Information transmission methods and apparatuses, and device and storage medium

Abstract

Information transmission methods and apparatuses, and a device and a storage medium, which relate to the technical field of communications. An information transmission method is executed by a terminal device. The method comprises: receiving a modulation and coding scheme (MCS) indication message, wherein the MCS indication message is used for determining a first MCS from among candidate MCSs (410); and on the basis of the first MCS, transmitting first information (420), wherein the candidate MCSs include one or more of the following: AI-based modulation and a conventional channel coding rate; a modulation order and AI-based channel coding; and AI-based modulation and channel coding. Candidate MCSs may include a conventional MCS, and may also include an AI-based MCS. Determining a first MCS from among the candidate MCSs by means of an MCS indication message enables flexible switching between the conventional MCS and the AI-based MCS, such that a currently more suitable MCS can be selected for data transmission, thereby ensuring the data transmission performance.

Description

Information transmission methods, devices, equipment and storage media Technical Field

[0001] This application relates to the field of communication technology, and in particular to an information transmission method, apparatus, device, and storage medium. Background Technology

[0002] In related technologies, the modulation scheme and channel coding rate used by the current data are indicated by the MCS (Modulation Coding Scheme) indication message. However, if the modulation or channel coding process is based on AI (Artificial Intelligence), the corresponding modulation scheme or code rate cannot be indicated by traditional methods, which requires further discussion and research. Summary of the Invention

[0003] This application provides an information transmission method, apparatus, device, and storage medium. The technical solution is as follows:

[0004] According to one aspect of the embodiments of this application, an information transmission method is provided, the method being executed by a terminal device, the method comprising:

[0005] Receive an MCS indication message, the MCS indication message being used to determine a first MCS from candidate MCSs;

[0006] First information is transmitted based on the first MCS;

[0007] The candidate MCS includes one or more of the following:

[0008] AI-based modulation and traditional channel coding code rate;

[0009] Modulation order and AI-based channel coding;

[0010] AI-based modulation and channel coding.

[0011] According to one aspect of the embodiments of this application, an information transmission method is provided, the method being executed by a network device, the method comprising:

[0012] Send an MCS indication message, which is used to determine a first MCS from the candidate MCSs;

[0013] First information is transmitted based on the first MCS;

[0014] The candidate MCS includes one or more of the following:

[0015] AI-based modulation and traditional channel coding code rate;

[0016] Modulation order and AI-based channel coding;

[0017] AI-based modulation and channel coding.

[0018] According to one aspect of the embodiments of this application, an information transmission apparatus is provided, the apparatus comprising:

[0019] A receiving module is configured to receive an MCS indication message, wherein the MCS indication message is used to determine a first MCS from candidate MCSs;

[0020] The transmission module is used to transmit first information based on the first MCS;

[0021] The candidate MCS includes one or more of the following:

[0022] AI-based modulation and traditional channel coding code rate;

[0023] Modulation order and AI-based channel coding;

[0024] AI-based modulation and channel coding.

[0025] According to one aspect of the embodiments of this application, an information transmission apparatus is provided, the apparatus comprising:

[0026] The sending module is used to send an MCS indication message, which is used to determine a first MCS from candidate MCSs;

[0027] The transmission module is used to transmit first information based on the first MCS;

[0028] The candidate MCS includes one or more of the following:

[0029] AI-based modulation and traditional channel coding code rate;

[0030] Modulation order and AI-based channel coding;

[0031] AI-based modulation and channel coding.

[0032] According to one aspect of the embodiments of this application, a communication device is provided, the communication device including a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the above-described information transmission method. The communication device is a terminal device, or the communication device is a network device.

[0033] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program for execution by a processor to implement the above-described information transmission method.

[0034] According to one aspect of the embodiments of this application, a chip is provided, the chip including programmable logic circuits and / or program instructions, which, when the chip is running, are used to implement the above-described information transmission method.

[0035] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium, and a processor reading from the computer-readable storage medium and executing the computer instructions to implement the above-described information transmission method.

[0036] The technical solutions provided in this application embodiment may have the following beneficial effects:

[0037] Candidate MCSs can include traditional modulation and coding schemes or AI-based modulation and coding schemes. The first MCS is determined from the candidate MCSs through the MCS indication message. This enables flexible switching between traditional modulation and coding schemes and AI-based modulation and coding schemes, allowing the selection of the better modulation and coding scheme for data transmission and ensuring data transmission performance. Attached Figure Description

[0038] Figure 1 is a schematic diagram of a network architecture provided in one embodiment of this application;

[0039] Figure 2 is a schematic diagram of an AI-based CSI (Channel State Information) autoencoder framework provided in an embodiment of this application;

[0040] Figure 3 is a schematic diagram of an AI-based source-channel joint CSI feedback framework provided in an embodiment of this application;

[0041] Figure 4 is a flowchart of an information transmission method provided in an embodiment of this application;

[0042] Figure 5 is a block diagram of an information transmission device provided in an embodiment of this application;

[0043] Figure 6 is a block diagram of an information transmission device provided in another embodiment of this application;

[0044] Figure 7 is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0046] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. 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 in the embodiments of this application are also applicable to similar technical problems.

[0047] Please refer to Figure 1, which shows a schematic diagram of a network architecture 100 provided in one embodiment of this application. The network architecture 100 may include: a terminal device 10, an access network device 20, and a core network element 30.

[0048] Terminal device 10 can refer to UE (User Equipment), STA (Station), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, wireless communication device, user agent, or user equipment. In some embodiments, terminal device 10 can also be a cellular phone, cordless phone, SIP (Session Initiation Protocol) phone, WLL (Wireless Local Loop) station, PDA (Personal Digital Assistant), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, vehicle-mounted device, wearable device, terminal device in 5GS (5th Generation System), or terminal device in the future evolved PLMN (Public Land Mobile Network), etc., and this application embodiment is not limited to these. For ease of description, the devices mentioned above are collectively referred to as terminal devices. The number of terminal devices 10 is usually multiple, and one or more terminal devices 10 can be distributed within the cell managed by each access network device 20. Terminal equipment can also be simply referred to as terminal or UE, the meaning of which can be understood by those skilled in the art.

[0049] Access network device 20 is a device deployed in an access network to provide wireless communication functionality to terminal device 10. Access network device 20 may include various forms of macro base stations, micro base stations, relay stations, APs (Access Points), etc. In systems employing different wireless access technologies, the name of the device with access network device functionality may differ; for example, in a 5G NR (New Radio) system, it is called gNodeB or gNB (Next Generation Node B). As communication technologies evolve, the name "access network device" may change. For ease of description, in this embodiment, the aforementioned devices providing wireless communication functionality to terminal device 10 are collectively referred to as access network devices. In some embodiments, a communication relationship can be established between terminal device 10 and core network element 30 through access network device 20. For example, in an LTE (Long Term Evolution) system, access network device 20 can be one or more eNodeBs within an EUTRAN (Evolved Universal Terrestrial Radio Access Network); in a 5G NR system, access network device 20 can be one or more gNBs within a RAN (Radio Access Network). In the embodiments of this application, unless otherwise specified, "network device" refers to access network device 20, such as a base station.

[0050] Core network element 30 is a network element deployed in the core network. Its main functions are to provide user connectivity, manage users, and bear services, serving as an interface to external networks. For example, core network elements in a 5G NR system may include AMF (Access and Mobility Management Function) entities, UPF (User Plane Function) entities, and SMF (Session Management Function) entities.

[0051] In some embodiments, the access network device 20 and the core network element 30 communicate with each other via some air interface technology, such as the NG interface in a 5G NR system. The access network device 20 and the terminal device 10 communicate with each other via some air interface technology, such as the Uu interface.

[0052] The "5G NR system" in this application embodiment can also be referred to as a 5G system or an NR system, but those skilled in the art will understand its meaning. The technical solutions described in this application embodiment can be applied to LTE systems, 5G NR systems, and subsequent evolution systems of 5G NR systems (such as B5G (Beyound 5G) systems, 6G systems (6th Generation System), and other communication systems such as NB-IoT (Narrow Band Internet of Things) systems. This application does not limit these applications.

[0053] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) on the carrier used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0054] Before introducing the technical solution of this application, some related technical knowledge involved in this application will be introduced and explained. The following related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0055] 1. Traditional modulation and coding methods indicate

[0056] In NR systems, the modulation and coding schemes used for uplink and downlink data are indicated by a 5-bit MCS indication message in the DCI used for scheduling PDSCH (Physical Downlink Shared Channel) / PUSCH (Physical Uplink Shared Channel). Specifically, each state in the MCS indication message corresponds to a modulation scheme (QPSK (Quadrature Phase Shift Keying), 16QAM (Quadrature Amplitude Modulation), 64QAM, 256QAM, etc.) and a code rate (represented by the code rate * 1024). For example, when the maximum modulation order is 64QAM, the following table can be used to indicate the MCS used in the current transmission. MCS29-31 are used for retransmission indication, where 2 represents QPSK, 4 represents 16QAM, and 6 represents 64QAM. The constellation points corresponding to each modulation scheme are also pre-agreed upon by the terminal equipment and the network equipment. Different MCS indication tables are used when the maximum modulation order is different. Table 1 shows the modulation coding scheme indication table corresponding to 64QAM.

[0057] Table 1: Modulation and coding scheme indications for 64QAM

[0058] 2. AI-based source-channel joint coding

[0059] Given the tremendous success of AI technology, especially deep learning, in computer vision and natural language processing, the communications field has begun to explore using deep learning to solve technical challenges that are difficult to address with traditional communication methods. Deep learning's commonly used neural network architectures are non-linear and data-driven, capable of extracting features from actual channel matrix data and reconstructing the compressed channel matrix information from the UE (User Equipment) at the base station side as accurately as possible. This not only ensures the reconstruction of channel information but also provides the possibility of reducing CSI (Content Support Interface) feedback overhead at the UE side. Deep learning-based CSI feedback treats channel information as an image to be compressed, using a deep learning autoencoder to compress the input channel information and then reconstructing the compressed channel image at the transmitting end, thus preserving channel information to a greater extent.

[0060] The basic implementation framework of AI-based CSI feedback is described below. Employing an AI-based CSI autoencoder method, the entire feedback system is divided into encoder and decoder parts, deployed at the user transmitter and base station receiver, respectively. After obtaining channel information through channel estimation, the user uses it as input to the encoder. The encoder's neural network compresses and encodes the channel information matrix, and the compressed bitstream is fed back to the base station via the air interface feedback link. The base station uses the decoder to recover the channel information based on the feedback bitstream and outputs complete feedback channel information. The neural networks of the encoder and decoder shown in Figure 2 can employ structures such as DNN (Deep Neural Network) composed of multiple fully connected layers, CNN (Convolutional Neural Network) composed of multiple convolutional layers, or RNN (Recurrent Neural Network) with structures such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit). Various neural network architectures, such as residual and self-attention mechanisms, can also be used to improve the performance of the encoder and decoder.

[0061] The CSI input and output mentioned above can both be full-channel information or feature vector information obtained based on full-channel information. Therefore, current deep learning-based channel information feedback methods are mainly divided into full-channel information feedback and feature vector feedback. While the former can achieve compression and feedback of full-channel information, it has high feedback bitstream overhead and is not supported in existing NR systems. Feature vector-based feedback methods are the feedback architecture currently supported by NR systems. AI-based feature vector feedback methods can achieve higher CSI feedback accuracy with the same feedback bit overhead, or significantly reduce feedback overhead while achieving the same CSI feedback accuracy.

[0062] Besides the AI-based CSI feedback discussed in 5G standardization, there is another type of AI-based joint source-channel CSI feedback method, as shown in Figure 3. In this method, noise in the uplink feedback is considered in the CSI feedback process. The encoder deployed on the terminal side implicitly implements CSI compression (source coding) and uplink channel coding; the decoder on the network side implicitly implements channel decoding and CSI recovery functions. Furthermore, the encoder can simultaneously implement CSI compression, channel coding, and modulation, and the corresponding decoder can implement demodulation, CSI recovery, and channel decoding. In other words, the modulation and demodulation processes can be implemented using traditional methods or integrated into the joint source-channel coding process using AI.

[0063] This CSI feedback method based on Joint Source-Channel Coding (JSCC) can take into account the impact of noise and jointly implement source-channel coding. It combines the lossy source coding process of CSI compression with the redundancy-adding process of channel coding, which further optimizes the noise resistance performance of CSI encoder and CSI decoder under non-ideal channels with limited uplink feedback resources, and significantly improves CSI feedback performance in low signal-to-noise ratio environments.

[0064] In related technologies, the modulation scheme and channel coding rate used by the current data are indicated by the MCS indication message. However, if the modulation or channel coding process is based on AI, the corresponding modulation scheme or code rate cannot be indicated by traditional methods (the terminal and base station cannot obtain it directly). A new modulation and coding indication method is needed to support the MCS corresponding to AI-based modulation and / or channel coding.

[0065] Please refer to Figure 4, which shows a flowchart of an information transmission method provided in one embodiment of this application. The method is performed by a terminal device. The method includes at least one of the following steps 410 to 420.

[0066] Step 410: The terminal device receives an MCS indication message, which is used to determine the first MCS from the candidate MCSs.

[0067] Accordingly, the network device sends an MCS indication message.

[0068] In some embodiments, candidate MCSs include one or more of the following:

[0069] AI-based modulation and traditional channel coding code rate;

[0070] Modulation order and AI-based channel coding;

[0071] AI-based modulation and channel coding.

[0072] In some embodiments, AI-based modulation refers to modulation based on an AI model or employing Machine Learning (ML) methods, and can also be called ML-based modulation. For example, the signal to be modulated is used as input to an AI model to infer the modulated signal, without relying on pre-agreed constellation points between the communicating parties in traditional communication. In some embodiments, the traditional channel coding rate refers to the code rate corresponding to traditional channel coding methods such as LDPC, generally represented by a code rate R*1024. In some embodiments, AI-based modulation includes the equivalent modulation order corresponding to AI-based modulation.

[0073] In some embodiments, the constellation points corresponding to the modulation order are constellation points pre-agreed upon by the terminal device and the network device, i.e., using a traditional constellation-point-based modulation method (the constellation points can be regular or irregular). AI-based channel coding refers to channel coding based on an AI model or using an ML (Machine Learning) approach; it can also be called ML-based channel coding. For example, uncoded information is used as input to an AI model to infer coded information. In some embodiments, AI-based channel coding includes AI-based source-channel joint coding. For instance, the measured raw channel information is used as input to an AI model to infer CSI information after CSI compression and channel coding. In some embodiments, AI-based channel coding includes the equivalent code rate corresponding to AI-based channel coding.

[0074] In some embodiments, AI-based modulation and channel coding refers to modulation and channel coding based on an AI model or using an ML approach. For example, information that has not undergone channel coding and modulation is used as input to an AI model to infer the signal after channel coding and modulation. The AI-based modulation and AI-based channel coding can be performed using independent AI models, or both functions can be performed using the same AI model. In some embodiments, AI-based modulation and channel coding includes AI-based modulation and source-channel joint coding. For example, the terminal device uses the measured raw channel information as input to an AI model to infer CSI compressed, channel coded, and modulated CSI through the AI ​​model.

[0075] For example, the candidate MCS is predefined (e.g., defined in a protocol) or preconfigured, such as by network device configuration.

[0076] In some embodiments, the MCS indication message can be indicated by DCI or by RRC signaling. In some embodiments, when indicated by RRC (Radio Resource Control) signaling, the RRC signaling can be RRC signaling used for scheduling PDSCH.

[0077] In some embodiments, the MCS indication message can directly indicate the first MCS or indirectly indicate the first MCS. For example, the MCS indication message directly indicates the AI-based modulation and conventional channel coding code rate.

[0078] Step 420: The terminal device transmits the first information based on the first MCS.

[0079] Accordingly, the network device transmits the first information based on the first MCS.

[0080] In some embodiments, the first information can be data information or control information. For example, the first information can be data information transmitted by PDSCH or control information transmitted by PDCCH.

[0081] In some embodiments, the terminal device transmits first information, which may be either sending or receiving the first information. The first information may be uplink information, downlink information, or sidelink information.

[0082] For example, if the first information is uplink information, the terminal device modulates and channels the first information based on the first MCS, and the network device decodes and demodulates the first information based on the first MCS. For example, if the first information is downlink information, the network device modulates and channels the first information based on the first MCS, and the terminal device decodes and demodulates the first information based on the first MCS.

[0083] The technical solution provided in this application embodiment allows candidate MCSs to include traditional modulation and coding schemes or AI-based modulation and coding schemes. The first MCS is determined from the candidate MCSs through an MCS indication message, which enables flexible switching between traditional modulation and coding schemes and AI-based modulation and coding schemes. The better modulation and coding scheme is selected for data transmission, ensuring data transmission performance.

[0084] How to instruct the first MCS with an MCS instruction message.

[0085] I. MCS indication messages include a first state set and a second state set.

[0086] In some embodiments, the MCS indication message includes a first state set and a second state set, wherein the first state set is used to indicate the modulation order and the conventional channel coding code rate, and the second state set is used to indicate one or more of the following MCSs:

[0087] AI-based modulation and traditional channel coding code rate;

[0088] Modulation order and AI-based channel coding;

[0089] AI-based modulation and channel coding.

[0090] In some embodiments, the MCS indication message can indicate either traditional MCS or AI-based modulation and / or channel coding, thereby enabling dynamic switching between traditional modulation and coding and AI-based modulation and coding, thus improving transmission performance. In some embodiments, the technical solutions provided in this application are at least applicable to terminal devices that support dynamic model switching.

[0091] In some embodiments, the first state set is N states in the MCS indication message, such as the first N states in the MCS indication message. In some embodiments, the second state set is M states in the MCS indication message, such as the last M states in the MCS indication message. In some embodiments, the first state set and the second state set do not include the same states.

[0092] 1. The second state set is used to indicate the AI-based modulation and traditional channel coding code rates.

[0093] 1) The second state set is used to indicate the AI-based modulation, traditional channel coding code rate, and spectral efficiency.

[0094] In some embodiments, the second state set is used to indicate the AI-based modulation and conventional channel coding rates, and the corresponding spectral efficiency. For example, the MCS indicating the MCS corresponding to different states of the message can be shown in Table 2 below.

[0095] Table 2: Examples of different states of MCS indication messages

[0096] In some embodiments, the code rate (R0-44) and spectral efficiency (S0-44) shown in Table 2 are values ​​pre-agreed upon by the terminal device and the network device. In some embodiments, the MCS indication message can indicate the equivalent modulation scheme corresponding to the AI-based modulation scheme.

[0097] 2) The second state set is used to indicate the traditional channel coding code rate.

[0098] In some embodiments, the second state set may indicate only the conventional channel coding rate, without indicating the modulation scheme. In this case, the AI-based modulation scheme may be agreed upon by the terminal device and the network device, or indicated to the terminal device by the network device. For example, the MCS corresponding to different states of the MCS indication message may be shown in Table 3 below.

[0099] Table 3: Examples of different states of MCS indicator messages

[0100] The above method enables dynamic switching between traditional modulation methods based on agreed constellation points and AI-based modulation methods, thereby achieving higher transmission performance.

[0101] 2. The second state set is used to indicate the modulation order and AI-based channel coding.

[0102] 1) The second state set is used to indicate the modulation order, AI-based channel coding, and spectral efficiency.

[0103] In some embodiments, the second state set is used to indicate the modulation order (i.e., the modulation scheme based on traditional constellation points), the AI-based channel coding, and the spectral efficiency. In this case, the AI-based channel coding scheme (e.g., the AI ​​model used) may be agreed upon by the terminal device and the network device or indicated to the terminal device by the network device. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 4 below.

[0104] Table 4: Examples of different states of MCS indicator messages

[0105] In some embodiments, the code rate (R0-28) and spectral efficiency (S0-31) shown in Table 4 are values ​​pre-agreed upon by the terminal device and the network device.

[0106] In some embodiments, the MCS indication message, in addition to indicating the modulation order and spectral efficiency, can also indicate the equivalent code rate corresponding to AI-based channel coding. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 5 below.

[0107] Table 5: Examples of different states of MCS indicator messages

[0108] 2) The second state set is used to indicate the modulation method.

[0109] In some embodiments, the second state set may indicate only the modulation scheme based on conventionally agreed constellation points, without indicating the code rate. In this case, the AI-based channel coding scheme (e.g., the AI ​​model used) may be agreed upon by the terminal device and the network device, or indicated to the terminal device by the network device, such as AI-based source-channel joint coding. For example, the MCS indicating the different states of the message can be shown in Table 6 below.

[0110] Table 6: Examples of different states of MCS indicator messages

[0111] The above method enables dynamic switching between traditional channel coding methods (such as LDPC) and AI-based channel coding methods, thereby achieving higher transmission performance.

[0112] 3. The second state set is used to indicate AI-based modulation and channel coding.

[0113] 1) The second state set is used to indicate the AI-based modulation scheme, AI-based channel coding, and spectral efficiency.

[0114] In some embodiments, the second state set is used for AI-based modulation schemes, AI-based channel coding, and spectral efficiency. For example, the MCS indicating the different states of a message can be shown in Table 7 below.

[0115] Table 7: Examples of different states of MCS indicator messages

[0116] In some embodiments, the code rate (R0-28) and spectral efficiency (S0-44) shown in Table 7 are values ​​pre-agreed upon by the terminal device and the network device.

[0117] In some embodiments, if AI-based modulation and AI-based channel coding are performed using independent AI models, the MCS indication message can be used to indicate the equivalent modulation scheme corresponding to the AI-based modulation and the equivalent code rate corresponding to the AI-based channel coding. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 8 below.

[0118] Table 8: Examples of different states of MCS indicator messages

[0119] In some embodiments, the second state set may not indicate spectral efficiency. In this case, AI-based modulation and AI-based channel coding may be agreed upon by the terminal device and the network device, such as AI-based source-channel joint coding and modulation. For example, the MCS indicating the MCS corresponding to different states of the message can be shown in Table 9 below.

[0120] Table 9: Examples of different states of MCS indicator messages

[0121] The above method enables dynamic switching between traditional modulation and coding schemes and AI-based modulation and channel coding schemes, thereby achieving higher transmission performance.

[0122] 4. The second state set is used to indicate at least two of the candidate MCSs.

[0123] In some embodiments, the three methods described above can be used in combination.

[0124] 1) The second state information is used to indicate the code rate of AI-based modulation and traditional channel coding, and the AI-based modulation and channel coding.

[0125] In some embodiments, a portion of the states in the second state set may indicate the AI-based modulation and conventional channel coding rate (based on conventional channel coding), while another portion of the states may indicate the AI-based modulation and channel coding. For example, the MCS indicating the MCS corresponding to different states of the message can be shown in Table 10 below.

[0126] Table 10: Examples of different states of MCS indicator messages

[0127] 2) The second state set is used to indicate the modulation order and AI-based channel coding, AI-based modulation and channel coding.

[0128] In some embodiments, a portion of the states in the second state set may indicate the modulation order (based on traditional constellation points) and the AI-based channel coding scheme (e.g., JSCC), while another portion of the states may indicate the AI-based modulation and channel coding scheme (e.g., joint JSCC and modulation). For example, the MCS indicating the MCS corresponding to different states of the message can be shown in Table 11 below.

[0129] Table 11: Examples of different states of MCS indicator messages

[0130] 3) The second state set is used to indicate the code rate, modulation order, and AI-based channel coding of both AI-based modulation and traditional channel coding.

[0131] In some embodiments, a subset of states in the second state set may indicate the AI-based modulation and conventional channel coding rate, another subset of states may indicate the modulation order and AI-based channel coding, and the remaining states may indicate both AI-based modulation and channel coding. For example, the MCS indicating the MCS corresponding to different states of the message can be shown in Table 12 below.

[0132] Table 12: Examples of different states of MCS indicator messages

[0133] II. Instructing the first MCS via MCS instruction messages and instruction MCS tables.

[0134] In some embodiments, the terminal device receives first indication information, which is used to indicate the MCS form used to transmit the first information from the candidate MCS form.

[0135] In some embodiments, the candidate MCS table includes a first MCS table and a second MCS table. The MCS in the first MCS table includes the modulation order and the conventional channel coding code rate. The second MCS table includes one or more of the following MCS:

[0136] AI-based modulation and traditional channel coding code rate;

[0137] Modulation order and AI-based channel coding;

[0138] AI-based modulation and channel coding.

[0139] In some embodiments, the terminal device receives MCS table indication information, which is used to indicate the currently used MCS table from a first MCS table and a second MCS table. In some embodiments, the first MCS table is a conventional MCS table, wherein the MCS includes the modulation order (based on conventional constellation points) and the channel coding rate (based on conventional channel coding, such as LDPC), as shown in Table 1. The second MCS table is used to support AI-based modulation and / or channel coding.

[0140] 1. The second MCS table includes AI-based modulation schemes and traditional channel coding rates.

[0141] 1) The second MCS table is used to indicate the AI-based modulation, conventional channel coding code rate, and spectral efficiency.

[0142] In some embodiments, the MCS in the second MCS table includes AI-based modulation, traditional channel coding rate, and corresponding spectral efficiency. For example, the MCS indicating different states of the message can be shown in Table 13 below.

[0143] Table 13: Examples of different states of MCS indicator messages

[0144] In some embodiments, the code rate (R0-14) and spectral efficiency (S0-14) shown in Table 13 are values ​​agreed upon in advance by the terminal device and the network device.

[0145] In some embodiments, the MCS indication message can be used for the equivalent modulation scheme corresponding to the AI-based modulation scheme. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 14 below.

[0146] Table 14: Examples of different states of MCS indicator messages

[0147] 2) The second MCS table is used to indicate the conventional channel coding code rate.

[0148] In some embodiments, the second MCS table may only indicate the conventional channel coding rate and not the modulation scheme. In this case, the AI-based modulation scheme may be agreed upon by the terminal device and the network device, for example, using an AI model configured by the network device. For example, the MCS indicating the MCS corresponding to different states of the message may be shown in Table 15 below.

[0149] Table 15: Examples of different states of MCS indicator messages

[0150] The above method enables dynamic switching between traditional modulation methods based on agreed constellation points and AI-based modulation methods, thereby achieving higher transmission performance.

[0151] 2. The second MCS table is used to indicate the modulation order and AI-based channel coding.

[0152] 1) The second MCS table is used to indicate the modulation order, AI-based channel coding, and spectral efficiency.

[0153] In some embodiments, the second MCS table is used to indicate the modulation order, AI-based channel coding, and spectral efficiency. For example, the MCS indicating the MCS corresponding to different states of the message can be shown in Table 16 below.

[0154] Table 16: Examples of different states of MCS indicator messages

[0155] In some embodiments, the MCS indication message may also indicate the equivalent code rate corresponding to the AI-based channel coding. For example, the MCS corresponding to different states of the MCS indication message may be shown in Table 17 below.

[0156] Table 17: Examples of different states of MCS indicator messages

[0157] 2) The second MCS table is used to indicate the modulation method.

[0158] In some embodiments, the second MCS table may only indicate the modulation scheme based on conventionally agreed constellation points, without indicating the code rate. In this case, the AI-based channel coding may be agreed upon by the terminal device and the network device, such as AI-based source-channel joint coding. For example, the MCS indicating the MCS corresponding to different states of the message may be shown in Table 18 below.

[0159] Table 18: Examples of different states of MCS indicator messages

[0160] The above method can achieve quasi-static switching between traditional channel coding methods (such as LDPC) and AI-based channel coding methods, thereby achieving higher transmission performance.

[0161] 3. The second MCS table is used to indicate AI-based modulation and channel coding.

[0162] 1) The second MCS table is used to indicate the AI-based modulation scheme, the code rate of the AI-based channel coding, and the spectral efficiency.

[0163] In some embodiments, the second MCS table is used to indicate the AI-based modulation scheme, AI-based channel coding, and spectral efficiency. For example, the MCS indicating the MCS corresponding to different states of the message can be shown in Table 19 below.

[0164] Table 19: Examples of different states of MCS indicator messages

[0165] In some embodiments, if AI-based modulation and AI-based channel coding are performed using independent AI models, the MCS indication message can be used to indicate the equivalent modulation scheme corresponding to the AI-based modulation and the equivalent code rate corresponding to the AI-based channel coding. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 20 below.

[0166] Table 20: Examples of different states of MCS indicator messages

[0167] In some embodiments, the second MCS table may not indicate spectral efficiency. In this case, AI-based modulation and AI-based channel coding may be agreed upon by the terminal device and the network device, such as AI-based source-channel joint coding and modulation. For example, the MCS indicating the MCS corresponding to different states of the message may be shown in Table 21 below.

[0168] Table 21: Examples of different states of MCS indication messages

[0169] Using the above methods, a quasi-static switching between traditional modulation and coding schemes and AI-based modulation and coding schemes can be achieved, thereby obtaining higher transmission performance.

[0170] 4. The second MCS table is used to indicate at least two of the candidate MCSs.

[0171] In some embodiments, the three methods described above can be used in combination.

[0172] 1) The second MCS table is used to indicate the code rate of AI-based modulation and traditional channel coding, and the AI-based modulation and channel coding.

[0173] In some embodiments, some states in the second MCS table may indicate AI-based modulation and conventional channel coding rates (based on conventional channel coding), while other states may indicate AI-based modulation and channel coding. For example, the MCS indicating different states of a message may be shown in Table 22 below.

[0174] Table 22: Examples of different states of MCS indicator messages

[0175] 2) The second MCS table is used to indicate the modulation order and AI-based channel coding, AI-based modulation and channel coding.

[0176] In some embodiments, some states in the second MCS table may indicate the modulation order (based on traditional constellation points) and the AI-based channel coding scheme (e.g., JSCC), while other states may indicate the AI-based modulation and channel coding scheme (e.g., joint JSCC and modulation). For example, the MCS indicating the different states of a message may be shown in Table 23 below.

[0177] Table 23: Examples of different states of MCS indicator messages

[0178] 3) The second MCS table is used to indicate the code rate, modulation order, and AI-based channel coding for both modulation and conventional channel coding.

[0179] In some embodiments, some states in the second MCS table may indicate the AI-based modulation and conventional channel coding rate, while other states may indicate the modulation order and AI-based channel coding. Other states indicate AI-based modulation and channel coding. For example, the MCS corresponding to different states of the message may be shown in Table 24 below.

[0180] Table 24: Examples of different states of MCS indicator messages

[0181] The above embodiments provide two methods for indicating the first MCS through MCS indication messages, which can realize flexible switching between traditional modulation and coding methods and AI-based modulation and coding methods, select the current better modulation and coding method for data transmission, and ensure data transmission performance.

[0182] First information is transmitted based on the first MCS.

[0183] I. Downlink Transmission

[0184] In some embodiments, the terminal device receives first information based on a first MCS. In some embodiments, after receiving downlink information, the terminal device performs channel decoding and demodulation on the downlink information based on the first MCS to obtain the first information.

[0185] In some embodiments, when the first MCS is a conventional MCS (including modulation order and conventional channel coding rate), the terminal device modulates the information (based on agreed constellation points) and channels (such as LDPC) according to existing protocol methods to obtain the information source bits.

[0186] 1. The first MCS uses AI-based modulation and traditional channel coding code rate.

[0187] In some embodiments, when the MCS indication message indicates the AI-based modulation and conventional channel coding code rate, the terminal device obtains the channel-coded information based on a conventional channel coding method (such as LDPC), inputs the coded information into the AI ​​model, and then infers and transmits the modulated signal. The AI ​​model corresponds to the first AI model used during modulation. The terminal device can determine the first AI model used for demodulation based on either method 1 or method 2.

[0188] Method 1: Determining the first AI model for demodulation based on traditional channel coding rate.

[0189] In some embodiments, the network device performs channel coding on the information to be transmitted based on the traditional channel coding rate, and inputs the channel-coded information into a fourth AI model for modulation. The fourth AI model for modulation outputs first information, and the network device sends the first information to the terminal device. Here, the fourth AI model is the AI ​​model corresponding to the first AI model for demodulation. In some embodiments, the fourth AI model for modulation is determined based on the traditional channel coding rate. The method for determining the AI ​​model for modulation based on the traditional channel coding rate is the same as the method for determining the first AI model for demodulation described below; please refer to the introduction on how the terminal device determines the first AI model for demodulation.

[0190] In some embodiments, the terminal device determines the first AI model used for demodulation based on the conventional channel coding rate.

[0191] In some embodiments, the terminal device determines the number of output bits for channel coding based on the conventional channel coding code rate and the number of source bits of the first information; and determines a first AI model based on the number of output bits and the resources used to transmit the first information. In some embodiments, the number of output bits can be obtained based on the number of source bits and the conventional channel coding code rate. In some embodiments, the number of output bits is equal to the number of source bits divided by the conventional channel coding code rate.

[0192] In some embodiments, the terminal device determines the equivalent modulation order based on the number of output bits and the resources used to transmit the first information; and determines a first AI model from candidate AI models based on the equivalent modulation order. In some embodiments, the resources used to transmit the first information refer to the REs used to transmit the first information. In some embodiments, the equivalent modulation order is equal to the ratio of the number of output bits to the number of REs used to transmit the first information. In some embodiments, if the ratio is not an integer, a rounding operation can be performed. In some embodiments, the equivalent modulation order is equal to the number of source bits divided by the conventional channel coding rate, and then divided by the number of REs used to transmit the first information; if the result is not an integer, a rounding operation can be performed.

[0193] In some embodiments, a candidate AI model corresponds to an equivalent modulation order, or a range of equivalent modulation orders. The terminal device can determine the first AI model used for demodulation based on the equivalent modulation order. For example, modulation orders 2, 4, 6, and 8 can correspond to different candidate AI models, or modulation order ranges 1–3, 3–5, 5–7, and 7–9 can each correspond to different candidate AI models.

[0194] Method 2: Determine the first AI model to be used for demodulation based on pre-configuration information.

[0195] In some embodiments, the network device performs channel coding on the information to be transmitted based on the traditional channel coding code rate, and inputs the channel-coded information into a fourth AI model for modulation. The fourth AI model for modulation outputs first information, and the network device sends the first information to the terminal device. In some embodiments, the fourth AI model for modulation is pre-configured. The network device sends pre-configuration information to the terminal device, which indicates the identification information of the first AI model. The fourth AI model used for modulation by the network device and the first AI model used for demodulation by the terminal device correspond to or are associated with each other.

[0196] In some embodiments, the terminal device determines the first AI model to be used for demodulation based on pre-configuration information, wherein the pre-configuration information is used to indicate the identification information of the first AI model.

[0197] For example, pre-configured information is used to indicate the ID of the first AI model. For example, the terminal device determines the first AI model to be used for demodulation based on the pre-configured model ID, association ID, or dataset ID. The model ID, association ID, or dataset ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different AI models. The network device can configure an AI model corresponding to the AI ​​model used for modulation for demodulation on the terminal device side.

[0198] 2. The first MCS is the modulation order and AI-based channel coding.

[0199] In some embodiments, the terminal device demodulates the received signal based on a conventional demodulation method and inputs the information to be decoded into a second AI model to infer the decoded information. The second AI model corresponds to the AI ​​model used for channel coding. The terminal device can determine the AI ​​model used for channel decoding based on either method 1 or method 2.

[0200] Method 1: Determine the second AI model used for channel decoding based on the modulation order.

[0201] In some embodiments, the network device determines the fifth AI model used for channel coding based on the modulation order, inputs the information to be transmitted into the fifth AI model for channel coding, outputs the channel-coded information, and modulates the channel-coded information based on the modulation order to obtain first information. The network device then sends the first information to the terminal device. The fifth AI model corresponds to the first AI model used for channel decoding. The method for determining the fifth AI model for channel coding based on the modulation order is the same as the method for determining the fifth AI model for channel decoding described below; refer to the description of the second AI model used by the terminal device for channel decoding.

[0202] In some embodiments, the terminal device determines the second AI model used for channel decoding based on the modulation order. In some embodiments, the terminal device determines the number of output bits for channel coding based on the modulation order and the resources used to transmit the first information; and determines the second AI model based on the number of output bits. Exemplarily, the number of output bits is equal to the modulation order multiplied by the number of REs used to transmit the first information.

[0203] In some embodiments, the terminal device determines a second AI model from candidate AI models based on the number of output bits. In some embodiments, one candidate AI model corresponds to one range of output bits, and the terminal device can demodulate the second AI model used according to the range of output bits. For example, different ranges of output bits can correspond to different models.

[0204] In some embodiments, the terminal device determines the equivalent code rate based on the number of output bits and the number of source bits of the first information; and determines a second AI model from candidate AI models based on the equivalent code rate. Exemplarily, the equivalent code rate is equal to the number of source bits divided by the number of output bits. Exemplarily, the equivalent code rate is equal to the number of source bits divided by the modulation order, and then divided by the number of REs used to transmit the first information. In some embodiments, one candidate AI model corresponds to a range of equivalent code rates, and the terminal device can demodulate the second AI model used according to the range of equivalent code rates. Exemplarily, different ranges of equivalent code rates can correspond to different models.

[0205] Method 2: Determine the second AI model for channel decoding based on pre-configured information.

[0206] In some embodiments, the network device inputs the information to be transmitted into the fifth AI model used for channel coding, outputs the channel-coded information, and modulates the channel-coded information based on the modulation order to obtain first information. The network device then sends the first information to the terminal device. In some embodiments, the fifth AI model used for channel coding is pre-configured. The network device sends pre-configuration information to the terminal device, which indicates the identification information of the second AI model. The fifth AI model used by the network device for channel coding and the second AI model used by the terminal device for channel decoding are corresponding or related.

[0207] In some embodiments, the terminal device determines the second AI model used for channel decoding based on pre-configuration information, the pre-configuration information being used to indicate the identification information of the second AI model.

[0208] For example, pre-configured information is used to indicate the ID of the second AI model. For example, the terminal device determines the second AI model to be used for demodulation based on the pre-configured model ID, association ID, or dataset ID. The model ID, association ID, or dataset ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different AI models. The network device can configure an AI model corresponding to the AI ​​model used for modulation for demodulation on the terminal device side.

[0209] 3. The first MCS is based on AI-based modulation and channel coding.

[0210] In some embodiments, the terminal device inputs the signal to be decoded and demodulated into a third AI model to infer the decoded and demodulated information bits. The third AI model corresponds to the AI ​​model used for channel coding and modulation. The terminal device can determine the AI ​​model used for channel decoding and demodulation based on mode 1, mode 2, or mode 3.

[0211] Method 1: Determine the third AI model used for demodulation and channel decoding based on the source bit count of the first information and the resources used to transmit the first information.

[0212] In some embodiments, the network device inputs the information to be transmitted into the sixth AI model used for channel coding and modulation, outputs first information, and sends the first information to the terminal device. The sixth AI model is an AI model corresponding to the third AI model. In some embodiments, the sixth AI model used for channel coding and modulation is determined based on the source bit count of the first information and the resources used to transmit the first information, and is the same as the method for determining the third AI model used for channel decoding and demodulation described below; for details, please refer to the description on the terminal device side.

[0213] In some embodiments, the terminal device determines the equivalent spectral efficiency based on the number of source bits of the first information and the resources used to transmit the first information; and determines a third AI model from candidate AI models based on the equivalent spectral efficiency. The third AI model is used to demodulate and decode the first information. In some embodiments, the equivalent spectral efficiency is equal to the number of source bits divided by the resources used to transmit the first information. For example, the equivalent spectral efficiency is equal to the number of source bits divided by the number of REs used to transmit the first information.

[0214] In some embodiments, a candidate AI model corresponds to a range of equivalent spectral efficiencies, and the terminal device can demodulate the third AI model used based on the range of equivalent spectral efficiencies. For example, different ranges of equivalent spectral efficiencies can correspond to different models.

[0215] Method 2: Determine the third AI model used for demodulation and channel decoding based on the resources used to transmit the first information.

[0216] In some embodiments, the network device inputs the information to be transmitted into the sixth AI model used for channel coding and modulation, outputs first information, and sends the first information to the terminal device. In some embodiments, the sixth AI model used for channel coding and modulation is determined based on the resources used to transmit the first information, and is the same as the method for determining the third AI model used for channel decoding and demodulation described below, which can be specifically referred to in the description on the terminal device side.

[0217] In some embodiments, the terminal device determines a third AI model from candidate AI models based on resources used to transmit the first information. The third AI model is used to demodulate the first information and decode the source channel.

[0218] In some embodiments, if the first information is obtained by channel coding and modulation of channel state information, the terminal device can determine a third AI model based on the resources used to transmit the first information. The third AI model demodulates and decodes the source channel of the first information to obtain the channel state information. The channel state information can be CSI, such as a feature vector.

[0219] For example, the resource used to transmit the first information is a RE used to transmit the first information. In some embodiments, a candidate AI model corresponds to a range of RE numbers, and the terminal device can demodulate the third AI model used according to the range of RE numbers. For example, different ranges of RE numbers can correspond to different models.

[0220] Method 3: Determine the third AI model used for demodulation and channel decoding based on pre-configuration information.

[0221] In some embodiments, the network device inputs the information to be transmitted into the sixth AI model used for channel coding and modulation, outputs first information, and sends the first information to the terminal device. In some embodiments, the sixth AI model used for channel coding and modulation is pre-configured. The network device sends pre-configuration information to the terminal device, which is used to indicate the identification information of the third AI model. The sixth AI model used by the network device for channel coding and modulation and the third AI model used by the terminal device for demodulation and channel decoding correspond to or are associated with each other.

[0222] In some embodiments, the terminal device determines the third AI model used for demodulation and channel decoding based on pre-configuration information, the pre-configuration information being used to indicate the identification information of the third AI model.

[0223] For example, pre-configured information is used to indicate the ID of the third AI model. For example, the terminal device determines the third AI model to be used for demodulation based on the pre-configured model ID, association ID, or dataset ID. The model ID, association ID, or dataset ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different AI models. The network device can configure an AI model corresponding to the AI ​​model used for modulation for demodulation on the terminal device side.

[0224] II. Uplink Transmission

[0225] In some embodiments, the terminal device transmits first information based on a first MCS. In some embodiments, the terminal device modulates and channels the uplink information based on the first MCS to obtain the first information.

[0226] In some embodiments, when the first MCS is a conventional MCS (including modulation order and conventional channel coding rate), the terminal device modulates the information source bits (based on agreed constellation points) and channels (such as LDPC) according to existing protocol methods to obtain the first information.

[0227] 1. The first MCS uses AI-based modulation and traditional channel coding code rate.

[0228] In some embodiments, when the MCS indication message indicates the AI-based modulation and conventional channel coding code rate, the terminal device obtains the channel-coded information based on a conventional channel coding method (such as LDPC), inputs the coded information into the AI ​​model, and then infers and transmits the modulated signal. The AI ​​model corresponds to the first AI model used during modulation. The terminal device can determine the first AI model used during modulation based on either method 1 or method 2.

[0229] Method 1: Determining the first AI model for modulation based on traditional channel coding rate.

[0230] In some embodiments, the terminal device determines the first AI model used for modulation based on the conventional channel coding code rate.

[0231] In some embodiments, the terminal device determines the number of output bits for channel coding based on the conventional channel coding code rate and the number of source bits of the first information; and determines a first AI model based on the number of output bits and the resources used to transmit the first information. In some embodiments, the number of output bits can be obtained based on the number of source bits and the conventional channel coding code rate. In some embodiments, the number of output bits is equal to the number of source bits divided by the conventional channel coding code rate.

[0232] In some embodiments, the terminal device determines the equivalent modulation order based on the number of output bits and the resources used to transmit the first information; and determines a first AI model from candidate AI models based on the equivalent modulation order. In some embodiments, the resources used to transmit the first information refer to the REs used to transmit the first information. In some embodiments, the equivalent modulation order is equal to the ratio of the number of output bits to the number of REs used to transmit the first information. In some embodiments, if the ratio is not an integer, a rounding operation can be performed. In some embodiments, the equivalent modulation order is equal to the number of source bits divided by the conventional channel coding rate, and then divided by the number of REs used to transmit the first information; if the result is not an integer, a rounding operation can be performed.

[0233] In some embodiments, a candidate AI model corresponds to an equivalent modulation order, or a range of equivalent modulation orders. The terminal device can determine the first AI model used for modulation based on the equivalent modulation order. For example, modulation orders 2, 4, 6, and 8 can correspond to different candidate AI models, or modulation order ranges 1–3, 3–5, 5–7, and 7–9 can each correspond to different candidate AI models.

[0234] In some embodiments, the network device inputs first information into the fourth AI model used for demodulation, outputs the demodulated information, and performs channel decoding on the demodulated information based on the traditional channel coding rate. The network device then sends the first information to the terminal device. In some embodiments, the fourth AI model used for demodulation is determined based on the traditional channel coding rate. The method for determining the AI ​​model used for demodulation based on the traditional channel coding rate is the same as the method for determining the first AI model used for modulation described above. Refer to the description of the terminal device determining the first AI model used for modulation.

[0235] Method 2: Determine the first AI model to be used for modulation based on pre-configuration information.

[0236] In some embodiments, the terminal device determines the first AI model to be used for modulation based on pre-configuration information, the pre-configuration information being used to indicate the identification information of the first AI model.

[0237] For example, pre-configured information is used to indicate the ID of the first AI model. For example, the terminal device determines the first AI model to be used for modulation based on the pre-configured model ID, association ID, or dataset ID. The model ID, association ID, or dataset ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different AI models. The network device can configure the AI ​​model corresponding to the AI ​​model used for demodulation for modulation on the terminal device side.

[0238] In some embodiments, the network device inputs first information into the fourth AI model used for demodulation, outputs the demodulated information, and performs channel decoding on the demodulated information based on the traditional channel coding rate to obtain the first information. The network device then sends the first information to the terminal device. In some embodiments, the fourth AI model used for demodulation is pre-configured. The network device sends pre-configuration information to the terminal device, which indicates the identification information of the first AI model. The fourth AI model used by the network device for demodulation and the first AI model used by the terminal device for modulation are corresponding or associated.

[0239] 2. The first MCS is the modulation order and AI-based channel coding.

[0240] In some embodiments, the terminal device inputs the information to be encoded into a second AI model to infer the encoded information, and then modulates the encoded information based on a conventional modulation method. The second AI model corresponds to the AI ​​model used for channel decoding. The terminal device can determine the AI ​​model used for channel coding based on either method 1 or method 2.

[0241] Method 1: Determine the second AI model for channel coding based on modulation order.

[0242] In some embodiments, the terminal device determines a second AI model for channel coding based on the modulation order. In some embodiments, the terminal device determines the number of output bits for channel coding based on the modulation order and the resources used to transmit the first information; and determines the second AI model based on the number of output bits. Exemplarily, the number of output bits is equal to the modulation order multiplied by the number of REs used to transmit the first information.

[0243] In some embodiments, the terminal device determines a second AI model from candidate AI models based on the number of output bits. In some embodiments, one candidate AI model corresponds to a range of output bits, and the terminal device can determine the second AI model used for channel coding based on the range of output bits. Exemplarily, different ranges of output bits can correspond to different models.

[0244] In some embodiments, the terminal device determines the equivalent code rate based on the number of output bits and the number of source bits of the first information; and determines a second AI model from candidate AI models based on the equivalent code rate. Exemplarily, the equivalent code rate is equal to the number of source bits divided by the number of output bits. Exemplarily, the equivalent code rate is equal to the number of source bits divided by the modulation order, and then divided by the number of REs used to transmit the first information. In some embodiments, one candidate AI model corresponds to a range of equivalent code rates, and the terminal device can determine the second AI model used for channel coding based on the range of equivalent code rates. Exemplarily, different ranges of equivalent code rates can correspond to different models.

[0245] In some embodiments, the network device demodulates the first information based on the modulation order, inputs the demodulated information into the fifth AI model used for channel decoding, and outputs the channel-decoded information. In some embodiments, the fifth AI model used for channel decoding is determined based on the modulation order. The method for determining the fifth AI model used for channel decoding based on the modulation order is the same as the method for determining the second AI model used for channel coding described above; please refer to the introduction on how the terminal device determines the second AI model used for channel coding.

[0246] Method 2: Determine the second AI model for channel coding based on pre-configured information.

[0247] In some embodiments, the terminal device determines the second AI model used for channel coding based on pre-configuration information, the pre-configuration information being used to indicate the identification information of the second AI model.

[0248] For example, pre-configured information is used to indicate the ID of the second AI model. For example, the terminal device determines the second AI model used for channel coding based on the pre-configured model ID, association ID, or dataset ID. The model ID, association ID, or dataset ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different AI models. The network device can configure an AI model corresponding to the AI ​​model used for channel decoding for channel coding on the terminal device side.

[0249] In some embodiments, the network device demodulates the first information based on the modulation order, inputs the demodulated information into the fifth AI model used for channel decoding, and outputs the channel-decoded information. In some embodiments, the fifth AI model used for channel decoding is pre-configured. The network device sends pre-configuration information to the terminal device, which indicates the identification information of the second AI model. The fifth AI model used by the network device for demodulation and the first AI model used by the terminal device for modulation correspond to or are associated with each other.

[0250] 3. The first MCS is based on AI-based modulation and channel coding.

[0251] In some embodiments, the terminal device inputs the signal to be encoded and modulated into a third AI model to infer the channel-coded and modulated information bits. The third AI model corresponds to the AI ​​model used for channel coding and modulation. The terminal device can determine the AI ​​model used for channel coding and modulation based on mode 1, mode 2, or mode 3.

[0252] Method 1: Determine the third AI model used for modulation and channel coding based on the number of source bits of the first information and the resources used to transmit the first information.

[0253] In some embodiments, the terminal device determines the equivalent spectral efficiency based on the number of source bits of the first information and the resources used to transmit the first information; and determines a third AI model from candidate AI models based on the equivalent spectral efficiency. The third AI model is used to modulate and channel-code the first information. In some embodiments, the equivalent spectral efficiency is equal to the number of source bits divided by the resources used to transmit the first information. For example, the equivalent spectral efficiency is equal to the number of source bits divided by the number of REs used to transmit the first information.

[0254] In some embodiments, a candidate AI model corresponds to a range of equivalent spectral efficiencies, and the terminal device can determine the third AI model used for modulation and channel coding based on the range of equivalent spectral efficiencies. For example, different ranges of equivalent spectral efficiencies can correspond to different models.

[0255] In some embodiments, the network device inputs the first information into the sixth AI model used for demodulation and channel decoding, and outputs the channel-decoded information. In some embodiments, the sixth AI model used for demodulation and channel decoding is determined based on the source bit count of the first information and the resources used to transmit the first information, which is the same as the method used to determine the third AI model used for channel coding and modulation described above. For details, please refer to the description on the terminal device side.

[0256] Method 2: Determine the third AI model for modulation and channel coding based on the resources used to transmit the first information.

[0257] In some embodiments, the terminal device determines a third AI model from candidate AI models based on resources used to transmit the first information. The third AI model is used to compress, channel code, and modulate the first information.

[0258] In some embodiments, if the first information is obtained by channel coding and modulation of channel state information, the terminal device can determine a third AI model based on the resources used to transmit the first information. The third AI model compresses, channels-codes, and modulates the first information to obtain the channel state information. The channel state information can be CSI, such as a feature vector.

[0259] For example, the resource used to transmit the first information is a RE used to transmit the first information. In some embodiments, a candidate AI model corresponds to a range of RE numbers, and the terminal device can determine a third AI model for modulation and channel coding based on the range of RE numbers. For example, different ranges of RE numbers can correspond to different models.

[0260] In some embodiments, the network device inputs the first information into the sixth AI model used for demodulation and channel decoding, and outputs the channel-decoded information. In some embodiments, the sixth AI model used for demodulation and channel decoding is determined based on the resources used to transmit the first information, and is the same as the method used to determine the third AI model used for channel coding and modulation described above. For details, please refer to the description on the terminal device side.

[0261] Method 3: Determine the third AI model for modulation and channel coding based on pre-configured information.

[0262] In some embodiments, the terminal device determines the third AI model used for modulation and channel coding based on pre-configuration information, which is used to indicate the identification information of the third AI model.

[0263] For example, pre-configured information is used to indicate the ID of the third AI model. For example, the terminal device determines the third AI model used for modulation based on the pre-configured model ID, associated ID, or dataset ID. The model ID, associated ID, or dataset ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different AI models. The network device can configure the AI ​​model corresponding to the AI ​​model used for demodulation and channel decoding for modulation and channel coding on the terminal device side.

[0264] In some embodiments, the network device inputs first information into the sixth AI model used for demodulation and channel decoding, and outputs the channel-decoded information. In some embodiments, the sixth AI model used for demodulation and channel decoding is pre-configured. The network device sends pre-configuration information to the terminal device, which indicates the identification information of the third AI model. The sixth AI model used by the network device for demodulation and channel decoding corresponds to or is associated with the third AI model used by the terminal device for channel coding and modulation.

[0265] Using the above method, under different first MCS, the terminal device can determine the AI ​​model used for modulation, demodulation, channel coding, and channel decoding.

[0266] The overall scheme of this application embodiment will be illustrated by taking uplink transmission and downlink transmission as examples respectively.

[0267] I. Downlink Transmission

[0268] 1. The network device sends an MCS indication message to the terminal device. The MCS indication message is used to indicate the MCS to be used for the first information transmission from the candidate MCSs.

[0269] In some embodiments, the first information may be data (PDSCH) or control information (PDCCH).

[0270] Specifically, the MCS indication message can be indicated via DCI or via RRC signaling of the PDSCH scheduler.

[0271] 2. The network device sends information according to the indicated MCS.

[0272] Specifically, the network device determines the modulation scheme and channel coding scheme to be used according to the indicated MCS, and performs information modulation and channel coding based on the determined modulation scheme and channel coding scheme.

[0273] 3. The terminal device receives the MCS indication message from the network device.

[0274] Specifically, the MCS indication message can be indicated via DCI or via RRC signaling of the PDSCH scheduler.

[0275] 4. The terminal device determines the MCS to be used for information transmission from the candidate MCSs according to the MCS indication message;

[0276] In some embodiments, the candidate MCS includes one or more of the following: AI / ML-based modulation and conventional channel coding code rate; modulation order and AI / ML-based channel coding; AI / ML-based modulation and channel coding;

[0277] Among them, AI / ML-based modulation refers to modulation based on AI models, that is, using the modulated signal as the input of the AI ​​model to infer the modulated signal, without relying on the constellation points agreed upon in advance by the two parties in traditional communication; the traditional channel coding rate refers to the code rate corresponding to the traditional channel coding method such as LDPC, which is generally represented by the value of code rate R*1024.

[0278] In this context, the constellation points corresponding to the modulation order are pre-agreed constellation points between the terminal and the network, employing a traditional constellation-point-based modulation method (constellation points can be regular or irregular). AI / ML-based channel coding refers to channel coding based on AI models, where uncoded information is used as input to an AI model to infer coded information. AI / ML-based channel coding also includes AI / ML-based source-channel joint coding, such as using measured raw channel information as input to an AI model to infer CSI information after CSI compression and channel coding.

[0279] In this context, AI / ML-based modulation and channel coding refers to modulation and channel coding based on AI models. This involves using information that has not undergone channel coding and modulation as input to an AI model to infer the channel-coded and modulated signal. AI-model-based modulation and channel coding can be performed using independent AI models or by using the same AI model to perform both functions. AI / ML-based modulation and channel coding also include AI / ML-based source-channel joint coding and modulation. For example, the terminal device uses the measured raw channel information as input to an AI model, and then uses the AI ​​model to infer CSI information that has undergone CSI compression, channel coding, and modulation.

[0280] In some embodiments, the first set of states of the MCS indicates the modulation order (i.e., modulation based on agreed constellation points) and the channel coding rate (i.e., based on conventional channel coding such as LDPC), and the second set of states indicates one or more of the following MCSs: AI / ML-based modulation and conventional channel coding rate; modulation order and AI / ML-based channel coding; AI / ML-based modulation and channel coding.

[0281] In other words, the MCS indication message can indicate both traditional MCS and AI / ML-based modulation and / or channel coding, thereby enabling dynamic switching between traditional modulation and coding and AI / ML-based modulation and coding, thus improving transmission performance. This method is at least applicable to terminals that support dynamic model switching. For terminals that do not support dynamic model switching, the method in Example 2 can be used.

[0282] The first set of states can be the first N states of the MCS indication message, and the second set of states can be the last M states of the MCS indication message.

[0283] In one implementation, the second state set can indicate the AI / ML-based modulation scheme, different code rates based on traditional channel coding, and the corresponding spectral efficiency. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 2. Furthermore, the equivalent modulation scheme corresponding to the AI / ML-based modulation scheme can also be indicated by the MCS indication message.

[0284] In another implementation, the second state set may indicate only the code rate based on traditional channel coding, without indicating the modulation scheme, so that the terminal device and the network device can agree to adopt the AI / ML-based modulation scheme, as shown in Table 3.

[0285] In this way, dynamic switching can be achieved between traditional modulation methods based on agreed constellation points and modulation methods based on AI / ML, thereby obtaining higher transmission performance.

[0286] In one implementation, the second state set can indicate different conventional modulation orders, AI / ML-based channel coding, and corresponding spectral efficiencies. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 4. Furthermore, the equivalent code rate corresponding to the AI / ML-based channel coding method can also be indicated by the MCS indication message, as shown in Table 5.

[0287] In another implementation, the second state set may only indicate the modulation scheme based on the conventional constellation points, without indicating the code rate, so that the terminal device and the network device can agree to adopt an AI / ML-based channel coding scheme, such as AI-based source-channel joint coding, as shown in Table 6.

[0288] In this way, dynamic switching between traditional channel coding methods (such as LDPC) and AI / ML-based channel coding methods can be achieved, thereby obtaining higher transmission performance.

[0289] In one implementation, the second state set can indicate the AI / ML-based modulation scheme and channel coding scheme, as well as the corresponding spectral efficiency. For example, the MCS corresponding to different states of the MCS indication message can be shown in Table 7. Furthermore, when AI / ML-based modulation and AI / ML-based channel coding are performed through independent models, the corresponding equivalent modulation scheme and equivalent code rate can also be indicated by the MCS indication message, as shown in Table 8.

[0290] In another implementation, the second state set may not indicate spectral efficiency, so that the terminal device and the network device can agree on the use of AI / ML-based modulation and channel coding methods, such as AI-based source-channel joint coding and modulation, as shown in Table 9.

[0291] In this way, dynamic switching between traditional modulation and coding methods and AI / ML-based modulation and coding methods can be achieved, resulting in higher transmission performance.

[0292] In one implementation, the above methods can also be used in combination. For example, some states in the second state set can indicate AI / ML-based modulation and conventional channel coding rate (based on conventional channel coding), while other states indicate AI / ML-based modulation and channel coding, as shown in Table 10. Alternatively, some states in the second state set can indicate modulation order (based on conventional constellation points) and AI / ML-based channel coding (e.g., JSCC), while other states indicate AI / ML-based modulation and channel coding (e.g., combined JSCC and modulation), as shown in Table 11. Alternatively, some states in the second state set can indicate AI / ML-based modulation and conventional channel coding rate, while other states can indicate modulation order and AI / ML-based channel coding, and other states indicate AI / ML-based modulation and channel coding, as shown in Table 12.

[0293] 5. The terminal device receives information according to the determined MCS.

[0294] In some embodiments, when the MCS is a traditional MCS (including modulation order and channel coding rate), the terminal device demodulates the information and decodes the channel based on existing protocol methods to obtain the information source bits.

[0295] In some embodiments, when the MCS indication message indicates the AI / ML-based modulation and conventional channel coding rate, the terminal device inputs the signal to be demodulated into the AI ​​model to infer the demodulated information. The AI ​​model corresponds to the AI ​​model used during modulation. The terminal device performs channel decoding on the demodulated information using conventional methods (such as conventional LDPC decoding) to obtain the information source bits. The terminal device can determine the AI ​​model used for demodulation based on either method 1 or method 2.

[0296] Method 1: The terminal device determines the AI ​​model used for demodulation based on the code rate. Specifically, the terminal device determines the number of output bits for channel coding based on the code rate and the number of source bits, and determines the AI ​​model based on the number of output bits and the resources used for transmitting information.

[0297] Furthermore, the terminal device determines the equivalent modulation order based on the number of output bits and the resources used for transmitting information, and then determines the corresponding AI model from the candidate AI models based on the equivalent modulation order.

[0298] The number of output bits for channel coding can be obtained by dividing the number of information source bits by the code rate.

[0299] The equivalent modulation order is equal to the ratio of the number of output bits to the number of REs used for information transmission (optionally, further rounding can be performed). In other words, the equivalent modulation order is equal to the number of information source bits divided by the code rate and then divided by the number of REs used for information transmission (optionally, further rounding can be performed).

[0300] Each candidate AI model can correspond to an equivalent modulation order or a range of equivalent modulation orders, allowing the terminal device to determine the AI ​​model to use based on the equivalent modulation order. For example, modulation orders 2, 4, 6, and 8 can correspond to different models, or modulation order ranges 1–3, 3–5, 5–7, and 7–9 can each correspond to different models.

[0301] Method 2: The terminal device determines the AI ​​model used for demodulation based on a pre-configured model ID or associated ID. The model ID or associated ID is pre-configured by the network device to the terminal device, and different IDs can correspond to different models. The network device can configure an AI model corresponding to the AI ​​model used for modulation for demodulation on the terminal device side.

[0302] In some embodiments, when the MCS indication message indicates the modulation order and AI / ML-based channel coding, the terminal device demodulates the received signal using a conventional demodulation method and inputs the information to be decoded into the AI ​​model to infer the decoded information. The AI ​​model corresponds to the AI ​​model used for channel coding. The terminal device can determine the AI ​​model used for channel decoding based on either method 1 or method 2.

[0303] Method 1: The terminal device determines the AI ​​model used for channel decoding based on the modulation order. Specifically, the terminal device determines the number of output bits for channel coding based on the modulation order and the resources used for transmitting information, and then determines the AI ​​model based on the number of output bits.

[0304] Furthermore, the terminal device determines the AI ​​model corresponding to the number of output bits from the candidate AI models based on the number of output bits; or, the terminal device determines the equivalent code rate based on the number of output bits and the number of information source bits, and determines the AI ​​model corresponding to the equivalent code rate from the candidate AI models based on the equivalent code rate.

[0305] The number of output bits for channel coding can be obtained by multiplying the modulation order by the number of REs used to transmit information.

[0306] The equivalent code rate is equal to the number of source bits divided by the number of output bits. In other words, the equivalent code rate is equal to the number of source bits divided by the modulation order and the number of REs used to transmit information.

[0307] Each candidate AI model can correspond to a range of output bit counts or a range of equivalent bit rates, allowing the terminal device to determine the AI ​​model to use based on these ranges. For example, different ranges of output bit counts can correspond to different models, or different ranges of equivalent bit rates can correspond to different models.

[0308] Method 2: The terminal device determines the AI ​​model used for channel decoding based on a pre-configured model ID or association ID. The model ID or association ID is pre-configured by the network device for the terminal device, and different IDs can correspond to different models. The network device can configure an AI model corresponding to the AI ​​model used for channel coding at the transmitting end for channel decoding on the terminal device side.

[0309] In some embodiments, when the MCS indication message indicates AI / ML-based modulation and channel coding, the terminal device inputs the signal to be decoded and demodulated into the AI ​​model to infer the decoded and demodulated information bits. The AI ​​model corresponds to the AI ​​model used for channel coding and modulation. The terminal device can determine the AI ​​model used for channel decoding and demodulation based on method 1, method 2, or method 3.

[0310] Method 1: When the input to the corresponding AI model is information source bits (data), the terminal device determines the equivalent spectral efficiency based on the number of information source bits and the resources used to transmit information; the corresponding AI model is determined from the candidate AI models based on the equivalent spectral efficiency; and the information is demodulated and the channel is decoded based on the AI ​​model.

[0311] The equivalent spectral efficiency can be obtained by dividing the number of information source bits by the number of REs used to transmit information.

[0312] Each candidate AI model can correspond to a range of equivalent spectral efficiencies, allowing the terminal device to determine the AI ​​model to use based on these spectral efficiencies. For example, different ranges of equivalent spectral efficiencies can correspond to different models.

[0313] Method 2: When the input to the corresponding AI model is channel state information, the terminal device determines the corresponding AI model from the candidate AI models based on the resources used for transmitting information; based on the AI ​​model, the information is demodulated and the source channel is decoded to obtain channel state information (such as feature vector).

[0314] Each candidate AI model can correspond to a range of REs, so that the terminal device can determine the AI ​​model to use based on the number of REs used to transmit information.

[0315] Method 3: The terminal device determines the AI ​​model used for channel decoding and demodulation based on a pre-configured model ID or associated ID. The model ID or associated ID is pre-configured by the network device to the terminal device, and different IDs can correspond to different models. The network device can configure an AI model corresponding to the AI ​​model used for channel coding and modulation at the transmitting end for channel decoding and demodulation on the terminal device side.

[0316] II. Uplink Transmission

[0317] 1. The network device indicates an MCS indication message to the terminal device, the MCS indication message being used to indicate the MCS to be used for the first information transmission from among the candidate MCSs.

[0318] For a description of the candidate MCS, please refer to the subsequent terminal-side description.

[0319] The first piece of information can be data or control information, such as CSI information.

[0320] Specifically, the MCS indication message can be indicated by DCI or by RRC signaling of the PUSCH scheduling.

[0321] 2. The terminal device receives the MCS indication message from the network device.

[0322] Specifically, the MCS indication message can be indicated by DCI or by RRC signaling of the PDSCH scheduling.

[0323] 3. The terminal device determines the MCS to be used for information transmission from the candidate MCSs according to the MCS indication message;

[0324] In some embodiments, the candidate MCS includes one or more of the following: AI / ML-based modulation and conventional channel coding code rate; modulation order and AI / ML-based channel coding; AI / ML-based modulation and channel coding;

[0325] In some embodiments, the terminal device receives indication information from the network device, the indication information being used to indicate the currently used MCS table from a candidate MCS table, wherein the candidate MCS table includes a first MCS table and a second MCS table, the MCS in the first MCS table includes modulation order and channel coding code rate, and the second MCS table includes one or more of the following MCS: AI / ML-based modulation and conventional channel coding code rate; modulation order and AI / ML-based channel coding; AI / ML-based modulation and channel coding.

[0326] The indication information can be carried through higher-layer signaling (RRC or MAC CE). That is, based on the pre-configured MCS table indication information, the MCS indication message can indicate either a traditional MCS or AI / ML-based modulation and / or channel coding, thereby achieving a quasi-static handover between traditional modulation and coding and AI / ML-based modulation and coding. This method is at least applicable to terminal devices that do not support dynamic model switching. For terminals that support dynamic model switching, the method in Embodiment 1 can be considered. In other words, depending on the model switching capability of the terminal device, the network device can consider indicating the MCS using the method in Embodiment 1, or it can indicate the MCS using the method in this embodiment.

[0327] The first MCS table is a traditional MCS table, where the MCS includes the modulation order (based on traditional constellation points) and the channel coding rate (based on traditional channel coding, such as LDPC), as shown in Table 1. The second MCS table is used to support AI / ML-based modulation and / or channel coding.

[0328] In one implementation, the MCS in the second MCS table includes AI / ML-based modulation schemes, different code rates based on traditional channel coding, and corresponding spectral efficiencies. For example, the MCS indicating different states of the message can be shown in Table 13.

[0329] Furthermore, the equivalent modulation scheme corresponding to the AI / ML-based modulation scheme can also be indicated by the MCS indication message, as shown in Table 14.

[0330] In another implementation, the MCS in the second MCS table may only contain the code rate based on traditional channel coding, without indicating the modulation scheme, so that the terminal device and the network device can agree to adopt the modulation scheme based on AI / ML, as shown in Table 15.

[0331] In this way, a quasi-static switching can be achieved between traditional modulation methods based on agreed constellation points and modulation methods based on AI / ML, thereby obtaining higher transmission performance.

[0332] In one implementation, the MCS in the second MCS table may include different traditional modulation orders, AI / ML-based channel coding, and corresponding spectral efficiencies. For example, the MCS indicating different states of the message may be as shown in Table 16.

[0333] Furthermore, the equivalent code rate corresponding to the AI / ML-based channel coding method can also be indicated by the MCS indication message, as shown in Table 17.

[0334] In another implementation, the MCS in the second MCS table may only include the modulation scheme based on the conventional constellation points, without indicating the code rate. This allows the terminal device and the network device to agree on the use of an AI / ML-based channel coding scheme, such as AI-based source-channel joint coding. For example, as shown in Table 18.

[0335] In this way, a quasi-static switch can be achieved between traditional channel coding methods and AI / ML-based channel coding methods, thereby obtaining higher transmission performance.

[0336] In one implementation, the MCS in the second MCS table may include AI / ML-based modulation schemes and channel coding schemes, as well as the corresponding spectral efficiency. For example, the MCS indicating different states of the message may be shown in Table 19 below.

[0337] Furthermore, when the AI / ML-based modulation and AI / ML-based channel coding are performed using independent models, the corresponding equivalent modulation scheme and equivalent code rate can also be indicated by the MCS indication message, as shown in Table 20.

[0338] In another implementation, the MCS in the second MCS table may not include spectral efficiency, allowing the terminal device and network device to agree on the use of AI / ML-based modulation and channel coding methods, such as AI-based source-channel joint coding and modulation. For example, as shown in Table 21.

[0339] In this way, a quasi-static switching between traditional modulation and coding methods and AI / ML-based modulation and coding methods can be achieved, thereby obtaining higher transmission performance.

[0340] In one implementation, the above methods can also be used in combination. For example, some MCSs in the second MCS table may include AI / ML-based modulation schemes and conventional channel coding rates (based on conventional channel coding), while other MCSs may include AI / ML-based modulation and channel coding schemes, as shown in Table 22. Alternatively, some MCSs in the second MCS table may include modulation order (based on conventional constellation points) and AI / ML-based channel coding schemes (e.g., JSCC), while other MCSs may include AI / ML-based modulation and channel coding schemes (e.g., combined JSCC and modulation), as shown in Table 23. Alternatively, some MCSs in the second MCS table may include AI / ML-based modulation schemes and conventional channel coding rates, while other MCSs may include modulation order and AI / ML-based channel coding schemes, and the remaining MCSs may include AI / ML-based modulation and channel coding schemes, as shown in Table 24.

[0341] 4. The terminal device sends information according to the determined MCS.

[0342] In some embodiments, when the MCS is a traditional MCS (including modulation order and channel coding rate), the terminal device modulates the information (based on agreed constellation points) and channels (such as LDPC) according to existing protocol methods to obtain the information source bits.

[0343] In some embodiments, when the MCS indication message indicates the modulation and conventional channel coding rate based on AI / ML, the terminal device obtains the channel-coded information based on a conventional channel coding method (such as LDPC), inputs the coded information into the AI ​​model, and then infers and transmits the modulated signal. The AI ​​model corresponds to the AI ​​model used during modulation. The terminal device can determine the AI ​​model used during modulation based on either method 1 or method 2.

[0344] Method 1: The terminal device determines the AI ​​model used for modulation based on the code rate. Specifically, the terminal device determines the number of output bits for channel coding based on the code rate and the number of information source bits, and determines the AI ​​model based on the number of output bits and the resources used to transmit the information. Further, the terminal device determines the equivalent modulation order based on the number of output bits and the resources used to transmit the information, and determines the corresponding AI model from the candidate AI models based on the equivalent modulation order.

[0345] Method 2: The terminal device determines the AI ​​model used for modulation based on a pre-configured model ID or associated ID. The model ID or associated ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different models. The network device can configure an AI model corresponding to the AI ​​model used for demodulation for the modulation process on the terminal device side.

[0346] In some embodiments, when the MCS indication message indicates the modulation order and AI / ML-based channel coding, the terminal device inputs the information to be coded into the AI ​​model to infer the channel-coded information, then modulates the information using agreed-upon constellation points and transmits it. The AI ​​model corresponds to the AI ​​model used for channel decoding. The terminal device can determine the AI ​​model used for channel coding based on either method 1 or method 2.

[0347] Method 1: The terminal device determines the AI ​​model used for channel coding based on the modulation order. Specifically, the terminal device determines the number of output bits for channel coding based on the modulation order and the resources used to transmit the information, and determines the AI ​​model based on the number of output bits. Further, the terminal device determines the AI ​​model corresponding to the number of output bits from candidate AI models based on the number of output bits; or, the terminal device determines the equivalent code rate based on the number of output bits and the number of information source bits, and determines the AI ​​model corresponding to the equivalent code rate from candidate AI models based on the equivalent code rate. Refer to the description in Embodiment 1 for specific methods.

[0348] Method 2: The terminal device determines the AI ​​model used for channel coding based on a pre-configured model ID or association ID. The model ID or association ID is pre-configured to the terminal device by the network device, and different IDs can correspond to different models. The network device can configure an AI model corresponding to the AI ​​model used for channel decoding at the receiving end for channel coding on the terminal device side.

[0349] In some embodiments, when the MCS indication message indicates AI / ML-based modulation and channel coding, the terminal device inputs the information to be encoded and modulated into the AI ​​model to infer and transmit the channel-coded and modulated signal. The AI ​​model corresponds to the AI ​​model used for channel decoding and demodulation. The terminal device can determine the AI ​​model used for channel coding and modulation based on method 1, method 2, or method 3.

[0350] Method 1: When the input to the corresponding AI model is information source bits (data), the terminal device determines the equivalent spectral efficiency based on the number of information source bits and the resources used to transmit the information; it then determines the corresponding AI model from the candidate AI models based on the equivalent spectral efficiency; and finally, it performs channel coding and modulation of the information based on the AI ​​model. See the description in Example 1 for details.

[0351] Method 2: When the input to the corresponding AI model is channel state information, the terminal device determines the corresponding AI model from the candidate AI models based on the resources used to transmit the information; channel coding and modulation of the information are then performed based on the AI ​​model. Each candidate AI model can correspond to a range of REs (Resources Required for Transmission), allowing the terminal device to determine the AI ​​model to use based on the number of REs available for transmitting the information.

[0352] Method 3: The terminal device determines the AI ​​model used for channel decoding and demodulation based on a pre-configured model ID or associated ID. The model ID or associated ID is pre-configured by the network device to the terminal device, and different IDs can correspond to different models. The network device can configure an AI model corresponding to the AI ​​model used for channel decoding and demodulation at the receiving end for channel coding and modulation on the terminal device side.

[0353] 5. The network device receives information according to the indicated MCS.

[0354] Specifically, the network device determines the modulation scheme and channel coding scheme to be used according to the indicated MCS, and performs modulation and channel coding of the information based on the determined modulation scheme and channel coding scheme.

[0355] It should be noted that, in the above method embodiments, the steps performed by the terminal device can be implemented separately as an information transmission method on the terminal device side; the steps performed by the network device can be implemented separately as an information transmission method on the network device side.

[0356] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0357] Please refer to Figure 5, which shows a block diagram of an information transmission apparatus provided in one embodiment of this application. This apparatus has the function of implementing the above-described information transmission method example; the function can be implemented in hardware or by hardware executing corresponding software. This apparatus can be the terminal device described above, or it can be installed within a terminal device. As shown in Figure 5, the apparatus 500 may include a receiving module 510 and a transmitting module 520.

[0358] The receiving module 510 is used to receive a modulation and coding strategy (MCS) indication message, which is used to determine a first MCS from candidate MCSs.

[0359] Transmission module 520 is used to transmit first information based on the first MCS;

[0360] The candidate MCS includes one or more of the following:

[0361] Modulation and traditional channel coding rate based on artificial intelligence (AI);

[0362] Modulation order and AI-based channel coding;

[0363] AI-based modulation and channel coding.

[0364] In some embodiments, the first MCS is the AI-based modulation and conventional channel coding code rate, and the device 500 further includes a processing module (not shown in the figure).

[0365] The processing module is used to determine the first AI model used for modulation or demodulation based on the traditional channel coding code rate; or...

[0366] The processing module is used to determine the first AI model to be used for modulation or demodulation based on pre-configuration information, wherein the pre-configuration information is used to indicate the identification information of the first AI model.

[0367] In some embodiments, the processing module is configured to determine the number of output bits of the channel coding based on the conventional channel coding code rate and the number of source bits of the first information; and to determine the first AI model based on the number of output bits and the resources used to transmit the first information.

[0368] In some embodiments, the processing module is configured to determine an equivalent modulation order based on the number of output bits and the resources used to transmit the first information; and to determine the first AI model from candidate AI models based on the equivalent modulation order.

[0369] In some embodiments, the first MCS is the modulation order and AI-based channel coding, and the processing module is configured to determine a second AI model for channel coding or channel decoding based on the modulation order; or, the processing module is configured to determine a second AI model for channel coding or channel decoding based on pre-configuration information, wherein the pre-configuration information is used to indicate the identification information of the second AI model.

[0370] In some embodiments, the processing module is configured to determine the number of output bits for channel coding based on the modulation order and the resources for transmitting the first information; and to determine the second AI model based on the number of output bits.

[0371] In some embodiments, the processing module is configured to determine the second AI model from candidate AI models based on the number of output bits; or, to determine the equivalent code rate based on the number of output bits and the number of source bits of the first information; and to determine the second AI model from candidate AI models based on the equivalent code rate.

[0372] In some embodiments, the first MCS is the AI-based modulation and channel coding, and the input of the third AI model is the source bits of the first information. The processing module is configured to determine the equivalent spectral efficiency based on the number of source bits of the first information and the resources used to transmit the first information; and to determine the third AI model from the candidate AI models based on the equivalent spectral efficiency. The third AI model is used to perform channel coding and modulation on the source bits, or the third AI model is used to demodulate and channel decode the first information.

[0373] In some embodiments, the first MCS is the AI-based modulation and channel coding, and the input of the third AI model is channel state information. The processing module is used to determine the third AI model from candidate AI models based on the resources used to transmit the first information. The third AI model is used to compress, channel code, and modulate the channel state information, or the third AI model is used to demodulate and decode the first information.

[0374] In some embodiments, the first MCS is the AI-based modulation and channel coding, and the processing module is configured to determine the third AI model used for channel coding and modulation based on pre-configuration information, or to determine the third AI model used for demodulation and channel decoding, wherein the pre-configuration information is used to indicate the identification information of the third AI model.

[0375] In some embodiments, the MCS indication message includes a first state set and a second state set, wherein the first state set is used to indicate the modulation order and the traditional channel coding code rate, and the second state set is used to indicate one or more of the following MCSs:

[0376] The AI-based modulation and traditional channel coding code rates;

[0377] The modulation order and AI-based channel coding;

[0378] The AI-based modulation and channel coding.

[0379] In some embodiments, the receiving module 510 is configured to receive first indication information, the first indication information being used to indicate, from the candidate MCS table, the MCS table used for transmitting the first information; wherein the candidate MCS table includes a first MCS table and a second MCS table, the MCS in the first MCS table includes a modulation order and a conventional channel coding rate, and the second MCS table includes one or more of the following MCS:

[0380] The AI-based modulation and traditional channel coding code rates;

[0381] The modulation order and AI-based channel coding;

[0382] The AI-based modulation and channel coding.

[0383] In some embodiments, the AI-based channel coding includes AI-based source-channel joint coding.

[0384] In some embodiments, the AI-based modulation and channel coding includes AI-based modulation and source-channel joint coding.

[0385] In some embodiments, the AI-based modulation includes the equivalent modulation order corresponding to the AI-based modulation.

[0386] In some embodiments, the AI-based channel coding includes the equivalent code rate corresponding to the AI-based channel coding.

[0387] The technical solution provided in this application embodiment allows candidate MCSs to include traditional modulation and coding schemes or AI-based modulation and coding schemes. The first MCS is determined from the candidate MCSs through an MCS indication message, which enables flexible switching between traditional modulation and coding schemes and AI-based modulation and coding schemes. The better modulation and coding scheme is selected for data transmission, ensuring data transmission performance.

[0388] Please refer to Figure 6, which shows a block diagram of an information transmission apparatus according to an embodiment of this application. This apparatus has the function of implementing the above-described information transmission method example; the function can be implemented by hardware or by hardware executing corresponding software. This apparatus can be a network device as described above, or it can be installed within a network device. As shown in Figure 5, the apparatus 600 may include a sending module 610 and a transmission module 620.

[0389] The transmitting module 610 is used to transmit a modulation and coding strategy (MCS) indication message, which is used to determine a first MCS from candidate MCSs.

[0390] Transmission module 620 is used to transmit first information based on the first MCS;

[0391] The candidate MCS includes one or more of the following:

[0392] Modulation and traditional channel coding rate based on artificial intelligence (AI);

[0393] Modulation order and AI-based channel coding;

[0394] AI-based modulation and channel coding.

[0395] In some embodiments, when the first MCS is the AI-based modulation and conventional channel coding code rate, the first AI model used for modulation or demodulation is determined based on the conventional channel coding code rate; or, the first AI model used for modulation or demodulation is indicated to the terminal device through pre-configuration information, wherein the pre-configuration information is used to indicate the identification information of the first AI model.

[0396] In some embodiments, the first AI model is determined based on the number of output bits of channel coding and the resources used to transmit the first information, wherein the number of output bits is determined based on the conventional channel coding code rate and the number of source bits of the first information.

[0397] In some embodiments, the first AI model is determined from candidate AI models based on an equivalent modulation order; the equivalent modulation order is determined based on the number of output bits and the resources used to transmit the first information.

[0398] In some embodiments, the first MCS is a modulation order and an AI-based channel coding, and the second AI model used for channel coding or channel decoding is determined based on the modulation order; or, the second AI model used for channel coding or channel decoding is indicated to the terminal device through pre-configuration information, which is used to indicate the identification information of the second AI model.

[0399] In some embodiments, the second AI model is determined based on the number of output bits of channel coding, which is determined based on the modulation order and the resources used to transmit the first information.

[0400] In some embodiments, the second AI model is determined from candidate AI models based on the number of output bits; or, the second AI model is determined from candidate AI models based on an equivalent code rate, which is determined based on the number of output bits and the number of source bits of the first information.

[0401] In some embodiments, the first MCS is the AI-based modulation and channel coding, and the input of the third AI model is the source bits of the first information. The third AI model is determined from candidate AI models based on the equivalent spectral efficiency, which is determined based on the number of source bits of the first information and the resources used to transmit the first information. The third AI model is used to perform channel coding and modulation on the source bits, or the third AI model is used to demodulate and channel decode the first information.

[0402] In some embodiments, the first MCS is the AI-based modulation and channel coding, and the input of the third AI model is channel state information. The third AI model is determined from candidate AI models based on the resources used to transmit the first information. The third AI model is used to compress, channel code, and modulate the channel state information, or the third AI model is used to demodulate and decode the first information.

[0403] In some embodiments, the first MCS is the AI-based modulation and channel coding, the third AI model used in the channel coding and modulation, or the determination of the third AI model used in demodulation and channel decoding is indicated to the terminal device through pre-configuration information, the pre-configuration information being used to indicate the identification information of the third AI model.

[0404] In some embodiments, the MCS indication message includes a first state set and a second state set, wherein the first state set is used to indicate the modulation order and the traditional channel coding code rate, and the second state set is used to indicate one or more of the following MCSs:

[0405] The modulation and traditional channel coding code rates based on artificial intelligence (AI);

[0406] The modulation order and AI-based channel coding;

[0407] The AI-based modulation and channel coding.

[0408] In some embodiments, the transmitting module 610 is configured to transmit first indication information, the first indication information being used to indicate from the candidate MCS table the MCS table used for transmitting the first information; wherein the candidate MCS table includes a first MCS table and a second MCS table, the MCS in the first MCS table includes modulation order and conventional channel coding code rate, and the second MCS table includes one or more of the following MCS:

[0409] The modulation and traditional channel coding code rates based on artificial intelligence (AI);

[0410] The modulation order and AI-based channel coding;

[0411] The AI-based modulation and channel coding.

[0412] In some embodiments, the AI-based channel coding includes AI-based source-channel joint coding.

[0413] In some embodiments, the AI-based modulation and channel coding includes AI-based modulation and source-channel joint coding.

[0414] In some embodiments, the AI-based modulation includes the equivalent modulation order corresponding to the AI-based modulation.

[0415] In some embodiments, the AI-based channel coding includes the equivalent code rate corresponding to the AI-based channel coding.

[0416] The technical solution provided in this application embodiment allows candidate MCSs to include traditional modulation and coding schemes or AI-based modulation and coding schemes. The first MCS is determined from the candidate MCSs through an MCS indication message, which enables flexible switching between traditional modulation and coding schemes and AI-based modulation and coding schemes. The better modulation and coding scheme is selected for data transmission, ensuring data transmission performance.

[0417] It should be noted that the device provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules according to actual needs, that is, the content structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0418] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0419] Please refer to Figure 7, which shows a schematic diagram of the structure of a communication device provided in one embodiment of this application. The communication device can be a terminal device or a network device as described above. The communication device 700 may include: a processor 701, a transceiver 702, and a memory 703. The transceiver 702 is used to implement sending or receiving functions, such as implementing the functions of the receiving module 810 described above. The processor 701 can be used to implement other processing functions or control sending and / or receiving, such as implementing the functions of the processing module 710 described above.

[0420] The processor 701 includes one or more processing cores. The processor 701 executes various functional applications and information processing by running software programs and modules.

[0421] The transceiver 702 may include a receiver and a transmitter. For example, the receiver and transmitter may be implemented as the same wireless communication component, which may include a wireless communication chip and a radio frequency antenna.

[0422] The memory 703 can be connected to the processor 701 and the transceiver 702.

[0423] The memory 703 can be used to store a computer program executed by the processor, and the processor 701 is used to execute the computer program to implement the various steps in the above method embodiments.

[0424] In some embodiments, when the communication device 700 is a terminal device, the transceiver 702 is used to receive an MCS indication message, the MCS indication message being used to determine a first MCS from candidate MCSs; and to transmit first information based on the first MCS; wherein the candidate MCSs include one or more of the following:

[0425] AI-based modulation and traditional channel coding code rate;

[0426] Modulation order and AI-based channel coding;

[0427] AI-based modulation and channel coding.

[0428] In some embodiments, when the communication device 700 is a network device, the transceiver 702 is used to send an MCS indication message, the MCS indication message being used to determine a first MCS from candidate MCSs; and to transmit first information based on the first MCS; wherein the candidate MCSs include one or more of the following:

[0429] AI-based modulation and traditional channel coding code rate;

[0430] Modulation order and AI-based channel coding;

[0431] AI-based modulation and channel coding.

[0432] For details not described in this embodiment, please refer to the embodiments above, which will not be repeated here.

[0433] Furthermore, the memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, including but not limited to: magnetic disks or optical disks, electrically erasable programmable read-only memory, erasable programmable read-only memory, statically accessible memory, read-only memory, magnetic memory, flash memory, and programmable read-only memory.

[0434] This application embodiment also provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the aforementioned information transmission method on the terminal device side or the aforementioned information transmission method on the network device side. Optionally, the computer-readable storage medium may include: ROM (Read-Only Memory), RAM (Random-Access Memory), SSD (Solid State Drives), or optical disc, etc. The random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0435] This application also provides a chip, which includes programmable logic circuits and / or program instructions. When the chip is running, it is used to implement the above-mentioned information transmission method on the terminal device side or the above-mentioned information transmission method on the network device side.

[0436] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor reads and executes the computer program from the computer-readable storage medium to implement the above-described information transmission method on the terminal device side or the above-described information transmission method on the network device side.

[0437] It should be understood that the term "instruction" mentioned in the embodiments of this application can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0438] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0439] In some embodiments of this application, "predefined" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and APs). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0440] In some embodiments of this application, the term "protocol" may refer to standard protocols in the field of communications, such as LTE protocols, NR protocols, and related protocols applied in future communication systems. This application does not limit the scope of these protocols.

[0441] In this article, "multiple" refers to two or more. "And / or" describes 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, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0442] In this article, "greater than or equal to" can mean greater than or equal to, and "less than or equal to" can mean less than or equal to.

[0443] Furthermore, the step numbers described herein are merely illustrative of one possible execution order between steps. In some other embodiments, the steps may not be executed in the order of their numbers, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0444] Those skilled in the art will recognize that the functions described in the embodiments of this application in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of a computer program from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0445] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An information transmission method, characterized in that, The method is executed by a terminal device, and the method includes: Receive a modulation and coding strategy (MCS) indication message, the MCS indication message being used to determine a first MCS from candidate MCSs; First information is transmitted based on the first MCS; The candidate MCS includes one or more of the following: Modulation and traditional channel coding rate based on artificial intelligence (AI); Modulation order and AI-based channel coding; AI-based modulation and channel coding.

2. The method according to claim 1, characterized in that, The first MCS is the AI-based modulation and traditional channel coding code rate, and the method further includes: The first AI model used for modulation or demodulation is determined based on the traditional channel coding rate; or... The first AI model to be used for modulation or demodulation is determined based on pre-configuration information, wherein the pre-configuration information is used to indicate the identification information of the first AI model.

3. The method according to claim 2, characterized in that, The first AI model for determining modulation or demodulation based on the traditional channel coding rate includes: Based on the traditional channel coding code rate and the number of source bits of the first information, the number of output bits of the channel coding is determined; The first AI model is determined based on the number of output bits and the resources used to transmit the first information.

4. The method according to claim 3, characterized in that, Determining the first AI model based on the number of output bits and the resources used to transmit the first information includes: Based on the number of output bits and the resources used to transmit the first information, the equivalent modulation order is determined; The first AI model is determined from the candidate AI models based on the equivalent modulation order.

5. The method according to claim 1, characterized in that, The first MCS is the modulation order and AI-based channel coding, and the method further includes: The second AI model used for channel coding or channel decoding is determined based on the modulation order; or... The second AI model used for channel coding or channel decoding is determined based on pre-configuration information, wherein the pre-configuration information is used to indicate the identification information of the second AI model.

6. The method according to claim 5, characterized in that, The second AI model used to determine channel coding or channel decoding based on the modulation order includes: Based on the modulation order and the resources used to transmit the first information, determine the number of output bits for channel coding; The second AI model is determined based on the number of output bits.

7. The method according to claim 6, characterized in that, Determining the second AI model based on the number of output bits includes: Based on the number of output bits, the second AI model is determined from the candidate AI models; or... Based on the number of output bits and the number of source bits of the first information, the equivalent code rate is determined; based on the equivalent code rate, the second AI model is determined from the candidate AI models.

8. The method according to claim 1, characterized in that, The first MCS is the AI-based modulation and channel coding, and the input of the third AI model is the source bits of the first information. The method further includes: The equivalent spectral efficiency is determined based on the number of source bits of the first information and the resources used to transmit the first information. The third AI model is determined from the candidate AI models based on the equivalent spectral efficiency. The third AI model is used to perform channel coding and modulation on the source bits, or the third AI model is used to demodulate and channel decode the first information.

9. The method according to claim 1, characterized in that, The first MCS is the AI-based modulation and channel coding, and the input of the third AI model is channel state information. The method further includes: The third AI model is determined from candidate AI models based on the resources used to transmit the first information. The third AI model is used to compress, channel code, and modulate the channel state information, or the third AI model is used to demodulate and decode the first information.

10. The method according to claim 1, characterized in that, The first MCS is the AI-based modulation and channel coding, and the method further includes: The third AI model used for channel coding and modulation is determined based on pre-configuration information, or the third AI model used for demodulation and channel decoding is determined, wherein the pre-configuration information is used to indicate the identification information of the third AI model.

11. The method according to any one of claims 1 to 10, characterized in that, The MCS indication message includes a first state set and a second state set. The first state set is used to indicate the modulation order and the conventional channel coding rate. The second state set is used to indicate one or more of the following MCS: The AI-based modulation and traditional channel coding code rates; The modulation order and AI-based channel coding; The AI-based modulation and channel coding.

12. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Receive first indication information, which is used to indicate the MCS table used for transmitting the first information from the candidate MCS table; wherein, the candidate MCS table includes a first MCS table and a second MCS table, the MCS in the first MCS table includes modulation order and conventional channel coding code rate, and the second MCS table includes one or more of the following MCS: The AI-based modulation and traditional channel coding code rates; The modulation order and AI-based channel coding; The AI-based modulation and channel coding.

13. The method according to any one of claims 1 to 12, characterized in that, The AI-based channel coding includes AI-based source-channel joint coding.

14. The method according to any one of claims 1 to 13, characterized in that, The AI-based modulation and channel coding includes AI-based modulation and source-channel joint coding.

15. The method according to any one of claims 1 to 14, characterized in that, The AI-based modulation includes the equivalent modulation order corresponding to the AI-based modulation.

16. The method according to any one of claims 1 to 15, characterized in that, The AI-based channel coding includes the equivalent code rate corresponding to the AI-based channel coding.

17. An information transmission method, characterized in that, The method is performed by a network device, and the method includes: Send a modulation and coding strategy (MCS) indication message, which is used to determine a first MCS from candidate MCSs; First information is transmitted based on the first MCS; The candidate MCS includes one or more of the following: Modulation and traditional channel coding rate based on artificial intelligence (AI); Modulation order and AI-based channel coding; AI-based modulation and channel coding.

18. The method according to claim 17, characterized in that, When the first MCS is the AI-based modulation and traditional channel coding code rate, The first AI model used for modulation or demodulation is determined based on the traditional channel coding rate; or, The first AI model used for modulation or demodulation is indicated to the terminal device through pre-configuration information, which is used to indicate the identification information of the first AI model.

19. The method according to claim 18, characterized in that, The first AI model used for modulation or demodulation is determined based on the traditional channel coding rate, and includes: The first AI model is determined based on the number of output bits of channel coding and the resources used to transmit the first information. The number of output bits is determined based on the conventional channel coding rate and the number of source bits of the first information.

20. The method according to claim 19, characterized in that, The first AI model is determined based on the number of output bits and the resources used to transmit the first information, including: The first AI model is determined from candidate AI models based on the equivalent modulation order; the equivalent modulation order is determined based on the number of output bits and the resources used to transmit the first information.

21. The method according to claim 17, characterized in that, The first MCS is the modulation order and AI-based channel coding. The second AI model used for channel coding or channel decoding is determined based on the modulation order; or, The second AI model used for channel coding or channel decoding is indicated to the terminal device through pre-configuration information, which is used to indicate the identification information of the second AI model.

22. The method according to claim 21, characterized in that, The second AI model used for channel coding or channel decoding is determined based on the modulation order and includes: The second AI model is determined based on the number of output bits of channel coding, which is determined based on the modulation order and the resources used to transmit the first information.

23. The method according to claim 22, characterized in that, The second AI model is determined based on the number of output bits and includes: The second AI model is determined from candidate AI models based on the number of output bits; or, The second AI model is determined from candidate AI models based on an equivalent code rate, which is determined based on the number of output bits and the number of source bits of the first information.

24. The method according to claim 17, characterized in that, The first MCS is the AI-based modulation and channel coding, and the input to the third AI model is the source bits of the first information. The third AI model is determined from the candidate AI models based on the equivalent spectral efficiency, which is determined based on the number of source bits of the first information and the resources used to transmit the first information. The third AI model is used to perform channel coding and modulation on the source bits, or the third AI model is used to demodulate and channel decode the first information.

25. The method according to claim 17, characterized in that, The first MCS is the AI-based modulation and channel coding, and the input of the third AI model is channel state information. The third AI model is determined from candidate AI models based on the resources used to transmit the first information. The third AI model is used to compress, channel code, and modulate the channel state information, or the third AI model is used to demodulate and decode the first information.

26. The method according to claim 17, characterized in that, The first MCS is the AI-based modulation and channel coding. The third AI model used for channel coding and modulation, or the third AI model used for demodulation and channel decoding, is indicated to the terminal device through pre-configuration information, which is used to indicate the identification information of the third AI model.

27. The method according to any one of claims 17 to 26, characterized in that, The MCS indication message includes a first state set and a second state set. The first state set is used to indicate the modulation order and the conventional channel coding rate. The second state set is used to indicate one or more of the following MCS: The modulation and traditional channel coding code rates based on artificial intelligence (AI); The modulation order and AI-based channel coding; The AI-based modulation and channel coding.

28. The method according to any one of claims 17 to 26, characterized in that, The method further includes: Send first indication information, which is used to indicate the MCS table used for transmitting the first information from the candidate MCS table; wherein, the candidate MCS table includes a first MCS table and a second MCS table, the MCS in the first MCS table includes modulation order and conventional channel coding code rate, and the second MCS table includes one or more of the following MCS: The modulation and traditional channel coding code rates based on artificial intelligence (AI); The modulation order and AI-based channel coding; The AI-based modulation and channel coding.

29. The method according to any one of claims 17 to 28, characterized in that, The AI-based channel coding includes AI-based source-channel joint coding.

30. The method according to any one of claims 17 to 29, characterized in that, The AI-based modulation and channel coding includes AI-based modulation and source-channel joint coding.

31. The method according to any one of claims 17 to 30, characterized in that, The AI-based modulation includes the equivalent modulation order corresponding to the AI-based modulation.

32. The method according to any one of claims 17 to 31, characterized in that, The AI-based channel coding includes the equivalent code rate corresponding to the AI-based channel coding.

33. An information transmission device, characterized in that, The device includes: The receiving module is used to receive a modulation and coding strategy (MCS) indication message, which is used to determine a first MCS from candidate MCSs. The transmission module is used to transmit first information based on the first MCS; The candidate MCS includes one or more of the following: Modulation and traditional channel coding rate based on artificial intelligence (AI); Modulation order and AI-based channel coding; AI-based modulation and channel coding.

34. An information transmission device, characterized in that, The device includes: The transmitting module is used to transmit a modulation and coding strategy (MCS) indication message, which is used to determine a first MCS from candidate MCSs; The transmission module is used to transmit first information based on the first MCS; The candidate MCS includes one or more of the following: Modulation and traditional channel coding rate based on artificial intelligence (AI); Modulation order and AI-based channel coding; AI-based modulation and channel coding.

35. A communication device, characterized in that, The communication device includes a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement the method as claimed in any one of claims 1 to 16, or to implement the method as claimed in any one of claims 17 to 32.

36. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1 to 16, or to implement the method as described in any one of claims 17 to 32.

37. A chip, characterized in that, The chip includes programmable logic circuitry and / or program instructions, which, when the chip is running, are used to implement the method as described in any one of claims 1 to 16, or to implement the method as described in any one of claims 17 to 32.

38. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, which a processor reads from and executes to implement the method as claimed in any one of claims 1 to 16, or the method as claimed in any one of claims 17 to 32.

Images