Communication method, communication apparatus, storage medium, and program product

Abstract

A communication method, a communication apparatus, a storage medium, and a program product. The method is applied to a first node, and comprises: receiving first indication information sent by a second node, the first indication information being used for indicating a first type of physical channel, the first type of physical channel being used for participating in a reinforcement-learning-based adaptive modulation and coding scheme (MCS), the first type of physical channel satisfying a first characteristic, and the first characteristic comprising at least one of the following: not carrying information originating from higher layers of the protocol stack; not being retransmitted; a decoding result not being used for control of a block error rate (BLER); and a decoding result not being used as a trigger condition for communication procedures other than the adaptive modulation and coding scheme (MCS).

Description

A communication method, communication device, storage medium, and program product.

[0001] This disclosure claims priority to Chinese patent application No. 202510316289.6, filed on March 14, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of communication technology, and in particular to a communication method, communication device, storage medium, and program product. Background Technology

[0003] Adaptive Modulation and Coding Scheme (MCS) technology can dynamically adjust the modulation and coding scheme (MCS) to meet the modulation and coding requirements of channel fading changes in wireless communication systems. Furthermore, the reinforcement learning-based adaptive MCS method enables the network (such as servers, base stations, etc.) to learn the optimal adaptive MCS strategy through information interaction with user equipment (UE) based on the air interface channel, thereby ensuring optimal spectral efficiency and user experience rate. Summary of the Invention

[0004] On the one hand, a communication method is provided, which is applied to a first node, including: receiving first indication information sent by a second node, the first indication information being used to indicate a first type of physical channel, the first type of physical channel being used to participate in a reinforcement learning-based adaptive modulation and coding scheme (MCS), the first type of physical channel satisfying a first feature, the first feature including at least one of the following: not carrying information originating from higher layers of the protocol stack; not being retransmitted; the decoding result not being used for block error rate (BLER) control; the decoding result not being used as a triggering condition for other communication processes outside of the MCS.

[0005] On another front, a communication method is provided, applied to a first node, comprising: receiving second indication information transmitted by a second node, the second indication information indicating a first type of reference signal, the first type of reference signal being used to participate in a reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of reference signal satisfies at least one of the following: the first type of reference signal includes a portion known to the receiving node and a portion unknown to the receiving node; the portion known to the receiving node in the first type of reference signal is used to decode the portion unknown to the receiving node; and the physical layer processing of the first type of reference signal includes channel coding and modulation.

[0006] On another front, a communication method is provided, which is applied to a second node and includes: sending first indication information to a first node, the first indication information being used to indicate a first type of physical channel, the first type of physical channel being used to participate in a reinforcement learning-based adaptive modulation and coding scheme (MCS), the first type of physical channel satisfying a first characteristic, the first characteristic including at least one of the following: not carrying information originating from higher layers of the protocol stack; not being retransmitted; the decoding result not being used for block error rate (BLER) control; the decoding result not being used as a triggering condition for other communication processes outside of the MCS.

[0007] On another front, a communication method is provided, applied to a second node, comprising: sending second indication information to a first node, the second indication information indicating a first type of reference signal, the first type of reference signal being used to participate in a reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of reference signal satisfies at least one of the following: the first type of reference signal includes a portion known to the receiving node and a portion unknown to the receiving node; the portion known to the receiving node in the first type of reference signal is used to decode the portion unknown to the receiving node; and the physical layer processing of the first type of reference signal includes channel coding and modulation.

[0008] On the other hand, a communication device is provided for use in a first node, the device comprising: a receiving module.

[0009] The receiving module is used to receive first indication information sent by the second node. The first indication information is used to indicate a first type of physical channel. The first type of physical channel is used to participate in the reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of physical channel satisfies a first feature, which includes at least one of the following: it does not carry information originating from higher layers of the protocol stack; it is not retransmitted; the decoding result is not used for block error rate (BLER) control; and the decoding result is not used as a triggering condition for other communication processes outside of the MCS.

[0010] On the other hand, a communication device is provided for use in a first node, the device comprising: a receiving module.

[0011] A receiving module is configured to receive second indication information transmitted by a second node. The second indication information indicates a first type of reference signal, which participates in a reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of reference signal satisfies at least one of the following: the first type of reference signal includes a portion known to the receiving node and a portion unknown to the receiving node; the portion known to the receiving node is used to decode the portion unknown to the receiving node; and the physical layer processing of the first type of reference signal includes channel coding and modulation.

[0012] On the other hand, a communication device is provided for use in a second node, the device comprising: a transmitting module.

[0013] The sending module is used to send first indication information to the first node. The first indication information is used to indicate a first type of physical channel. The first type of physical channel is used to participate in the reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of physical channel satisfies a first feature, which includes at least one of the following: it does not carry information originating from higher layers of the protocol stack; it is not retransmitted; the decoding result is not used for block error rate (BLER) control; and the decoding result is not used as a triggering condition for other communication processes outside of the MCS.

[0014] On the other hand, a communication device is provided for use in a second node, the device comprising: a transmitting module.

[0015] The transmitting module is used to transmit second indication information to the first node. The second indication information indicates a first type of reference signal, which is used to participate in the reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of reference signal satisfies at least one of the following: the first type of reference signal includes a portion known to the receiving node and a portion unknown to the receiving node; the portion known to the receiving node in the first type of reference signal is used to decode the portion unknown to the receiving node; the physical layer processing of the first type of reference signal includes channel coding and modulation.

[0016] In another aspect, a communication device is provided, comprising: a memory and a processor. The memory and the processor are coupled. The memory is used to store a computer program. When the processor executes the computer program, it implements the aforementioned communication method.

[0017] In another aspect, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the above-described communication method.

[0018] On the other hand, a computer program product is provided, which includes computer program instructions that, when executed, implement the above-described communication method. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this disclosure, the accompanying drawings used in some embodiments of this disclosure will be briefly described below. Obviously, the drawings described below are merely drawings of some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings.

[0020] Figure 1 is an architecture diagram of a communication system according to some embodiments.

[0021] Figure 2 is a flowchart of a communication method according to some embodiments.

[0022] Figure 3 is a flowchart of another communication method according to some embodiments.

[0023] Figure 4 is a flowchart of another communication method according to some embodiments.

[0024] Figure 5 is a flowchart of another communication method according to some embodiments.

[0025] Figure 6 is a flowchart of another communication method according to some embodiments.

[0026] Figure 7 is a flowchart of another communication method according to some embodiments.

[0027] Figure 8 is a block diagram of a communication device according to some embodiments.

[0028] Figure 9 is a block diagram of another communication device according to some embodiments.

[0029] Figure 10 is a block diagram of another communication device according to some embodiments.

[0030] Figure 11 is a block diagram of another communication device according to some embodiments.

[0031] Figure 12 is a block diagram of another communication device according to some embodiments. Detailed Implementation

[0032] The technical solutions of this disclosure will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0033] It should be noted that, in this disclosure, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0034] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0035] In the description of this disclosure, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "more than one" means two or more.

[0036] Existing adaptive MCS methods require information such as channel state information (CSI) and data decoding results from the air interface channel to determine the modulation order and coding rate for data transmission. The air interface channel CSI includes downlink CSI measured based on the channel state information reference signal (CSI-RS) and uplink CSI measured based on the sounding reference signal (SRS). Downlink CSI includes the rank indicator (RI), precoding matrix indicator (PMI), and channel quality indicator (CQI), while uplink CSI includes the signal-to-interference-plus-noise ratio (SINR) of the uplink channel. The decoding result of the downlink data is indicated by the acknowledgment (ACK) or negative acknowledgment (NACK) reported by the UE.

[0037] The network determines the Modulation Sequence (MCS) primarily based on two parts of SINR: the first part SINR and the second part SINR. The sum of the first and second parts SINR equals the total SINR, which is used to map the modulation order and coding rate. The first part SINR is obtained through uplink and / or downlink CSI. The second part SINR is obtained through the data decoding result. The second part SINR is a cumulative value, accumulated from a series of SINR increments. Each SINR increment corresponds to a data decoding result (correct or incorrect). A positive SINR increment corresponds to correct decoding, while a negative SINR increment corresponds to incorrect decoding. The magnitude of positive and negative SINR increments is proportional, and this proportion is related to the target block error rate (BLER). As data transmission continues, positive or negative SINR increments are continuously accumulated, causing the second part SINR to dynamically change until convergence. Because the first part SINR is a static value, the total SINR also converges at this point, and the data transmission BLER equals the target BLER.

[0038] Existing adaptive MCS methods are mainly designed based on experience and mathematical models, requiring certain assumptions, namely, a large amount of data transmission and sufficient data decoding results to dynamically adjust the total SINR until convergence. However, most real-world communication services consist of small data packets, which may only require one or two transmissions to complete. In this case, the total SINR has not been sufficiently adjusted, so its value may not be the most suitable for the wireless channel capacity.

[0039] With the rapid development of artificial intelligence (AI) technology, reinforcement learning (RL) can help wireless communication adaptive MCS achieve the optimal match between the modulation order and coding rate of data transmission and the wireless channel.

[0040] Reinforcement learning (RL) is a paradigm and methodology in machine learning used to describe and solve problems where agents learn strategies to maximize rewards or achieve specific goals through interaction with their environment. RL focuses on online learning and attempts to maintain a balance between exploration and exploitation. Reinforcement learning involves two interacting objects: the agent and the environment. The agent perceives the state of the external environment and the reward it receives, and then learns and makes decisions. The agent's decision-making function refers to taking different actions based on the state of the external environment, while its learning function refers to adjusting its strategy based on the reward from the external environment. The environment refers to everything outside the agent, whose state is changed by the agent's actions, and which provides the agent with corresponding rewards.

[0041] In general, the primary goal of reinforcement learning is to obtain optimal decisions. Reinforcement learning uses action-state-value functions, state-value functions, and policy functions to derive the optimal policy. Deep reinforcement learning can be simply understood as using deep neural networks to fit action-state-value functions, state-value functions, and policy functions.

[0042] Reinforcement learning can help networks obtain optimal adaptive MCS strategies. By interacting with the UE through air interface channels, reinforcement learning enables the network to learn the optimal adaptive MCS strategy, thereby ensuring optimal spectral efficiency and user experience rate.

[0043] The RL agent learns online the demodulation capabilities of the wireless channel and the receiver, thereby formulating the optimal adaptive modulation and coding scheme. In the RL adaptive MCS, the agent resides in the network scheduler, and the online learning process includes:

[0044] Step 1: The network scheduler receives status information, including but not limited to: CSI of the wireless channel and the results of data demodulation.

[0045] Step 2: The network sends downlink control information (DCI) to the UE based on the policy function or action state value function to schedule the physical downlink shared channel (PDSCH) or physical uplink shared channel (PUSCH). The DCI contains at least information on the modulation order and coding rate.

[0046] The downlink adaptive MCS primarily indicates the modulation order and coding rate to the PDSCH to match the radio channel capacity. The network determines the modulation order and coding rate based on the air interface channel state and the demodulation capability of the physical channel and sends the indication information to the UE.

[0047] Step 3: The UE receives PDSCH or sends PUSCH according to the DCI. If it receives PDSCH, the UE sends an ACK or NACK for PDSCH to the network. If it sends PUSCH, the network decodes the PUSCH.

[0048] Step four: The network trains or updates the policy function and / or action-state value function based on the CSI and the decoding results of the data. The policy function or action-state value function can be considered a mapping between states and actions.

[0049] Step 5, repeat step 1.

[0050] To learn the optimal policy function and / or value function, the network needs to collect training and validation data. To achieve high-quality data collection, the network requires an exploration process to explore a more comprehensive state space and collect diverse state trajectories. This exploration process refers to the network instructing the transmitter to send PDSCH or PUSCH at specific modulation orders and coding rates at multiple different times and collecting the decoding results. During this process, the network receives state trajectories in the time dimension and corresponding feedback information. During this exploration process, the network may randomly or based on a non-convergent policy instruct MCS information for data transmission. The mismatch between these MCSs used for exploration purposes and the air interface channel capacity can have a serious negative impact on data transmission. An SE corresponding to the instructed MCS information being greater than the air interface channel capacity will lead to data decoding errors, requiring data retransmission. During retransmission, the service data (such as user data) carried by the physical channel will be buffered at the receiver's physical layer. Retransmission not only wastes air interface resources but also increases the latency of delivering user data to higher layers. Data decoding errors affect the network's control over the block error rate (BLER). If a large amount of data is decoded incorrectly, it may trigger abnormal processes, including radio link failure or re-establishment.

[0051] Therefore, how to reduce the impact of reinforcement learning-based adaptive MCS on transmitted service data has become a technical problem that urgently needs to be solved.

[0052] To address the aforementioned technical problems, this disclosure provides a communication method applicable to a reinforcement learning-based adaptive MCS scenario. By specifying a dedicated medium (such as a physical channel or reference signal) for transmitting training data required for reinforcement learning-based adaptive MCS, a distinction is made between this method and the physical channel used for transmitting service data. This avoids conflicts in service data transmission during reinforcement learning-based adaptive MCS, thereby reducing the impact of reinforcement learning-based adaptive MCS on the transmitted service data.

[0053] In this embodiment of the invention, the network architecture of the mobile communication network (including but not limited to second-generation mobile communication technology (2G), third-generation mobile communication technology (3G), fourth-generation mobile communication technology (4G), fifth-generation mobile communication technology (5G), and future mobile communication networks (such as the evolution of the fifth-generation mobile communication technology (5G-A), sixth-generation mobile communication technology (6G)), and seventh-generation mobile communication technology (7G)) may include at least a first communication node and a second communication node, which may be referred to as the first node and the second node, respectively.

[0054] For example, as shown in FIG1, an architecture diagram of a communication system provided in an embodiment of the present disclosure is provided. The communication system may include: a first node 101 and a second node 102.

[0055] The second node 102 can indicate to the first node 101 a physical channel (i.e., a first type of physical channel) dedicated to participating in the reinforcement learning-based adaptive MCS, so that the first node 101 can perform information exchange with the second node 102 based on the first type of physical channel and air interface channel to complete the sample collection of training data for the reinforcement learning-based adaptive MCS.

[0056] Furthermore, the service data transmitted between the first node 101 and the second node 102 will not be transmitted in the first type of physical channel. The service data transmitted between the first node 101 and the second node 102 will be carried and transmitted by other types of physical channels (i.e., physical channels not used to participate in the reinforcement learning-based adaptive MCS, or physical channels dedicated to transmitting service data).

[0057] In this way, by designating a physical channel dedicated to carrying training data for participation in reinforcement learning-based adaptive MCS, it is possible to distinguish it from the physical channel for transmitting service data, thereby avoiding conflicts with the transmission of service data during the reinforcement learning-based adaptive MCS process and reducing the impact of reinforcement learning-based adaptive MCS on the transmitted service data.

[0058] Optionally, the medium by which the second node 102 indicates to the first node 101, specifically for transmitting the training data required for the reinforcement learning-based adaptive MCS, can also be a reference signal.

[0059] This distinguishes it from the physical channel used to transmit service data.

[0060] It should be noted that the first node 101 can be a user equipment node, such as a passive IoT device, tag, or terminal. The second node 102 can be a network equipment node, such as a base station, auxiliary node, or intermediate node.

[0061] In this context, a base station (BS) can be a base station in LTE, Long Term Evolution Advanced (LTEA) or an evolved Node B (eNB or eNodeB), a base station device (gNB) in a 5G network, or a base station in a future communication system. Base stations can include various macro base stations, micro base stations, femtocell base stations, wireless remote extensions, reconfigurable intelligent surfaces (RISS), routers, relay stations, transmission and reception points (TRPs), receivers, access points (APs), wireless fidelity (Wi-Fi) devices, and other network-side equipment. A base station can sometimes also be referred to as a reader or reader used for communication with terminals.

[0062] A terminal can be a device with wireless transceiver capabilities. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, virtual reality (VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control, wireless terminals in self-driving vehicles, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, and so on. The embodiments of this disclosure do not limit the application scenarios. A terminal may also be referred to as a user, user equipment (UE), A-IoT device, access terminal, UE unit, UE station, mobile station, mobile station, remote station, transmitter, remote terminal, mobile device, UE terminal, wireless communication device, UE agent, or UE device, etc., and the embodiments of this disclosure do not limit this to these terms.

[0063] It should be noted that Figure 1 is only an exemplary framework diagram. The number of devices included in Figure 1 and the names of each device are not limited. In addition to the devices shown in Figure 1, the communication system may also include other devices, such as core network devices.

[0064] The application scenarios of the embodiments disclosed herein are not limited. The system architecture and business scenarios described in the embodiments of this disclosure are for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of this disclosure. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this disclosure are also applicable to similar technical problems.

[0065] Figure 2 shows a flowchart of a communication method. As shown in Figure 2, the communication method is applied to the first node and includes: S201.

[0066] In S201, the first indication information sent by the second node is received.

[0067] The first indication information is used to indicate a first type of physical channel, and the first type of physical channel is used to participate in reinforcement learning-based adaptive MCS.

[0068] In other words, the first type of physical channel is only used to obtain the first information required by the reinforcement learning-based adaptive MCS (such as the decoding result of the physical channel based on a given modulation order and coding rate), and is not used to carry other data information (such as user data) other than the first data information.

[0069] In this embodiment of the disclosure, the first type of physical channel can satisfy a first feature, which may include at least one of the following 1.1-1.4:

[0070] 1.1 It does not carry information originating from higher layers of the protocol stack;

[0071] 1.2. Not to be retransmitted;

[0072] 1.3 The decoding results are not used for controlling the Block Error Rate (BLER);

[0073] 1.4 The decoding result is not used as a trigger condition for other communication processes besides adaptive MCS.

[0074] Among them, the feature corresponding to 1.1 above, "the first type of physical channel does not carry information originating from the higher layers of the protocol stack" can include: the transport block of the first type of physical channel is a random bit sequence or a pseudo-random bit sequence.

[0075] In other words, the data carried by the first type of physical channel is randomly generated information that will not be read and used by subsequent user services.

[0076] Alternatively, "the first type of physical channel does not carry information originating from higher layers of the protocol stack" can also include: the first type of physical channel does not carry information from the medium access control (MAC) layer.

[0077] Regarding the feature corresponding to 1.2 above, "the first type of physical channel is not retransmitted" can include: if the decoding result of the first type of physical channel by the receiving node is correct or incorrect, the content carried by the first type of physical channel is discarded by the physical layer of the receiving node.

[0078] In other words, regardless of whether the first node successfully decodes the received first type of physical channel (i.e., whether the decoding result is correct), the physical layer of the first node will discard the content carried by the first type of physical channel. In this way, even if the first node fails to decode the first type of physical channel (i.e., the decoding result is incorrect), the physical layer of the first node will discard the content carried by the first type of physical channel, and the second node will not need to retransmit the first type of physical channel.

[0079] Similarly, regardless of whether the second node successfully decodes the received first type of physical channel (i.e., whether the decoding result is correct), the physical layer of the second node will discard the content carried by the first type of physical channel. In this way, even if the second node fails to decode the first type of physical channel (i.e., the decoding result is incorrect), the physical layer of the second node will discard the content carried by the first type of physical channel, without requiring the first node to retransmit the first type of physical channel.

[0080] Furthermore, for the feature corresponding to 1.3 above, "the decoding result of the first type of physical channel is not used for BLER control" can include: the decoding result of the first type of physical channel is not used to calculate the block error rate (BLER).

[0081] In other words, the decoding results of the first type of physical channel are not used for BLER statistics, so that BLER will not exceed the preset threshold due to decoding errors of the first type of physical channel, nor will BLER be reduced due to successful or incorrect decoding of the first type of physical channel.

[0082] Furthermore, for the feature corresponding to 1.4 above, "the decoding result of the first type of physical channel is not used as a triggering condition for other communication processes besides the adaptive MCS" may include: the decoding result of the first type of physical channel is not used as a triggering condition for the Layer 1 process, Layer 2 process, or Layer 3 process of the radio access network.

[0083] In other words, the first type of physical channel is used for RL training and will not be used as service data by subsequent communication services to trigger the corresponding communication process.

[0084] It should be noted that the configuration method of the first indication information is not limited in the embodiments disclosed herein. For example, the first indication information can be configured using DCI. Another example is that the first indication information can be configured using a system information block. Yet another example is that the first indication information can be configured using a synchronization signal block.

[0085] Understandably, this can be achieved by designating a dedicated medium (such as a physical channel) for transmitting the training data required for reinforcement learning-based adaptive MCS, distinguishing it from the physical channel used for transmitting service data. This avoids conflicts with service data transmission during the reinforcement learning-based adaptive MCS process, thereby reducing the impact of reinforcement learning-based adaptive MCS on the transmitted service data.

[0086] In some embodiments, the first type of physical channel may include a first type of PDSCH and a first type of PUSCH, and the first type of physical channel indicated by the first indication information may be a first type of PDSCH or a first type of PUSCH.

[0087] It should be noted that both the first type of PDSCH and the first type of PUSCH satisfy the first feature mentioned above.

[0088] Taking the first type of PDSCH as an example, the first type of PDSCH carries the first type of medium access control control element (MAC CE). Regarding the feature corresponding to 1.1 above, "the first type of physical channel does not carry information originating from the higher layers of the protocol stack" can include at least one of the following 2.1-2.2:

[0089] 2.1 The first type of PDSCH does not carry MAC CEs of any type other than the first type of MAC CE;

[0090] 2.2 The first type of PDSCH does not carry a medium access control service data unit (MAC SDU).

[0091] In this embodiment of the disclosure, the logical channel identifier (LCID) in the MAC sub-header identifier of the first type of MAC CE is the target identifier.

[0092] The target identifier differs from the LCID in the MAC subheader identifier of other types of MAC CEs.

[0093] In other words, by configuring an LCID in the MAC sub-header identifier to indicate participation in reinforcement learning-based adaptive MCS, it can be distinguished from other LCIDs, making the MAC CE corresponding to this MAC sub-header identifier a first-type MAC CE. That is, the first-type MAC CE is only used to participate in reinforcement learning-based adaptive MCS.

[0094] In some embodiments, the first indication information includes at least one of the following 3.1-3.2:

[0095] 3.1 The number and location of resource elements mapped in each resource block by the first type of physical channel;

[0096] 3.2 Modulation order and coding rate of the first type of physical channel.

[0097] It should be noted that the first node can perform different send and receive operations based on the first type of PDSCH or the first type of PUSCH.

[0098] In some embodiments, the first type of physical channel is a first type of PDSCH. After the first node receives the first indication information sent by the second node (i.e., S201), the first node can also receive the first type of PDSCH sent by the second node based on the above-mentioned 3.1 carried in the first indication information, and send ACK information or NACK information to the second node based on the decoding status of the first type of PDSCH.

[0099] It should be noted that the ACK message can indicate that the first node has successfully decoded the first type of PDSCH (i.e., the decoding result is correct), while the NACK message can indicate that the first node has failed to decode the first type of PDSCH (i.e., the decoding result is incorrect).

[0100] During the process of the first node receiving the first type of PDSCH sent by the second node, the first node can receive the first type of PDSCH and other types of PDSCH sent by the second node on the same time domain resource.

[0101] It should be noted that other types of PDSCH do not meet the first feature mentioned above, and the temporal resources may include at least one of the following: time slots, subframes, and symbols.

[0102] For example, if the first indication information is represented by a DCI, the DCI format representing the first indication information (i.e., scheduling the first type of PDSCH) can be at least one of the following: DCI format 1-0, DCI format 1-1, DCI format 1-2, DCI format 4-0, DCI format 4-1, DCI format 4-2.

[0103] Furthermore, the method by which the DCI characterizes the first indication information (i.e., scheduling the first type of PDSCH) can be at least one of the following: the DCI field is used to indicate whether the PDSCH is the first type of PDSCH, or the radio network temporary identifier (RNTI) type used for scrambling the PDCCH for cyclic redundancy check (CRC) indicates whether the scheduled PDSCH is the first type of PDSCH.

[0104] The DCI field is used to indicate whether the PDSCH is a first-type PDSCH. For example, the DCI can contain a PDSCH type indicator field, which is 1 bit long. When the field is 1, it indicates that the PDSCH is a first-type PDSCH; when the field is 0, it indicates that the PDSCH is not a first-type PDSCH.

[0105] Furthermore, the RNTI type of the CRC used to scramble the PDSCH indicates whether the scheduled PDSCH is a Type I PDSCH. For example, the PDSCH scheduled by the physical downlink control channel (PDCCH) of the Type I RNTI scrambled CRC is a Type I PDSCH; the PDSCH scheduled by the PDCCH of other types of RNTI scrambled CRC is not a Type I PDSCH.

[0106] The first type of RNTI is a 4-digit hexadecimal number, ranging from 0001 to FFF2 or FFF3 to FFFD. The purpose of the first type of RNTI is to schedule first type of PDSCH transmissions. The first type of RNTI can be used for at least one of the following: dynamically scheduled unicast transmissions, dynamically scheduled broadcast-multicast transmissions, configuration-scheduled unicast transmissions, and configuration-scheduled broadcast-multicast transmissions. First type of PDSCH can be dynamically scheduled or non-dynamically scheduled. First type of PDSCH can be either unicast or broadcast-multicast transmissions.

[0107] Furthermore, the DCI for scheduling the first type of PDSCH includes at least time-domain resource allocation information, frequency-domain resource allocation information, and modulation and coding scheme information. The time-domain resource allocation information indicates at least one of the following: the offset of the first type of PDSCH relative to the PDCCH, the starting time-domain symbol, and the time-domain symbol length. The frequency-domain resource allocation information indicates at least one of the following: the starting resource block (RB) and the number of RBs corresponding to the first type of PDSCH. The MCS information indicates at least one of the following: the modulation order and coding rate corresponding to the first type of PDSCH.

[0108] The transport block of the first type of PDSCH does not correspond to the data of the MAC layer. This transport block can be a random or pseudo-random bit sequence, and the physical layer processing of this bit sequence includes at least: channel coding, modulation, and resource mapping.

[0109] Type I PDSCH can map at least one resource element (RE) in each RB. Type I PDSCH can map one RE, two REs, or all REs in each RB. DCI indicates the number of REs mapped by Type I PDSCH in each RB and the pattern of the mapped REs.

[0110] Here, RE pattern refers to which REs the first type of PDSCH maps among the 12 REs in the RB. For example, DCI indicates that the first type of PDSCH maps one RE in each RB, and that the mapped RE is the first RE in the RB.

[0111] Fields in a DCI can be used to indicate the number of REs and the mapped RE pattern. For example, a DCI may contain a bitmap of 12 bits, where the most significant bit is the leftmost bit and the least significant bit is the rightmost bit, or vice versa. This bitmap can correspond to the 12 REs in the RB from left to right, or from right to left. For instance, if the left-to-right correspondence is used, the first bit from the left corresponds to the first RE in the RB, the second bit from the left corresponds to the second RE in the RB, and so on, with the twelfth bit from the left corresponding to the twelfth RE in the RB.

[0112] If a bit value is 1, it means that the first type of PDSCH maps to the corresponding RE in each RB. For example, in DCI, the bit map corresponds to 12 REs in the RB from left to right. If the value of the first bit on the left side of the bit map is 1 and the value of the second bit is 1, and the values ​​of the other bits are all 0, it means that the first type of PDSCH maps to 2 REs in one RB, namely the first RE and the second RE.

[0113] The UE (i.e., the first node) receives a DCI sent by the network (i.e., the second node), instructing the UE to receive a Type 1 PDSCH. The DCI indicates the modulation order and coding rate of the Type 1 PDSCH. The UE receives the Type 1 PDSCH and decodes it based on the modulation order and coding rate. If the Type 1 PDSCH is decoded correctly, the UE's physical layer will not pass the data to higher layers. If the Type 1 PDSCH cannot be decoded correctly, the UE's physical layer will not place the data in the soft buffer or soft information buffer, and the UE does not expect to receive retransmissions of the Type 1 PDSCH. The UE's physical layer will discard the content carried by the Type 1 PDSCH. The decoding result of the Type 1 PDSCH on the UE side will not be used for BLER control. The decoding result of the Type 1 PDSCH on the UE side will not be used to calculate the BLER. The decoding result of the Type 1 PDSCH will not be used to trigger Layer 1, Layer 2, or Layer 3 procedures of the RAN. The UE sends an ACK or NACK for the Type 1 PDSCH to the network. If the Type 1 PDSCH is decoded correctly, the UE sends an ACK to the network. If the first type of PDSCH cannot be decoded correctly, the UE sends a NACK to the network.

[0114] The UE expects to receive one or two PDSCHs on the same time-domain resource. If the UE receives two PDSCHs in the same time slot, the UE expects one to be a Type 1 PDSCH and the other to be a non-Type 1 PDSCH. When a Type 1 PDSCH and a non-Type 1 PDSCH are received in the same time slot, the UE expects to receive the other PDSCH on an RE that is not mapped to a Type 1 PDSCH in a RB. The time-domain resource can be one of the following: time slot, subframe, or time-domain symbol.

[0115] In other embodiments, the first type of physical channel is a first type of PUSCH. After the first node receives the first indication information sent by the second node (i.e., S201), the first node can send the first type of PUSCH indicated by the first indication information to the second node based on the above 3.1 carried by the first indication information.

[0116] During the process of the first node sending the first type of PUSCH to the second node, the first node can send the first type of PUSCH and other types of PUSCH to the second node on the same time domain resource.

[0117] It should be noted that other types of PUSCH do not satisfy the first feature mentioned above, and the temporal resources may include at least one of the following: time slots, subframes, and symbols.

[0118] For example, if the first indication information is represented by a DCI, the DCI format representing the first indication information (i.e., scheduling the first type of PUSCH) can be at least one of the following: DCI format 0-0, DCI format 0-1, DCI format 0-2.

[0119] Furthermore, the method by which the DCI characterizes the first indication information (i.e., scheduling the first type of PUSCH) can be at least one of the following: the DCI field is used to indicate whether the PUSCH is the first type of PDSCH, or the RNTI type of the CRC of the PDCCH used to scramble the PUSCH indicates whether the scheduled PUSCH is the first type of PUSCH.

[0120] The DCI field is used to indicate whether the PUSCH is a first-type PUSCH. For example, the DCI can contain a PUSCH type indicator field, which is 1 bit long. When the field is 1, it indicates that the PUSCH is a first-type PUSCH; when the field is 0, it indicates that the PUSCH is not a first-type PUSCH.

[0121] Furthermore, the RNTI type of the CRC used to scramble the PDCCH indicates whether the scheduled PUSCH is a Type I PUSCH. For example, the PUSCH scheduled by the PDCCH with the Type I RNTI scrambled CRC is a Type I PUSCH; the PUSCH scheduled by the PDCCH with other types of RNTI scrambled CRC is not a Type I PUSCH.

[0122] The first type of RNTI is a 4-digit hexadecimal number, ranging from 0001 to FFF2 or FFF3 to FFFD. The purpose of the first type of RNTI is to schedule first type of PUSCH transmissions. The first type of RNTI can be used for at least one of the following: dynamically scheduled unicast transmissions or non-dynamically scheduled unicast transmissions. First type of PUSCH can be either dynamically or non-dynamically scheduled.

[0123] The DCI for scheduling the first type of PUSCH includes at least time-domain resource allocation information, frequency-domain resource allocation information, and modulation and coding scheme information. The time-domain resource allocation information indicates at least one of the following: the offset of the first type of PUSCH relative to the PDCCH, the starting time-domain symbol, and the time-domain symbol length. The frequency-domain resource allocation information indicates at least one of the following: the starting RB and the number of RBs corresponding to the first type of PUSCH. The modulation and coding scheme information indicates at least one of the following: the modulation order and coding rate corresponding to the first type of PUSCH.

[0124] The first type of PUSCH transport block does not have corresponding MAC layer data. This transport block can be a random or pseudo-random bit sequence, and the physical layer processing of this bit sequence includes at least: channel coding, modulation, and resource mapping.

[0125] Type I PUSCH can map at least one RE in each RB. Type I PUSCH can map one RE, two REs, or all REs in each RB. DCI indicates the number of REs mapped by Type I PUSCH in each RB and the pattern of the mapped REs.

[0126] Here, RE pattern refers to which REs a type 1 PUSCH maps among the 12 REs in an RB. For example, DCI indicates that a type 1 PUSCH maps one RE in each RB, and that the mapped RE is the first RE in the RB.

[0127] Fields in a DCI can be used to indicate the number of REs and the mapped RE pattern. For example, a DCI may contain a bitmap of 12 bits, where the most significant bit is the leftmost bit and the least significant bit is the rightmost bit, or vice versa. This bitmap can correspond to the 12 REs in the RB from left to right, or from right to left. For instance, if the left-to-right correspondence is used, the first bit from the left corresponds to the first RE in the RB, the second bit from the left corresponds to the second RE in the RB, and so on, with the twelfth bit from the left corresponding to the twelfth RE in the RB.

[0128] If a bit value is 1, it means that the first type of PUSCH maps to the corresponding RE in each RB. For example, in DCI, the bit map corresponds to 12 REs in the RB from left to right. If the value of the first bit on the left side of the bit map is 1 and the value of the second bit is 1, and the values ​​of the other bits are all 0, it means that the first type of PUSCH maps to 2 REs in one RB, namely the first RE and the second RE.

[0129] The UE (i.e., the first node) receives a DCI sent by the network (i.e., the second node), instructing the UE to send a Type 1 PUSCH. The DCI indicates the modulation order and coding rate of the Type 1 PUSCH. The network receives the Type 1 PUSCH and decodes it based on the modulation order and coding rate. If the Type 1 PUSCH is decoded correctly, the network's physical layer will not pass the data to higher layers. If the Type 1 PUSCH cannot be decoded correctly, the network's physical layer will not place the data in a soft buffer or soft information buffer, and the network will not instruct the UE to retransmit the Type 1 PUSCH. The network's physical layer will discard the content carried by the Type 1 PUSCH. The UE does not expect to retransmit the Type 1 PUSCH. The decoding result of the Type 1 PUSCH on the network side is not used for BLER control. The decoding result of the Type 1 PUSCH on the network side is not used to calculate the BLER. The decoding result of the Type 1 PUSCH is not used to trigger Layer 1, Layer 2, or Layer 3 procedures of the RAN.

[0130] The UE expects to transmit one or two PUSCHs on the same time-domain resource. If the UE transmits two PUSCHs on the same time slot, the UE expects one to be a Type 1 PUSCH and the other to be a non-Type 1 PUSCH. When a Type 1 PUSCH and a non-Type 1 PUSCH are transmitted in the same time slot, the UE expects to transmit the other PUSCH on a RE that is not mapped to a Type 1 PUSCH in a RB. The time-domain resource can be one of the following: time slot, subframe, or time-domain symbol.

[0131] The following section introduces the configuration method for the first instruction information using specific examples.

[0132] For example, the UE (i.e., the first node) can receive a DCI from the network (i.e., the second node), which indicates that the scheduled PDSCH carries a first-type MAC CE. The UE can send an ACK or NACK for this PDSCH to the network. The PDSCH carrying the first-type MAC CE satisfies one of the following conditions:

[0133] PDSCH carries a first-type MAC CE;

[0134] PDSCH does not carry MAC SDU;

[0135] PDSCH does not carry MAC CEs of any type other than the first type;

[0136] UE does not expect PDSCH to be retransmitted;

[0137] The decoding results of PDSCH will not be used for BLER control;

[0138] The decoding result of PDSCH will not be used as a condition to trigger Layer 1, Layer 2, or Layer 3 procedures in the radio access network.

[0139] Among them, the PDSCH that carries the first type of MAC CE can also carry padding (i.e. useless padding information).

[0140] If the UE cannot correctly decode the PDSCH, it sends a NACK to the network and does not expect to receive PDSCH retransmissions. If the UE can correctly decode the PDSCH, it sends an ACK to the network, and the UE's physical layer passes the decoded data to the MAC layer. If the MAC entity recognizes a Type I MAC CE, it ignores the rest of the MAC PDU. If the MAC entity recognizes a Type I MAC CE, it discards the rest of the MAC PDU.

[0141] In this type, the first type of MAC CE is identified by a MAC sub-header containing the LCID, and its size is fixed at zero bits. The UE can determine that the MAC CE is a first type of MAC CE based on the MAC sub-header containing the LCID.

[0142] This disclosure also provides a communication method applied to a second node, as shown in FIG3. The communication method may include: S301.

[0143] In S301, the first instruction information is sent to the first node.

[0144] It should be noted that the description of the first instruction information can be found in the above embodiment S201, and will not be repeated here.

[0145] In some embodiments, after the second node sends the first indication information to the first node (i.e., S301), the second node can perform different send and receive operations according to the first type of PDSCH or the first type of PUSCH indicated by the first indication information.

[0146] In some embodiments, the second node may send a first type of PDSCH and other types of PDSCH to the first node on the same time domain resource.

[0147] Other types of PDSCH do not satisfy the first feature shown in 1.1-1.4 above, and the temporal resources may include at least one of the following: time slot, subframe, symbol.

[0148] In other embodiments, the second node may receive the first type of PUSCH and other types of PUSCH sent by the first node on the same time domain resource.

[0149] Other types of PUSCH do not satisfy the first feature shown in 1.1-1.4 above, and the temporal resources may include at least one of the following: time slot, subframe, symbol.

[0150] The following describes the communication method provided in the above embodiment, taking the interaction between the first node and the second node as an example, as shown in Figure 4, including: S401-S402.

[0151] In S401, the second node sends the first instruction information to the first node.

[0152] In S402, the first node receives the first instruction information sent by the second node.

[0153] The above embodiments use a new physical channel as the medium for transmitting the training data required for reinforcement learning-based adaptive MCS.

[0154] Furthermore, this disclosure also provides a new reference signal as a medium for transmitting test data required for reinforcement learning-based adaptive MCS, as follows:

[0155] Figure 5 shows a flowchart of another communication method. As shown in Figure 5, this communication method is applied to the first node and includes: S501.

[0156] In S501, the second instruction information sent by the second node is received.

[0157] The second indication information is used to indicate the first type of reference signal, and the first type of reference signal is used to participate in the reinforcement learning-based adaptive MCS.

[0158] In other words, the training data required for reinforcement learning-based adaptive MCS is obtained through a first-type reference signal instead of the physical channel, thus distinguishing it from the transmission of service data through the physical channel. This avoids conflicts with service data transmission during the reinforcement learning-based adaptive MCS process, thereby reducing the impact of reinforcement learning-based adaptive MCS on the transmitted service data.

[0159] In this embodiment of the disclosure, the reference signal of the first type may satisfy at least one of the following 4.1-4.3:

[0160] 4.1 The first type of reference signal includes both the portion known to the receiving node and the portion unknown to the receiving node;

[0161] 4.2 In the first type of reference signal, the portion known to the receiving node is used to decode the portion unknown to the receiving node;

[0162] 4.3 The physical layer processing of the first type of reference signal includes channel coding and modulation.

[0163] Specifically, for the feature corresponding to 4.2 above, "the portion of the reference signal known to the receiving node in the first type is used to decode the portion unknown to the receiving node" can include: the portion of the reference signal known to the receiving node in the first type is used for air interface channel estimation, and the obtained air interface channel estimation is used to decode the portion of the reference signal unknown to the receiving node in the first type.

[0164] In some embodiments, the time-domain behavior of the first type of reference signal is semi-persistent, and the MAC CE associated with the first type of reference signal may include at least one of the following 5.1-5.3:

[0165] 5.1 A first field used to indicate the modulation order and coding rate of the reference signal of the first type;

[0166] 5.2 The second field of the MCS table used to indicate the application of the first type of reference signal;

[0167] 5.3 The third field used to indicate the activation or deactivation of the first type of reference signal.

[0168] In some embodiments, the first type of reference signal may include a first type of uplink reference signal and a first type of downlink reference signal, and the first type of reference signal indicated by the first indication information may be a first type of uplink reference signal or a first type of downlink reference signal.

[0169] It should be noted that both the first type of uplink reference signal and the first type of downlink reference signal satisfy the characteristics shown in 4.1-4.3 above.

[0170] In some embodiments, taking a first type of reference signal as an example of a first type of downlink reference signal, after the first node receives the second indication information sent by the second node (i.e., S501), the first node can also receive the first type of downlink reference signal sent by the second node. The first type of downlink reference signal includes a portion known to the first node and a portion unknown to the first node. Then, the first node can send first verification information to the second node. The first verification information is used to indicate whether the portion of the first type of downlink reference signal unknown to the first node was successfully decoded or failed to decode.

[0171] For example, the first type of reference signal may comprise two parts: a first part known to the UE (i.e., the first node); and a second part unknown to the UE. The physical layer processing of the first type of reference signal at the transmitting end (i.e., the second node) includes at least: CRC addition, channel coding, and modulation. The second part of the first type of reference signal includes at least: CRC addition, channel coding, and modulation. The physical layer processing of the first type of reference signal at the transmitting end may include, but is not limited to: CRC addition of the reference signal sequence, reference signal sequence segmentation, CRC addition of the segmented subsequences, channel coding, physical layer hybrid automatic repeat request (HARQ) processing, rate matching, code block concatenation, scrambling, modulation, layer mapping, precoding, antenna port mapping, and resource mapping.

[0172] The resource mapping of the first and second parts of the first type of reference signal includes, but is not limited to: the first and second parts mapping to different time-domain symbols; the first and second parts mapping to different RBs of the same time-domain symbol; and the first and second parts mapping to different REs of the same RB of the same time-domain symbol. Each layer of the second part corresponds to one port of the first part. Any two ports of the first part can reuse resources in a frequency-division or code-division manner.

[0173] The UE receives a first-type reference signal, where a first part of the first-type reference signal is used to decode a second part of the first-type reference signal. The UE obtains an air interface channel estimate using the first part of the first-type reference signal. The air interface channel estimate can be a matrix, where each element consists of an amplitude and a phase. This matrix has at least two dimensions; for example, the air interface channel matrix is ​​three-dimensional, where the number of antenna ports in the first dimension equals the number of antenna ports in the receiver, the number of antenna ports in the second dimension equals the number of antenna ports in the transmitter, and the number of antenna ports in the third dimension equals the number of receiver antenna ports or the number of receiver antenna ports.

[0174] The UE sends the decoding result of the first type of reference signal to the network (i.e., the second node). The UE then sends the decoding result of the second part of the first type of reference signal to the network. If the UE correctly decodes the second part of the first type of reference signal, the UE sends an ACK to the network; if the UE cannot correctly demodulate the second part of the first type of reference signal, the UE sends a NACK to the network.

[0175] The time-domain behavior of a first-type reference signal can be at least one of the following: periodic, semi-continuous, or aperiodic.

[0176] For a reference signal of type 1 with a period, the RRC reconfiguration message configures the basic information of the reference signal, including period, time slot offset, modulation order, and channel coding rate.

[0177] For a semi-persistent first-type reference signal, the RRC reconfiguration message configures the basic information of the reference signal, including period, slot offset, modulation order, and channel coding rate. Alternatively, the RRC reconfiguration message configures the basic information of the reference signal, including period and slot offset, and the MAC CE indicating the modulation order and channel coding rate of the reference signal to activate / deactivate the semi-persistent first-type reference signal.

[0178] For a non-periodic first-type reference signal, the RRC reconfiguration message configures the basic information of the reference signal, and the DCI indicates the modulation order and channel coding rate of the reference signal.

[0179] Configuration information for the UE to receive the first type of reference signal transmitted by the network. The configuration information includes at least one of the following:

[0180] The configuration information includes resource information for the first type of reference signal, reporting configuration information for the first type of reference signal, and configuration information for basic information of the first type of reference signal. The reporting configuration information for the first type of reference signal at least indicates the configuration information of the PUCCH resources, used to send ACK or NACK of the first type of reference signal to the network. The configuration information for the basic information of the first type of reference signal at least indicates the time-domain behavior information of the first type of reference signal, wherein, for periodic and semi-persistent first type of reference signals, the time-domain behavior information at least includes the period and time slot offset.

[0181] For periodic and semi-continuous first-type reference signals, the configuration information of the first-type reference signal may include modulation order information and channel coding rate information, which are used to indicate the modulation order and coding rate of the first-type reference signal, respectively.

[0182] The configuration information for the basic information of the first type of reference signal at least indicates the density information of the first type of reference signal. The density information indicates how many REs the first type of reference signal occupies in a RB. There are multiple options for configuring the density of the first type of reference signal, and the UE can configure one of them. If the UE is not configured with the density information of the first type of reference signal, the density of the reference signal is expected to be the default configuration.

[0183] MAC CE for activating / deactivating a semi-persistent first-type reference signal can include:

[0184] One field indicates whether the indicated first-type reference signal is activated or deactivated; a value of 1 indicates activation, and a value of 0 indicates deactivation.

[0185] One field is used to contain an index of the first type of reference signal, which indicates the resource of the semi-persistent first type of reference signal that should be activated or deactivated;

[0186] The MAC CE for activating / deactivating a semi-persistent first-type reference signal may include: a field indicating the modulation order and coding rate of the first-type reference signal, the value of which corresponds to an MCS index. The MCS index corresponds to a modulation order and a coding rate, which are located in a row of the MCS index table. The UE uses the MCS index and the MCS index table to determine the modulation order and coding rate of the first-type reference signal.

[0187] The MAC CE for activating / deactivating the semi-persistent first type of reference signal can include: a table with a field indicating the MCS index used by the UE. The UE can be configured with multiple MCS index tables.

[0188] The DCI format for triggering an aperiodic first-type reference signal can be at least one of the following: DCI format 1-0, DCI format 1-1, DCI format 1-2, DCI format 4-0, DCI format 4-1, or DCI format 4-2. The DCI fields are used to trigger the aperiodic first-type reference signal. For example, the DCI may contain a field indicating a state. One state corresponds to one first-type reference signal resource and one PUCCH resource. This correspondence can be included in the configuration information of the first-type reference signal. The PUCCH resource is used to transmit the ACK or NACK of the first-type reference signal.

[0189] In other embodiments, taking a first-type reference signal as an example of an uplink reference signal of the first type, after the first node receives the second indication information sent by the second node (i.e., S501), the first node can also send the first-type uplink reference signal to the second node. The first-type uplink reference signal includes a part known to the second node and a part unknown to the second node. Then, the first node can receive second verification information sent by the second node. The second verification information is used to indicate whether the part of the first-type uplink reference signal unknown to the second node was successfully decoded or failed to decode.

[0190] For example, the first type of reference signal may comprise two parts: a first part known to the network (i.e., the second node); and a second part unknown to the network. The physical layer processing of the first type of reference signal at the UE (i.e., the first node) includes at least: CRC addition, channel coding, and modulation. The second part of the first type of reference signal includes at least: channel coding and modulation. The physical layer processing of the first type of reference signal at the transmitting end may include, but is not limited to: CRC addition of the reference signal sequence, reference signal sequence segmentation, CRC addition of the segmented subsequences, channel coding, physical layer HARQ processing, rate matching, code block concatenation, scrambling, modulation, layer mapping, precoding, antenna port mapping, and resource mapping.

[0191] The resource mapping of the first and second parts of the first type of reference signal includes, but is not limited to: the first and second parts mapping to different time-domain symbols; the first and second parts mapping to different RBs of the same time-domain symbol; and the first and second parts mapping to different REs of the same RB of the same time-domain symbol. Each layer of the second part corresponds to one port of the first part. Any two ports of the first part can reuse resources in a frequency-division or code-division manner.

[0192] The UE transmits a first-type reference signal, where a first part of the first-type reference signal is used to decode a second part of the first-type reference signal. The network (i.e., the second node) obtains an air interface channel estimate using the first part of the first-type reference signal. The air interface channel estimate can be a matrix where each element consists of an amplitude and a phase. This matrix has at least two dimensions; for example, the air interface channel matrix is ​​three-dimensional, where the number of the first dimension equals the number of receiver antenna ports, the number of the second dimension equals the number of transmitter antenna ports, and the number of the third dimension equals the number of receiver arrays (REs) or receiver arrays (RBs).

[0193] The network decodes the Type I reference signal. The network does not need to send the decoding result of the Type I reference signal to the UE. The UE does not need the decoding result of the Type I reference signal.

[0194] The time-domain behavior of a first-type reference signal can be at least one of the following: periodic, semi-continuous, or aperiodic.

[0195] For a reference signal of type 1 with a period, the RRC reconfiguration message configures the basic information of the reference signal, including period, time slot offset, modulation order, and channel coding rate.

[0196] For a semi-persistent first-type reference signal, the RRC reconfiguration message configures the basic information of the reference signal, including period, slot offset, modulation order, and channel coding rate. Alternatively, the RRC reconfiguration message configures the basic information of the reference signal, including period and slot offset, and the MAC CE indicating the modulation order and channel coding rate of the reference signal to activate / deactivate the semi-persistent first-type reference signal.

[0197] For a non-periodic first-type reference signal, the RRC reconfiguration message configures the basic information of the reference signal, and the DCI indicates the modulation order and channel coding rate of the reference signal.

[0198] Configuration information for the UE to receive the first type of reference signal transmitted by the network. The configuration information includes at least one of the following:

[0199] The configuration information of the resources of the first type of reference signal, and the configuration information of the basic information of the first type of reference signal. The configuration information of the basic information of the first type of reference signal at least indicates the information of the time domain behavior of the first type of reference signal, wherein, for periodic and semi-continuous first type of reference signals, the time domain behavior information includes at least the period and time slot offset.

[0200] For periodic and semi-continuous first-type reference signals, the configuration information of the first-type reference signal may include modulation order information and channel coding rate information, which are used to indicate the modulation order and coding rate of the first-type reference signal, respectively.

[0201] The configuration information for the basic information of the first type of reference signal at least indicates the density information of the first type of reference signal. The density information indicates how many REs the first type of reference signal occupies in a RB. There are multiple options for configuring the density of the first type of reference signal, and the UE can configure one of them. If the UE is not configured with the density information of the first type of reference signal, the density of the reference signal is expected to be the default configuration.

[0202] MAC CE for activating / deactivating a semi-persistent first-type reference signal can include:

[0203] One field indicates whether the indicated first-type reference signal is activated or deactivated; a value of 1 indicates activation, and a value of 0 indicates deactivation.

[0204] One field is used to contain an index of the first type of reference signal, which indicates the semi-persistent first type of reference signal resource that should be activated or deactivated;

[0205] The MAC CE for activating / deactivating a semi-persistent first-type reference signal may include: a field indicating the modulation order and coding rate of the first-type reference signal, the value of which corresponds to an MCS index. The MCS index corresponds to a modulation order and a coding rate, which are located in a row of the MCS index table. The UE uses the MCS index and the MCS index table to determine the modulation order and coding rate of the first-type reference signal.

[0206] The MAC CE for activating / deactivating the semi-persistent first type of reference signal can include: a table with a field indicating the MCS index used by the UE. The UE can be configured with multiple MCS index tables.

[0207] The DCI format for triggering aperiodic first-type reference signals can be at least one of the following: DCI format 0-0, DCI format 0-1, or DCI format 0-2. The DCI fields are used to trigger aperiodic first-type reference signals. For example, the DCI may contain a field indicating a state. One state corresponds to one first-type reference signal resource. This correspondence can be included in the configuration information of the first-type reference signal.

[0208] This disclosure also provides a communication method applied to a second node, as shown in FIG6. The communication method may include: S601.

[0209] In S601, a second instruction message is sent to the first node.

[0210] It should be noted that the description of the second instruction information can be found in the above embodiment S501, and will not be repeated here.

[0211] In some embodiments, after the second node sends the second indication information to the first node (i.e., S601), the second node can perform different transmit and receive operations based on the first type of uplink reference signal or the first type of downlink reference signal indicated by the second indication information.

[0212] In some embodiments, the second node may send a first type of downlink reference signal to the first node and receive first verification information sent by the first node.

[0213] The first type of downlink reference signal includes a known part of the first node and an unknown part of the first node; the first verification information is used to indicate whether the unknown part of the first node in the first type of downlink reference signal is successfully decoded or fails to be decoded.

[0214] In other embodiments, the second node may receive a first type of uplink reference signal sent by the first node and send second verification information to the first node.

[0215] The first type of uplink reference signal includes a part known to the second node and a part unknown to the second node; the second verification information is used to indicate whether the part unknown to the second node in the first type of uplink reference signal is successfully decoded or fails to decode.

[0216] The following describes the communication method provided in the above embodiment, taking the interaction between the first node and the second node as an example, as shown in Figure 7, including: S701-S702.

[0217] In S701, the second node sends a second instruction message to the first node.

[0218] In S702, the first node receives the second instruction information sent by the second node.

[0219] In summary, both the first type of physical channel and the first type of reference signal are used in the same or similar way to collect the training data required for reinforcement learning-based adaptive MCS (i.e., they belong to a unified concept) to distinguish them from the physical channel transmitting service data. This avoids conflicts with service data transmission during reinforcement learning-based adaptive MCS, thereby reducing the impact of reinforcement learning-based adaptive MCS on the transmitted service data.

[0220] It is understood that, in order to achieve the above-mentioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the algorithmic steps of the examples described in conjunction with the embodiments of this disclosure, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0221] This disclosure embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one functional module. The integrated module can be implemented in hardware or software. It should be noted that the module division in this disclosure embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the example of dividing each functional module according to each function.

[0222] Figure 8 is a block diagram of a communication device according to some embodiments. The communication device can be applied to a first node and execute the communication method shown in Figure 2 above, as well as the embodiment on the first node side in Figure 4. As shown in Figure 8, the communication device 800 includes: a receiving module 801.

[0223] The receiving module 801 is configured to receive first indication information sent by the second node. The first indication information indicates a first type of physical channel, which is used to participate in the reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of physical channel satisfies a first feature, which includes at least one of the following:

[0224] It does not carry information originating from higher layers of the protocol stack;

[0225] Not to be retransmitted;

[0226] The decoding results are not used for controlling the block error rate (BLER).

[0227] The decoding result is not used as a trigger condition for other communication processes besides the adaptive modulation and coding scheme (MCS).

[0228] In some embodiments, the first type of physical channel does not carry information originating from higher layers of the protocol stack, including: the transport blocks of the first type of physical channel are random bit sequences or pseudo-random bit sequences.

[0229] In some embodiments, the first type of physical channel is not retransmitted, including: if the decoding result of the first type of physical channel by the receiving node is correct or incorrect, the content carried by the first type of physical channel is discarded by the physical layer of the receiving node.

[0230] In some embodiments, the decoding results of the first type of physical channel are not used for controlling the block error rate (BLER), including: the decoding results of the first type of physical channel are not used to calculate the block error rate (BLER).

[0231] In some embodiments, the decoding result of the first type of physical channel is not used as a triggering condition for other communication processes besides the adaptive modulation and coding scheme (MCS), including: the decoding result of the first type of physical channel is not used as a triggering condition for the layer 1 process, layer 2 process, or layer 3 process of the radio access network.

[0232] In some embodiments, the first type of physical channel includes a first type of physical downlink shared channel carrying a first type of Media Access Control (MAC) CE. The first type of physical channel does not carry information originating from higher layers of the protocol stack, including at least one of the following:

[0233] The first type of physical downlink shared channel does not carry media access control and control units (MAC CEs) of any type other than the first type of media access control and control unit (MAC CE).

[0234] The first type of physical downlink shared channel does not carry Media Access Control Service Data Unit (MAC SDU).

[0235] In some embodiments, the logical channel identifier in the media access control subheader identifier of the first type of media access control control unit (MAC CE) is the target identifier, and the target identifier is different from the logical channel identifier in the media access control subheader identifier of other types of media access control control unit (MAC CE).

[0236] In some embodiments, the first type of physical channel includes a first type of physical uplink shared channel; the communication device 800 may further include a transmitting module 802. The transmitting module 802 is configured to transmit the first type of physical uplink shared channel and other types of physical uplink shared channels to the second node on the same time domain resources; wherein, the other types of physical uplink shared channels do not satisfy the first feature; the time domain resources include at least one of the following: time slots, subframes, and symbols.

[0237] In some embodiments, the first type of physical channel includes a first type of physical downlink shared channel; the receiving module 801 is further configured to receive the first type of physical downlink shared channel and other types of physical downlink shared channels transmitted by the second node on the same time domain resource; wherein, other types of physical downlink shared channels do not satisfy the first feature; the time domain resource includes at least one of the following: time slot, subframe, symbol.

[0238] In some embodiments, the first indication information includes: the number and location of resource elements (REs) mapped by the first type of physical channel in each resource block (RB).

[0239] Figure 9 is a block diagram of another communication device according to some embodiments. The communication device can be applied to a first node and perform the communication method shown in Figure 5 above, as well as the embodiment on the first node side in Figure 7. As shown in Figure 9, the communication device 900 includes: a receiving module 901.

[0240] The receiving module 901 is configured to receive second indication information transmitted by the second node. The second indication information indicates a first type of reference signal, which participates in the reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of reference signal satisfies at least one of the following:

[0241] The first type of reference signal includes both the portion known to the receiving node and the portion unknown to the receiving node;

[0242] In the first type of reference signal, the portion known to the receiving node is used to decode the portion unknown to the receiving node;

[0243] The physical layer processing of the first type of reference signal includes channel coding and modulation.

[0244] In some embodiments, the portion of the first type of reference signal known to the receiving node is used to decode the portion unknown to the receiving node, including: the portion of the first type of reference signal known to the receiving node is used for air interface channel estimation, and the air interface channel estimation is used to decode the portion of the first type of reference signal unknown to the receiving node.

[0245] In some embodiments, the time-domain behavior of the first type of reference signal is semi-persistent, and the media access control unit (MAC CE) associated with the first type of reference signal includes at least one of the following:

[0246] The first field is used to indicate the modulation order and coding rate of the reference signal of the first type;

[0247] The second field of the modulation and coding scheme (MCS) table used to indicate the application of the first type of reference signal.

[0248] In some embodiments, the first type of reference signal includes a first type of downlink reference signal; the communication device 900 may further include: a transmitting module 902. A receiving module 901 is further configured to receive the first type of downlink reference signal transmitted by the second node, the first type of downlink reference signal including a portion known to the first node and a portion unknown to the first node; the transmitting module 902 is configured to transmit first verification information to the second node, the first verification information indicating whether the portion of the first type of downlink reference signal unknown to the first node was successfully decoded or failed to be decoded.

[0249] Figure 10 is a block diagram of another communication device according to some embodiments. The communication device can be applied to a second node and execute the communication method shown in Figure 3 above, as well as the embodiment on the second node side in Figure 4. As shown in Figure 10, the communication device 1000 includes: a transmitting module 1001.

[0250] The transmitting module 1001 is configured to transmit first indication information to the first node. The first indication information indicates a first type of physical channel, which is used to participate in the reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of physical channel satisfies a first feature, which includes at least one of the following:

[0251] It does not carry information originating from higher layers of the protocol stack;

[0252] Not to be retransmitted;

[0253] The decoding results are not used for controlling the block error rate (BLER).

[0254] The decoding result is not used as a trigger condition for other communication processes besides the adaptive modulation and coding scheme (MCS).

[0255] In some embodiments, the first type of physical channel does not carry information originating from higher layers of the protocol stack, including: the transport blocks of the first type of physical channel are random bit sequences or pseudo-random bit sequences.

[0256] In some embodiments, the first type of physical channel is not retransmitted, including: if the decoding result of the first type of physical channel by the receiving node is correct or incorrect, the content carried by the first type of physical channel is discarded by the physical layer of the receiving node.

[0257] In some embodiments, the decoding results of the first type of physical channel are not used for controlling the block error rate (BLER), including: the decoding results of the first type of physical channel are not used to calculate the block error rate (BLER).

[0258] In some embodiments, the decoding result of the first type of physical channel is not used as a triggering condition for other communication processes besides the adaptive modulation and coding scheme (MCS), including: the decoding result of the first type of physical channel is not used as a triggering condition for the layer 1 process, layer 2 process, or layer 3 process of the radio access network.

[0259] In some embodiments, the first type of physical channel includes a first type of physical downlink shared channel carrying a first type of Media Access Control (MAC) CE. The first type of physical channel does not carry information originating from higher layers of the protocol stack, including at least one of the following:

[0260] The first type of physical downlink shared channel does not carry media access control and control units (MAC CEs) of any type other than the first type of media access control and control unit (MAC CE).

[0261] The first type of physical downlink shared channel does not carry Media Access Control Service Data Unit (MAC SDU).

[0262] In some embodiments, the logical channel identifier in the media access control subheader identifier of the first type of media access control control unit (MAC CE) is the target identifier, and the target identifier is different from the logical channel identifier in the media access control subheader identifier of other types of media access control control unit (MAC CE).

[0263] In some embodiments, the first type of physical channel includes a first type of physical uplink shared channel; the communication device 1000 may further include a receiving module 1002. The receiving module 1002 is configured to receive the first type of physical uplink shared channel and other types of physical uplink shared channels transmitted by the first node on the same time domain resources; wherein, the other types of physical uplink shared channels do not satisfy the first feature; the time domain resources include at least one of the following: time slot, subframe, symbol.

[0264] In some embodiments, the first type of physical channel includes a first type of physical downlink shared channel; the transmitting module 1001 is further configured to transmit the first type of physical downlink shared channel and other types of physical downlink shared channels to the first node on the same time domain resources; wherein, other types of physical downlink shared channels do not satisfy the first feature; the time domain resources include at least one of the following: time slot, subframe, symbol.

[0265] In some embodiments, the first indication information includes: the number and location of resource elements (REs) mapped by the first type of physical channel in each resource block (RB).

[0266] Figure 11 is a block diagram of another communication device according to some embodiments. The communication device can be applied to a second node and execute the communication method shown in Figure 6 above, as well as the embodiment on the second node side in Figure 7. As shown in Figure 11, the communication device 1100 includes: a transmitting module 1101.

[0267] The transmitting module 1101 is used to transmit second indication information to the first node. The second indication information indicates a first type of reference signal, which is used to participate in the reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of reference signal satisfies at least one of the following:

[0268] The first type of reference signal includes both the portion known to the receiving node and the portion unknown to the receiving node;

[0269] In the first type of reference signal, the portion known to the receiving node is used to decode the portion unknown to the receiving node;

[0270] The physical layer processing of the first type of reference signal includes channel coding and modulation.

[0271] In some embodiments, the portion of the first type of reference signal known to the receiving node is used to decode the portion unknown to the receiving node, including: the portion of the first type of reference signal known to the receiving node is used for air interface channel estimation, and the air interface channel estimation is used to decode the portion of the first type of reference signal unknown to the receiving node.

[0272] In some embodiments, the time-domain behavior of the first type of reference signal is semi-persistent, and the media access control unit (MAC CE) associated with the first type of reference signal includes at least one of the following:

[0273] The first field is used to indicate the modulation order and coding rate of the reference signal of the first type;

[0274] The second field of the modulation and coding scheme (MCS) table used to indicate the application of the first type of reference signal.

[0275] In some embodiments, the first type of reference signal includes a first type of downlink reference signal; the communication device 1100 may further include a receiving module 1102.

[0276] The transmitting module 1101 is further configured to transmit a first type of downlink reference signal to the first node, the first type of downlink reference signal including a part known to the first node and a part unknown to the first node; the receiving module 1102 is configured to receive first verification information transmitted by the first node, the first verification information being used to indicate whether the part unknown to the first node in the first type of downlink reference signal was successfully decoded or failed to be decoded.

[0277] In implementing the functions of the integrated modules described above in hardware, this disclosure provides another structure for the communication device involved in the above embodiments. As shown in FIG12, the communication device 1200 includes a processor 1202 and a bus 1204. In some embodiments, the communication device may further include a memory 1201. In some embodiments, the communication device may further include a communication interface 1203.

[0278] Processor 1202 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 1202 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 1202 may also be a combination of functions implementing computation, such as a combination of one or more microprocessors, a digital signal processor (DSP), and a microprocessor, etc.

[0279] The communication interface 1203 is used to connect with other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0280] The memory 1201 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0281] In some embodiments, the memory 1201 may exist independently of the processor 1202. The memory 1201 may be connected to the processor 1202 via a bus 1204 and may be used to store instructions or program code. When the processor 1202 calls and executes the instructions or program code stored in the memory 1201, it can implement the communication method provided in the embodiments of this disclosure.

[0282] In other embodiments, the memory 1201 may also be integrated with the processor 1202.

[0283] Bus 1204 can be an extended industry standard architecture (EISA) bus, etc. Bus 1204 can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in Figure 12, but this does not mean that there is only one bus or one type of bus.

[0284] Some embodiments of this disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) storing computer program instructions that, when executed on a computer, cause the computer to perform the communication method as described in any of the above embodiments.

[0285] Exemplary examples show that the aforementioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical discs (e.g., compact disks (CDs), digital versatile disks (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROMs), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this disclosure may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0286] This disclosure provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the communication method shown in any of the embodiments described above.

[0287] The above descriptions are merely specific embodiments of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions within the technical scope disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A communication method, wherein, Applied to the first node, the method includes: The system receives first indication information sent by a second node. This first indication information indicates a first type of physical channel used to participate in a reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of physical channel satisfies a first feature, which includes at least one of the following: It does not carry information originating from higher layers of the protocol stack; Not to be retransmitted; The decoding results are not used for controlling the block error rate (BLER). The decoding result is not used as a trigger condition for other communication processes besides the adaptive modulation and coding scheme (MCS).

2. The method according to claim 1, wherein, The first type of physical channel does not carry information originating from higher layers of the protocol stack, including: The transmission blocks of the first type of physical channel are random bit sequences or pseudo-random bit sequences.

3. The method according to claim 1, wherein, The first type of physical channel is not retransmitted, including: If the decoding result of the first type of physical channel by the receiving node is correct or incorrect, the content carried by the first type of physical channel is discarded by the physical layer of the receiving node.

4. The method according to claim 1, wherein, The decoding results of the first type of physical channel are not used for block error rate (BLER) control, including: The decoding results of the first type of physical channel are not used to calculate the block error rate (BLER).

5. The method according to claim 1, wherein, The decoding result of the first type of physical channel is not used as a trigger condition for other communication processes besides the adaptive modulation and coding scheme (MCS), including: The decoding result of the physical channel of the first type is not used as the triggering condition for the Layer 1, Layer 2 or Layer 3 process of the wireless access network.

6. The method according to claim 1, wherein, The first type of physical channel includes a first type of physical downlink shared channel carrying a first type of Media Access Control (MAC) CE. The first type of physical channel does not carry information originating from higher layers of the protocol stack, including at least one of the following: The first type of physical downlink shared channel does not carry media access control and control unit (MAC CE) of any type other than the first type of MAC CE; The first type of physical downlink shared channel does not carry Media Access Control Service Data Unit (MAC SDU).

7. The method according to claim 6, wherein, The logical channel identifier in the media access control subheader of the first type of media access control control unit (MAC CE) is the target identifier, and the target identifier is different from the logical channel identifier in the media access control subheader of the other types of media access control control unit (MAC CE).

8. The method according to claim 1, wherein, The first type of physical channel includes the first type of physical uplink shared channel; the method further includes: Send the first type of physical uplink shared channel and other types of physical uplink shared channels to the second node on the same time domain resources; Wherein, the other types of physical uplink shared channels do not satisfy the first feature; the time-domain resources include at least one of the following: time slots, subframes, and symbols.

9. The method according to claim 1, wherein, The first type of physical channel includes the first type of physical downlink shared channel; the method further includes: Receive the first type of physical downlink shared channel and other types of physical downlink shared channels sent by the second node on the same time domain resources; Wherein, the other types of physical downlink shared channels do not satisfy the first feature; the time-domain resources include at least one of the following: time slots, subframes, and symbols.

10. The method according to claim 1, wherein, The first indication information includes: the number and location of resource elements (REs) mapped by the first type of physical channel in each resource block (RB).

11. A communication method, wherein, Applied to the first node, the method includes: The system receives second indication information sent by a second node. This second indication information indicates a first type of reference signal used to participate in a reinforcement learning-based adaptive modulation and coding scheme (MCS). The first type of reference signal satisfies at least one of the following: The first type of reference signal includes a portion known to the receiving node and a portion unknown to the receiving node; The portion of the reference signal known to the receiving node in the first type is used to decode the portion unknown to the receiving node; The physical layer processing of the reference signal of the first type includes channel coding and modulation.

12. The method according to claim 11, wherein, The portion of the reference signal of the first type known to the receiving node is used to decode the portion unknown to the receiving node, including: The portion of the reference signal of the first type that is known to the receiving node is used for air interface channel estimation, and the air interface channel estimation is used to decode the portion of the reference signal of the first type that is unknown to the receiving node.

13. The method according to claim 11, wherein, The time-domain behavior of the first type of reference signal is semi-persistent, and the media access control unit (MAC CE) associated with the first type of reference signal includes at least one of the following: A first field used to indicate the modulation order and coding rate of the reference signal of the first type; The second field of the modulation and coding scheme (MCS) table used to indicate the application of the first type of reference signal.

14. The method according to claim 11, wherein, The first type of reference signal includes the first type of downlink reference signal; the method further includes: Receive the first type of downlink reference signal sent by the second node, wherein the first type of downlink reference signal includes a portion known to the first node and a portion unknown to the first node; Send first verification information to the second node, the first verification information being used to indicate whether the part of the downlink reference signal of the first type that is unknown to the first node has been successfully decoded or has failed to be decoded.

15. A communication method, wherein, Applied to the second node, the method includes: Send first indication information to the first node, the first indication information being used to indicate a first type of physical channel, the first type of physical channel being used to participate in the reinforcement learning-based adaptive modulation and coding scheme MCS, the first type of physical channel satisfying a first feature, the first feature including at least one of the following: It does not carry information originating from higher layers of the protocol stack; Not to be retransmitted; The decoding results are not used for controlling the block error rate (BLER). The decoding result is not used as a trigger condition for other communication processes besides the adaptive modulation and coding scheme (MCS).

16. The method according to claim 15, wherein, The first type of physical channel does not carry information originating from higher layers of the protocol stack, including: The transmission blocks of the first type of physical channel are random bit sequences or pseudo-random bit sequences.

17. The method according to claim 15, wherein, The first type of physical channel is not retransmitted, including: If the decoding result of the first type of physical channel by the receiving node is correct or incorrect, the content carried by the first type of physical channel is discarded by the physical layer of the receiving node.

18. The method according to claim 15, wherein, The decoding results of the first type of physical channel are not used for block error rate (BLER) control, including: The decoding results of the first type of physical channel are not used to calculate the block error rate (BLER).

19. The method according to claim 15, wherein, The decoding result of the first type of physical channel is not used as a trigger condition for other communication processes besides the adaptive modulation and coding scheme (MCS), including: The decoding result of the physical channel of the first type is not used as the triggering condition for the Layer 1, Layer 2 or Layer 3 process of the wireless access network.

20. The method of claim 15, wherein, The first type of physical channel includes a first type of physical downlink shared channel carrying a first type of Media Access Control (MAC) CE. The first type of physical channel does not carry information originating from higher layers of the protocol stack, including at least one of the following: The first type of physical downlink shared channel does not carry media access control and control unit (MAC CE) of any type other than the first type of MAC CE; The first type of physical downlink shared channel does not carry Media Access Control Service Data Unit (MAC SDU).

21. The method according to claim 20, wherein, The logical channel identifier in the media access control subheader of the first type of media access control control unit (MAC CE) is the target identifier, and the target identifier is different from the logical channel identifier in the media access control subheader of the other types of media access control control unit (MAC CE).

22. The method according to claim 15, wherein, The first type of physical channel includes the first type of physical uplink shared channel; the method further includes: Receive the first type of physical uplink shared channel and other types of physical uplink shared channels sent by the first node on the same time domain resources; Wherein, the other types of physical uplink shared channels do not satisfy the first feature; the time-domain resources include at least one of the following: time slots, subframes, and symbols.

23. The method according to claim 15, wherein, The first type of physical channel includes the first type of physical downlink shared channel; the method further includes: Send the first type of physical downlink shared channel and other types of physical downlink shared channels to the first node on the same time domain resources; Wherein, the other types of physical downlink shared channels do not satisfy the first feature; the time-domain resources include at least one of the following: time slots, subframes, and symbols.

24. The method according to claim 15, wherein, The first indication information includes: the number and location of resource elements (REs) mapped by the first type of physical channel in each resource block (RB).

25. A communication method, wherein, Applied to the second node, the method includes: Send second indication information to the first node, the second indication information being used to indicate a first type of reference signal, the first type of reference signal being used to participate in the reinforcement learning-based adaptive modulation and coding scheme MCS, wherein the first type of reference signal satisfies at least one of the following: The first type of reference signal includes a portion known to the receiving node and a portion unknown to the receiving node; The portion of the reference signal known to the receiving node in the first type is used to decode the portion unknown to the receiving node; The physical layer processing of the reference signal of the first type includes channel coding and modulation.

26. The method of claim 25, wherein, The portion of the reference signal of the first type known to the receiving node is used to decode the portion unknown to the receiving node, including: The portion of the reference signal of the first type that is known to the receiving node is used for air interface channel estimation, and the air interface channel estimation is used to decode the portion of the reference signal of the first type that is unknown to the receiving node.

27. The method according to claim 25, wherein, The time-domain behavior of the first type of reference signal is semi-persistent, and the media access control unit (MAC CE) associated with the first type of reference signal includes at least one of the following: A first field used to indicate the modulation order and coding rate of the reference signal of the first type; The second field of the modulation and coding scheme (MCS) table used to indicate the application of the first type of reference signal.

28. The method according to claim 25, wherein, The first type of reference signal includes the first type of downlink reference signal; the method further includes: Send the first type of downlink reference signal to the first node, wherein the first type of downlink reference signal includes a portion known to the first node and a portion unknown to the first node; The system receives first verification information sent by the first node, which indicates whether the decoding of a portion of the downlink reference signal of the first type that is unknown to the first node was successful or failed.

29. A communication device, wherein, include: Memory and processor; Memory and processor are coupled; The memory is used to store instructions that can be executed by the processor; When the processor executes the instructions, it performs the method as described in any one of claims 1-28.

30. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-28.

31. A computer program product, wherein, The computer program product includes computer program instructions that, when executed, implement the method as described in any one of claims 1-28.

Images