公开(公告)号：US12165020B2

公开(公告)日：2024-12-10

申请号：US17139561

申请日：2020-12-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Di Wu ,  Jikun Kang ,  Hang Li ,  Xi Chen ,  Yi Tian Xu ,  Dmitriy Rivkin ,  Taeseop Lee ,  Intaik Park ,  Michael Jenkin ,  Xue Liu ,  Gregory Lewis Dudek

IPC: G06N20/00 ,  G06F18/20 ,  G06F18/21 ,  G06N3/044 ,  G06N3/08 ,  H04W28/02 ,  H04W28/08

Abstract: Rapid and data-efficient training of an artificial intelligence (AI) algorithm are disclosed. Ground truth data are not available and a policy must be learned based on limited interactions with a system. A policy bank is used to explore different policies on a target system with shallow probing. A target policy is chosen by comparing a good policy from the shallow probing with a base target policy which has evolved over other learning experiences. The target policy then interacts with the target system and a replay buffer is built up. The base target policy is then updated using gradients found with respect to the transition experience stored in the replay buffer. The base target policy is quickly learned and is robust for application to new, unseen, systems.

公开(公告)号：US11941663B2

公开(公告)日：2024-03-26

申请号：US17829883

申请日：2022-06-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Xi Chen ,  Hang Li ,  Chenyi Zhou ,  Xue Liu ,  Di Wu ,  Gregory L. Dudek

IPC: G06Q30/0251 ,  G06N3/04 ,  G06N3/08 ,  H04R1/32 ,  H04R3/12 ,  H04W4/029 ,  G06F1/3231 ,  H04W84/12

CPC classification number: G06Q30/0261 ,  G06N3/04 ,  G06N3/08 ,  G06Q30/0267 ,  H04R1/32 ,  H04R3/12 ,  H04W4/029 ,  G06F1/3231 ,  H04W84/12

Abstract: A location-aware electronic device is provided. The electronic device trains feature extraction layers, reconstruction layers, and classification layers. The training may be based on a reconstruction loss and/or a clustering loss. The electronic device processes a fingerprint to obtain an augmented fingerprint using randomization based on statistics of the fingerprint. The feature extraction layers provide feature data to both the reconstruction layers and the classification layers. The classification layers operate on the codes to obtain an estimated location label. An application processor operates on the estimated location label to provide a location-aware application result to a person.

公开(公告)号：US11847591B2

公开(公告)日：2023-12-19

申请号：US16953586

申请日：2020-11-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Di Wu ,  Yi Tian Xu ,  Xi Chen ,  Ju Wang ,  Michael Jenkin ,  Hang Li ,  Gregory Lewis Dudek ,  Xue Liu

IPC: G06Q10/04 ,  G06N20/20 ,  G06Q50/06

CPC classification number: G06Q10/04 ,  G06N20/20 ,  G06Q50/06

Abstract: A method, computer program, and computer system are provided for load forecasting. Datasets corresponding to source machine learning models and a target domain base model are identified. A set of forecasting models corresponding to the identified datasets are learned. An ensemble model is determined from the learned set of forecasting models based on gradient boosting. An available resource is allocated based on the ensemble model.

公开(公告)号：US11363416B2

公开(公告)日：2022-06-14

申请号：US16913493

申请日：2020-06-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Xi Chen ,  Hang Li ,  Chenyi Zhou ,  Xue Liu ,  Di Wu ,  Gregory L. Dudek

IPC: H04W4/029 ,  H04R1/32 ,  G06Q30/02 ,  G06N3/04 ,  G06N3/08 ,  H04R3/12 ,  G06F1/3231 ,  H04W84/12

Abstract: A location-aware electronic device is provided. The electronic device trains feature extraction layers, reconstruction layers, and classification layers. The training may be based on a reconstruction loss and/or a clustering loss. The electronic device processes a fingerprint to obtain an augmented fingerprint using randomization based on statistics of the fingerprint. The feature extraction layers provide feature data to both the reconstruction layers and the classification layers. The classification layers operate on the codes to obtain an estimated location label. An application processor operates on the estimated location label to provide a location-aware application result to a person.

公开(公告)号：US12052584B2

公开(公告)日：2024-07-30

申请号：US18199666

申请日：2023-05-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Xi Chen ,  Ju Wang ,  Hang Li ,  Yi Tian Xu ,  Di Wu ,  Xue Liu ,  Gregory Lewis Dudek ,  Taeseop Lee ,  Intaik Park

IPC: H04W16/18 ,  H04W16/22

CPC classification number: H04W16/22 ,  H04W16/18

Abstract: Transfer learning based on prediction determines a similarity between a source base station and a target base station. Importance of parameters is determined and training is adjusted to respect the importance of parameters. A lack of historical data is compensated by selecting a base station as source base station which has a larger amount of historical data.

公开(公告)号：US11870831B2

公开(公告)日：2024-01-09

申请号：US17549283

申请日：2021-12-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Di Wu ,  Ye Sun ,  Siyuan Huang ,  Chunbo Zhu ,  Lie Zou

IPC: H04L65/612 ,  H04N21/2187 ,  H04N21/231 ,  H04N21/236 ,  H04N21/239 ,  H04N21/262 ,  H04N21/6587 ,  H04L65/70 ,  H04L65/75

CPC classification number: H04L65/612 ,  H04L65/70 ,  H04L65/765 ,  H04N21/2187 ,  H04N21/2393 ,  H04N21/23106 ,  H04N21/23605 ,  H04N21/26283 ,  H04N21/6587

Abstract: A transmission control method and an apparatus of multimedia streaming data are provided. The method includes, when an edge server is to transmit a data packet of a video requested by user equipment to the user equipment, and it is a first time that the edge server transmits the data packet according to the request, filtering, by the edge server, the data packet, and transmitting the filtered data packet to the user equipment, otherwise, directly transmitting the data packet to the user equipment, wherein the video includes an on-demand video and a real-time video, and playing, by the user equipment, the video directly according to the received data packet.

公开(公告)号：US11751115B2

公开(公告)日：2023-09-05

申请号：US17363918

申请日：2021-06-30

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jikun Kang ,  Xi Chen ,  Di Wu ,  Yi Tian Xu ,  Xue Liu ,  Gregory Lewis Dudek ,  Taeseop Lee ,  Intaik Park

IPC: H04W36/22 ,  G06N3/08 ,  H04W24/02 ,  G06N3/044 ,  H04W28/086

CPC classification number: H04W36/22 ,  G06N3/044 ,  G06N3/08 ,  H04W24/02 ,  H04W28/0861

Abstract: Hybrid use of dual policies is provided to improve a communication system. In a multiple access scenario, when an inactive user equipment (UE) transitions to an active state, it may be become a burden to a radio cell on which it was previously camping. In some embodiments, hybrid load balancing is provided using a hierarchical machine learning paradigm based on reinforcement learning in which an LSTM generates a goal for one policy influencing cell reselection so that another policy influencing handover over active UEs can be assisted. The communication system as influenced by the policies is modeled as a Markov decision process (MDP). The policies controlling the active UEs and inactive UEs are coupled, and measureable system characteristics are improved. In some embodiments, policy actions depend at least in part on energy saving.

公开(公告)号：US11461699B2

公开(公告)日：2022-10-04

申请号：US17008218

申请日：2020-08-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hang Li ,  Xi Chen ,  Di Wu ,  Xue Liu

IPC: G06N20/00 ,  H04W4/02 ,  G01S5/02 ,  G06N5/04 ,  G01P13/00 ,  H04W84/12

Abstract: A method of location determination with a WiFi transceiver and an AI model includes jointly training, based on various losses: a feature extractor, a location classifier, and a domain classifier. The domain classifier may include a first domain classifier and a second domain classifier. The losses used for training tend to cause feature data from the feature extractor to cluster even if a physical object in an environment has moved after training is completed. Then, the location classifier is able to accurately estimate the position of, for example, a person in a room, even if a door or window has changed from open to close or close to open between the time of training and the time of estimating the person's position.

公开(公告)号：US20240422667A1

公开(公告)日：2024-12-19

申请号：US18631726

申请日：2024-04-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Junliang LUO ,  Yi Tian Xu ,  Di Wu ,  Xue Liu ,  Gregory Lewis Dudek

IPC: H04W52/02 ,  H04L41/16 ,  H04W28/24

Abstract: A method performed by at least one processor of a network device in communication with a plurality of base stations, the method including: receiving historical data collected by one or more base stations from the plurality of base stations, the historical data indicating one or more of a power consumption, handover data, and quality of service (QOS); generating, from the historical data, training data comprising a plurality of cell states and a corresponding random action for each cell state; and training one or more neural network estimators based on the training data, where the one or more neural network estimators comprise one or more of a power consumption estimator, a QoS estimator, and a handover prediction estimator, and where each base station from the plurality of base stations is associated with a respective cell.

公开(公告)号：US11991531B2

公开(公告)日：2024-05-21

申请号：US17570767

申请日：2022-01-07

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chengming Hu ,  Xi Chen ,  Ju Wang ,  Hang Li ,  Jikun Kang ,  Yi Tian Xu ,  Xue Liu ,  Di Wu ,  Seowoo Jang ,  Intaik Park ,  Gregory Lewis Dudek

IPC: H04W16/22 ,  G06N3/047 ,  H04L41/14 ,  H04L41/147 ,  H04L41/16 ,  H04W24/02 ,  H04W24/08

CPC classification number: H04W16/22 ,  G06N3/047 ,  H04L41/145 ,  H04L41/147 ,  H04L41/16 ,  H04W24/02 ,  H04W24/08

Abstract: A method is provided. The method includes receiving a first dimension set, extracting a first latent feature set from the first dimension set, training a first base predictor based on the first feature set, generating a second dimension set based on the first dimension set, the second dimension set having fewer dimensions than the first dimension set, extracting a second latent feature set from the second dimension set, training a second base predictor based on the second feature set, and generating a traffic prediction based on the first base predictor and the second base predictor.