公开(公告)号：US20230246694A1

公开(公告)日：2023-08-03

申请号：US18003567

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 ,  Hwan Joon KWON ,  Tingfang JI

IPC: H04B7/06 ,  H04B7/0456 ,  H04L5/00

CPC classification number: H04B7/0645 ,  H04B7/0478 ,  H04L5/0057 ,  H04B7/0626 ,  G06N3/045

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first device may receive an indication to use a first number of bits to report neural network based channel state information feedback (CSF). The first device may transmit, using a second number of bits that is different from the first number of bits, a report that indicates the CSF to a second device. Numerous other aspects are provided.

公开(公告)号：US20230180152A1

公开(公告)日：2023-06-08

申请号：US17544581

申请日：2021-12-07

Applicant: QUALCOMM Incorporated

Inventor： Eren BALEVI ,  Taesang YOO ,  Tao LUO ,  Srinivas YERRAMALLI ,  Junyi LI ,  Hamed PEZESHKI

IPC: H04W52/50 ,  H04W52/36 ,  H04W52/24 ,  H04W52/22 ,  H04W4/06

CPC classification number: H04W52/50 ,  H04W52/36 ,  H04W52/242 ,  H04W52/225 ,  H04W4/06

Abstract: A parameter server located at a base station may coordinate federated learning among multiple user equipment (UEs) using over-the-air (OTA) aggregation with power control to mitigate aggregation distortion due to amplitude misalignment. The parameter server may select a first group of UEs for a first OTA aggregation session of a federated learning round based on a common received power property of each UE in the first group of UEs. The parameter server may transmit a global model to the first group of UEs. Each UE in the first group may train the global model based on a local dataset and transmit values associated with the trained local model. The parameter server may receive, on resource elements for the first group of UEs, a first aggregate amplitude modulated analog signal representing a combined response from the first group of UEs.

公开(公告)号：US20230136354A1

公开(公告)日：2023-05-04

申请号：US17452697

申请日：2021-10-28

Applicant: QUALCOMM Incorporated

Inventor： June NAMGOONG ,  Yang YANG ,  Hyojin LEE ,  Taesang YOO

IPC: H04W24/10 ,  H04B7/0456 ,  H04W72/04 ,  H04L5/00

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a transformer configuration that includes a transmitter neural network configured to be used to generate at least one latent vector corresponding to one or more computation tasks of a plurality of computation tasks associated with a transformer-based cross-node machine learning system. The UE may transmit the at least one latent vector based at least in part on instantiating the transmitter neural network. Numerous other aspects are described.

公开(公告)号：US20230136038A1

公开(公告)日：2023-05-04

申请号：US17516321

申请日：2021-11-01

Applicant: QUALCOMM Incorporated

Inventor： Mohamed Fouad Ahmed MARZBAN ,  Wooseok NAM ,  Tao LUO ,  Taesang YOO ,  Arumugam CHENDAMARAI KANNAN ,  Hamed PEZESHKI ,  Mahmoud TAHERZADEH BOROUJENI

IPC: H04W24/02 ,  H04W72/08

Abstract: Aspects of the present disclosure include methods, apparatuses, and computer readable media for receiving interference information relating to at least one of a scheduling granularity, a subcarrier spacing, a scheduler type, resource utilization, a number of active UEs, a number of active beams, an elevation and an azimuth angle of each of the number of active beams, a synchronization signal block index, or a semi-persistent scheduling configuration associated with at least one neighbor base station (BS), estimating or predicting, based on the interference information received, an interference power profile caused by the at least one neighbor BS, receiving at least one of data information or control information, and decoding the at least one of the data information or the control information based on the interference power profile.

公开(公告)号：US20230084883A1

公开(公告)日：2023-03-16

申请号：US17898180

申请日：2022-08-29

Applicant: QUALCOMM Incorporated

Inventor： Hamed PEZESHKI ,  Tao LUO ,  Taesang YOO ,  Mahmoud TAHERZADEH BOROUJENI ,  Eren BALEVI ,  Srinivas YERRAMALLI ,  Junyi LI

IPC: H04L5/00 ,  H04W72/12 ,  H04W24/02

Abstract: Aspects presented herein may enable a network entity to configure a group of UEs to simultaneously transmit reference signals and to simultaneously transmit gradient vectors to the network entity, such that the network entity may receive the gradient vectors from the group of UEs as an aggregated gradient vector over the air. In one aspect, a base transmits, to a group of UEs, a configuration that configures the group of UEs to simultaneously transmit one or more group-common reference signals and to simultaneously transmit one or more gradient vectors associated with a federated learning procedure. The network entity receives, from the group of UEs, the one or more group-common reference signals and the one or more gradient vectors based on the configuration via multiple channels. The network entity calculates an average gradient vector based on the one or more group-common reference signals and the one or more gradient vectors.

公开(公告)号：US20230084164A1

公开(公告)日：2023-03-16

申请号：US17801505

申请日：2020-04-17

Applicant: Bo CHEN ,  Pavan Kumar THALADEVUNI ,  Taesang YOO ,  Naga BHUSHAN ,  Jay Kumar SUNDARARAJAN ,  Ruifeng MA ,  June NAMGOONG ,  Krishna Kiran MUKKAVILLI ,  Tingfang JI ,  Hao XU ,  QUALCOMM Incorporated

Inventor： Bo CHEN ,  Pavan Kumar VITTHALADEVUNI ,  Taesang YOO ,  Naga BHUSHAN ,  Jay Kumar SUNDARARAJAN ,  Ruifeng MA ,  June NAMGOONG ,  Krishna Kiran MUKKAVILLI ,  Hao XU ,  Tingfang JI

IPC: H04B7/06

Abstract: A method of wireless communication, by a user equipment (UE), includes receiving multiple neural network training configurations for channel state feedback (CSF). Each configuration corresponds to a different neural network framework. The method also includes training each of a group of neural network decoder/encoder pairs in accordance with the received training configurations. A method of wireless communication, by a base station, includes transmitting multiple neural network training configurations to a user equipment (UE) for channel state feedback (CSF). Each configuration corresponds to a different neural network framework. The method also includes receiving a neural network decoder/encoder pair trained in accordance with the training configurations.

公开(公告)号：US20230019644A1

公开(公告)日：2023-01-19

申请号：US17374694

申请日：2021-07-13

Applicant: QUALCOMM Incorporated

Inventor： Roohollah AMIRI ,  Srinivas YERRAMALLI ,  Rajat PRAKASH ,  Taesang YOO

IPC: H04W4/02 ,  H04W24/10 ,  G01S5/02 ,  G01S5/10

Abstract: Disclosed are techniques for wireless positioning. In an aspect, a user equipment (UE) determines a positioning measurement of a first multipath component of a radio frequency (RF) signal transmitted by a transmission-reception point (TRP), determines a first additional positioning measurement of a second multipath component of the RF signal, determines a second additional positioning measurement of a third multipath component of the RF signal, and transmits a measurement report to a location server, the measurement report including at least the positioning measurement, the first additional positioning measurement, the second additional positioning measurement, and one or more parameters associated with the first additional positioning measurement and the second additional positioning measurement.

公开(公告)号：US20220405602A1

公开(公告)日：2022-12-22

申请号：US17352922

申请日：2021-06-21

Applicant: QUALCOMM Incorporated

Inventor： Taesang YOO ,  Kirty Prabhakar VEDULA ,  Pavan Kumar VITTHALADEVUNI ,  June NAMGOONG ,  Srinivas YERRAMALLI ,  Hamed PEZESHKI

IPC: G06N3/08 ,  H04W16/28 ,  H04B7/06 ,  H04B7/0413 ,  H04B17/391 ,  G06N3/04

Abstract: A method for wireless communication by a receiving device, includes receiving, from a transmitting device, a latent representation of a channel sequence for a wireless signal. A decoder applies a physical propagation channel model to the latent representation to reconstruct the channel sequence for the wireless signal.

公开(公告)号：US20220377844A1

公开(公告)日：2022-11-24

申请号：US17323242

申请日：2021-05-18

Applicant: QUALCOMM Incorporated

Inventor： Rajeev KUMAR ,  Eren BALEVI ,  Taesang YOO ,  Xipeng ZHU ,  Gavin Bernard HORN ,  Shankar KRISHNAN ,  Aziz GHOLMIEH

IPC: H04W88/08 ,  G06K9/62 ,  G06N20/00

Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for an ML model training procedure. A network entity may receive a trigger to activate an ML model training procedure based on at least one of an indication from an ML model repository or a protocol of the network entity. The network entity may transmit an ML model training request to activate the ML model training at one or more nodes. The one or more nodes may be associated with a RAN that may transmit, based on receiving the ML model training request, ML model training results indicative of a trained ML model. In aspects, an apparatus, such as a UE, may train the ML model based on an ML model training configuration received from the RAN, and transmit an ML model training report indicative of the trained ML model.

公开(公告)号：US20220338145A1

公开(公告)日：2022-10-20

申请号：US17230658

申请日：2021-04-14

Applicant: QUALCOMM Incorporated

Inventor： Hamed PEZESHKI ,  Tao LUO ,  Taesang YOO ,  Sony AKKARAKARAN

IPC: H04W56/00 ,  G06N20/00

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, an apparatus for wireless communication at a user equipment (UE) may receive assistance information indicating synchronization signal block (SSB) set information associated with a geographic area. The UE may perform a wireless communication action based at least in part on the SSB set information. Numerous other aspects are described.