-
公开(公告)号:US12140689B2
公开(公告)日:2024-11-12
申请号:US17648218
申请日:2022-01-18
Applicant: QUALCOMM Incorporated
Inventor: Mohammed Ali Mohammed Hirzallah , Taesang Yoo , Srinivas Yerramalli , Rajat Prakash , Xiaoxia Zhang , Marwen Zorgui , Roohollah Amiri
Abstract: Disclosed are techniques for positioning. In an aspect, a network entity receives, from at least one network node, a measurement report including one or more radio frequency fingerprint (RFFP) measurements, wherein the one or more RFFP measurements include at least one RFFP measurement of at least one sidelink channel between a first user equipment (UE) and a second UE, determines one or more locations of a target UE based on the one or more RFFP measurements and a machine learning module, wherein the machine learning module is trained based on previously collected RFFP measurements of one or more downlink channels, RFFP measurements of one or more uplink channels, RFFP measurements of one or more sidelink channels, locations of one or more sidelink anchor UEs, locations of one or more base stations, or any combination thereof.
-
公开(公告)号:US12089291B2
公开(公告)日:2024-09-10
申请号:US17348522
申请日:2021-06-15
Applicant: QUALCOMM Incorporated
Inventor: Xipeng Zhu , Gavin Bernard Horn , Taesang Yoo , Rajeev Kumar , Shankar Krishnan , Aziz Gholmieh , Rajat Prakash , Eren Balevi
Abstract: Certain aspects of the present disclosure provide techniques and apparatus for determining neural network functions (NNFs) and configuring and using corresponding machine learning (ML) models for performing one or more ML-based wireless communications management procedures. An example method performed by a user equipment includes transmitting, to a base station (BS), UE capability information indicating at least one radio capability of the UE and at least one machine learning (ML) capability of the UE and receiving, from the BS based on the UE capability information, ML configuration information indicating at least one neural network function (NNF) and at least one ML model corresponding to the at least one NNF.
-
公开(公告)号:US12088378B2
公开(公告)日:2024-09-10
申请号:US17447778
申请日:2021-09-15
Applicant: QUALCOMM Incorporated
Inventor: Taesang Yoo , Pavan Kumar Vitthaladevuni , Naga Bhushan , Krishna Kiran Mukkavilli , Tingfang Ji , Hwan Joon Kwon , June Namgoong , Jay Kumar Sundararajan , Sooryanarayanan Gopalakrishnan , Wanshi Chen
IPC: H04J3/14 , G06N3/02 , H04B7/0417 , H04B7/06 , H04L5/00
CPC classification number: H04B7/0626 , G06N3/02 , H04B7/0417 , H04L5/0051
Abstract: A base station may precode a first reference signal using a first precoder (P1) and at least one second reference signal using at least one second precoder (P2). At least two UEs may measure the first reference signal and the at least one second reference signal, and transmit channel state feedback based on the measuring (m11 and m12 for a first UE, and m21 and m22 for a second UE). The channel state feedback may comprise channel state information compressed by at least one neural network. The base station may derive a higher-level precoder (W) for multiple-input multiple-output (MIMO) downlink transmission to the at least two UEs.
-
公开(公告)号:US20240292338A1
公开(公告)日:2024-08-29
申请号:US18174258
申请日:2023-02-24
Applicant: QUALCOMM Incorporated
Inventor: Akash Sandeep Doshi , June Namgoong , Taesang Yoo , Hyojin Lee
CPC classification number: H04W52/146 , H04W52/242 , H04W52/245
Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive, from a network entity, an activation signal that transitions the UE from a first mode where the UE is capable of determining a channel quality using reference signals from the network entity to a second mode where the UE is capable of determining the channel quality using radio maps associated with the network entity. The UE may receive, based at least in part on the activation signal, an indication of a set of radio maps associated with the network entity. The UE may perform a channel performance procedure to determine the channel quality associated with the network entity using the set of radio maps and a geographic location of the UE, the geographic location of the UE being mapped within the set of radio maps associated with the network entity.
-
公开(公告)号:US12041534B2
公开(公告)日:2024-07-16
申请号:US17412634
申请日:2021-08-26
Applicant: QUALCOMM Incorporated
Inventor: Shankar Krishnan , Xipeng Zhu , Taesang Yoo , Rajeev Kumar , Gavin Bernard Horn , Aziz Gholmich , Eren Balevi
IPC: H04W48/16 , H04W24/10 , H04W48/08 , H04W72/542
CPC classification number: H04W48/16 , H04W24/10 , H04W48/08 , H04W72/542
Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may communicate with a network entity within a wireless communications network. The UE may transmit a request for information to the network entity and, in response to the request, the UE may receive the requested information from the network entity. For example, the UE may request data from one or more data repositories associated with the network entity. In some examples, the information request may be associated with one or more measurements associated with operations of the network. In some instances, the UE may use a machine learning model to perform training or inference based on the information associated with the one or more measurements.
-
公开(公告)号:US12035256B2
公开(公告)日:2024-07-09
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
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:US12015947B2
公开(公告)日:2024-06-18
申请号:US17365510
申请日:2021-07-01
Applicant: QUALCOMM Incorporated
Inventor: Pavan Kumar Vitthaladevuni , Taesang Yoo , Naga Bhushan
CPC classification number: H04W28/06 , G06N20/20 , H03M7/6011 , H04W24/10 , H03M7/3059
Abstract: Certain aspects of the present disclosure provide techniques for measurement encoding and decoding using neural networks to compress and decompress measurement data. One example method generally includes: generating, via each of a plurality of neural network encoders operating on measurement data, a compressed measurement based on a respective portion of the measurement data, wherein each of the neural network encoders is based on the same neural network model; generating at least one message indicative of the measurement data based on the compressed measurements; and transmitting the at least one message.
-
公开(公告)号:US11984955B2
公开(公告)日:2024-05-14
申请号:US17801505
申请日:2020-04-17
Applicant: 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
CPC classification number: H04B7/0626 , H04B7/0695
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.
-
349.
公开(公告)号:US11971500B2
公开(公告)日:2024-04-30
申请号:US17461397
申请日:2021-08-30
Applicant: QUALCOMM Incorporated
Inventor: Weimin Duan , Alexandros Manolakos , Seyong Park , Renqiu Wang , Hwan Joon Kwon , Krishna Kiran Mukkavilli , Taesang Yoo
CPC classification number: G01S7/006 , G01S13/003
Abstract: In an aspect, a radar controller determines a radar slot format that configures transmission of a reference radar signal on a first symbol over a first link from a first base station to a second base station followed by at least one target radar signal on at least one second symbol over at least one second link from the first base station to the second base station, and transmits an indication of the radar slot format to the first base station and the second base station. The first base station transmits, and the second base station receives, the reference radar signal and the at least one target radar signal in accordance with the radar slot format.
-
公开(公告)号:US11968151B2
公开(公告)日:2024-04-23
申请号:US17675980
申请日:2022-02-18
Applicant: QUALCOMM Incorporated
Inventor: Yeliz Tokgoz , Jay Kumar Sundararajan , Krishna Kiran Mukkavilli , Hwan Joon Kwon , Naga Bhushan , Taesang Yoo , Tingfang Ji
IPC: H04W4/00 , H04B7/06 , H04L5/00 , H04W72/044 , H04W72/541
CPC classification number: H04L5/0073 , H04B7/0639 , H04L5/0082 , H04W72/046 , H04W72/541
Abstract: A method of wireless communication by a first network device includes predicting spatial inter-cell downlink interference experienced by a UE. The method also includes communicating with a second network device to reduce the spatial inter-cell downlink interference in a direction of the UE by protecting resources across selected resource sets.
-
-
-
-
-
-
-
-
-