-
公开(公告)号：EP4425382A1
公开(公告)日：2024-09-04
申请号：EP22892105.2
申请日：2022-11-11
发明人： YE, Deshi , CHEN, Songyang , XU, Chen , LI, Rong
IPC分类号： G06N3/08
CPC分类号： G06F18/25 , G06N5/04 , G06F18/214 , G06N3/08 , G06N3/06 , G06N3/084 , G06N3/0464
摘要： This application provides a model training method and a communication apparatus. The method includes: An ith device in a kth group of devices performs n*M times of model training, where the ith device completes model parameter exchange with at least one other device in the kth group of devices in every M times of model training, M is a quantity of devices in the kth group of devices, M is greater than or equal to 2, and n is an integer; and the ith device sends a model Mi,n*M to a target device, where the model Mi,n*M is a model obtained by the ith device by completing the n*M times of model training. According to the solutions provided in this application, a convergence speed and utilization of data and computing power in a model training process can be improved, and requirements on computing, storage, and communication capabilities of a device can be reduced.
-
公开(公告)号：EP4422099A1
公开(公告)日：2024-08-28
申请号：EP22897523.1
申请日：2022-10-26
发明人： WANG, Xianbin , ZHANG, Huazi , TONG, Jiajie , LI, Rong , WANG, Jun
IPC分类号： H04L1/00
CPC分类号： H04L1/00
摘要： Embodiments of this application disclose a channel coding method and apparatus. The method includes: obtaining a subsequence based on a first sequence and a second sequence; and determining a generator polynomial or a generator matrix based on the subsequence, where the generator polynomial or the generator matrix is used for cyclic code encoding. According to embodiments of this application, generator polynomials or generator matrices for channel coding of different lengths and different bit rates are determined by using two sequences, so that storage space is reduced, and storage complexity is reduced.
-
公开(公告)号：EP4418763A1
公开(公告)日：2024-08-21
申请号：EP22889211.3
申请日：2022-10-28
发明人： WANG, Xiaolu , LUO, Hejia , LI, Rong , WANG, Jun
CPC分类号： H04W72/1268 , H04W72/0457 , H04W72/0453 , H04W72/04 , H04W56/00 , H04W72/23
摘要： A wireless communication method and an apparatus are provided. The method includes: A first communication apparatus obtains first indication information in a first slot, where the first indication information indicates the first communication apparatus to switch from an uplink transmission bandwidth to a first transmission bandwidth; then, the first communication apparatus determines a second slot based on the first slot and a first switching delay, where the first switching delay is determined based on a first timing offset value, and the first timing offset value is determined based on a round-trip delay between a first location in an area covered by a second communication apparatus and the second communication apparatus; and the first communication apparatus sends uplink information to the second communication apparatus by using the first transmission bandwidth from the second slot. Therefore, in an uplink transmission bandwidth switching process, this method can ensure that the second communication apparatus can receive the uplink information sent by the first communication apparatus.
-
公开(公告)号：EP4412287A1
公开(公告)日：2024-08-07
申请号：EP22882799.4
申请日：2022-10-17
发明人： WANG, Jian , LI, Rong , ZHANG, Gongzheng , WANG, Jun
IPC分类号： H04W24/02
摘要： This application discloses a communication method, apparatus, and system, a storage medium, and a program product. The method includes: A first distributed node sends communication mechanism indication information to at least one second distributed node adjacent to the first distributed node, where the communication mechanism indication information is obtained based on a robustness requirement of a distributed learning system; the first distributed node receives at least one piece of first data from the at least one second distributed node, where the at least one piece of first data is transmitted by the at least one second distributed node based on the communication mechanism indication information; and the first distributed node performs inference based on second data of the first distributed node and the at least one piece of first data by using a distributed learning model. According to the solution, a target node indicates a communication mechanism to a neighboring node based on the robustness requirement of the distributed learning system, and the neighboring node transmits data according to the communication mechanism, to improve efficiency and robustness of distributed inference.
-
公开(公告)号：EP4412117A1
公开(公告)日：2024-08-07
申请号：EP22900203.5
申请日：2022-11-04
发明人： TONG, Jiajie , WANG, Xianbin , ZHANG, Huazi , LI, Rong , WANG, Jun
IPC分类号： H04L1/00
摘要： The application relates to the field of wireless communication technologies, and provides a communication method and apparatus, so that a fading channel can implement a good error correction capability. This helps improve information transmission reliability. The method includes: A transmit end device determines, based on N bit sets, a first sequence and a second sequence that are obtained through quadrature amplitude modulation QAM. The first sequence includes N in-phase components, and the second sequence includes N quadrature components; or the first sequence includes N quadrature components, and the second sequence includes N in-phase components, where N is an integer greater than or equal to 2. Then, the transmit end device performs interleaving processing on the first sequence, to obtain a third sequence. Then, the transmit end device sends, to a receive end device, a symbol sequence determined based on the second sequence and the third sequence. The symbol sequence includes N QAM symbols.
-
公开(公告)号：EP4401487A1
公开(公告)日：2024-07-17
申请号：EP22874520.4
申请日：2022-08-29
发明人： YU, Tianhang , LUO, Hejia , LI, Rong , WANG, Jun
IPC分类号： H04W72/04
摘要： Embodiments of this application disclose a communication method. The method includes: A first communication device receives a first signal from a second communication device, where a first band used for communication between the first communication device and a third communication device overlaps a second band used for communication between the second communication device and a fourth communication device. The first communication device adjusts a start moment of a first transmission frame of the first communication device or an end moment of the first transmission frame based on the first signal. A time interval between an adjusted start moment of the first transmission frame and a start moment of a second transmission frame of the second communication device falls within an interval from T1 - T2 to T1 + T2, and/or a time interval between an adjusted end moment of the first transmission frame and an end moment of the second transmission frame falls within an interval from T1 - T3 to T1 + T3. T1 is equal to 0 or a timing advance TA, T2 is a first threshold, and T3 is a second threshold. This alleviates or avoids co-channel coverage interference between the first communication device and the second communication device.
-
公开(公告)号：EP4351096A1
公开(公告)日：2024-04-10
申请号：EP22827626.7
申请日：2022-06-22
发明人： HUANGFU, Yourui , ZHANG, Gongzheng , WANG, Jian , LI, Rong
摘要： This application relates to the field of communication technologies, and provides a method and an apparatus for updating a preprocessing parameter. A first apparatus performs preprocessing and power amplification on a first signal by using a first preprocessing parameter, to obtain a third signal; and then sends the third signal to a second apparatus, where the third signal is changed to a fourth signal after passing through a channel between the first apparatus and the second apparatus. The second apparatus performs channel estimation and channel equalization by using the fourth signal, to obtain a fifth signal, and then determines an updated preprocessing parameter based on the fifth signal. Next, the second apparatus indicates the updated preprocessing parameter to the first apparatus. Channel estimation and channel equalization can eliminate a linear part of the fourth signal. When the updated preprocessing parameter is estimated, only impact of a nonlinear part on the signal is considered, so that an optimal preprocessing parameter can be obtained more accurately, to implement accurate preprocessing and improve working efficiency of a communication device.
-
公开(公告)号：EP4318310A1
公开(公告)日：2024-02-07
申请号：EP22787608.3
申请日：2022-04-14
发明人： ZHANG, Gongzheng , XU, Chen , LI, Rong , WANG, Jian , WANG, Jun
摘要： This application provides a distributed learning method and apparatus, to combine wireless communication with distributed learning, which can save resources, and improve performance of distributed learning in a wireless environment. The method includes: A first node processes first data by using a first data model to obtain first intermediate data, and 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.
-
公开(公告)号：EP4277132A1
公开(公告)日：2023-11-15
申请号：EP22752180.4
申请日：2022-01-29
发明人： ZHANG, Huazi , TONG, Wen , WANG, Jun , LI, Rong , TONG, Jiajie , WANG, Xianbin
IPC分类号： H03M13/11
摘要： Embodiments of this application provide an encoding and decoding method and a related apparatus, to reduce encoding and decoding complexity and improve encoding and decoding performance. In this method, a sending device may obtain a first to-be-encoded vector. The sending device may perform first encoding on the first to-be-encoded vector, to obtain a second to-be-encoded vector. The sending device may encode the second to-be-encoded vector based on a first generator matrix, to obtain an encoded codeword. The first generator matrix may include at least N + 1 submatrixes a, and N of the submatrixes a may be located on a main diagonal of the first generator matrix. The first generator matrix may be a block upper triangular matrix, or the first generator matrix may be a block lower triangular matrix. The submatrix a is a polar kernel matrix with a size of 2 m * 2 m , m is a natural number, and N is a natural number. The sending device may send the encoded codeword.
-
公开(公告)号：EP4246815A1
公开(公告)日：2023-09-20
申请号：EP21914424.3
申请日：2021-12-28
发明人： CHEN, Li , LI, Rong , CHENG, Jinjun , WANG, Xianbin
IPC分类号： H03M13/15
摘要： A coding method and apparatus are provided. The method includes: coding an information bit by using a preset generator matrix of a systematic (U|U+V)-code to obtain a codeword of a systematic code. The preset generator matrix of the systematic (UIU+V)-code includes a first identity sub-matrix of a U code and a second identity sub-matrix of a V code. A plurality of elements in a same column as the first identity sub-matrix are all 0. A plurality of elements in a same column as the second identity sub-matrix are all 0. In this coding manner, not only are low decoding complexity and a good code distance ensured, but also convenience of engineering implementation is improved. Furthermore, in the foregoing manner, a plurality of code lengths and coding rates may be flexibly adapted only by storing a generator matrix of a systematic code of a mother code, so that this manner is lower in storage overhead than a manner of storing a generator matrix of a (UIU+V)-code.
-
-
-
-
-
-
-
-
-
搜索结果
246 条记录 (耗时 0.01 秒)
