公开(公告)号：US20240348478A1

公开(公告)日：2024-10-17

申请号：US18749904

申请日：2024-06-21

申请人： HUAWEI TECHNOLOGIES CO., LTD.

发明人： Jiaxuan CHEN ,  Haicun HANG ,  Yiqun WU ,  Jing LIANG ,  Huangping JIN

IPC分类号： H04L25/02 ,  H03M7/30

CPC分类号： H04L25/0202 ,  H03M7/70

摘要： This disclosure relates to a communication method and apparatus. A terminal device obtains M channel estimation results corresponding to M time units, where M is greater than 1. The terminal device performs joint compression on the M channel estimation results by using an encoder network, to obtain N pieces of compression information. The terminal device sends the N pieces of compression information to an access network device. Because the terminal device performs joint compression, correlation between downlink channels at different time points is fully utilized. The access network device recovers the N pieces of compression information obtained through joint compression, so that more accurate and effective downlink channel information can be obtained.

公开(公告)号：US12093972B1

公开(公告)日：2024-09-17

申请号：US18427716

申请日：2024-01-30

申请人： AtomBeam Technologies Inc.

发明人： Zhu Li ,  Brian R. Galvin ,  Paras Maharjan

IPC分类号： H03M7/00 ,  G06N3/0895 ,  G06Q30/0203 ,  H03M7/30

CPC分类号： G06Q30/0203 ,  G06N3/0895 ,  H03M7/3059 ,  H03M7/70

摘要： A system and methods for upsampling of decompressed financial time-series data after lossy compression using a neural network that integrates AI-based techniques to enhance compression quality. It incorporates a novel deep-learning neural network that upsamples decompressed data to restore information lost during lossy compression, taking advantage of cross-correlations between time-series data sets.

公开(公告)号：US20240274241A1

公开(公告)日：2024-08-15

申请号：US18392060

申请日：2023-12-21

申请人： Life Technologies Corporation

发明人： Cheng-Zong BAI

IPC分类号： G16B50/50 ,  C12Q1/6869 ,  G16B20/00 ,  G16B20/20 ,  G16B20/40 ,  G16B30/00 ,  G16B30/10 ,  G16B40/00 ,  G16B40/10 ,  G16B50/00 ,  H03M7/30

CPC分类号： G16B50/50 ,  G16B20/00 ,  G16B20/20 ,  G16B20/40 ,  G16B30/00 ,  G16B40/00 ,  G16B40/10 ,  G16B50/00 ,  H03M7/70 ,  C12Q1/6869 ,  G16B30/10

摘要： A method for compressing molecular tagged sequence data includes: grouping sequence reads associated with a molecular tag sequence to form a family of sequence reads, corresponding vectors of flow space signal measurements and corresponding sequence alignments, calculating an arithmetic mean of the corresponding vectors of flow space signal measurements to form a vector of consensus flow space signal measurements, calculating a standard deviation of the corresponding vectors of flow space signal measurements to form a vector of standard deviations, determining a consensus base sequence based on the vector of consensus flow space signal measurements, determining a consensus sequence alignment and generating a compressed data structure comprising consensus compressed data, the consensus compressed data including for each family, the consensus base sequence, the consensus sequence alignment, the vector of consensus flow space signal measurements, the vector of standard deviations and the number of members.

公开(公告)号：US11947723B2

公开(公告)日：2024-04-02

申请号：US17425705

申请日：2020-01-24

申请人： Sony Group Corporation

发明人： Hirofumi Takeda ,  Shuichiro Nishigori ,  Takuma Domae ,  Toshiyuki Nakagawa ,  Shiro Suzuki ,  Takahiro Watanabe

IPC分类号： G06F3/01 ,  H03M7/30

CPC分类号： G06F3/016 ,  H03M7/6005 ,  H03M7/70

摘要： Provided is a decoding device including a decoding unit configured to decode a plurality of pieces of encoded data on the basis of encoding method information that has been received, received bitstream data including the plurality of pieces of encoded data in which a plurality of segments of a tactile signal has been respectively encoded, in which the encoding method information includes information indicating in which encoding method of a plurality of encoding methods the respective segments of the tactile signal have been encoded, the plurality of encoding methods includes a simple tactile encoding method corresponding to a simple tactile signal related to a beginning segment of the tactile signal, the plurality of pieces of encoded data includes simple tactile encoded data in which the simple tactile signal has been encoded in the simple tactile encoding method, and the decoding unit decodes the simple tactile encoded data, in a case where the encoding method information indicates the simple tactile encoding method.

公开(公告)号：US11924069B2

公开(公告)日：2024-03-05

申请号：US17581208

申请日：2022-01-21

申请人： Dell Products L.P.

发明人： Ben Fauber

IPC分类号： G06F15/173 ,  G06F18/20 ,  H03M7/30 ,  H04L43/02 ,  H04L43/04

CPC分类号： H04L43/02 ,  G06F18/20 ,  H03M7/3059 ,  H03M7/70 ,  H04L43/04

摘要： A system can identify a first group of time-series telemetry data that represents performance metrics of a computing device, wherein the first group of time-series telemetry data identifies respective first values and corresponding respective first timestamps. The system can create a second group of time-series telemetry data that identifies second timestamps. The system can populate the second group of time-series telemetry data with the respective first values at respective first locations of the second group of time-series telemetry data that correspond to the respective first timestamps of the respective first values. The system can create a tensor that identifies third timestamps. The system can populate the tensor with the respective first values at respective second locations of the tensor that correspond to the respective first timestamps of the respective first values, wherein populating the tensor comprises combining two values of the respective first values.

公开(公告)号：US11811429B2

公开(公告)日：2023-11-07

申请号：US17034739

申请日：2020-09-28

申请人： TENCENT AMERICA LLC

发明人： Wei Jiang ,  Wei Wang ,  Shan Liu

IPC分类号： H03M7/00 ,  H03M7/30 ,  G06N3/084 ,  G06N5/046 ,  G06F18/211 ,  G06F18/214 ,  G06V10/764 ,  G06V10/82

CPC分类号： H03M7/70 ,  G06F18/211 ,  G06F18/2155 ,  G06N3/084 ,  G06N5/046 ,  G06V10/764 ,  G06V10/82 ,  H03M7/60

摘要： A method, computer program, and computer system is provided for compressing a deep neural network model. Weight coefficients associated with a deep neural network are quantize and entropy-coded. The quantized and entropy-coded weight coefficients are locally smoothed. The smoothed weight coefficients are compressed based on applying a variational dropout to the weight coefficients.

公开(公告)号：US11734548B2

公开(公告)日：2023-08-22

申请号：US16698108

申请日：2019-11-27

申请人： Cambricon Technologies Corporation Limited

发明人： Shaoli Liu ,  Xinkai Song ,  Bingrui Wang ,  Yao Zhang ,  Shuai Hu

IPC分类号： G06N3/063 ,  G06N3/082 ,  H03M7/30

CPC分类号： G06N3/063 ,  G06N3/082 ,  H03M7/70

摘要： The present disclosure provides an integrated circuit chip device and a related product. The integrated circuit chip device includes: a primary processing circuit and a plurality of basic processing circuits. The primary processing circuit or at least one of the plurality of basic processing circuits includes the compression mapping circuits configured to perform compression on each data of a neural network operation. The technical solution provided by the present disclosure has the advantages of a small amount of computations and low power consumption.

公开(公告)号：US11700014B2

公开(公告)日：2023-07-11

申请号：US17714631

申请日：2022-04-06

申请人： Socionext Inc.

发明人： Yoshinobu Hashimoto

IPC分类号： H03M5/00 ,  H03M7/30 ,  G06N3/08 ,  H03M7/46

CPC分类号： H03M7/6011 ,  G06N3/08 ,  H03M7/6005 ,  H03M7/70 ,  H03M7/46

摘要： A weight data compression method includes: generating a 4-bit data string of 4-bit data items each expressed as any one of nine 4-bit values, by dividing ternary weight data into data items each having 4 bits; and generating first compressed data including a first flag value string and a first non-zero value string by (i) generating the first flag value string by assigning one of 0 and 1 as a first flag value of a 1-bit flag to a 4-bit data item 0000 and assigning an other of 0 and 1 as a second flag value of the 1-bit flag to a 4-bit data item other than 0000 among the 4-bit data items in the 4-bit data string and (ii) generating the first non-zero value string by converting the 4-bit data item other than 0000 into a 3-bit data item having any one of eight 3-bit values.

公开(公告)号：US20180025285A1

公开(公告)日：2018-01-25

申请号：US15721143

申请日：2017-09-29

申请人： Adam Jeffries

发明人： Adam Jeffries

IPC分类号： G06N7/00 ,  H04N19/463 ,  G06F17/30 ,  H04N19/91 ,  H03M7/30

CPC分类号： G06N7/005 ,  G06F17/30595 ,  H03M7/3068 ,  H03M7/3079 ,  H03M7/70 ,  H04N19/463 ,  H04N19/91

摘要： A method, article comprising machine-readable instructions and apparatus that processes data systems for encoding, decoding, pattern recognition/matching and data generation is disclosed. State subsets of a data system are identified for the efficient processing of data based, at least in part, on the data system's systemic characteristics.

公开(公告)号：US09787321B1

公开(公告)日：2017-10-10

申请号：US15354553

申请日：2016-11-17

申请人： Google Inc.

发明人： Michael Hemmer ,  Ondrej Stava

IPC分类号： H03M7/30 ,  G06T9/20

CPC分类号： H03M7/30 ,  G06T9/00 ,  G06T9/20 ,  G06T17/00 ,  G06T2207/10028 ,  H03M7/3059 ,  H03M7/3064 ,  H03M7/3082 ,  H03M7/70

摘要： Techniques of data compression involve ordering the points of a point cloud according to distance along a space-filling curve. Advantageously, a space-filling curve has the property that points close in distance along the curve are close together in Euclidean space. Thus, differences between points ordered by distance along such a curve, e.g., a Hilbert curve, will be close. When the curve is fractal, i.e., self-similar at all levels, the differences will be small even when the points are very unevenly clustered throughout the point cloud. Such small differences will provide greatly improved compression to the resulting delta-encoded set of points.