-
公开(公告)号：US20250086450A1
公开(公告)日：2025-03-13
申请号：US18463108
申请日：2023-09-07
Applicant: QUALCOMM Incorporated
Inventor： Kyle Chi GUAN , Qing LI , Himaja KESAVAREDDIGARI , Kapil GULATI , Hong CHENG
IPC: G06N3/08
Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning training process. Input data for a first portion of a neural network is accessed, and output data is generated based on processing the input data using the first portion of the neural network. At a first point in time, the output data is transmitted to a second computing system for the second computing system to update one or more parameters of a second portion of the neural network based on the output data. It is determined, at a second point in time subsequent to the first point in time, that one or more communication criteria are not satisfied. In response to the determining, reduced communication training of the neural network is performed, the performing comprising reducing an amount of data transmitted for one or more rounds of training.
-
公开(公告)号：US20230308892A1
公开(公告)日：2023-09-28
申请号：US17649763
申请日：2022-02-02
Applicant: QUALCOMM Incorporated
Inventor： Qing LI , Kapil GULATI , Hong CHENG , Kyle Chi GUAN , Himaja KESAVAREDDIGARI
Abstract: Aspects presented herein may enable wireless communications to be adaptive to a dynamic environment, where wireless devices may manage wireless communications, such as performing beam managements, based at least in part on environmental conditions. In one aspect, a network entity receives, from a sensor device or a UE, a request for an ML data service. The network entity establishes, with the sensor device or the UE, the ML data service based on the request. The network entity receives, from the sensor device, ML data including a set of features extracted from at least one sensor of the sensor device or information indicative of at least one beam for the ML data service. The network entity transmits, to the UE, a beam indication to modify the at least one beam based at least in part on the ML data received from the sensor device during the ML data service.
-
3.发明公开公开(公告)号：US20240214814A1
公开(公告)日：2024-06-27
申请号：US18145005
申请日：2022-12-21
Applicant: QUALCOMM Incorporated
Inventor： Himaja KESAVAREDDIGARI , Qing LI , Kapil GULATI , Hong CHENG , Kyle Chi GUAN
IPC: H04W12/122 , H04W12/63
CPC classification number: H04W12/122 , H04W12/63
Abstract: The apparatus may be a first wireless device configured to receive a first indication that a second wireless device associated with the first wireless device and a network device is classified as providing data of a first type. The apparatus may further be configured to receive a first set of data elements from the second wireless device. The apparatus may be configured to identify, based on the first set of data elements and a second set of data elements available at the first wireless device, that the classification of the second wireless device may be inaccurate and transmit, based on the identification that the classification of the second wireless device may be inaccurate, at least one of a second indication for the second wireless device to transmit a re-evaluation request or a third indication to the second wireless device to terminate a communication session with the first wireless device.
-
4.发明公开公开(公告)号：US20240214812A1
公开(公告)日：2024-06-27
申请号：US18069994
申请日：2022-12-21
Applicant: QUALCOMM Incorporated
Inventor： Himaja KESAVAREDDIGARI , Qing LI , Kapil GULATI , Hong CHENG
IPC: H04W12/122 , H04W12/082
CPC classification number: H04W12/122 , H04W12/082
Abstract: An apparatus configured to revoke, for one or more wireless devices, access to at least one service for at least one context in response to the one or more wireless devices providing incorrect data elements for a wireless communication service, and output an indication for data from the one or more wireless devices to be excluded from subsequent processing for the at least one service in the at least one context. An additional apparatus configured to provide a first set of data elements for processing by a set of service entities, receive an indication that at least one component of the first wireless device provides incorrect data elements for a wireless communication service, and omit information derived from the at least one component of the first wireless device in subsequent sets of data elements corresponding to the first set of data elements provided for the set of service entities.
-
公开(公告)号：US20240214797A1
公开(公告)日：2024-06-27
申请号：US18069988
申请日：2022-12-21
Applicant: QUALCOMM Incorporated
Inventor： Himaja KESAVAREDDIGARI , Kapil GULATI , Hong CHENG , Qing LI , Kyle Chi GUAN , Mahmoud ASHOUR
IPC: H04W12/00
CPC classification number: H04W12/009
Abstract: An apparatus may be a UE configured to receive, from a network entity associated with a machine learning procedure, a first indication that a first set of data elements transmitted by the wireless device at a first time is categorized as misinformation and that, based on the categorization of the first set of data elements as misinformation, the network entity will temporarily exclude data from the wireless device from propagation as input for a subsequent machine learning procedure. The apparatus may further be configured to receive a second indication of a set of criteria for requesting a reevaluation of the categorization and transmit, based on meeting one or more criteria in the set of criteria, a second set of data elements to the network entity at a second time.
-
Patent Agency Ranking
公开(公告)号：US20230422117A1
公开(公告)日：2023-12-28
申请号：US17806164
申请日：2022-06-09
Applicant: QUALCOMM Incorporated
Inventor： Qing LI , Hong CHENG , Kapil GULATI , Kyle Chi GUAN , Himaja KESAVAREDDIGARI
CPC classification number: H04W36/08 , H04W74/0833 , H04W36/0058
Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit, to first network node for use by a first inference host associated with a first network node, first machine learning data associated with a machine learning service. The UE may receive, from the first network node, a handover command communication indicating that the UE is to perform a handover from the first network node to a second network node, wherein the handover command communication indicates machine learning inference information associated with a second inference host that is associated with the second network node. The UE may transmit, to the second network node for use by the second inference host associated with the second network node, second machine learning data for the machine learning service based at least in part on receiving the handover command communication. Numerous other aspects are described.
-
公开(公告)号：US20220286875A1
公开(公告)日：2022-09-08
申请号：US17249500
申请日：2021-03-03
Applicant: QUALCOMM Incorporated
Inventor： Himaja KESAVAREDDIGARI , Chang-Sik CHOI , Kapil GULATI , Anantharaman BALASUBRAMANIAN
IPC: H04W24/04 , H04W4/40 , H04W16/28 , H04B7/0408 , H04B7/06
Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first wireless communication device may determine that a second wireless communication device is to communicate with a third wireless communication device using one or more beams that pass through a target area. The first wireless communication device may obtain information indicating a first object that is approaching the target area and that has a beam blocking size above a threshold. The first wireless communication device may cause the one or more of the second wireless communication device or third wireless communication device to adjust usage of the one or more beams during an expected blockage time in the target area. Numerous other aspects are described.
-
公开(公告)号：US20250016588A1
公开(公告)日：2025-01-09
申请号：US18348325
申请日：2023-07-06
Applicant: QUALCOMM Incorporated
Inventor： Mahmoud ASHOUR , Kapil GULATI , Himaja KESAVAREDDIGARI
IPC: H04W24/08 , H04B7/08 , H04B17/318 , H04W48/08
Abstract: Aspects of the disclosure are directed to method of selecting receive beams using a neural network (e.g., via a reinforcement learning process). In some examples, a user equipment (UE) may select one or more receive beams for receiving synchronization signal blocks (SSBs) of a first synchronization signal burst set (SSBS). In some examples, the UE may measure a power of a first SSB of the first SSBS received via a first receive beam of the one or more receive beams. In some examples, the UE may store, in a local storage, the measured power of the first SSB and at least one parameter associated with receiving the first SSB.
-
公开(公告)号：US20240284522A1
公开(公告)日：2024-08-22
申请号：US18170761
申请日：2023-02-17
Applicant: QUALCOMM Incorporated
Inventor： Sourjya Dutta , Kapil GULATI , Mahmoud ASHOUR , Himaja KESAVAREDDIGARI , Kyle Chi GUAN , Navid ABEDINI
Abstract: Aspects of the present disclosure provide apparatus, methods, processing systems, and computer readable mediums for user equipment (UE) managing of assisting devices for Uu link relay, such as, for example, vehicles equipped with reconfigurable intelligent surfaces (RIS), or UE-controlled repeaters. In some aspects of the disclosure, assisting devices may use sensor-based perception and machine learning capabilities to enhance control of the transmission mode configuration of the assisting device.
-
公开(公告)号：US20240107594A1
公开(公告)日：2024-03-28
申请号：US17934986
申请日：2022-09-23
Applicant: QUALCOMM Incorporated
Inventor： Kyle Chi GUAN , Anantharaman BALASUBRAMANIAN , Mahmoud ASHOUR , Kapil GULATI , Himaja KESAVAREDDIGARI , Qing LI , Hong CHENG , Preeti KUMARI
Abstract: Aspects presented herein may enable a first UE to utilize inference results provided by at least a second UE to improve its inference accuracy. In one aspect, a first UE establishes an ML inference result sharing session with one or more second UEs for at least one ML inference task. The first UE receives a first set of ML inference results associated with the at least one ML inference task, where the first set of ML inference results is received from the one or more second UEs during the ML inference result sharing session. The first UE estimates an aggregated ML inference result based on at least one of the first set of ML inference results or a second set of ML inference results, where the second set of ML inference results is configured by the first UE for the at least one ML inference task.
-
-
-
-
-
-
-
-
-
Search Results
15
records
(took 0.013 seconds)
