Channel encoding and decoding method and communication apparatus
This application provides a channel encoding method and a communication apparatus. A second communication apparatus obtains a first parameter of a first communication apparatus, where the first parameter includes a parameter related to channel coding and decoding and a reinforcement learning training parameter. The second communication apparatus determines, based on the first parameter, first code construction information for constructing a coded bit sequence based on an information bit sequence during channel encoding; and after sending the first code construction information to the first communication apparatus, performs channel encoding and decoding on communication data between the first communication apparatus and the second communication apparatus by using the first code construction information to improve channel encoding performance and further improve communication reliability.
1. A communication method, comprising:
sending, by a first communication apparatus, a first parameter to a second communication apparatus, wherein the first parameter comprises a parameter related to channel encoding and decoding and a reinforcement learning training parameter;
obtaining, by the first communication apparatus, exploration code construction information of the second communication apparatus, wherein the exploration code construction information corresponds to the first parameter;
sending, by the first communication apparatus, performance information of the exploration code construction information to the second communication apparatus; and
obtaining, by the first communication apparatus, first code construction information of the second communication apparatus, wherein the first code construction information corresponds to the performance information and the first parameter, and the first code construction information is used to construct a coded bit based on an information bit during channel encoding.
2. The method according to claim 1 , wherein the first code construction information is a polar channel reliability sorting sequence of a polar code or a base matrix of low-density parity-check code LDPC.
3. The method according to claim 1 , wherein the first code construction information is obtained by using a reinforcement learning method.
4. The method according to claim 3 , wherein before obtaining, by the first communication apparatus, the first code construction information, the method further comprises:
assessing, by the first communication apparatus, performance of the exploration code construction information, and generating the performance information of the exploration code construction information based on the first parameter.
5. The method according to claim 1 , wherein the method further comprises:
sending, by the first communication apparatus, capability information to the second communication apparatus, wherein the capability information is used to indicate whether the first communication apparatus supports an update of code construction information.
6. The method according to claim 1 , wherein the channel encoding is channel encoding for one or more of the following communication information:
uplink data, downlink data, uplink control information, downlink control information, sidelink data, or sidelink control information.
7. The method according to claim 1 , wherein the parameter related to channel encoding and decoding comprises one or more of the following:
channel state information (CSI), precoding matrix information (PMI), an encoding length, an information bit length, a code rate, or a modulation order.
8. The method according to claim 1 , wherein the reinforcement learning training parameter comprises one or more of:
a modulation order distribution, an encoding length distribution, a code rate distribution, an information bit length distribution, a codec parameter, a channel feature parameter, or a decoding result.
9. A communication apparatus, comprising:
a processor, configured to determine a first parameter, wherein the first parameter comprises a parameter related to channel encoding and decoding and a reinforcement learning training parameter; and
a transceiver, configured to;
send the first parameter to a second communication apparatus;
obtain exploration code construction information of the second communication apparatus, wherein the exploration code construction information corresponds to the first parameter;
send performance information of the exploration code construction information to the second communication apparatus; and
obtain first code construction information of the second communication apparatus, wherein the first code construction information corresponds to the first parameter, and the first code construction information is used to construct a coded bit based on an information bit during channel encoding.
10. The apparatus according to claim 9 , wherein the first code construction information is a polar channel reliability sorting sequence of a polar code or a base matrix of low-density parity-check code (LDPC).
11. The apparatus according to claim 9 , wherein the first code construction information is obtained by using a reinforcement learning method.
12. The apparatus according to claim 9 , wherein
the processor is further configured to assess performance of the exploration code construction information, and generate performance information of the exploration code construction information based on the first parameter.
13. The apparatus according to claim 9 , wherein
the transceiver is further configured to send capability information to the second communication apparatus, wherein the capability information is used to indicate whether an update of code construction information is supported.
14. The apparatus according to claim 9 , wherein the channel encoding is channel encoding for one or more of the following communication information:
uplink data, downlink data, uplink control information, downlink control information, sidelink data, or sidelink control information.
15. The apparatus according to claim 9 , wherein the parameter related to channel encoding and decoding comprises one or more of the following:
channel state information (CSI), precoding matrix information (PMI), an encoding length, an information bit length, a code rate, or a modulation order.
16. The apparatus according to claim 9 , wherein the reinforcement learning training parameter comprises one or more of:
a modulation order distribution, an encoding length distribution, a code rate distribution, an information bit length distribution, a codec parameter, a channel feature parameter, or a decoding result.
17. A communication apparatus, comprising:
a transceiver, configured to obtain a first parameter of a first communication apparatus, wherein the first parameter comprises a parameter related to channel encoding and decoding and a reinforcement learning training parameter; and
a processor, configured to;
generate exploration code construction information based on the first parameter;
determine first code construction information based on the first parameter and the exploration code construction information, wherein the first code construction information is used to construct a coded bit sequence based on an information bit sequence during channel encoding; and
the transceiver is further configured to send the first code construction information to the first communication apparatus.
18. The apparatus according to claim 17 , wherein the first code construction information is a polar channel reliability sorting sequence of a polar code or a base matrix of low-density parity-check code (LDPC).
19. The apparatus according to claim 17 , wherein
the transceiver or the processor is further configured to obtain performance information of the exploration code construction information;
the processor is further configured to train a code construction information generation model by using the performance information as a reward; and
the processor generates the first code construction information by using a trained code construction information generation model.
20. The apparatus according to claim 19 , wherein the processor is further configured to obtain performance information of the exploration code construction information comprises:
the processor is configured to assess performance of the exploration code construction information, and generate performance information of the exploration code construction information based on the first parameter.