DATA MODEL TRAINING METHOD AND APPARATUS
    1.
    发明公开

    公开(公告)号:US20230281513A1

    公开(公告)日:2023-09-07

    申请号:US18313590

    申请日:2023-05-08

    CPC classification number: G06N20/00

    Abstract: A data model training method and apparatus are provided. The method includes receiving data subsets from a plurality of subnodes and performing data convergence based on the plurality of data subsets to obtain a first data set. A first data model and at least one of the first data set or a subset of the first data set are sent to a first subnode, where an artificial intelligence (AI) algorithm is configured for the first subnode. A second data model is received from the first subnode, where the second data model is obtained by training the first data model based on the first data set or the subset of the first data set. The first data model is updated based on the second data model to obtain a target data model, the target data model is sent to the plurality of subnodes.

    DATA TRANSMISSION METHOD, APPARATUS, AND SYSTEM

    公开(公告)号:US20230308325A1

    公开(公告)日:2023-09-28

    申请号:US18323449

    申请日:2023-05-25

    CPC classification number: H04L27/1563 H04L1/0057

    Abstract: A data transmission method includes obtaining a data stream. The data stream includes a plurality of bit groups. The method also includes modulating the data stream into a modulated symbol stream according to a modulation rule, and generating a modulated signal based on the modulated symbol stream. The modulated symbol stream includes a plurality of modulated symbol. The modulation rule includes determining, in a symbol period of one modulated symbol based on a value of a first bit group, a zero time point corresponding to the first bit group. The zero time point is a zero crossing point of the modulated signal in the symbol period. The first bit group includes at least one bit. The first bit group is one of the plurality of bit groups. The method further includes sending the modulated signal.

    SCHEDULING METHOD AND APPARATUS IN COMMUNICATION SYSTEM, AND STORAGE MEDIUM

    公开(公告)号:US20210410161A1

    公开(公告)日:2021-12-30

    申请号:US17471640

    申请日:2021-09-10

    Abstract: According to a scheduling method and apparatus in a communication system, and a storage medium, a communication device obtains system status information, where the system status information includes network status information; obtains a scheduling policy based on the system status information and a deep neural network; and performs communication according to the scheduling policy. The deep neural network is obtained through training based on historical system status information, and the historical system status information includes system status information in all scheduling periods before a current scheduling period. Therefore, the scheduling policy obtained based on the deep neural network can meet a balancing requirement of throughput and fairness and solves a problem of low performance of an existing communication system.

    DATA RETRANSMISSION METHOD AND APPARATUS
    5.
    发明申请

    公开(公告)号:US20200244291A1

    公开(公告)日:2020-07-30

    申请号:US16849643

    申请日:2020-04-15

    Abstract: This disclosure provides a data retransmission method and apparatus. The method includes: A transmitting device obtains information to be transmitted for a tth time, where the information to be transmitted for the tth time includes Rt extension locations and information to be transmitted for a (t−1)th time, and the extension locations include Mt information bits and Lt check bits corresponding to the Mt information bits. The transmitting device then performs Polar encoding on the information to be transmitted for the tth time, to obtain a codeword after the Polar encoding, obtains a codeword for (t−1)th retransmission based on the codeword after the Polar encoding, and transmits the codeword for (t−1)th retransmission. A receiving device performs polar decoding after receiving the codeword for (t−1)th retransmission, to obtain a decoding result of codewords for t times of transmission. By performing, on an encoding side, check encoding on the information bits in an extension part, a decoding path can be reduced in a decoding process, thereby greatly reducing decoding complexity, and reducing storage overheads and calculation overheads.

    ENCODING METHOD AND APPARATUS
    7.
    发明申请

    公开(公告)号:US20200212933A1

    公开(公告)日:2020-07-02

    申请号:US16811934

    申请日:2020-03-06

    Abstract: This application provides an encoding method and apparatus in a wireless communications system. The method includes: performing cyclic redundancy check (CRC) encoding on A to-be-encoded information bits based on a CRC polynomial, to obtain a first bit sequence, where the first bit sequence includes L CRC bits and the A information bits; and performing polar encoding on the first bit sequence, where L has a value of one of 3, 4, 5, 8, and 16. Based on an improved CRC polynomial, coding satisfying a false alarm rate (FAR) requirement is implemented.

    MODEL TRAINING METHOD AND RELATED APPARATUS
    8.
    发明公开

    公开(公告)号:US20240152766A1

    公开(公告)日:2024-05-09

    申请号:US18405019

    申请日:2024-01-05

    CPC classification number: G06N3/096

    Abstract: A model training method and a related apparatus to help improve a convergence speed of model training and improve end-to-end communication quality. The method includes: a first communication apparatus sends first data to a second communication apparatus through a channel, where the first data is an output result of the first machine learning model. The second communication apparatus receives second data through a channel, inputs the second data into a second machine learning model to obtain third data; determines a first loss function based on the third data and the first training data; and sends the first loss function to the first communication apparatus through a feedback channel.

    DISTRIBUTED LEARNING METHOD AND APPARATUS
    9.
    发明公开

    公开(公告)号:US20240054324A1

    公开(公告)日:2024-02-15

    申请号:US18486807

    申请日:2023-10-13

    CPC classification number: G06N3/045 G06N3/082

    Abstract: A distributed learning method and apparatus for combining wireless communication with distributed learning to save resources, and improve performance of distributed learning in a wireless environment. A first node processes first data using a first data model to obtain first intermediate data. The first node sends the first intermediate data to a second node through a first channel. The first channel is updated based on error information of second intermediate data, information about the first channel, and the first intermediate data. The second intermediate data is a result of transmitting the first intermediate data to the second node through the first channel. The first channel is a channel between the first node and the second node.

    GRADIENT TRANSMISSION METHOD AND RELATED APPARATUS

    公开(公告)号:US20240049188A1

    公开(公告)日:2024-02-08

    申请号:US18486482

    申请日:2023-10-13

    CPC classification number: H04W72/04 H04L41/16

    Abstract: A first communication apparatus receives training data, and determines a first intermediate gradient based on the training data. The first intermediate gradient is used to update a parameter of a first neural network located in a second communication apparatus. The first communication apparatus maps the first intermediate gradient to an air interface resource to generate a first gradient signal, and sends the first gradient signal to the second communication apparatus. The first gradient signal includes one or more first gradient symbols, and each of the first gradient symbols is corresponding to one or more gradient values.

Patent Agency Ranking