公开(公告)号：US20220078626A1

公开(公告)日：2022-03-10

申请号：US17463053

申请日：2021-08-31

Applicant: QUALCOMM Incorporated

Inventor： Akash Sandeep DOSHI ,  Srinivas YERRAMALLI ,  Lorenzo FERRARI ,  Taesang YOO

IPC: H04W16/14 ,  H04W24/08 ,  G06N3/08 ,  G06N3/04

Abstract: A method of wireless communication performed by a first transmission device includes determining a set of spectrum sharing parameters based on sensing performed during a sensing period of a current time slot in a fixed contention based spectrum sharing system. The first transmission device shares a spectrum with a second transmission device. The method also includes determining, at a first artificial neural network of the first transmission device, a transmission device action, and/or a transmission parameter in response to receiving the set of spectrum sharing parameters. The method further includes transmitting, from the first transmission device, to a first receiving device during a data transmission phase of the current time slot based on the transmission device action and/or the transmission parameter.

公开(公告)号：US20250062811A1

公开(公告)日：2025-02-20

申请号：US18738268

申请日：2024-06-10

Applicant: QUALCOMM Incorporated

Inventor： June NAMGOONG ,  Akash Sandeep DOSHI ,  Taesang YOO ,  Hyojin LEE

IPC: H04B7/06 ,  H04B7/0456 ,  H04W72/0457

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a network node, 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 channel state information (CSI) feedback tasks of a plurality of CSI feedback tasks associated with a transformer-based cross-node machine learning system, and 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：US20220095119A1

公开(公告)日：2022-03-24

申请号：US17478669

申请日：2021-09-17

Applicant: QUALCOMM Incorporated

Inventor： Akash Sandeep DOSHI ,  Srinivas YERRAMALLI ,  Lorenzo FERRARI ,  Taesang YOO

IPC: H04W16/14 ,  H04W24/08 ,  G06N3/08

Abstract: A method of wireless communication performed by a first transmission device incudes receiving a first set of observations from a first receiving device based on transmissions from the first transmission device to the first receiving device at a previous time slot of a fixed contention-based spectrum sharing system. The first transmission device shares a spectrum with a second transmission device. The method also includes measuring an energy level from an ongoing data transmission of the second transmission device at a current time slot. The method further includes generating, at an artificial neural network of the first transmission device, at least one of a transmission determination, a set of transmission parameters, or a combination thereof, based on a second set of observations, the energy level, and a counter. The method also includes transmitting, to the first receiving device, during the current time slot based on at least one of the transmission determination, the set of transmission parameters, or the combination thereof.

公开(公告)号：US20250062810A1

公开(公告)日：2025-02-20

申请号：US18450821

申请日：2023-08-16

Applicant: QUALCOMM Incorporated

Inventor： June NAMGOONG ,  Akash Sandeep DOSHI ,  Taesang YOO ,  Hyojin LEE

IPC: H04B7/06 ,  H04B7/0456 ,  H04W72/0457

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a network node, decoder configuration information associated with 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 query-based cross-node machine learning system. The UE may receive, from the network node, query configuration information associated with a query-based decoder. The UE may transmit, to the network node and based at least in part on instantiation of the transmitter neural network by the UE, the at least one latent vector. Numerous other aspects are described.

公开(公告)号：US20240364437A1

公开(公告)日：2024-10-31

申请号：US18584572

申请日：2024-02-22

Applicant: QUALCOMM Incorporated

Inventor： Thomas Markus HEHN ,  Tribhuvanesh OREKONDY ,  Arash BEHBOODI ,  Ori SHENTAL ,  Taesang YOO ,  June NAMGOONG ,  Akash Sandeep DOSHI ,  Ashwin SAMPATH ,  Juan Carlos BUCHELI GARCIA ,  Joseph Binamira SORIAGA

IPC: H04B17/309 ,  H04B17/391

CPC classification number: H04B17/347 ,  H04B17/3913

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a network node may obtain position information associated with a first subset of network node positions, of a set of network node positions, in connection with a map associated with a wireless coverage area. The network node may obtain map information associated with the map and may determine, based on a machine learning component, a first plurality of predicted pathloss values associated with a second subset of network node positions of the set of network node positions. Numerous other aspects are described.