公开(公告)号：US10278227B2

公开(公告)日：2019-04-30

申请号：US15694269

申请日：2017-09-01

Applicant: Google LLC

Inventor： Jibing Wang ,  Erik Stauffer ,  Aamir Akram

IPC: H04W4/00 ,  H04W76/15 ,  H04B7/0413 ,  H04W84/04 ,  H04W16/28 ,  H04B7/06 ,  H04B17/318

Abstract: In aspects of downlink-only fifth generation new radio, a mobile communication device includes a radio frequency transceiver, a radio frequency receiver, and a processor and memory system to implement a radio control manager application that establishes an LTE anchor link with a base station using the LTE transceiver, establishes a 5G NR downlink from the base station to the mobile communication device using the radio frequency receiver, and manages the 5G NR downlink via an uplink of the LTE anchor link. In another aspect, a mobile communication device estimates channel conditions for a 5G NR downlink, selects a precoding matrix to beamform the 5G NR downlink, and provides an indication of the selected precoding matrix via the LTE anchor link.

公开(公告)号：US20240419953A1

公开(公告)日：2024-12-19

申请号：US18701168

申请日：2022-10-12

Applicant: Google LLC

Inventor： Jibing Wang ,  Erik Stauffer

IPC: G06N3/0495 ,  H04W72/04

Abstract: Aspects describe communicating quantized machine-learning, ML, configuration information over a wireless network. A base station selects (605) a quantization configuration for quantizing ML configuration information for a deep neural network, DNN, where the quantization configuration indicates one or more quantization formats associated with quantizing the ML configuration information. The base station transmits (610) an indication of the quantization configuration to a user equipment, UE and transfers (615), over the wireless network and with the UE, quantized ML configuration information using the quantization configuration.

公开(公告)号：US12127179B2

公开(公告)日：2024-10-22

申请号：US17413494

申请日：2020-01-10

Applicant: GOOGLE LLC

Inventor： Erik Stauffer ,  Jibing Wang

IPC: H04W72/044 ,  H04W16/14

CPC classification number: H04W72/046 ,  H04W16/14

Abstract: The systems, methods, and techniques described in this disclosure allow different wireless systems that operate in accordance with different Radio Access Technologies (RATs) to coexist within a same frequency domain with minimal (if any) inter-RAT interference. Specifically, the described techniques allocate a respective, mutually-exclusive portion of a plurality of Space-Time-Frequency (STF) resources for use in communicating in accordance with each different RAT. For example, mutually-exclusive portions of spatial domain resources, time domain resources, and/or frequency domain resources may be respectively allocated for exclusive use by different RATs. A centralized, third-party controller (120) may perform the allocations, or the allocations may be cooperatively arrived at between systems supporting different RATs, e.g., in a peer-to-peer manner. STF resource allocations may be static and/or dynamic over time, and STF resources may be uniquely identified by respective resource identifiers.

公开(公告)号：US20240236862A1

公开(公告)日：2024-07-11

申请号：US18554428

申请日：2022-03-23

Applicant: Google LLC

Inventor： Jibing Wang ,  Erik Stauffer

IPC: H04W52/02

CPC classification number: H04W52/0261

Abstract: Techniques for improving, for a set of conditions at a UE, the usage of energy stored at a UE include determining a preferred or requested partitioning of the UE's stored energy usage during wireless data transfer between the UE and the base station (e.g., an amount or percentage of stored energy utilized by the UE for baseband signal processing with respect to the amount or percentage of energy utilized by the UE for radio interface signal processing tasks), and indicating the preferred partitioning to the base station or network. Based on the indication, the base station/network may modify the baseband communication scheme, parameters, and/or values, and/or the radio interface communication scheme, parameters, and/or values utilized for the wireless transfers of data between the base station and the UE, thereby better managing (and in some cases, optimizing) the UE's stored energy usage and increasing battery life at the UE.

公开(公告)号：US20230325679A1

公开(公告)日：2023-10-12

申请号：US18027059

申请日：2021-09-14

Applicant: Google LLC

Inventor： Jibing Wang ,  Erik Stauffer

IPC: G06N3/098 ,  G06N3/045

CPC classification number: G06N3/098 ,  G06N3/045

Abstract: Techniques and apparatuses are described for user equipment-coordination set (UECS) federated learning for deep neural networks (DNNs). A coordinating user equipment (UE) in a UECS communicates (1505), to at least a subset of UEs in the UECS, one or more update conditions that indicate when to generate updated ML configuration information for a respective DNN that processes UECS communications. The coordinating UE then receives (1510) one or more reports that include the updated ML configuration information from respective UEs of at least the subset of UEs. In aspects, the respective UE generates the updated ML configuration information using a training procedure and local input data. The coordinating UE determines (1515) a common UECS ML configuration by applying federated learning techniques to the updated ML configuration information and directs (1520) at least one UE in the subset to update the respective DNN using the at least one common UECS ML configuration.