公开(公告)号：US20240154710A1

公开(公告)日：2024-05-09

申请号：US18446334

申请日：2023-08-08

Applicant: QUALCOMM Incorporated

Inventor： Rajeev KUMAR ,  Taesang YOO

IPC: H04B17/391

CPC classification number: H04B17/3913 ,  H04B17/3912

Abstract: Methods, systems, and devices for wireless communications are described that provide for machine learning model generalization in which a machine learning model may be initially configured for a first set of conditions, and the machine learning model may be generalized to apply to one or more conditions that are outside of the first set of conditions. A network entity may provide a user equipment (UE) with one or more machine learning models, the first set of conditions, and information for model evaluation in which one or more key performance indicators (KPIs) may be evaluated for conditions outside of the first set of conditions. The UE may measure the KPIs, and transmit an evaluation report to the network entity that indicates the KPIs for the identified condition. The network entity may generalize the corresponding model based on the reported KPIs, and provide an updated machine learning model.

公开(公告)号：US20240114477A1

公开(公告)日：2024-04-04

申请号：US18466088

申请日：2023-09-13

Applicant: QUALCOMM Incorporated

Inventor： Srinivas YERRAMALLI ,  Mohammed Ali Mohammed HIRZALLAH ,  Taesang YOO ,  Jay Kumar SUNDARARAJAN

IPC: H04W64/00 ,  G06N20/00

CPC classification number: H04W64/00 ,  G06N20/00

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, an apparatus may obtain a set of training measurement information associated with a user equipment (UE). The apparatus may obtain a training position value associated with the UE. The apparatus may provide the training position value and the set of training measurement information for training of a model using a machine learning (ML) technique, the model being trained to output location information based at least in part on measurement information. Numerous other aspects are described.

公开(公告)号：US20240064692A1

公开(公告)日：2024-02-22

申请号：US18494299

申请日：2023-10-25

Applicant: QUALCOMM Incorporated

Inventor： Mohammed Ali Mohammed HIRZALLAH ,  Srinivas YERRAMALLI ,  Taesang YOO ,  Rajat PRAKASH ,  Xiaoxia ZHANG

IPC: H04W64/00 ,  G06F18/214 ,  H04W72/23

CPC classification number: H04W64/003 ,  G06F18/2155 ,  H04W72/23 ,  H04W64/006

Abstract: Disclosed are techniques for training a position estimation module. In an aspect, a first network entity obtains a plurality of positioning measurements, obtains a plurality of positions of one or more user equipments (UEs), the plurality of positions determined based on the plurality of positioning measurements, stores the plurality of positioning measurements as a plurality of features and the plurality of positions as a plurality of labels corresponding to the plurality of features, and trains the position estimation module with the plurality of features and the plurality of labels to determine a position of a UE from positioning measurements taken by the UE.

公开(公告)号：US20240049023A1

公开(公告)日：2024-02-08

申请号：US17817304

申请日：2022-08-03

Applicant: QUALCOMM Incorporated

Inventor： Hamed PEZESHKI ,  Arash BEHBOODI ,  Taesang YOO ,  Tao LUO ,  Mahmoud TAHERZADEH BOROUJENI

IPC: H04W24/10

CPC classification number: H04W24/10

Abstract: In a wireless communication system, a user equipment (UE) may report channel state information (CSI) using a learned dictionary defining a set of sparse vectors. The UE determines a learned dictionary for CSI reporting. For example, the UE receives a shared dictionary from a similar and nearby UE or the UE trains the learned dictionary based on logged CSI measurements. The UE indicates the learned dictionary to a serving base station. The UE measures CSI for a plurality of channels. The UE reports a sparse vector representing the CSI based on the learned dictionary to the serving base station.

公开(公告)号：US20240008067A1

公开(公告)日：2024-01-04

申请号：US17855147

申请日：2022-06-30

Applicant: QUALCOMM Incorporated

Inventor： Changhwan PARK ,  Prashant SHARMA ,  Taesang YOO

IPC: H04W72/12 ,  H04L41/16 ,  H04L5/00

CPC classification number: H04W72/1257 ,  H04L41/16 ,  H04L5/0096

Abstract: Aspects of the present disclosure provide apparatuses and methods for providing time gaps that can be used for training, verifying, compiling, and/or switching artificial intelligence (AI)/machine learning (ML) models for use in wireless communication. In the time gaps, a wireless apparatus can deprioritize certain normally or routinely performed processes and functions to spare processing power and/or resources for performing AI/ML model related functions. In one example, an apparatus can provide one or more time gaps associated an AI/ML model used for communication with a network entity. The apparatus can deprioritize, in the one or more time gaps, at least one of uplink (UL) communication or downlink (DL) communication with the network entity. The apparatus can perform, in the one or more time gaps, one or more AI/ML model related processes.

公开(公告)号：US20230396531A1

公开(公告)日：2023-12-07

申请号：US18330237

申请日：2023-06-06

Applicant: QUALCOMM Incorporated

Inventor： Tao LUO ,  Juan MONTOJO ,  Tamer KADOUS ,  Junyi LI ,  Xiaoxia ZHANG ,  Jing SUN ,  Taesang YOO ,  Siddhartha MALLIK

IPC: H04L45/16 ,  H04W52/54 ,  H04B17/318 ,  H04B7/06 ,  H04W52/34 ,  H04B17/24 ,  H04W52/24 ,  H04W72/20 ,  H04W72/21 ,  H04W72/52 ,  H04W72/53 ,  H04W72/54 ,  H03M13/09 ,  H04L12/18 ,  H04L5/00 ,  H04W72/044 ,  H04B7/216 ,  H04W52/14 ,  H04W52/16 ,  H04W52/38 ,  H04W52/42 ,  H04W52/50 ,  H04W52/56 ,  H04L41/0668 ,  H04W76/22 ,  H04W24/08

CPC classification number: H04L45/16 ,  H04W52/54 ,  H04B17/318 ,  H04B7/0691 ,  H04B7/0626 ,  H04W52/346 ,  H04B17/24 ,  H04W52/243 ,  H04W72/20 ,  H04W72/21 ,  H04W72/52 ,  H04W72/53 ,  H04W72/54 ,  H03M13/09 ,  H04L12/185 ,  H04L5/0094 ,  H04W72/044 ,  H04B7/216 ,  H04W52/146 ,  H04W52/16 ,  H04W52/241 ,  H04W52/386 ,  H04W52/42 ,  H04W52/50 ,  H04W52/56 ,  H04L41/0668 ,  H04W76/22 ,  H04W24/08 ,  H04L2001/0093

Abstract: Various aspects of the disclosure relate to event triggers for independent links. For example, an event trigger may be based on measurements from multiple links. In some aspects, the independent links may involve a first device (e.g., a user equipment) communicating via different independent links with different devices (e.g., transmit receive points (TRPs) or sets of TRPs). For example, the first device may communicate with a second device (e.g., a TRP) via a first link and communicate with a third device (e.g., a TRP) via a second link. In some scenarios, an event trigger may be based on aggregated measurements from multiple links.

公开(公告)号：US20230359886A1

公开(公告)日：2023-11-09

申请号：US18017598

申请日：2021-08-13

Applicant: QUALCOMM Incorporated

Inventor： Pavan Kumar VITTHALADEVUNI ,  Alexandros MANOLAKOS ,  Taesang YOO ,  Naga BHUSHAN ,  June NAMGOONG ,  Jay Kumar SUNDARARAJAN ,  Krishna Kiran MUKKAVILLI ,  Tingfang JI

IPC: G06N3/08 ,  H04L41/16 ,  H04W72/232 ,  G06N3/0455

CPC classification number: G06N3/08 ,  G06N3/0455 ,  H04L41/16 ,  H04W72/232

Abstract: A network entity may transmit a configuration for neural network training parameters for wireless communication by the UE, and the UE may train the neural network at the UE based on the configuration received from the network entity. The network entity may transmit a training command in a wireless message to the UE, and the UE may train the neural network based on the received configuration in response to the received training command. The configuration may include a period of time associated with the training the neural network. The period of time may indicate an action for the UE to perform when the period of time expires, and/or indicate the periodicity of the neural network training.

公开(公告)号：US20230336950A1

公开(公告)日：2023-10-19

申请号：US18336817

申请日：2023-06-16

Applicant: QUALCOMM Incorporated

Inventor： Srinivas YERRAMALLI ,  Mohammed Ali Mohammed HIRZALLAH ,  Roohollah AMIRI ,  Marwen ZORGUI ,  Rajat PRAKASH ,  Xiaoxia ZHANG ,  Taesang YOO

IPC: H04W4/029 ,  G01S5/02 ,  H04W24/08

CPC classification number: H04W4/029 ,  G01S5/02523 ,  H04W24/08

Abstract: In an aspect, a network component (e.g., BS, server, etc.) obtains measurement information associated with uplink signal(s) from UE(s), with the uplink signal(s) having reciprocity with one or more downlink beams of wireless node(s) (e.g., TRP, reference UE, etc.). The network component determines (e.g., generates or refines) a measurement (e.g., RFFP-P) model based on the measurement information. The network component provides the measurement (e.g., RFFP-P) model to a target UE. The target UE receives at least one signal (e.g., PRS) on the one or more downlink beams from the wireless node(s). The target UE processes the at least one signal (e.g., predicts target UE location) based at least in part on the measurement (e.g., RFFP-P) model.

公开(公告)号：US20230328559A1

公开(公告)日：2023-10-12

申请号：US18014445

申请日：2021-08-13

Applicant: QUALCOMM Incorporated

Inventor： Alexandros MANOLAKOS ,  Pavan Kumar VITTHALADEVUNI ,  Taesang YOO ,  June NAMGOONG ,  Jay Kumar SUNDARARAJAN ,  Tingfang JI ,  Naga BHUSHAN ,  Hwan Joon KWON ,  Krishna Kiran MUKKAVILLI

IPC: H04W24/08 ,  H04W24/10 ,  G06N3/04 ,  G06N3/08

CPC classification number: H04W24/08 ,  H04W24/10 ,  G06N3/04 ,  G06N3/08

Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for reporting configurations for neural network-based processing at a UE. A network entity may transmit to the UE a CSI configuration that includes one or more parameters for a neural network and one or more reference signals. The UE may measure the one or more reference signals based on the CSI configuration. A CSI may be based on the one or more parameters and the measurement of the one or more reference signals. The UE may report the CSI to the network entity based on output of the neural network.

公开(公告)号：US20230319750A1

公开(公告)日：2023-10-05

申请号：US17696720

申请日：2022-03-16

Applicant: QUALCOMM Incorporated

Inventor： Eren BALEVI ,  Taesang YOO ,  Xiaoxia ZHANG ,  Zhifei FAN ,  Jing SUN

IPC: H04W56/00 ,  H04B17/391 ,  H04W72/04

CPC classification number: H04W56/0035 ,  H04B17/391 ,  H04W72/0413

Abstract: Disclosed are systems and techniques for wireless communications. For instance, a user equipment (UE) can perform federated learning to generate a first set of updated model parameters corresponding to a machine learning model. In some cases, the UE can receive a request for the first set of updated model parameters from a network entity, wherein the request includes a resource allocation associated with an uplink channel. In some examples, the UE can determine a signal phase corresponding to the uplink channel. In some aspects, the UE can transmit, based on the signal phase, the first set of updated model parameters using the resource allocation on the uplink channel.