capability information of the first device that indicates a capability of the first device to process one or more portions of an artificial intelligence or machine learning (AI / ML) model at the first device, wherein the AI / ML model is associated with a positioning procedure; and generate first information associated with a position of an object, wherein the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based at least in part on one or more measurements input to the first portion of the AI / ML model at the first device.

2. The first device of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first device to: transmit, to a second device, the first information associated with the position of the object.

3. The first device of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first device to: receive a reference signal, wherein the one or more measurements are of the reference signal.

4. The first device of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first device to: obtain the one or more measurements via one or more sensors, the one or more measurements comprising a range measurement, a Doppler measurement, aAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO142 velocity measurement, an angle measurement, or a position measurement associated with the object.

5. The first device of claim 1, wherein: the AI / ML model comprises the first portion and a second portion, the first portion comprises one or more first nodes, one or more first layers, one or more first residual blocks, one or more first attention mechanism stages, a first portion of a graph structure, or a combination thereof, and the second portion comprises one or more second nodes, one or more second layers, one or more second residual blocks, one or more second attention mechanism stages, a second portion of a graph structure, or a combination thereof.

6. The first device of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first device to: obtain, from a second device, model information indicating the AI / ML model or the first portion of the AI / ML model, wherein the second device is a wireless device or a network entity.

7. The first device of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first device to: obtain, from a second device, an indication of the one or more portions of the AI / ML model.

8. The first device of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first device to: transmit, to a second device, model information indicating the AI / ML model or a second portion of the AI / ML model, wherein the second device is a wireless device or a network entity.

9. A second device, comprising: one or more memories storing processor-executable code; andAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO143 one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the second device to: obtain, from a first device, first information associated with a position of an object, wherein the first information is an output of a first portion of an artificial intelligence or machine learning (AI / ML) model, wherein the AI / ML model is associated with a positioning procedure; and generate second information associated with the position of the object, wherein the second information is an output of a second portion of the AI / ML model based at least in part on the first information input to the second portion of the AI / ML model at the second device.

10. The second device of claim 9, wherein the one or more processors are individually or collectively further operable to execute the code to cause the second device to: transmit the second information associated with the position of the object.

11. The second device of claim 9, wherein: the first portion comprises one or more first nodes, one or more first layers, one or more first residual blocks, one or more first attention mechanism stages, a first portion of a graph structure, or a combination thereof, and the second portion comprises one or more second nodes, one or more second layers, one or more second residual blocks, one or more second attention mechanism stages, a second portion of a graph structure, or a combination thereof.

12. The second device of claim 9, wherein the one or more processors are individually or collectively further operable to execute the code to cause the second device to: transmit, to the first device, model information indicating the AI / ML model or the first portion of the AI / ML model, wherein the second device is a wireless device or a network entity.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO14413. The second device of claim 9, wherein the one or more processors are individually or collectively further operable to execute the code to cause the second device to: transmit, to the first device, an indication of one or more portions of the AI / ML model.

14. The second device of claim 9, wherein the one or more processors are individually or collectively further operable to execute the code to cause the second device to: obtain, from the first device, model information indicating the AI / ML model or a second portion of the AI / ML model, wherein the second device is a wireless device or a network entity.

15. The second device of claim 9, wherein the one or more processors are individually or collectively further operable to execute the code to cause the second device to: transmit capability information of the second device that indicates a capability of the second device to process one or more portions of the AI / ML model at the second device, wherein the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

16. The second device of claim 9, wherein the one or more processors are individually or collectively further operable to execute the code to cause the second device to: communicate an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and the second portion of the AI / ML model, wherein the location of the split is associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO14517. A network entity, compri sing : one or more memories storing processor-executable code; and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the network entity to: obtain capability information of a first device that indicates a capability of the first device to process one or more portions of an artificial intelligence or machine learning (AI / ML) model at the first device, wherein the AI / ML model is associated with a positioning procedure; and obtain first information or second information associated with a position of an object, wherein the first information is an output of a first portion of the AI / ML model or the second information is an output of a second portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model and the second portion of the AI / ML model.

18. The network entity of claim 17, wherein, to method, the one or more processors are individually or collectively further operable to execute the code to cause the network entity to: generate second information associated with the position of the object, wherein the second information is an output of a second portion of the AI / ML model based at least in part on the first information input to the second portion of the AI / ML model at the network entity.

19. The network entity of claim 17, wherein, to method, the one or more processors are individually or collectively further operable to execute the code to cause the network entity to: generate third information associated with the position of the object, wherein the third information is an output of a third portion of the AI / ML model based at least in part on the second information input to the third portion of the AI / ML model at the network entity.

20. The network entity of claim 17, wherein the one or more processors are individually or collectively further operable to execute the code to cause the network entity to:Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO146 transmit, to the first device or a second device, model information indicating the AI / ML model, the first portion of the AI / ML model, or the second portion of the AI / ML model.

21. The network entity of claim 17, wherein the one or more processors are individually or collectively further operable to execute the code to cause the network entity to: transmit, to the first device or a second device, an indication of the one or more portions of the AI / ML model.

22. The network entity of claim 17, wherein the one or more processors are individually or collectively further operable to execute the code to cause the network entity to: obtain, from the first device or a second device, model information indicating the AI / ML model, the first portion of the AI / ML model, or the second portion of the AI / ML model.

23. The network entity of claim 17, wherein the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

24. The network entity of claim 17, wherein the one or more processors are individually or collectively further operable to execute the code to cause the network entity to: obtain capability information of a second device that indicates a capability of the second device to process one or more portions of the AI / ML model at the second device, wherein the capability information of the second device indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / MLAttorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO147 model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

25. A method for wireless communications at a first device, comprising: transmitting capability information of the first device that indicates a capability of the first device to process one or more portions of an artificial intelligence or machine learning (AI / ML) model at the first device, wherein the AI / ML model is associated with a positioning procedure; and generating first information associated with a position of an object, wherein the first information is an output of a first portion of the AI / ML model, the one or more portions of the AI / ML model including the first portion of the AI / ML model, and the output of the first portion of the AI / ML model based at least in part on one or more measurements input to the first portion of the AI / ML model at the first device.

26. The method of claim 25, wherein the capability information indicates one or more quantities of supported computations respectively corresponding to each of the one or more portions of the AI / ML model, one or more quantities of supported parameters respectively corresponding to each of the one or more portions of the AI / ML model, or one or more quantities of available memory respectively corresponding to each of the one or more portions of the AI / ML model.

27. The method of claim 25, further comprising: communicating an indication of a location of a split of the AI / ML model between the first portion of the AI / ML model and a second portion of the AI / ML model, wherein the location of the split is associated with a layer of the AI / ML model, an attention mechanism stage of the AI / ML model, a residual block of the AI / ML model, a location of a graph structure, or a combination thereof.

28. The method of claim 25, further comprising: transmitting an indication of a reason for portioning the AI / ML model, wherein the reason is associated with a memory limit, a processing limit, a battery level, or a combination thereof.

29. The method of claim 25, further comprising:Attorney Docket No. PB0007GR.WQ (114958.5250)Qualcomm Ref. No. 2405199WO148 obtaining configuration information that indicates one or more candidate devices for offloading processing associated with a second portion of the AI / ML model, wherein the second device is one of the one or more candidate devices.

30. The method of claim 25, further comprising: obtaining configuration information that indicates one or more locations to split the AI / ML model, wherein the one or more portions of the AI / ML model are associated with the one or more locations.Attorney Docket No. PB0007GR.WQ (114958.5250)

Images