公开(公告)号：US20240323870A1

公开(公告)日：2024-09-26

申请号：US18732407

申请日：2024-06-03

Applicant: QUALCOMM Incorporated

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

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

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

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：US20240314606A1

公开(公告)日：2024-09-19

申请号：US18185940

申请日：2023-03-17

Applicant: QUALCOMM Incorporated

Inventor： Hua WANG ,  Tao LUO ,  Taesang YOO ,  Junyi LI

IPC: H04W24/10 ,  H04B17/318 ,  H04B17/336

CPC classification number: H04W24/10 ,  H04B17/328 ,  H04B17/336

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 reference signal associated with a beam management. The UE may perform a layer 1 (L1) reference signal received power (RSRP) or an L1 signal-to-interference-plus-noise ratio (SINR) (RSRP/SINR) measurement based at least in part on the reference signal. The UE may determine, based at least in part on a search of a lookup table (LUT), an entry in the LUT that corresponds to the L1 RSRP/SINR measurement. The UE may transmit, to the network node, an L1 RSRP/SINR measurement report that indicates the entry in the LUT. Numerous other aspects are described.

公开(公告)号：US20240289687A1

公开(公告)日：2024-08-29

申请号：US18434080

申请日：2024-02-06

Applicant: QUALCOMM Incorporated

Inventor： Rajeev KUMAR ,  Aziz GHOLMIEH ,  Taesang YOO ,  Eren BALEVI

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit an indication of functionalities associated with artificial intelligence or machine learning (AI/ML) models supported by the UE. The UE may receive one or more AI/ML models associated with the functionalities. Numerous other aspects are described.

公开(公告)号：US20240267725A1

公开(公告)日：2024-08-08

申请号：US18514178

申请日：2023-11-20

Applicant: QUALCOMM Incorporated

Inventor： Jay Kumar SUNDARARAJAN ,  Eren BALEVI ,  Taesang YOO ,  Rajeev KUMAR ,  Aziz GHOLMIEH

IPC: H04W8/24 ,  H04W24/02

CPC classification number: H04W8/24 ,  H04W24/02

Abstract: Certain aspects of the present disclosure provide techniques for exchanging information between user equipments (UEs) and network entities regarding which models the UEs and network entities support. A method that may be performed by a UE includes: obtaining an indication of one or more machine learning (ML) based network-side models applicable at a network entity; and transmitting signaling indicating one or more of the ML-based network-side models supported by the UE.

公开(公告)号：US20240265306A1

公开(公告)日：2024-08-08

申请号：US18525577

申请日：2023-11-30

Applicant: QUALCOMM Incorporated

Inventor： Eren BALEVI ,  Taesang YOO ,  Jay Kumar SUNDARARAJAN ,  Rajeev KUMAR ,  Aziz GHOLMIEH

IPC: G06N20/00 ,  H04W24/02

CPC classification number: G06N20/00 ,  H04W24/02

Abstract: A method for wireless communication by a user equipment (UE) includes collaborating with a network device in accordance with a selected network-UE collaboration level of a number of network-UE collaboration levels for machine learning operations. At least one of the network-UE collaboration levels comprises a number of sub-categories. The UE may transmit an indication of a level of support for the selected network-UE collaboration level. The sub-categories may correspond to a life cycle management type and a model transfer/delivery format. The UE may also receive a machine learning configuration based on the level of support.

公开(公告)号：US20240223465A1

公开(公告)日：2024-07-04

申请号：US18415896

申请日：2024-01-18

Applicant: QUALCOMM Incorporated

Inventor： Xipeng ZHU ,  Gavin Bernard HORN ,  Vanitha Aravamudhan KUMAR ,  Vishal DALMIYA ,  Shankar KRISHNAN ,  Rajeev KUMAR ,  Taesang YOO ,  Eren BALEVI ,  Aziz GHOLMIEH ,  Rajat PRAKASH

IPC: H04L41/16 ,  G06N20/00 ,  H04L41/0803 ,  H04W88/08

CPC classification number: H04L41/16 ,  H04L41/0803 ,  H04W88/08 ,  G06N20/00

Abstract: Methods, systems, and devices for wireless communications are described. In some examples, a wireless communications system may support machine learning and may configure a user equipment (UE) for machine learning. The UE may transmit, to a base station, a request message that includes an indication of a machine learning model or a neural network function based at least in part on a trigger event. In response to the request message, the base station may transmit a machine learning model, a set of parameters corresponding to the machine learning model, or a configuration corresponding to a neural network function and may transmit an activation message to the UE to implement the machine learning model and the neural network function.

公开(公告)号：US20240161012A1

公开(公告)日：2024-05-16

申请号：US18457116

申请日：2023-08-28

Applicant: QUALCOMM Incorporated

Inventor： Hamed PEZESHKI ,  Taesang YOO ,  Jay Kumar SUNDARARAJAN

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: An apparatus, method and computer-readable media are disclosed for performing wireless communications. For example, a first network device can transmit, to one or more second network devices, configuration information associated with a trained machine learning model. The first network device can receive, from the one or more second network devices, information associated with a first fine-tuned machine learning model based on adaptation of parameters of the trained machine learning model. The first network device can further output, for transmission to one or more third network devices, configuration information associated with the first fine-tuned machine learning model.

公开(公告)号：US20240133995A1

公开(公告)日：2024-04-25

申请号：US18047946

申请日：2022-10-18

Applicant: QUALCOMM Incorporated

Inventor： Mohammed Ali Mohammed HIRZALLAH ,  Srinivas YERRAMALLI ,  Yun CHEN ,  Rajat PRAKASH ,  Taesang YOO

IPC: G01S5/02

CPC classification number: G01S5/02525 ,  G01S5/0264

Abstract: In an aspect, a method performed by a network node includes obtaining a first plurality of radio frequency fingerprint positioning (RFFP) measurements corresponding to a plurality of known displacements between positions of a user equipment (UE); and training a positioning model to provide a position estimate of the UE, wherein the training of the positioning model is at least based on the first plurality of RFFP measurements and the known displacements between the positions of the UE corresponding to the first plurality of RFFP measurements.

公开(公告)号：US20240129008A1

公开(公告)日：2024-04-18

申请号：US18543390

申请日：2023-12-18

Applicant: QUALCOMM Incorporated

Inventor： Taesang YOO ,  Weiliang ZENG ,  Naga BHUSHAN ,  Krishna Kiran MUKKAVILLI ,  Tingfang JI ,  Yongbin WEI ,  Sanaz BARGHI

IPC: H04B7/06 ,  G06N20/00 ,  H04B7/0456

CPC classification number: H04B7/0626 ,  G06N20/00 ,  H04B7/0486 ,  H04B7/0639

Abstract: Various aspects of the present disclosure generally relate to neural network based channel state information (CSI) feedback. In some aspects, a device may obtain a CSI instance for a channel, determine a neural network model including a CSI encoder and a CSI decoder, and train the neural network model based at least in part on encoding the CSI instance into encoded CSI, decoding the encoded CSI into decoded CSI, and computing and minimizing a loss function by comparing the CSI instance and the decoded CSI. The device may obtain one or more encoder weights and one or more decoder weights based at least in part on training the neural network model. Numerous other aspects are provided.

公开(公告)号：US20240089905A1

公开(公告)日：2024-03-14

申请号：US17932174

申请日：2022-09-14

Applicant: QUALCOMM Incorporated

Inventor： Sooryanarayanan GOPALAKRISHNAN ,  Jay Kumar SUNDARARAJAN ,  Taesang YOO ,  Naga BHUSHAN ,  Guttorm Ringstad OPSHAUG ,  Grant MARSHALL ,  Chandrakant MEHTA ,  Zongjun QI

IPC: H04W64/00 ,  G01S5/02 ,  H04W24/08

CPC classification number: H04W64/003 ,  G01S5/02526 ,  H04W24/08

Abstract: Aspects presented herein may enhance the accuracy and/or latency of UE positioning based on crowd-sourcing, where a network entity may compute a position estimate of a UE based on neighbor-cell scan data from the UE and one or more reference UEs. In one aspect, a network entity receives a first set of measurements associated with at least one cell from a UE. The network entity performs a position estimation of the UE based on at least one of the first set of measurements associated with the at least one cell, a second set of measurements for each of a set of reference UEs, or a location of each of the set of reference UEs via an ML model, where the UE and the set of reference UEs include at least one common cell.