SPLIT INFERENCE METHOD AND APPARATUS

    公开(公告)号:US20240430192A1

    公开(公告)日:2024-12-26

    申请号:US18827858

    申请日:2024-09-09

    Abstract: Embodiments of this application relate to the field of communication technologies, and provide a split inference method and an apparatus, to reduce communication overheads and also reduce a risk of leaking original data to a central server. The method includes: A first communication apparatus receives, from a second communication apparatus, first indication information indicating a previous-hop communication apparatus and a next-hop communication apparatus of the first communication apparatus, where the previous-hop communication apparatus and the next-hop communication apparatus each include at least one terminal device. The first communication apparatus receives data from the previous-hop communication apparatus, performs inference on the data based on a submodel corresponding to the first communication apparatus, to obtain an inference result, and sends the inference result to the next-hop communication apparatus.

    DATA TRANSMISSION METHOD AND APPARATUS
    2.
    发明公开

    公开(公告)号:US20230319632A1

    公开(公告)日:2023-10-05

    申请号:US18308423

    申请日:2023-04-27

    CPC classification number: H04W28/06 G06N7/01 H04L1/0036

    Abstract: A data transmission method and apparatus are described. The method includes a receive end receiving a first parameter, where the first parameter includes a parameter of a probability distribution of a hidden variable. The hidden variable is obtained by encoding first data by using an encoder of a variational auto-encoder. The receive end determines the probability distribution based on the first parameter, and samples the probability distribution M times to obtain M pieces of sampled data, where M is a positive integer. The receive end reconstructs the first data based on the M pieces of sampled data. According to the described data transmission method and apparatus, the first parameter is transmitted, so that the receive end can support a plurality of times of sampling, thereby reducing an amount of data transmitted over an air interface, and reducing data transmission overhead.

    Communication Method and Apparatus
    3.
    发明公开

    公开(公告)号:US20230171634A1

    公开(公告)日:2023-06-01

    申请号:US18153606

    申请日:2023-01-12

    CPC classification number: H04W24/10 H04W8/22 H04W72/20 H04W72/0446 H04W72/0453

    Abstract: This application provides a communication method and apparatus. The method may include: A first communication apparatus receives configuration information of a first neural network; the first communication apparatus determines the first neural network based on the configuration information of the first neural network; the first communication apparatus obtains first channel information based on channel information obtained through measurement and the first neural network, where a data amount of the first channel information is less than a data amount of the channel information obtained through measurement; and the first communication apparatus sends the first channel information, where the first channel information is used to obtain second channel information by using a second neural network, and the second channel information is used for data transmission.

    Channel coding method and apparatus in wireless communications

    公开(公告)号:US11121809B2

    公开(公告)日:2021-09-14

    申请号:US16693906

    申请日:2019-11-25

    Abstract: This application provides a channel encoding method and apparatus in wireless communications. The method includes: performing CRC encoding on A to-be-encoded information bits, to obtain a first bit sequence, where the first bit sequence includes L CRC bits and A information bits; performing a interleaving operation on the first bit sequence, to obtain a second bit sequence, where a first interleaving sequence used for the interleaving operation is obtained based on a system-supported maximum-length interleaving sequence with the length of Kmax+L, and Kmax is a maximum information bit quantity corresponding to the maximum-length interleaving sequence ad a preset rule, and a length of the first interleaving sequence is equal to A+L. Therefore, during distributed CRC encoding, when an information bit quantity is less than the maximum information bit quantity, an interleaving sequence required for completing an interleaving process is obtained based on the system-supported maximum-length interleaving sequence.

    Polar code encoding method and apparatus

    公开(公告)号:US11088708B2

    公开(公告)日:2021-08-10

    申请号:US16728594

    申请日:2019-12-27

    Abstract: The present disclosure relates to polar code encoding methods and apparatus. One example method includes separately performing check encoding on the at least two to-be-checked first bit sequences to obtain at least two check bit sequences, where a union set of the at least two to-be-checked first bit sequences includes the K information bits, and K is a positive integer, interleaving the K information bits and the at least two check bit sequences, or interleaving a first part of information bit sequence and a first check bit sequence to obtain an interleaved third bit sequence, where a second check bit sequence, a third check bit sequence, and a second part of information bit sequence in a sequence of all information bits except the first part of information bit sequence form a second bit sequence, and performing polar encoding on the second bit sequence.

    Method for encoding information bit sequence in communication network

    公开(公告)号:US10608788B2

    公开(公告)日:2020-03-31

    申请号:US16249910

    申请日:2019-01-17

    Abstract: Embodiments of this application provide a method for encoding data in a wireless communication network. A communication device obtains an information bit sequence of a bit length K and a code length M. When M is greater than or equal to a first threshold and K is greater than or equal to a second threshold, the device divides the information bit sequence into p subsequences that are of an equal length K1. Then the device encodes each of the p subsequence to obtain p encoded subsequences. The device rate-matches each of the p encoded subsequences to obtain p rate matched subsequences, concatenates the p rate matched subsequences to obtain the output sequence of the code length M, then outputs the output sequence.

    Method and coding apparatus for processing information using a polar code

    公开(公告)号:US10594436B2

    公开(公告)日:2020-03-17

    申请号:US16579867

    申请日:2019-09-24

    Abstract: Embodiments of this application provide an information processing method and a coding apparatus. An information bit sequence includes a K-bit information block. The information bit sequence is to be processed into an encoded bit sequence with a target code length M, M>1024. For a given code rate R, when the length K of the information block is greater than a preset threshold, the information bit sequence is segmented into two or more segments. Each segment is polar encoded into an encoded subsequence. The encoded subsequence has a length that equals to a mother code length Ni, and i=1, 2, . . . , p. Each of the p encoded subsequences is rate matched to obtain a rate-matched encoded subsequence. A rate-matched encoded subsequence i of the p rate-matched encoded subsequences has a code length Mi. The p rate-matched encoded subsequences are concatenated into an encoded bit sequence which has a code length M.

    Encoding Method and Apparatus
    9.
    发明申请

    公开(公告)号:US20200067534A1

    公开(公告)日:2020-02-27

    申请号:US16673118

    申请日:2019-11-04

    Abstract: An encoding method and apparatus are provided. The method by a transmit end includes: performing check encoding on to-be-encoded information to obtain a check encoding codeword that comprises K information bits and J check bits; performing an interleaving operation on the check encoding codeword with an interleaving sequence including J subsequences, and an ith subsequence includes a position index of an element 1 in an intermediate result vector Ti and a value of (K+i), where 1≤i≤J, i is an integer, Ti=(˜M)&(Vi), M=M|(Vi), M is a masked vector, Vi is a column vector of a checking part matrix P, P is a submatrix of a generator matrix G for check encoding, ˜ represents a bit-by-bit NOT operation, & represents a bit-by-bit AND operation, and | represents a bit-by-bit OR operation; and performing polar encoding on a check encoding codeword obtained after the interleaving operation.

    COMMUNCIATION METHOD USING POLAR CODE, AND WIRELESS DEVICE

    公开(公告)号:US20190260392A1

    公开(公告)日:2019-08-22

    申请号:US16391327

    申请日:2019-04-23

    Abstract: Embodiments of the application provide a polar coding method for communicating information in a wireless network. Information bits are encoded using a polar code process to obtain a polar-coded bit sequence. A rate matched bit sequence is output based on the polar-coded bit sequence. The rate matched bit sequence includes a quantity M of bits from the polar-coded bit sequence, and the M bits from the polar-coded bit sequence correspond to M channel indexes in a channel index sequence S. The channel index sequence S is obtained based on a puncturing/shortening proportion P′ and a prestored channel index sequence S′. Channel indexes in the prestored channel index sequence S′ are sorted by channel reliability or channel capacity, and a sorting order of the M channel indexes in the channel index sequence S is the same as a sorting order of the channel indexes in the prestored channel index sequence S′.

Patent Agency Ranking