Uplink transmission methods, terminal devices and network devices

Abstract

Provided are uplink transmission methods, terminal devices and network devices. A method comprises: a terminal device sending a first channel, wherein the first channel is used for bearing UCI, the UCI comprises CSI, the first channel comprises a first resource and a second resource, the first resource is used for bearing a first portion of information in the CSI, the second resource is used for bearing a second portion of information in the CSI, and the second portion of information is determined on the basis of an output sequence of a first model.

Description

Uplink transmission method, terminal device and network device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to an uplink transmission method, a terminal device, and a network device. Background Art

[0002] With the development of communication technology, new model-based channel state information (CSI) feedback schemes have been proposed, such as the artificial intelligence (AI)-based joint source-channel coding CSI feedback scheme. For these CSI feedback schemes, the question of how to perform uplink transmission remains unanswered.

[0003] Summary of the Invention

[0004] The embodiments of the present application provide an uplink transmission method, a terminal device, and a network device. The following describes in detail various aspects of the embodiments of the present application.

[0005] In a first aspect, an uplink transmission method is provided, including: a terminal device sends a first channel, where the first channel is used to carry uplink control information (UCI), where the UCI includes CSI, and the first channel includes a first resource and a second resource, where the first resource is used to carry a first part of information in the CSI, and the second resource is used to carry a second part of information in the CSI, where the second part of information is determined based on an output sequence of a first model.

[0006] In a second aspect, an uplink transmission method is provided, including: a network device receives a first channel sent by a terminal device, the first channel is used to carry UCI, the UCI includes CSI, the first channel includes a first resource and a second resource, the first resource is used to carry a first part of information in the CSI, the second resource is used to carry a second part of information in the CSI, and the second part of information is determined based on an output sequence of a first model.

[0007] According to a third aspect, a terminal device is provided, including: a communication unit for sending a first channel, the first channel is used to carry UCI, the UCI includes CSI, the first channel includes a first resource and a second resource, the first resource is used to carry a first part of information in the CSI, the second resource is used to carry a second part of information in the CSI, and the second part of information is determined based on the output sequence of the first model.

[0008] In a fourth aspect, a network device is provided, including: a communication unit for receiving a first channel sent by a terminal device, the first channel being used to carry UCI, the UCI including CSI, the first channel including a first resource and a second resource, the first resource being used to carry a first part of information in the CSI, the second resource being used to carry a second part of information in the CSI, and the second part of information being determined based on the output sequence of the first model.

[0009] In a fifth aspect, a terminal device is provided, comprising a transceiver, a memory and a processor, wherein the memory is used to store programs, and the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the terminal device executes the method described in the first aspect.

[0010] In the sixth aspect, a network device is provided, comprising a transceiver, a memory and a processor, wherein the memory is used to store programs, and the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the network device executes the method described in the second aspect.

[0011] In a seventh aspect, a device is provided, comprising a processor for calling a program from a memory so that the device executes the method as described in the first aspect or the second aspect.

[0012] In an eighth aspect, a chip is provided, characterized in that it includes a processor for calling a program from a memory so that a device equipped with the chip executes the method described in the first aspect or the second aspect.

[0013] In a ninth aspect, a computer-readable storage medium is provided, on which a program is stored, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0014] In a tenth aspect, a computer program product is provided, comprising a program, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0015] In an eleventh aspect, a computer program is provided, wherein the computer program enables a computer to execute the method as described in the first aspect or the second aspect.

[0016] This embodiment of the present application divides the CSI into two parts (one part of which is model-based) and carries these two parts on different resources of the first channel. This allows for a dedicated CSI reporting method to be designed for model-based information, thereby supporting model-based CSI feedback solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a diagram illustrating an example of a system architecture of a wireless communication system to which an embodiment of the present application may be applied.

[0018] FIG2 is a schematic diagram of a neuron to which embodiments of the present application are applicable.

[0019] FIG3 is a schematic diagram of a neural network applicable to an embodiment of the present application.

[0020] FIG4 is a schematic diagram of a convolutional neural network applicable to an embodiment of the present application.

[0021] FIG5 is a schematic diagram of a long short-term memory model applicable to an embodiment of the present application.

[0022] FIG6 is a diagram showing an example of a feedback framework for an AI-based CSI feedback solution.

[0023] Figure 7 is an example diagram of the feedback framework of the AI-based source-channel joint coding CSI feedback scheme.

[0024] FIG8 is a flow chart of an uplink transmission method provided in an embodiment of the present application.

[0025] FIG9 is a flow chart of a configuration method for uplink transmission provided in an embodiment of the present application.

[0026] FIG10 is an example diagram of a switching method of the first model provided in one embodiment of the present application.

[0027] FIG11 is an example diagram of a switching method of the first model provided in another embodiment of the present application.

[0028] FIG12 is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application.

[0029] FIG13 is a schematic diagram of the structure of the network device provided in an embodiment of the present application.

[0030] FIG14 is a schematic structural diagram of a device to which an embodiment of the present application can be applied. DETAILED DESCRIPTION

[0031] The technical solution in this application will be described below with reference to the accompanying drawings.

[0032] Communication system architecture

[0033] FIG1 is a diagram illustrating an exemplary system architecture of a wireless communication system 100 to which embodiments of the present application may be applied. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographic area and may communicate with the terminal device 120 within the coverage area.

[0034] FIG1 exemplarily shows a network device and a terminal device. Optionally, the wireless communication system 100 may include one or more network devices 110 and / or one or more terminal devices 120. For a network device 110, the one or more terminal devices 120 may all be located within the network coverage of the network device 110, or all be located outside the network coverage of the network device 110, or some may be located within the coverage of the network device 110 and others outside the network coverage of the network device 110. This is not limited in the embodiments of the present application.

[0035] Optionally, the wireless communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0036] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth generation (5G) system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0037] The terminal device in the embodiments of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal device in the embodiments of the present application may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity that provides sidelink signals between UEs in V2X or D2D, etc. For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through the base station.

[0038] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmission point (TP), master station MeNB, secondary station SeNB, multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. A base station can also refer to a communication module, modem or chip used to be set in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs base station functions in device-to-device D2D, vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. The base station can support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by the network equipment.

[0039] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0040] In some deployments, the network device in the embodiments of the present application may refer to a CU or a DU, or the network device may include a CU and a DU. The gNB may also include an AAU.

[0041] The network equipment and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal devices are located.

[0042] It should be understood that all or part of the functions of the communication device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).

[0043] Neural Networks

[0044] In recent years, artificial intelligence research, exemplified by neural networks, has achieved remarkable success in many fields, and will continue to play a vital role in people's lives and production for a long time to come. A neural network can be understood as a computational model consisting of multiple interconnected neuron nodes. The connections between these nodes represent the weighted values ​​from input signals to output signals, often referred to as weights. Each node performs a weighted summation of different input signals and outputs the result through a specific activation function.

[0045] As shown in Figure 2, neurons can rely on activation functions to implement nonlinear mapping, where the input of the neuron can be recorded as A, and each dimension of the input is recorded as a j , the corresponding weight is recorded as w j , together with the summation units (SU), the input is strengthened or weakened. In addition, the output of SU can be input into the activation function f to obtain the output t, where the value of j is 1, 2, ..., n.

[0046] Common neural networks include convolutional neural network (CNN), recurrent neural network (RNN), deep neural network (DNN), etc.

[0047] The following describes a neural network applicable to embodiments of the present application in conjunction with FIG3 . The neural network shown in FIG3 can be divided into three categories based on the location of different layers: input layer 310 , hidden layer 320 , and output layer 330 . Generally speaking, the first layer is the input layer 310 , the last layer is the output layer 330 , and the intermediate layers between the first and last layers are all hidden layers 320 .

[0048] The input layer 310 is used to input data, where the input data can be, for example, a received signal received by a receiver. The hidden layer 320 is used to process the input data, for example, decompress the received signal. The output layer 330 is used to output processed output data, for example, a decompressed signal.

[0049] As shown in Figure 3, a neural network consists of multiple layers, each of which contains multiple neurons. The neurons between layers can be fully connected or partially connected. For connected neurons, the output of the neurons in the previous layer can serve as the input of the neurons in the next layer.

[0050] With the continuous advancement of neural network research, deep learning algorithms have been proposed in recent years. These algorithms introduce a large number of hidden layers into neural networks, forming DNNs. More hidden layers allow DNNs to better capture complex real-world situations. Theoretically, a model with more parameters has higher complexity and a greater "capacity," meaning it can handle more complex learning tasks. These neural network models are widely used in pattern recognition, signal processing, optimization and combination, anomaly detection, and other fields.

[0051] CNN is a deep neural network with a convolutional structure, and its structure is shown in FIG4 , which may include an input layer 410 , a convolutional layer 420 , a pooling layer 430 , a fully connected layer 440 , and an output layer 450 .

[0052] Each convolution layer 420 may include a plurality of convolution operators, which are also called kernels. The convolution operator can be regarded as a filter for extracting specific information from the input signal. The convolution operator can essentially be a weight matrix, which is usually predefined.

[0053] The weight values ​​in these weight matrices need to be obtained through a lot of training in practical applications. The weight matrices formed by the weight values ​​obtained through training can extract information from the input signal, thereby helping CNN to make correct predictions.

[0054] When CNN has multiple convolutional layers, the initial convolutional layer tends to extract more general features, which can also be called low-level features. As the depth of CNN increases, the features extracted by the subsequent convolutional layers become more and more complex.

[0055] Pooling layers 430 are often required periodically after convolutional layers to reduce the number of training parameters. For example, a single convolutional layer can be followed by a pooling layer, as shown in Figure 4, or multiple convolutional layers can be followed by one or more pooling layers. In signal processing, the sole purpose of a pooling layer is to reduce the spatial size of the extracted information.

[0056] The fully connected layer 440, after being processed by the convolution layer 420 and the pooling layer 430, is not sufficient for CNN to output the required output information. Because as mentioned above, the convolution layer 420 and the pooling layer 430 only extract features and reduce the parameters brought by the input data. However, in order to generate the final output information (for example, the bit stream of the original information transmitted by the transmitter), CNN also needs to use the fully connected layer 440. Generally, the fully connected layer 440 may include multiple hidden layers, and the parameters contained in the multiple hidden layers may be pre-trained based on relevant training data of a specific task type. For example, the task type may include decoding a data signal received by a receiver. For another example, the task type may also include channel estimation based on a pilot signal received by the receiver.

[0057] Following the multiple hidden layers in the fully connected layer 440, the final layer of the CNN is the output layer 450, which is used to output the results. Typically, this output layer 450 is configured with a loss function (e.g., a loss function similar to categorical cross entropy) to calculate the prediction error, or to evaluate the degree of difference between the output of the CNN model (also known as the predicted value) and the ideal result (also known as the true value).

[0058] In order to minimize the loss function, the CNN model needs to be trained. In some implementations, the backpropagation algorithm (BP) can be used to train the CNN model. The BP training process consists of a forward propagation process and a backward propagation process. During the forward propagation process (for example, the propagation from 410 to 450 in Figure 4 is forward propagation), the input data is input into the above-mentioned layers of the CNN model, processed layer by layer, and transmitted to the output layer. If the output result of the output layer differs significantly from the ideal result, the minimization of the above-mentioned loss function is used as the optimization goal, and the backpropagation process is switched to (for example, the propagation from 450 to 410 in Figure 4 is backward propagation). The partial derivatives of the optimization goal with respect to each neuron weight are calculated layer by layer, forming the gradient of the optimization goal with respect to the weight vector, which serves as the basis for modifying the model weights. The CNN training process is completed during the weight modification process. When the above-mentioned error reaches the expected value, the CNN training process ends.

[0059] It should be noted that the CNN shown in Figure 4 is only an example of a convolutional neural network. In specific applications, the convolutional neural network can also exist in the form of other network models, and the embodiments of the present application are not limited to this.

[0060] RNNs are designed to process sequential data. In traditional neural network models (for example, CNN models), the layers are fully connected, from the input layer to the hidden layer to the output layer, and the nodes within each layer are disconnected. However, these ordinary neural networks are inadequate for many problems. For example, if you want to predict the next word in a sentence, you generally need to use the previous word, because the previous and next words in a sentence are not independent. RNNs are called recurrent neural networks because the current output of a sequence is also related to the previous output. Specifically, the network remembers the previous information and applies it to the calculation of the current output. That is, the nodes between hidden layers are no longer disconnected but connected, and the input of the hidden layer includes not only the output of the input layer but also the output of the hidden layer at the previous moment. In theory, RNNs can process sequence data of any length.

[0061] Training an RNN is similar to training a traditional ANN (artificial neural network). The same backpropagation error algorithm is used, but there is a slight difference. If the RNN is expanded, the parameters W, U, and V are shared, while traditional neural networks are not. Furthermore, when using the gradient descent algorithm, the output of each step depends not only on the network state at the current step, but also on the state of the network at the previous steps. For example, at t = 4, three steps need to be propagated backward, and various gradients need to be added to the three subsequent steps. This learning algorithm is called backpropagation through time (BPTT).

[0062] Given the existence of artificial neural networks and convolutional neural networks, why do we still need recurrent neural networks? The reason is simple. Both convolutional and artificial neural networks assume that elements are independent of each other, and that inputs and outputs are also independent, like cats and dogs. However, in the real world, many elements are interconnected, such as the changes in stock prices over time. For example, someone said, "I love traveling, and my favorite place is Yunnan. I must visit __ someday." Everyone knows to fill in the blank with "Yunnan." This is because we infer this information based on the context, but achieving this is quite difficult. Therefore, recurrent neural networks were developed. Their essence is that they possess memory, just like humans. Therefore, their output depends on the current input and memory.

[0063] At present, in order to solve the gradient explosion or vanishing problem of RNN, a transformation is made on the basis of RNN to obtain the long short-term memory (LSTM) model. As shown in Figure 5, LSTM introduces a new memory unit c t(also called "cell state"), which is used for linear cyclic information transmission and outputs information to the external state h of the hidden layer. t At each moment t, c t It records historical information up to the current moment. Unlike RNNs, which only consider the most recent state, memory cells determine which states should be retained and which should be forgotten, addressing the shortcomings of traditional RNNs in long-term memory.

[0064] Continuing to refer to FIG5, in order to achieve the above state selection, the memory unit introduces a gate control mechanism to control the path of information transmission, similar to the gate in the data circuit, "0" means closed, and "1" means open. The memory unit includes a forget gate 510, an input gate 520, and an output gate 530. Among them, the forget gate is used to control the memory unit c at the previous moment. t-1 How much information needs to be forgotten? The input gate is used to control the candidate state at the current moment. How much information needs to be stored? The output gate is used to control the memory unit c at the current moment. t How much information needs to be output to the external state h t .

[0065] AI-based CSI feedback

[0066] Given the tremendous success of AI technology, especially deep learning technology, in computer vision, natural language processing, and other areas, the communications field has begun to explore the use of AI technology to solve technical problems that are difficult to solve with traditional communication methods. The neural network architecture commonly used in deep learning is nonlinear and data-driven. It can extract features from actual channel matrix data and restore the channel matrix information compressed and fed back by the terminal device as much as possible on the network device side. The CSI feedback solution based on AI technology not only ensures the restoration of channel information but also provides the possibility of reducing CSI feedback overhead for terminal devices. AI-based CSI feedback treats channel information as an image to be compressed, uses a deep learning autoencoder to compress and feedback the input channel information, and reconstructs the compressed channel information at the transmitting end, thereby preserving the channel information to a greater extent.

[0067] In the ongoing Release 18 discussions, AI-based CSI feedback, as one of the key use cases for Release 18's AI projects, has garnered widespread attention from various companies. Multiple rounds of simulations have already been conducted, highlighting hypotheses and potential standards that will influence the discussion. While the details of implementing AI-based CSI feedback will require further discussion in Release 19, consensus has been reached on the basic implementation framework.

[0068] In the AI-based CSI feedback solution, the entire feedback system is divided into an encoder part and a decoder part, which are deployed on the terminal device side as the transmitter and the network device side as the receiver, respectively. After the terminal device obtains the channel information through channel estimation, it uses it as the input of the encoder. The channel information matrix is ​​compressed and encoded through the encoder's neural network, and the compressed bit stream is fed back to the network device through the air interface feedback link. The network device uses the decoder to recover the channel information based on the feedback bit stream to output complete channel information. Both the encoder and decoder shown in Figure 6 can use neural networks. The neural network can use CNN or DNN, or RNN with structures such as LSTM and gated recurrent unit (GRU), or various neural network architectures such as residual and self-attention mechanisms to improve the performance of the encoder and decoder.

[0069] In the AI-based CSI feedback scheme, the input and output of CSI can be full channel information, or can be eigenvectors obtained based on full channel information. Therefore, the current AI-based CSI feedback scheme is mainly divided into feedback schemes based on full channel information and feedback schemes based on eigenvectors. Although the former can achieve compression and feedback of full channel information, the feedback bit stream overhead is relatively high. Therefore, in the NR system, the full channel information feedback scheme is not supported. The eigenvector-based feedback scheme is the feedback scheme currently supported by the NR system. Compared with the traditional scheme (non-model-based CSI feedback scheme), the eigenvector-based feedback scheme can achieve higher CSI feedback accuracy with the same feedback overhead, or significantly reduce the feedback overhead while achieving the same CSI feedback accuracy.

[0070] In addition to the AI-based CSI feedback scheme discussed in Release 18, there is also an AI-based joint source-channel CSI feedback scheme. As shown in Figure 7, in this AI-based joint source-channel CSI feedback scheme, the CSI feedback process takes into account the impact of noise. In actual use, the encoder deployed in the terminal device implicitly implements the CSI compression, channel coding, and modulation processes; the decoder of the network device implicitly implements demodulation and channel decoding, as well as CSI recovery functions.

[0071] The AI-based source-channel joint CSI feedback scheme can take into account the impact of noise and jointly implement source-channel coding, thereby combining the lossy source coding process of CSI compression with the redundancy-increasing process of channel coding. In the case of limited uplink feedback resources, the noise resistance performance of the CSI encoder and CSI decoder in non-ideal channels is further optimized, significantly improving the CSI feedback performance in low signal-to-noise ratio environments.

[0072] While AI-based source-channel joint CSI feedback schemes have not yet been discussed in Releases 18 and 19, they have already garnered attention in academia and may be discussed in future sixth-generation (6G) mobile communication systems. Therefore, standardizing AI-based source-channel joint CSI feedback schemes warrants further research.

[0073] UCI's transfer process

[0074] In some communication protocols (such as the NR protocol), UCI needs to be transmitted to the network device through the physical uplink control channel (PUCCH) or the physical uplink shared channel (PUSCH). UCI generally includes hybrid automatic repeat request-acknoledgement (HARQ-ACK), scheduling request (SR), and CSI. The information in CSI includes one or more of the following: rank indicator (RI), layer indicator (LI), channel quality indicator (CQI), and precoding matrix indicator (PMI).

[0075] The process of carrying UCI through PUCCH generally includes the following steps.

[0076] Step 1: UCI bit sequence generation. Step 1 requires generating the specific content of the UCI. For example, the UCI may only include HARQ-ACK or SR. Alternatively, the UCI may only include CSI. Alternatively, the UCI may include HARQ-ACK, SR, and CSI. In this step, the terminal device arranges the UCI to be transmitted into a bit stream in the order of HARQ-ACK, SR, and CSI.

[0077] Step 2: Code block division and cyclic redundancy check (CRC) addition. Whether code block division and CRC addition are required can be determined based on the length A of the UCI bit sequence. For example, when A ≥ 12 bits, the bit stream generated in step 1 is divided into code blocks, CRC is added, and polar code encoding is used. When A < 12 bits, code block division and CRC addition are not required for the bit stream generated in step 1, and small code blocks are directly used for channel coding.

[0078] Step 3: Channel coding: Channel coding is performed on the sequence generated in step 2.

[0079] Step 4: Rate matching and resource mapping: The channel-coded sequence is rate-matched and modulated using quadrature phase shift keying (QPSK) or π / 2-binary phase shift keying (BPSK), and mapped to the corresponding PUCCH resource.

[0080] The detailed steps of the above process, as well as the specific implementation of channel coding and rate matching, can be found in Section 6.3.1 of the 3rd Generation Partnership Project (3GPP) TS 38.212. For CSI transmission, PUCCH supports periodic CSI (P-CSI) and semi-persistent CSI (SP-CSI) transmission, as shown in Table 1 below.

[0081] Table 1 CSI reporting carried by PUCCH

[0082] The transmission process of UCI on PUSCH is similar to that of PUCCH. The detailed steps of this transmission process and the specific implementation methods of channel coding and rate matching can be found in Section 6.3.2 of the protocol. PUSCH can carry SP-CSI and aperiodic CSI (A-CSI), as shown in Table 2 below.

[0083] Table 2 CSI carried by PUSCH

[0084] It should be understood that SP-CSI cannot be multiplexed with uplink data, while A-CSI can be multiplexed with uplink data. To ensure the effectiveness of PUSCH resource allocation, a subband-based CSI reporting method can be adopted. During the CSI reporting process, the terminal device can discard several blocks of resources in order of priority from low to high based on the allocated PUSCH resources. The terminal device can divide the subband part of Part 2 of each CSI into two parts: even subbands and odd subbands. Each part constitutes a CSI block, and the priority of the even subband is higher than that of the odd subband.

[0085] Traditional CSI feedback schemes (such as codebook-based CSI feedback schemes) typically assume ideal CSI feedback during system-level and link-level performance evaluations. This means that the CSI feedback process is error-free and network devices can perfectly decode the bitstream carrying CSI and recover the CSI.

[0086] However, in real-world systems, this ideal assumption cannot be achieved. For example, in communication systems, CSI is reported via the PUCCH or PUSCH. For CSI feedback based on Type I and Type II codebooks, taking PUSCH reporting as an example, the original CSI is converted into a bit stream after passing through the codebook, which is then channel-coded along with data information and transmitted via the PUSCH. During this CSI feedback process, network devices may experience errors when decoding the PUSCH due to noise. Therefore, the HARQ retransmission mechanism must be triggered to ensure correct PUSCH decoding. In low signal-to-noise ratio environments, such as at the cell edge or when the link is obstructed, the probability of CSI feedback errors is particularly high. Network devices must undergo one or more retransmissions before decoding the correct CSI and performing downlink transmission based on this CSI. Multiple retransmissions introduce significant latency, so by the time downlink transmission is based on the decoded CSI, the downlink channel may have changed, resulting in poor downlink performance.

[0087] AI-based CSI feedback solutions can significantly improve CSI recovery accuracy and reduce CSI feedback overhead. However, the AI-based CSI feedback solutions currently discussed in Release 18 also assume ideal feedback and do not consider the impact of noise. Therefore, they face the same issues as traditional codebook-based CSI feedback solutions and will not be further discussed here.

[0088] On the other hand, while the AI-based joint source-channel coding CSI feedback scheme can significantly improve CSI feedback performance under non-ideal feedback conditions, it may not explicitly go through the channel coding and symbol modulation processes. These channel coding and symbol modulation processes are implicitly implemented by the joint source-channel encoder on the terminal device side. As a result, the UCI transmission process on the PUCCH and PUSCH in traditional communication systems cannot be directly multiplexed into this CSI feedback scheme.

[0089] As described above, with the development of communication technology, new model-based CSI feedback schemes have been proposed, such as the AI-based source-channel joint coding CSI feedback scheme. Regarding these CSI feedback schemes, how to perform uplink transmission is a problem that needs to be solved. To address this issue, the following embodiments of the present application are described in detail.

[0090] Example 1: Uplink transmission method

[0091] FIG8 is a flow chart of an uplink transmission method provided in Example 1. The method in FIG8 is described from the perspective of interaction between a terminal device and a network device. The terminal device and the network device may be, for example, the terminal device 120 and the network device 110 in FIG1 .

[0092] In step S810, the terminal device transmits a first channel. The first channel can be used to carry UCI. For example, the first channel is the PUCCH. In another example, the first channel is the PUSCH. It should be understood that "the terminal device transmits the first channel" can also mean that the terminal device transmits information carried on the first channel. Therefore, step S810 can also be understood or replaced by: the terminal device transmits UCI via the first channel.

[0093] The UCI carried in the first channel may include CSI. For example, if the first channel is a PUCCH, the CSI may be periodic CSI or semi-persistent CSI. For another example, if the first channel is a PUSCH, the CSI may be semi-persistent CSI or aperiodic CSI. The CSI may include, for example, one or more of PMI, RI, CQI, and LI.

[0094] The first channel may include a first resource and a second resource. The first resource may be used to carry the first portion of CSI information. The second resource may be used to carry the second portion of CSI information. In other words, the CSI information may be divided into two portions, each carried in a different resource of the first channel.

[0095] The first portion of information may include, for example, one or more of the following: RI, CQI, LI. In addition to CSI-related information, in some implementations, the first resource is also used to carry first information other than CSI. The first information mentioned here may include, for example, one or more of the following: HARQ-ACK and SR.

[0096] The second portion of information may be information determined based on the first model (or the output sequence of the first model). For example, the output sequence of the first model may include the second portion of information. Exemplarily, the second portion of information may include PMI.

[0097] The first model mentioned above may also be referred to as the first function, the first AI / machine learning (ML) function, or the first AL / ML model. The first model may be, for example, an AI-based source-channel joint coding model (or encoder). Alternatively, the first model may also be other algorithms, modules, or a combination of algorithms and modules that can implement source-channel joint coding. The use of the first model can significantly improve the CSI feedback performance in low signal-to-noise ratio scenarios and reduce CSI feedback overhead. The input of the first model may be the original CSI. The original CSI may be measured by the terminal device. The original CSI may be single-layer information or may contain multiple layers of information. The original CSI may be full channel information, sub-band-level PMI, or broadband-level PMI.

[0098] Exemplarily, the first model is an AI-based source-channel joint coding model. The second portion of information determined based on the first model is the PMI. The PMI has a specific spatial and frequency domain structure, and thus joint source-channel coding can be effectively implemented based on the first model.

[0099] The information carried in the first resource and the information carried in the second resource can be reported in different ways. For example, the information carried in the first resource is reported in a traditional way based on the NR protocol. The information carried in the second resource can be reported separately. For example, the process of reporting the information in the first resource to the first resource includes one or more of the following: code block division, adding CRC, channel coding, rate matching, symbol modulation and resource mapping. For another example, the process of reporting the information in the second resource to the second resource includes resource mapping the output sequence of the first model.

[0100] This embodiment of the present application divides the CSI in the UCI into two parts, one of which is determined based on the output sequence of the first model. On this basis, this embodiment of the present application carries the two parts of information in different resources of the first channel. In other words, this embodiment of the present application adopts a framework in which the second part of information (information determined based on the model) is reported separately from the other information (the first part of information), so that the UCI transmission process can support the CSI feedback scheme based on the first model.

[0101] The sequence length of the output sequence of the first model usually supports only a limited number of configurations (or in other words, the candidate lengths of the output sequence of the first model are usually limited). Therefore, the sequence length of the output sequence of the first model may not be exactly equal to N PUCCH-2 Therefore, in some implementations, a suitable length may be selected from the candidate lengths of the output sequence of the first model to adapt N PUCCH-2That is, the sequence length of the output sequence of the first model can be determined based on the resource quantity of the second resource. Determining the sequence length of the output sequence of the first model based on the resource quantity of the second resource is equivalent to adjusting the output sequence of the first model according to the actual resource occupancy, thereby making the uplink transmission solution more flexible.

[0102] For the convenience of description, the sequence length of the output sequence of the first model is referred to as the first length L below. enc The first length L is configured (or determined) based on the number of resources of the second resource. enc There are many ways to configure it. The following are three configuration methods.

[0103] Configuration method 1:

[0104] In configuration mode 1, the first length L enc The value of is less than or equal to the first value. The first value mentioned here can be determined based on the resource quantity of the second resource. For example, the first value can be equal to the resource quantity of the second resource. The first length L enc The value of is less than or equal to the first value, which helps to ensure the feedback accuracy of the information (such as PMI) determined based on the first model.

[0105] For example, the first length L enc The value of is the maximum value of the candidate length of the output sequence that is less than or equal to the first value. For example, the number of resources of the second resource is 20, and the first value is equal to 20. The candidate lengths of the output sequence of the first model include 12, 14, 18, 22, and 24. In this case, the first length L enc The value of can be 18. enc The value of is set to the maximum value among the candidate lengths of the output sequence that is less than or equal to the first value, which can avoid resource waste.

[0106] Furthermore, in some implementations, if there are remaining resources in the second resource, the remaining resources may be left vacant or filled with zeros. Alternatively, the remaining resources may also be used to transmit other control information that may be transmitted on the PUCCH. For example, assuming that the number of resources in the second resource is N PUCCH-2 , the first length L enc The value is less than N PUCCH-2 , the remaining N PUCCH-2 -L enc The resources may be left vacant, padded with zeros, or used to transmit other control information that may be transmitted on the PUCCH.

[0107] Configuration method 2:

[0108] In configuration mode 2, the first length L encThe value of is greater than or equal to the first value. The first value mentioned here can be determined based on the number of resources of the second resource. For example, the first value can be equal to the number of resources of the second resource. The first length L enc The value of is greater than or equal to the first value, which can avoid resource waste.

[0109] For example, the first length L enc The value of is the minimum value greater than or equal to the first value among the candidate lengths of the output sequence. For example, the number of resources of the second resource is 20, and the first value is equal to 20. The candidate lengths of the output sequence of the first model include 12, 14, 18, 22, and 24. In this case, the first length L enc The value of can be 22. The first length L enc The value of is set to the minimum value greater than or equal to the first value among the candidate length values ​​of the output sequence, which can ensure the feedback accuracy of the information (such as PMI) determined based on the first model as much as possible under the premise of avoiding resource waste.

[0110] Furthermore, in some implementations, at the first length L enc When the value of is greater than the first value, the sequence in the output sequence of the first model that cannot be carried by the second resource can be discarded. For example, assuming that the number of resources of the second resource is N PUCCH-2 , the first length L enc The value is greater than N PUCCH-2 , then the first N in the output sequence of the first model can be PUCCH-2 Then, the first N symbols after truncation can be PUCCH-2 The symbols are mapped to N PUCCH-2 resources. enc -N PUCCH-2 The network device can use the N symbols at the end of the PUCCH-2 The filling process can be implemented locally by the network device.

[0111] The above two configurations can adapt to different PUCCH resource quantities. During uplink transmission, the specific configuration adopted by the terminal device can be determined based on the resource quantity of the second resource and the candidate length of the output sequence of the first model supported by the terminal device. For example, assuming that the candidate length L of the output length of the first model of the terminal device is enc There are two types: 16 and 32. If N PUCCH-2 =17, you can choose configuration mode 1, that is, L enc =16, which can reduce the waste of PUCCH resources; if N PUCCH-2 =30, you can choose configuration mode 2, that is, L enc=32, which can ensure the feedback accuracy of the information determined based on the first model (such as PMI).

[0112] Configuration method three:

[0113] In configuration mode 3, the first length L enc The value of is determined based on the configuration information of the network device. For example, the configuration information of the network device is used to configure the maximum length of the output sequence of the first model.

[0114] Furthermore, in some implementations, the maximum value of the sequence length of the output sequence of the first model configured by the network device can be less than the first value. The first value mentioned here can be determined based on the resource quantity of the second resource. For example, the first value can be equal to the resource quantity of the second resource.

[0115] This configuration method 3 can be used in the scenario where the first channel is PUSCH. For example, the network device can configure the maximum sequence length of the output sequence of the first model according to the amount of uplink data to be transmitted, so that some remaining resources of the second resource are reserved for UL-SCH transmission.

[0116] The following describes in detail how to determine the resource quantities of the first resource and the second resource.

[0117] 1. Method for determining the quantity of the first resource

[0118] As mentioned above, the first resource can be used to carry the first portion of information in the CSI. If the UCI includes other information in addition to the CSI, the first resource can also be used to carry the other information. Therefore, in some implementations, the number of first resources can be determined based on one or more of the following: the number of resources required for the first portion of information and the number of resources required for the other information in the UCI in addition to the CSI.

[0119] For example, UCI only contains CSI. The resources allocated by PUCCH for transmitting UCI (or CSI) are a fixed number of REs N. PUCCH The CSI to be fed back is divided into two parts according to the feedback mode, wherein the first part includes CQI, RI, LI and other bit information. The first part of the information is processed by code block division, CRC addition, channel coding, rate matching, symbol modulation and other processes to form a length of N PUCCH-1 Then, the constellation point sequence can be mapped to N PUCCH N in PUCCH-1 The N mentioned here PUCCH-1That is, the resource quantity of the first resource. In this example, the resource quantity of the first resource is determined based on the resource quantity required to be occupied by the bit information such as CQI, RI, LI, etc. in the CSI.

[0120] For example, UCI includes other information such as HARQ-ACK and / or SR. That is, other information such as HARQ-ACK and / or SR needs to be multiplexed with CSI for transmission. The resources allocated to UCI by PUCCH are a fixed number of REs, denoted as N. PUCCH At this time, the CQI, RI, LI and other bit information in the CSI (corresponding to the first part of the information mentioned above) need to go through code block division, CRC addition, channel coding, rate matching, symbol modulation and other processes together with HARQ-ACK / SR to form a length of N PUCCH-1 Then, the constellation point sequence can be mapped to N in order. PUCCH-1 Resources. The N mentioned here PUCCH-1 That is, the resource quantity of the first resource. In this example, the resource quantity of the first resource is determined based on the resource quantity required for bit information such as CQI, RI, LI in the CSI and the resource quantity required for HARQ-ACK / SR.

[0121] 2. Method for determining the quantity of the second resource

[0122] The method for determining the number of second resources may be different depending on the type of the first channel. The following describes the method for determining the number of second resources in detail, taking the first channels being PUCCH and PUSCH as examples.

[0123] 2.1. The first channel is PUCCH

[0124] In the case where the first channel is a PUCCH, the resource quantity of the second resource may be determined based on one or more of the following: the resource quantity of the first resource, and the resource quantity used for transmitting UCI in the first channel.

[0125] The resource quantity of the first resource can be found in the description of the section “Method for determining the resource quantity of the first resource” and will not be repeated here.

[0126] The number of resources used to transmit UCI in the first channel can be recorded as N PUCCH . N PUCCH It can be a fixed number of REs, and N PUCCH The determination may be based on predefined information and / or configuration information of the network device.

[0127] Exemplarily, the resource quantity of the second resource may be determined based on (or satisfy) the following formula: N PUCCH-2 =NPUCCH -N PUCCH-1 (1)

[0128] Among them, N PUCCH-2 Indicates the number of resources of the second resource, N PUCCH Indicates the number of resources used to transmit UCI in the first channel, N PUCCH-1 Indicates the resource quantity of the first resource.

[0129] 2.2. The first channel is PUSCH

[0130] When the first channel is a PUSCH, the number of second resources may be determined based on one or more of the following:

[0131] The number of resources in the first channel used to carry the reference signal;

[0132] The resource quantity of the first resource;

[0133] The number of resources reserved for UL-SCH in the first channel;

[0134] The number of resources of the first channel.

[0135] The first channel may carry a reference signal. The reference signal may include, for example, a DMRS and / or a PTRS. Therefore, in some implementations, when determining the number of resources of the second resource, the number of resources occupied by the reference signal may be considered.

[0136] The resource quantity of the first resource can be found in the description of the section “Method for determining the resource quantity of the first resource” and will not be repeated here.

[0137] The first channel may reserve resources for transmitting UL-SCH, or may not reserve resources for transmitting UL-SCH. In the embodiment of the present application, the situation of "allowing the reservation of resources for transmitting UL-SCH" is referred to as the first multiplexing mode of CSI and UL-SCH; the situation of "not allowing the reservation of resources for transmitting UL-SCH" is referred to as the second multiplexing mode of CSI and UL-SCH. If CSI and UL-SCH are transmitted using the first multiplexing mode, the number of resources reserved for UL-SCH can be considered when determining the number of resources for the second resource. Of course, if CSI and UL-SCH are transmitted using the second multiplexing mode, this factor does not need to be considered when determining the number of resources for the second resource.

[0138] As an example, if the CSI and UL-SCH are transmitted using multiplexing mode 1, the number of second resources may be determined based on (or satisfy) the following formula: N PUCCH-2 =N PUCCH -N UL-SCH -N PUCCH-1(2)

[0139] Among them, N PUCCH-2 Indicates the number of resources of the second resource, N PUCCH N represents the number of remaining resources in the first channel except for the resources used to carry the reference signal. UL-SCH Indicates the number of resources reserved for UL-SCH in the first channel, N PUCCH-1 Indicates the resource quantity of the first resource.

[0140] As another example, if the CSI and UL-SCH are transmitted using multiplexing mode 2, the number of second resources may be determined based on (or satisfy) the following formula: N PUCCH-2 =N PUCCH -N PUCCH-1 (3)

[0141] Among them, N PUCCH-2 Indicates the number of resources of the second resource, N PUCCH N represents the number of remaining resources in the first channel except for the resources used to carry the reference signal. PUCCH-1 Indicates the resource quantity of the first resource.

[0142] In some implementations, regardless of whether resources are reserved for transmitting UL-SCH, if the second resources include remaining resources other than the resources occupied by the second portion of information, the remaining resources can be used to carry UL-SCH, thereby avoiding resource waste.

[0143] To facilitate understanding, two more specific examples are given below.

[0144] Example 1: CSI and UL-SCH are transmitted in PUSCH using multiplexing mode 1

[0145] In Example 1, the number of PUSCH resources after removing reference signals such as DMRS and PTRS is N PUCCH , and the number of resources reserved for UL-SCH is N UL-SCH , these reserved resources cannot be used for CSI transmission. Therefore, the maximum number of resources in PUSCH that can be used for CSI transmission is N PUCCH -N UL-SCH Furthermore, the CSI is divided into the first part of information and the second part of information, wherein the first part of information carries CQI, RI, LI and other contents, and adopts the mapping process specified in NR, through code block division, adding CRC, channel coding, rate matching and symbol modulation, occupies N PUCCH-1 Therefore, the resources available for transmitting the second part of the information are N PUCCH-2 =N PUCCH -N UL-SCH-N PUCCH-1 Based on the number of resources, the configuration method 1 or configuration method 2 described above can be used to determine the sequence length of the output sequence of the first model, so as to provide feedback on the PMI in the second part of the information. It should be noted that when the configuration method 1 mentioned above is selected to report the second part of the information, the redundant N PUCCH-2 -L enc The resources can be used for UL-SCH transmission to ensure that there is no resource waste on PUSCH.

[0146] Example 2: CSI and UL-SCH are transmitted in PUSCH using multiplexing mode 2

[0147] In Example 2, the number of PUSCH resources after removing reference signals such as DMRS and PTRS is N PUCCH , but no resources are reserved for UL-SCH in PUSCH. That is to say, all potential resources in PUSCH can be used for CSI transmission. After dividing CSI into the first part of information and the second part of information, the number of resources occupied by the first part of information is N PUCCH-1 , so the amount of resources available to transmit the second part of the information is N PUCCH-2 =N PUCCH -N PUCCH-1 At this time, you can use N PUCCH-2 , use the configuration method 1 or configuration method 2 described above to determine the sequence length of the output sequence of the first model, so as to feedback the PMI in the second part of the information. It should be noted that when configuration method 1 is selected to transmit the second part of the information, the redundant N PUCCH-2 -L enc Resources can be used for UL-SCH transmission to ensure that there is no waste of resources on PUSCH. When configuration method 2 is selected for the second part of the information transmission, there are no redundant PUSCH resources, and the multiplexing transmission of UL-SCH and CSI is not supported at this time. Alternatively, in this multiplexing mode, in order to avoid CSI occupying too much uplink resources, the configuration method 3 mentioned above can be used to limit the maximum sequence length L output by the first mode. enc-max , so that L enc-max Satisfaction: L enc-max <N PUCCH-2 In this case, N PUCCH-2 The remaining N PUCCH-2 -L enc resources can still be used for UL-SCH transmission.

[0148] If the first channel is PUSCH, in addition to determining the number of first resources (used to carry the first part of the information in the CSI and / or other information in the UCI except CSI) and / or second resources (used to carry the second part of the information in the CSI), the arrangement of the first resources and the second resources on the PUSCH resources may also be determined. PUCCH-1 resources, the second resource includes N PUCCH-2 For example, the N PUCCH-1 resources and the N PUCCH-2 There are many ways to arrange N resources on PUSCH resources. For example, the N resources can be allocated in a continuous frequency domain. PUCCH-1 resources and the N PUCCH-2 The arrangement of N resources on PUSCH resources. For example, the resource allocation method of frequency hopping can be used to determine the N PUCCH-1 resources and the N PUCCH-2 The arrangement of resources on PUSCH resources.

[0149] As an example, N can be allocated continuously from low to high in the order of subcarrier index and then from front to back in the order of symbols. PUCCH-1 resources, the N PUCCH-1 The remaining N resources of PUSCH can be used to carry the first part of the CSI information and / or other information in the UCI except CSI. PUCCH-2 The resources may be used to carry the second part of the CSI information. After the above resource allocation process, if there are still remaining resources, the remaining resources may be used for UL-SCH transmission.

[0150] As another example, N can be allocated successively from low to high in the order of subcarrier index and then from front to back in the order of symbols. PUCCH-1 However, when allocating resources in descending order of subcarrier index, only odd subcarriers may be allocated without even subcarriers, or only even subcarriers may be allocated without odd subcarriers. PUCCH-2 The resources may be used to carry the second part of the CSI information. After the above resource allocation process, if there are still remaining resources, the remaining resources may be used for UL-SCH transmission.

[0151] The following describes embodiment 1 in more detail with reference to specific examples. In the following example, the first part of the information in the CSI includes bit information such as RI, LI and CQI; the second part of the information in the CSI includes PMI. The first model is an encoder based on source-channel joint coding. It should be noted that the following examples are only intended to help those skilled in the art understand the embodiments of the present application, and are not intended to limit the embodiments of the present application to the specific numerical values ​​or specific scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the examples given, and such modifications or changes also fall within the scope of the embodiments of the present application.

[0152] In this example, according to the content of the UCI, it can be divided into three cases, namely, case 1, case 2 and case 3 described below.

[0153] In case 1, UCI does not include CSI, but only HARQ-ACK and / or SR. In this case, the uplink transmission process of UCI is consistent with the traditional NR feedback and reporting method.

[0154] In case 2, UCI only includes CSI, excluding HARQ-ACK and SR. In this case, the PMI in the CSI can be reported using the output based on the first model, and other information included in the CSI, such as CQI, RI, LI, etc., can use traditional NR feedback and reporting methods.

[0155] In case three, UCI includes CSI. In addition to CSI, UCI also includes other information, such as HARQ-ACK, SR, and one or more other control information that may be transmitted via UCI. In this case, the PMI in the CSI can be reported based on the output of the first model. Other information in the CSI, such as CQI, RI, and LI, can be combined with other information in the UCI and use traditional NR feedback and reporting methods.

[0156] Example a: Only CSI transmission is performed on PUCCH

[0157] When UCI only contains CSI, the resources allocated by PUCCH for CSI transmission are a fixed number of REs, denoted as N PUCCH The CSI to be fed back is divided into two parts according to the feedback mode, and the first part of information and the second part of information are obtained. The first part of information needs to carry CQI, RI, LI and other bit information. The first part of information is mapped to the UCI on PUCCH specified by the NR system to form a length of N PUCCH-1 constellation point sequence, and mapped to N in order PUCCH-1 The mapping process of the first part of the information may include code block division, CRC addition, channel coding, rate matching, and symbol modulation.

[0158] The second part of the information contains PMI. The number of resources used to carry the second part of the information is N PUCCH-2 =N PUCCH -N PUCCH-1 The input of the first model can be the original CSI measured by the terminal device. The original CSI may be single-layer or multi-layer. Considering that the sequence length of the output sequence of the first model only supports a limited number of configurations, the sequence length may not be exactly equal to N PUCCH-2 , so it is necessary to select the sequence length of the output sequence of the first model to adapt to N PUCCH-2 The selection of the first model includes, for example, the two configuration methods described below.

[0159] Configuration method 1 (zero padding): Select the sequence length L of the output sequence of the first model enc The candidate lengths configured for the first model are no greater than N PUCCH-2 The maximum length of the remaining N PUCCH-2 -L enc The number of resources may be left idle or used to transmit other control information that may be transmitted on the PUCCH.

[0160] Configuration 2 (Truncation): Select the sequence length L of the output sequence of the first model enc The candidate lengths configured for the first model are greater than N PUCCH-2 The minimum length of the first N PUCCH-2 The symbols are truncated and mapped to N in sequence PUCCH-2 resources. enc -N PUCCH-2 The network device may fill in the terminal symbol when recovering it, and the filling process may be implemented locally by the network device.

[0161] The above two configuration methods can adapt to different PUCCH resource quantities. The specific configuration method to be used can be determined based on the specific N PUCCH-2 The number of resources and the candidate length supported by the terminal device (i.e., the candidate length of the output sequence of the first model) are determined. For example, the candidate lengths supported by the terminal device are 16 and 32. If N PUCCH-2 =17, then select configuration mode 1, that is, L enc =16, which can reduce the waste of PUCCH resources; if N PUCCH-2 =30, you can choose configuration mode 2, that is, L enc =32, which can ensure the feedback accuracy of PMI.

[0162] Example b: HARQ-ACK / SR and CSI multiplexing transmission on PUCCH

[0163] When UCI contains other information such as HARQ-ACK and / or SR, these information need to be multiplexed with CSI for transmission. The resources allocated to UCI transmission by PUCCH are a fixed number of REs, denoted as N. PUCCH At this time, the first part of the CSI information (i.e. CQI, RI, LI and other bit information) needs to be mapped together with HARQ-ACK / SR through the UCI mapping process on PUCCH specified by the NR system to form a length of N PUCCH-1 constellation point sequence, and mapped to N in order PUCCH-1 The mapping process of the first part of the information includes code block division, CRC addition, channel coding, rate matching, and symbol modulation.

[0164] The second part of the information includes PMI. The way of carrying PMI and the way of selecting the length of the output sequence of the first model are similar to those in Example a and will not be repeated here.

[0165] In example b, N PUCCH-1 resources and N PUCCH-2 N resources carry CSI feedback PUCCH The arrangement of PUCCH resources is similar to that in Example a and will not be repeated here.

[0166] Example c: Only CSI transmission is performed on PUSCH

[0167] Semi-persistent and aperiodic CSI may also be fed back via the PUSCH. In NR systems, semi-persistent CSI cannot be multiplexed with uplink data, while aperiodic CSI can be multiplexed with uplink data (UL-SCH). Therefore, the following discusses semi-persistent CSI and aperiodic CSI separately.

[0168] For semi-persistent CSI, the resources allocated by PUSCH for reporting CSI are N PUCCH During the reporting process, the CSI to be reported can be divided into two parts of information. The division method of the two parts of information, the reporting process of the two parts of information, and the selection method of the output sequence of the first model are similar to those in Example a and will not be repeated here.

[0169] For aperiodic CSI, the multiplexing mode with UL-SCH needs to be considered. This example supports two multiplexing modes of CSI and UL-SCH, namely multiplexing mode 1 and multiplexing mode 2 described below.

[0170] Multiplexing mode 1 (allowing UL-SCH resource reservation): In this multiplexing mode, the number of PUSCH resources after removing reference signals such as DMRS and PTRS is N PUCCH, and the number of resources reserved for UL-SCH is N UL-SCH Since the reserved resources cannot be used for CSI reporting, the maximum number of resources that can be used for CSI reporting in PUSCH is N PUCCH -N UL-SCH Furthermore, the CSI can be divided into the first part of information and the second part of information. The first part of information carries CQI, RI, LI and other bit information. The first part of information adopts the mapping process specified in NR, and occupies N after code block division, adding CRC, channel coding, rate matching and symbol modulation. PUCCH-1 Therefore, the resources available for transmitting the second part of the information are N PUCCH-2 =N PUCCH -N UL-SCH -N PUCCH-1 Based on the number of resources, the configuration method 1 or configuration method 2 as shown in Example a can be used to select the sequence length of the output sequence of the first model, so as to report the PMI in the second part of the information. It should be noted that when configuration method 1 is selected to report the second part of the information, the redundant N PUCCH-2 -L enc resources can be used for UL-SCH transmission to ensure that there is no resource waste on PUSCH.

[0171] Multiplexing mode 2 (UL-SCH resource reservation is not allowed): In this multiplexing mode, the number of PUSCH resources after removing reference signals such as DMRS and PTRS is N PUCCH The second multiplexing mode does not reserve resources for UL-SCH, that is, all potential N PUCCH All resources can be used for CSI reporting. After dividing CSI into the first part of information and the second part of information, the number of resources occupied by the first part of information is N PUCCH-1 , so the resources available for transmitting the second part of the information are N PUCCH-2 =N PUCCH -N PUCCH-1 At this time, according to the number of resources, the configuration method 1 or configuration method 2 as described in Example a can be used to select the sequence length of the output sequence of the first model to report the PMI in the second part of the information. It should be noted that when configuration method 1 is selected to report the second part of the information, the redundant N PUCCH-2 -L enc Resources can be used for UL-SCH transmission to ensure that there is no waste of resources on PUSCH. When configuration method 2 is selected for reporting the second part of information, there are no redundant PUSCH resources, and the multiplexing of UL-SCH and CSI is not supported at this time. In this multiplexing mode, in order to avoid excessive resources occupied by CSI reporting, the network device can also configure the maximum sequence length L of the first model output through downlink signaling.enc-max , and L enc-max <N PUCCH-2 At this time, L in configuration method 2 enc Can be no more than L enc-max In this case, the remaining N PUCCH-2 -L enc resources can still be used for UL-SCH transmission.

[0172] The N mentioned above PUCCH-1 resources and the N PUCCH-2 There are many ways to arrange N resources on PUSCH resources. For example, the N resources can be allocated in a continuous frequency domain. PUCCH-1 resources and the N PUCCH-2 The arrangement of N resources on PUSCH resources. For example, the resource allocation method of frequency hopping can be used to determine the N PUCCH-1 resources and the N PUCCH-2 The arrangement of resources on PUSCH resources.

[0173] As an example, N can be allocated continuously from low to high in the order of subcarrier index and then from front to back in the order of symbols. PUCCH-1 resources, the N PUCCH-1 The remaining N resources of PUSCH can be used to carry the first part of the CSI information and / or other information in the UCI except CSI. PUCCH-2 The resources may be used to carry the second part of the CSI information. After the above resource allocation process, if there are still remaining resources, the remaining resources may be used for UL-SCH transmission.

[0174] As another example, N can be allocated successively from low to high in the order of subcarrier index and then from front to back in the order of symbols. PUCCH-1 However, when allocating resources in descending order of subcarrier index, only odd subcarriers may be allocated without even subcarriers, or only even subcarriers may be allocated without odd subcarriers. PUCCH-2 The resources may be used to carry the second part of the CSI information. After the above resource allocation process, if there are still remaining resources, the remaining resources may be used for UL-SCH transmission.

[0175] Example d: HARQ-ACK / SR and CSI transmission on PUSCH

[0176] The number of resources after removing reference signals such as DMRS and PTRS in PUSCH is N PUCCHThese resources are allocated to UCI for HARQ-ACK / SR and CSI reporting. For semi-persistent CSI, since there is no CSI and UL-SCH multiplexing, the PUSCH resource mapping process is similar to the mapping process on PUCCH in Example b and will not be repeated here.

[0177] For non-periodic CSI, similar to example b, HARQ-ACK / SR and the first part of CSI information can be jointly processed, and the processed information occupies N PUCCH-1 At the same time, the second part of the CSI information and the UL-SCH can be multiplexed according to the multiplexing mode 1 or the multiplexing mode 2 in Example c.

[0178] N PUCCH-1 resources and N PUCCH-2 The arrangement of the resources in the PUSCH resources can be determined based on the method described in Example c, which will not be repeated here.

[0179] Example 2: Interaction of configuration information and / or reporting of terminal device capabilities

[0180] The second embodiment describes the interaction of configuration information between the terminal device and the network device and / or the capability reporting process of the terminal device to support the uplink transmission process described in the first embodiment.

[0181] Referring to Figure 9, in step S910, a terminal device receives first configuration information sent by a network device. The first configuration information may be used to indicate one or more of the following: a UCI transmission method, a multiplexing method of CSI and UL-SCH on the PUSCH, and configuration information of the first model. The following provides detailed examples of the contents of the first configuration information.

[0182] In some implementations, the first configuration information may indicate a transmission mode of UCI (or a reporting mode of UCI). The transmission mode of UCI may include a first transmission mode and a second transmission mode. The first transmission mode may be a transmission mode based on a first model. For example, if the first transmission mode is selected, the second part of the information in the CSI may be determined using the first model as described in Example 1, and the second part of the information may be transmitted. The second transmission mode may be a transmission mode not based on a model. For example, if the second transmission mode is selected, the UCI information may be reported in accordance with the NR protocol, that is, the information in the UCI may be processed and reported through processes such as code block division, CRC addition, channel coding, rate matching, symbol modulation, and resource mapping. Alternatively, the second transmission mode may be a transmission mode based on other models. The other models mentioned here refer to models with different functions from the first model. For example, the first model may be an AI-based source-channel joint coding model, and the other model may be an AI-based CSI feedback model introduced in R18.

[0183] For example, the first configuration information includes information a, which is used to indicate the transmission mode of UCI. When the value of information a is a first value (for example, information a occupies one bit and the value of the bit is 0), UCI is transmitted according to the NR protocol; when the value of information a is a second value (for example, information a occupies one bit and the value of the bit is 1), UCI is transmitted in the manner described in Example 1. Information a may also further indicate the transmission mode of UCI on PUCCH and / or PUSCH. For example, information a includes a first bit, and the first bit (which may include one or more bits) is used to indicate the transmission mode of UCI on PUCCH. When the value of the first bit is a first value (for example, the first bit is one bit and the value of the bit is 0), UCI is transmitted through PUCCH according to the NR protocol; when the value of the first bit is a second value (for example, the first bit is one bit and the value of the bit is 1), UCI is transmitted through PUCCH in the manner described in Example 1. For example, information a includes a second bit, and the second bit (which may include one or more bits) is used to indicate the transmission method of UCI on PUSCH. When the value of the second bit is the first value (for example, the second bit is one bit, and the value of the bit is 0), UCI is transmitted through PUSCH according to the NR protocol; when the value of the second bit is the second value (for example, the second bit is one bit, and the value of the bit is 1), UCI is transmitted through PUSCH in the manner described in Example 1.

[0184] In some implementations, the first configuration information may indicate a multiplexing method of the CSI and UL-SCH on the PUSCH. The multiplexing method of the CSI and UL-SCH may refer to the multiplexing method one and / or multiplexing method two described in Example 1. For example, the first configuration information includes information b, and information b is used to indicate a multiplexing method of the CSI and UL-SCH on the PUSCH. If the value of the information b is the first value, the multiplexing method of the CSI and UL-SCH on the PUSCH is the multiplexing method one described in Example 1, that is, resources are reserved for UL-SCH transmission; if the value of the information b is the second value, the multiplexing method of the CSI and UL-SCH on the PUSCH is the multiplexing method two described in Example 1, that is, no resources are reserved for UL-SCH transmission.

[0185] In some implementations, the first configuration information may indicate configuration information of the first model.

[0186] For example, the configuration information of the first model is used to indicate a determination method (or configuration method) for the sequence length of the output sequence of the first model. The configuration method for the sequence length of the output sequence of the first model can adopt configuration method 1 and configuration method 2 in Example 1. For detailed descriptions of configuration method 1 and configuration method 2, please refer to Example 1 and will not be repeated here.

[0187] For another example, the configuration information of the first model is used to indicate the candidate length L of the output sequence of the first model enc , that is, the sequence length of the output sequence that the first model can support. For example, assuming that the first model of the terminal device is trained and downloaded from the network device or an entity for training the model located on the network device side, the network device can indicate the output length L supported by the first model through the first configuration information. enc For example, the first configuration information indicates the output length L supported by the first model enc ={16, 32, 64, 128, 256, ...}. The output length of the first model actually used by the terminal device needs to be selected from the values ​​configured by the network device. There are multiple ways to select the output length of the first model. For example, the output length of the first model can be selected based on the number of PUCCH or PUSCH resources configured by the network device and according to configuration method 1 or configuration method 2 described in embodiment 1.

[0188] For another example, the configuration information of the first model is used to indicate the maximum length L of the output sequence of the first model enc-max And / or the adjustment step length l of the sequence length of the output sequence of the first model. For example, assuming that the first model of the terminal device is trained and downloaded from the network device or an entity for training the model located on the network device side, the network device can indicate the maximum output length L of the first model through the first configuration information.enc-max And adjust the step size l. The sequence length of the output sequence that the first model can support is: L enc-max -kl, k = 0, 1, 2, ... and other non-negative integer values. There are multiple ways to select the output length of the first model. For example, the output length of the first model can be selected based on the number of PUCCH or PUSCH resources configured by the network device and according to configuration method 1 or configuration method 2 described in embodiment 1.

[0189] For another example, the configuration information of the first model may indicate an input format of the first model. The first configuration information may indicate that the input format of the first model is one of the following: full channel information, subband-level PMI information, and wideband-level PMI information.

[0190] For another example, the configuration information of the first model may indicate the generalization capability of the first model. For example, the configuration information of the first model may indicate the adaptation scenario of the first model. For example, the configuration information of the first model indicates that the first model is a cell-specific model, a terminal device-specific model, a terminal device group-specific model, or a model corresponding to multiple cells. Alternatively, the configuration information of the first model indicates that the first model is a model exclusive to outdoor terminal devices, or a model exclusive to indoor terminal devices. Alternatively, the configuration information of the first model indicates that the first model is a model adapted for low-speed scenarios, or a model adapted for high-speed scenarios.

[0191] The embodiment of the present application does not specifically limit the transmission method of the first configuration information. For example, the first configuration information can be carried by one of the downlink signalings such as a broadcast message (such as a master information block (MIB), a system information block (SIB), a radio resource control (RRC) message, a medium access control control element (MAC CE), downlink control information (DCI), etc.), or carried by other AI / ML-related proprietary signaling. Alternatively, the first configuration information can also be carried by a combination of the above signaling. For example, the UCI reporting method can be configured by MAC CE, and the multiplexing method of CSI and UL-SCH on PUSCH can be dynamically indicated by DCI.

[0192] Referring again to FIG. 9 , in some implementations, after receiving the first configuration information, the terminal device may execute step S920, i.e., configure the uplink transmission mode according to the first configuration information. For example, after receiving the first configuration information, the terminal device may perform uplink transmission in the manner described in Example 1. For details, see Example 1 and are not further described here.

[0193] The foregoing description describes the network device sending configuration information to the terminal device. In some implementations, the terminal device may also send configuration information (this configuration information may be referred to as second configuration information) to the network device. For example, when the first model is trained by the terminal device or an entity for model training located on the terminal device side, the terminal device may send second configuration information to the network device to indicate the configuration of the first model.

[0194] The second configuration information may be used to indicate one or more of the following: a candidate length of the output sequence of the first model, a maximum length of the output sequence of the first model, an adjustment step size for the length of the output sequence of the first model, an input format of the first model, and the generalization capability of the first model. For details about the above information, please refer to the relevant description in the first configuration information and will not be detailed here.

[0195] In some implementations, the terminal device may send first capability information to the network device to support the terminal device in implementing an uplink transmission mode based on the first model. The first capability information may be used to indicate that the terminal device supports one or more of the following: the first model, the first configuration information, and the second configuration information.

[0196] For example, the first capability information indicates that the terminal device supports the first model or has the ability to support the first model. Further, as an implementation, the terminal device supporting the first model can also support receiving the first configuration information from the network device and / or sending the second configuration information to the network device.

[0197] For another example, the first capability information indicates that the terminal device supports the first configuration information (or has the ability to receive the first configuration information). Furthermore, as an implementation method, the terminal device that supports the first configuration information also has the ability to support the first model and / or the ability to send the second configuration information to the network device.

[0198] For another example, the first capability information indicates that the terminal device supports the second configuration information (or has the ability to send the second configuration information). Further, as an implementation method, the terminal device that supports the second configuration information also has the ability to support the first model and / or the ability to receive the first configuration information sent by the network device.

[0199] Example 3: Switching from the first model to the first processing solution

[0200] It should be understood that Example 3 can be implemented independently or in combination with Example 1 and / or Example 2. For example, the terminal device can exchange the configuration information mentioned in Example 2 with the network device. Then, based on this configuration information, the terminal device can perform uplink transmission based on the first model in the manner described in Example 1. In addition, when certain conditions are met, the first model can be switched to the first processing scheme.

[0201] The first processing scheme mentioned above may refer to a second model that is different from the first model. The second model may be a default model or an updated model. The second model may also be referred to as a second AL / ML model or a second function. Alternatively, the first processing scheme may also refer to a processing scheme that is not based on a model. Exemplarily, the first processing scheme may be a processing scheme specified by the NR protocol, that is, processing and transmitting UCI based on processes such as code block partitioning, adding CRC, channel coding, rate matching, symbol modulation, and resource mapping. If the first processing scheme is a processing scheme specified by the NR protocol, then the switching from the first model to the first processing scheme can also be understood as a fallback mechanism, that is, falling back from a model-based scheme to a traditional scheme.

[0202] The switching from the first model to the first processing scheme may be triggered based on a first condition. The first condition may be associated with one or more of the following: link-level information (such as transmission rate and / or bit error rate), PMI, changes in environmental information, changes in communication scenarios, etc.

[0203] For example, if the rate and / or the bit error rate is lower than or equal to a first threshold, switching from the first model to the first processing scheme is triggered.

[0204] For another example, if the rate and / or the bit error rate is higher than or equal to a first threshold, switching from the first model to the first processing solution is triggered.

[0205] For another example, if the cosine similarity of the PMI is lower than or equal to the second threshold, switching from the first model to the first processing solution is triggered.

[0206] For another example, if the cosine similarity of the PMI is higher than or equal to the second threshold, switching from the first model to the first processing solution is triggered.

[0207] For another example, if the improvement of the signal-to-noise ratio of the signal meets certain conditions, switching from the first model to the first processing solution is triggered.

[0208] For another example, if the decrease in the signal-to-noise ratio of the signal meets certain conditions, switching from the first model to the first processing solution is triggered.

[0209] For another example, if the terminal device moves from indoors to outdoors, switching from the first model to the first processing solution is triggered.

[0210] For another example, if the terminal device moves from outdoors to indoors, switching from the first model to the first processing solution is triggered.

[0211] For another example, if the moving speed of the terminal device changes from a low speed to a high speed, the switch from the first model to the first processing solution is triggered.

[0212] For another example, if the moving speed of the terminal device changes from high speed to low speed, the switch from the first model to the first processing solution is triggered.

[0213] Whether the first condition is satisfied can be monitored by the terminal device or by the network device. The monitoring process can be periodic or aperiodic. Alternatively, the monitoring method can be configured by the network device, such as semi-statically configuring the monitoring method.

[0214] To facilitate understanding, two more specific examples are given below in conjunction with FIG. 10 and FIG. 11 .

[0215] FIG10 is a flow chart of a network device monitoring whether the first condition is satisfied.

[0216] 10, in step S1010, the terminal device receives first configuration information sent by the network device. Detailed description of the first configuration information can be found in Example 2.

[0217] In step S1020, the terminal device configures the uplink transmission mode using the first configuration information.

[0218] In step S1030 , the network device detects the first model to determine whether a first condition is satisfied.

[0219] In step S1040, when the first condition is met, the network device sends first switching information to the terminal device. The first switching information is used to instruct the first model to switch to the first processing solution.

[0220] FIG11 is a flow chart showing a terminal device monitoring whether the first condition is satisfied.

[0221] 11 , in step S1110 , the terminal device receives first configuration information sent by the network device. Detailed description of the first configuration information can be found in Example 2.

[0222] In step S1120, the terminal device configures the uplink transmission mode using the first configuration information.

[0223] In step S1130 , the terminal device detects the first model to determine whether the first condition is met.

[0224] In step S1140, when the first condition is met, the terminal device sends first switching information to the network device. The first switching information is used to instruct the first model to switch to the first processing solution.

[0225] In some implementations, the switch from the first model to the first processing solution can be triggered based on a first timer. For example, after the terminal device receives the first configuration information, the first model can be activated. When starting uplink transmission based on the first model, the terminal device can start a first timer. When the first timer decrements to zero, it automatically switches to the first processing solution. Furthermore, in some implementations, the first timer can run synchronously on the network device side, so that the network device can synchronously switch to the first processing solution without the need for reporting or instructions from the terminal device.

[0226] It should be noted that the number of resources mentioned in any of the foregoing embodiments (such as the number of first resources and the number of second resources) may be the number of resources in units of RE, or may be the number of resources in units of other frequency domain units.

[0227] It should also be noted that the output sequence of the first model mentioned in any of the above embodiments may refer to the symbol sequence output by the first model. The sequence length of the output sequence of the first model may be understood as the sequence length of the symbol sequence, that is, the number of symbols contained in the symbol sequence.

[0228] It should also be noted that the process of determining the sequence length of the output sequence of the first model mentioned in Example 1 can also be understood as the process of determining the first model, that is, output sequences of different lengths can correspond to different models.

[0229] The method embodiment of the present application is described in detail above in conjunction with Figures 1 to 11. The device embodiment of the present application is described in detail below in conjunction with Figures 12 to 14. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment. Therefore, for parts not described in detail, reference can be made to the above method embodiment.

[0230] Figure 12 is a structural diagram of a terminal device provided in an embodiment of the present application. The terminal device 1200 in Figure 12 can execute the steps performed by the terminal device in any of the preceding embodiments. The terminal device 1200 may include a communication unit 1210. The communication unit 1210 is used to send a first channel. The first channel is used to carry UCI, the UCI includes CSI, the first channel includes a first resource and a second resource, the first resource is used to carry a first part of the information in the CSI, the second resource is used to carry a second part of the information in the CSI, and the second part of the information is determined based on the output sequence of the first model.

[0231] In some implementations, a sequence length of the output sequence is a first length, and the first length is determined based on a resource quantity of the second resource.

[0232] In some implementations, the value of the first length is less than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

[0233] In some implementations, the value of the first length is a maximum value among candidate lengths of the output sequence that is less than or equal to the first value.

[0234] In some implementations, the value of the first length is greater than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

[0235] In some implementations, the value of the first length is a minimum value among candidate lengths of the output sequence that is greater than or equal to the first value.

[0236] In some implementations, the value of the first length is determined based on configuration information of the network device.

[0237] In some implementations, the configuration information of the network device is used to configure a maximum value of a sequence length of the output sequence, and the maximum value of the sequence length of the output sequence is less than a first value, which is determined based on a resource quantity of the second resource.

[0238] In some implementations, the first resource is also used to carry first information other than the CSI.

[0239] In some implementations, the first information includes one or more of the following:

[0240] HARQ-ACK;

[0241] SR.

[0242] In some implementations, the first channel is a PUCCH, and the amount of the second resource is determined based on one or more of the following:

[0243] the resource quantity of the first resource;

[0244] The number of resources in the first channel used for transmitting the UCI.

[0245] In some implementations, the number of the second resource satisfies the following formula: PUCCH-2 =N PUCCH -N PUCCH-1 ;

[0246] Among them, N PUCCH-2Indicates the number of the second resource, N PUCCH represents the number of resources in the first channel used to transmit the UCI, N PUCCH-1 Indicates the resource quantity of the first resource.

[0247] In some implementations, the first channel is a PUSCH, and the amount of the second resource is determined based on one or more of the following:

[0248] the number of resources in the first channel used to carry a reference signal;

[0249] the resource quantity of the first resource;

[0250] the number of resources reserved for UL-SCH in the first channel;

[0251] The number of resources of the first channel.

[0252] In some implementations, the number of the second resource satisfies the following formula: PUCCH-2 =N PUCCH -N UL-SCH -N PUCCH-1 ;

[0253] Among them, N PUCCH-2 Indicates the number of the second resource, N PUCCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N UL-SCH Indicates the number of resources reserved for UL-SCH in the first channel, N PUCCH-1 Indicates the resource quantity of the first resource.

[0254] In some implementations, the number of the second resource satisfies the following formula: PUCCH-2 =N PUCCH -N PUCCH-1 ;

[0255] Among them, N PUCCH-2 Indicates the number of the second resource, N PUCCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N PUCCH-1 Indicates the resource quantity of the first resource.

[0256] In some implementations, if the second resources include remaining resources other than the resources occupied by the second part of information, the remaining resources in the second resources are used to carry UL-SCH.

[0257] In some implementations, the resource quantity of the first resource is determined based on one or more of the following:

[0258] The amount of resources required by the first part of information;

[0259] The amount of resources required for other information in the UCI except the CSI.

[0260] In some implementations, the communication unit 1210 is further configured to:

[0261] Receive first configuration information sent by a network device, where the first configuration information is used to indicate one or more of the following:

[0262] a transmission method of the UCI;

[0263] Multiplexing method of CSI on PUSCH and UL-SCH;

[0264] Configuration information of the first model.

[0265] In some implementations, the configuration information of the first model is used to indicate one or more of the following:

[0266] a method for determining the sequence length of the output sequence of the first model;

[0267] a candidate length of the output sequence of the first model;

[0268] The maximum length of the output sequence of the first model;

[0269] An adjustment step size for the sequence length of the output sequence of the first model;

[0270] the input format of the first model;

[0271] The generalization ability of the first model.

[0272] In some implementations, the communication unit 1210 is further configured to:

[0273] Send first capability information to a network device, where the first capability information is used to indicate that the first terminal device supports the first configuration information.

[0274] In some implementations, the communication unit 1210 is further configured to:

[0275] Sending second configuration information to the network device, where the second configuration information is used to indicate one or more of the following:

[0276] a candidate length of the output sequence of the first model;

[0277] The maximum length of the output sequence of the first model;

[0278] An adjustment step size for the sequence length of the output sequence of the first model;

[0279] the input format of the first model;

[0280] The generalization ability of the first model.

[0281] In some implementations, the communication unit 1210 is further configured to:

[0282] Send second capability information to the network device, where the second capability information is used to indicate that the first terminal device supports the second configuration information.

[0283] In some implementations, the communication unit 1210 is further configured to:

[0284] Send third capability information to the network device, where the third capability information is used to indicate that the terminal device supports the first model.

[0285] In some implementations, the switching from the first model to the first processing scheme is triggered based on one or more of the following:

[0286] first condition;

[0287] First Timer;

[0288] The first processing scheme is a second model different from the first model or the first processing scheme is a processing scheme not based on a model.

[0289] In some implementations, whether the first condition is met is monitored by the terminal device or the network device.

[0290] In some implementations, the first part of information includes one or more of RI, CQI, and LI.

[0291] In some implementations, the second portion of information includes a PMI.

[0292] In some implementations, the mapping process of the information in the first resource to the first resource includes one or more of the following: code block partitioning, adding CRC, channel coding, rate matching, symbol modulation, and resource mapping.

[0293] In some implementations, the mapping process of the information in the second resource to the second resource includes performing resource mapping on the output sequence of the first model.

[0294] In some implementations, the first model is a source-channel joint coding model based on artificial intelligence (AI).

[0295] Figure 13 is a structural diagram of a network device provided in an embodiment of the present application. The network device 1300 in Figure 13 can be used to execute the steps performed by the network device in any of the foregoing embodiments. The network device 1300 may include a communication unit 1310. The communication unit 1310 is used to receive a first channel sent by a terminal device, the first channel is used to carry UCI, the UCI includes CSI, the first channel includes a first resource and a second resource, the first resource is used to carry a first part of information in the CSI, the second resource is used to carry a second part of information in the CSI, and the second part of information is determined based on the output sequence of the first model.

[0296] In some implementations, a sequence length of the output sequence is a first length, and the first length is determined based on a resource quantity of the second resource.

[0297] In some implementations, the value of the first length is less than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

[0298] In some implementations, the value of the first length is a maximum value among candidate lengths of the output sequence that is less than or equal to the first value.

[0299] In some implementations, the value of the first length is greater than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

[0300] In some implementations, the value of the first length is a minimum value among candidate lengths of the output sequence that is greater than or equal to the first value.

[0301] In some implementations, the value of the first length is determined based on configuration information of the network device.

[0302] In some implementations, the configuration information of the network device is used to configure a maximum value of a sequence length of the output sequence, and the maximum value of the sequence length of the output sequence is less than a first value, which is determined based on a resource quantity of the second resource.

[0303] In some implementations, the first resource is also used to carry first information other than the CSI.

[0304] In some implementations, the first information includes one or more of the following:

[0305] HARQ-ACK;

[0306] SR.

[0307] In some implementations, the first channel is a physical uplink control channel (PUCCH), and the amount of the second resource is determined based on one or more of the following:

[0308] the resource quantity of the first resource;

[0309] The number of resources in the first channel used for transmitting the UCI.

[0310] In some implementations, the number of the second resource satisfies the following formula: PUCCH-2 =N PUCCH -N PUCCH-1 ;

[0311] Among them, N PUCCH-2 Indicates the number of the second resource, N PUCCH represents the number of resources in the first channel used to transmit the UCI, N PUCCH-1 Indicates the resource quantity of the first resource.

[0312] In some implementations, the first channel is a PUSCH, and the amount of the second resource is determined based on one or more of the following:

[0313] the number of resources in the first channel used to carry a reference signal;

[0314] the resource quantity of the first resource;

[0315] the number of resources reserved for UL-SCH in the first channel;

[0316] The number of resources of the first channel.

[0317] In some implementations, the number of the second resource satisfies the following formula: PUCCH-2 =N PUCCH -N UL-SCH -N PUCCH-1 ;

[0318] Among them, N PUCCH-2 Indicates the number of the second resource, N PUCCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N UL-SCH Indicates the number of resources reserved for UL-SCH in the first channel, N PUCCH-1 Indicates the resource quantity of the first resource.

[0319] In some implementations, the number of the second resource satisfies the following formula: PUCCH-2 =N PUCCH -N PUCCH-1 ;

[0320] Among them, N PUCCH-2 Indicates the number of the second resource, N PUCCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N PUCCH-1 Indicates the resource quantity of the first resource.

[0321] In some implementations, if the second resources include remaining resources other than the resources occupied by the second part of information, the remaining resources in the second resources are used to carry UL-SCH.

[0322] In some implementations, the resource quantity of the first resource is determined based on one or more of the following:

[0323] The amount of resources required by the first part of information;

[0324] The amount of resources required for other information in the UCI except the CSI.

[0325] In some implementations, the communication unit 1310 is further configured to:

[0326] Sending first configuration information to the terminal device, where the first configuration information is used to indicate one or more of the following:

[0327] a transmission method of the UCI;

[0328] Multiplexing method of CSI on PUSCH and UL-SCH;

[0329] Configuration information of the first model.

[0330] In some implementations, the configuration information of the first model is used to indicate one or more of the following:

[0331] a method for determining the sequence length of the output sequence of the first model;

[0332] a candidate length of the output sequence of the first model;

[0333] The maximum length of the output sequence of the first model;

[0334] An adjustment step size for the sequence length of the output sequence of the first model;

[0335] the input format of the first model;

[0336] The generalization ability of the first model.

[0337] In some implementations, the communication unit 1310 is further configured to:

[0338] Receive first capability information sent by the terminal device, where the first capability information is used to indicate that the first terminal device supports the first configuration information.

[0339] In some implementations, the communication unit 1310 is further configured to:

[0340] Receive second configuration information sent by the terminal device, where the second configuration information is used to indicate one or more of the following:

[0341] a candidate length of the output sequence of the first model;

[0342] The maximum length of the output sequence of the first model;

[0343] An adjustment step size for the sequence length of the output sequence of the first model;

[0344] the input format of the first model;

[0345] The generalization ability of the first model.

[0346] In some implementations, the communication unit 1310 is further configured to:

[0347] Receive second capability information sent by the terminal device, where the second capability information is used to indicate that the first terminal device supports the second configuration information.

[0348] In some implementations, the communication unit 1310 is further configured to:

[0349] Receive third capability information sent by the terminal device, where the third capability information is used to indicate that the terminal device supports the first model.

[0350] In some implementations, the switching from the first model to the first processing scheme is triggered based on one or more of the following:

[0351] first condition;

[0352] First Timer;

[0353] The first processing scheme is a second model different from the first model or the first processing scheme is a processing scheme not based on a model.

[0354] In some implementations, whether the first condition is met is monitored by the terminal device or the network device.

[0355] In some implementations, the first part of information includes one or more of RI, CQI, and LI.

[0356] In some implementations, the second portion of information includes a PMI.

[0357] In some implementations, the first model is an AI-based source-channel joint coding model.

[0358] FIG14 is a schematic block diagram of an apparatus according to an embodiment of the present application. The dashed lines in FIG14 indicate that the unit or module is optional. Apparatus 1400 may be used to implement the method described in the above method embodiment. Apparatus 1400 may be a chip, a terminal device, or a network device.

[0359] The device 1400 may include one or more processors 1410. The processor 1410 may support the device 1400 to implement the method described in the method embodiment above. The processor 1410 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0360] The apparatus 1400 may further include one or more memories 1420. The memories 1420 store programs that can be executed by the processor 1410, causing the processor 1410 to perform the methods described in the above method embodiments. The memories 1420 may be independent of the processor 1410 or integrated into the processor 1410.

[0361] The apparatus 1400 may further include a transceiver 1430. The processor 1410 may communicate with other devices or chips via the transceiver 1430. For example, the processor 1410 may transmit and receive data with other devices or chips via the transceiver 1430.

[0362] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to the communication device provided in the present application, and the program enables a computer to execute the method performed by the terminal device or network device in each embodiment of the present application.

[0363] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to the communication device provided in the present application, and the program causes a computer to execute the method performed by the terminal device or network device in each embodiment of the present application.

[0364] The present application also provides a computer program that can be applied to the communication device provided in the present application and enables a computer to execute the method performed by the terminal device or network device in each embodiment of the present application.

[0365] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application. The terms "first", "second", "third", and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0366] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0367] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0368] In the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and indication, configuration and configuration, etc.

[0369] In the embodiments of the present application, "pre-definition" or "pre-configuration" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device and a network device). The present application does not limit the specific implementation method. For example, pre-definition may refer to information defined in a protocol.

[0370] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0371] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0372] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0373] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0374] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0375] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0376] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0377] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An uplink transmission method, It is characterized in that include: The terminal device sends a first channel, where the first channel is used to carry uplink control information UCI, where the UCI includes channel state information CSI, and the first channel includes a first resource and a second resource, where the first resource is used to carry a first part of information in the CSI, and the second resource is used to carry a second part of information in the CSI, where the second part of information is determined based on an output sequence of the first model.

2. The method according to claim 1, It is characterized in that The sequence length of the output sequence is a first length, and the first length is determined based on the resource quantity of the second resource.

3. The method according to claim 2, It is characterized in that The value of the first length is less than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

4. The method according to claim 3, It is characterized in that The value of the first length is a maximum value among the candidate lengths of the output sequence that is less than or equal to the first value.

5. The method according to claim 2, It is characterized in that The value of the first length is greater than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

6. The method according to claim 5, It is characterized in that The value of the first length is a minimum value of candidate lengths of the output sequence that is greater than or equal to the first value.

7. The method according to claim 2, It is characterized in that The value of the first length is determined based on configuration information of the network device.

8. The method according to claim 7, It is characterized in that The configuration information of the network device is used to configure a maximum value of a sequence length of the output sequence, and the maximum value of the sequence length of the output sequence is less than a first value, and the first value is determined based on a resource quantity of the second resource.

9. The method according to any one of claims 1 to 8, It is characterized in that The first resource is also used to carry first information other than the CSI.

10. The method according to claim 9, It is characterized in that The first information includes one or more of the following: Hybrid Automatic Repeat Request-Acknowledgement HARQ-ACK; Scheduling request SR.

11. The method according to any one of claims 1 to 10, It is characterized in that The first channel is a physical uplink control channel PUCCH, and the resource quantity of the second resource is determined based on one or more of the following: the resource quantity of the first resource; The number of resources in the first channel used to transmit the UCI.

12. The method according to claim 11, It is characterized in that The number of the second resource satisfies the following formula: N PUCCH-2 =N PUCCH -N PUCCH-1 ; Among them, N PUCCH-2 Indicates the number of resources of the second resource, N PUCCH represents the number of resources in the first channel used to transmit the UCI, N PUCCH-1 Indicates the resource quantity of the first resource.

13. The method according to any one of claims 1 to 10, It is characterized in that The first channel is a physical uplink shared channel PUSCH, and the resource quantity of the second resource is determined based on one or more of the following: The number of resources in the first channel used to carry a reference signal; the resource quantity of the first resource; The number of resources reserved for an uplink shared channel UL-SCH in the first channel; The number of resources of the first channel.

14. The method according to claim 13, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N UL-SCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N UL-SCH represents the number of resources reserved for UL-SCH in the first channel, N PUSCH-1 Indicates the resource quantity of the first resource.

15. The method according to claim 13, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N PUSCH-1 Indicates the resource quantity of the first resource.

16. The method according to any one of claims 11 to 15, It is characterized in that If the second resources include remaining resources except the resources occupied by the second part of information, the remaining resources in the second resources are used to carry UL-SCH.

17. The method according to any one of claims 11 to 16, It is characterized in that The resource quantity of the first resource is determined based on one or more of the following: The amount of resources required by the first part of information; The amount of resources required to be occupied by other information in the UCI except the CSI.

18. The method according to any one of claims 1 to 17, It is characterized in that The method further comprises: The terminal device receives first configuration information sent by the network device, where the first configuration information is used to indicate one or more of the following: a transmission method of the UCI; Multiplexing method of CSI on PUSCH and UL-SCH; Configuration information of the first model.

19. The method according to claim 18, It is characterized in that The configuration information of the first model is used to indicate one or more of the following: A method for determining the sequence length of the output sequence of the first model; a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

20. The method according to claim 18 or 19, It is characterized in that The method further comprises: The terminal device sends first capability information to the network device, where the first capability information is used to indicate that the first terminal device supports the first configuration information.

21. The method according to any one of claims 1 to 17, It is characterized in that The method further comprises: The terminal device sends second configuration information to the network device, where the second configuration information is used to indicate one or more of the following: a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

22. The method according to claim 21, It is characterized in that The method further comprises: The terminal device sends second capability information to the network device, where the second capability information is used to indicate that the first terminal device supports the second configuration information.

23. The method according to any one of claims 1 to 22, It is characterized in that The method further comprises: The terminal device sends third capability information to the network device, where the third capability information is used to indicate that the terminal device supports the first model.

24. The method according to any one of claims 1 to 23, It is characterized in that The switching from the first model to the first processing scheme is triggered based on one or more of the following: first condition; First timer; The first processing scheme is a second model different from the first model or the first processing scheme is a processing scheme not based on a model.

25. The method according to claim 24, It is characterized in that Whether the first condition is met is monitored by the terminal device or the network device.

26. The method according to any one of claims 1 to 25, It is characterized in that The first part of information includes one or more of a rank indication RI, a channel quality indication CQI, and a layer indication LI.

27. The method according to any one of claims 1 to 26, It is characterized in that The second part of information includes a precoding matrix indicator PMI.

28. The method according to any one of claims 1 to 27, It is characterized in that The mapping process of the information in the first resource to the first resource includes one or more of the following: code block division, adding cyclic redundancy check CRC, channel coding, rate matching, symbol modulation and resource mapping.

29. The method according to any one of claims 1 to 28, It is characterized in that The mapping process of the information in the second resource to the second resource includes performing resource mapping on the output sequence of the first model.

30. The method according to any one of claims 1 to 29, It is characterized in that The first model is a source-channel joint coding model based on artificial intelligence AI.

31. An uplink transmission method, It is characterized in that include: A network device receives a first channel sent by a terminal device, where the first channel is used to carry uplink control information UCI, where the UCI includes channel state information CSI, and the first channel includes a first resource and a second resource, where the first resource is used to carry a first part of information in the CSI, and the second resource is used to carry a second part of information in the CSI, where the second part of information is determined based on an output sequence of the first model.

32. The method according to claim 31, It is characterized in that The sequence length of the output sequence is a first length, and the first length is determined based on the resource quantity of the second resource.

33. The method according to claim 32, It is characterized in that The value of the first length is less than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

34. The method according to claim 33, It is characterized in that The value of the first length is a maximum value among the candidate lengths of the output sequence that is less than or equal to the first value.

35. The method according to claim 32, It is characterized in that The value of the first length is greater than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

36. The method according to claim 35, It is characterized in that The value of the first length is a minimum value of candidate lengths of the output sequence that is greater than or equal to the first value.

37. The method according to claim 32, It is characterized in that The value of the first length is determined based on configuration information of the network device.

38. The method according to claim 37, It is characterized in that The configuration information of the network device is used to configure a maximum value of a sequence length of the output sequence, and the maximum value of the sequence length of the output sequence is less than a first value, and the first value is determined based on a resource quantity of the second resource.

39. The method according to any one of claims 31 to 38, It is characterized in that The first resource is also used to carry first information other than the CSI.

40. The method according to claim 39, It is characterized in that The first information includes one or more of the following: Hybrid Automatic Repeat Request-Acknowledgement HARQ-ACK; Scheduling request SR.

41. The method according to any one of claims 31 to 40, It is characterized in that The first channel is a physical uplink control channel PUCCH, and the resource quantity of the second resource is determined based on one or more of the following: the resource quantity of the first resource; The number of resources in the first channel used to transmit the UCI.

42. The method according to claim 41, It is characterized in that The number of the second resource satisfies the following formula: N PUCCH-2 =N PUCCH -N PUCCH-1 ; Among them, N PUCCH-2 Indicates the number of resources of the second resource, N PUCCH represents the number of resources in the first channel used to transmit the UCI, N PUCCH-1 Indicates the resource quantity of the first resource.

43. The method according to any one of claims 31 to 40, It is characterized in that The first channel is a physical uplink shared channel PUSCH, and the resource quantity of the second resource is determined based on one or more of the following: The number of resources in the first channel used to carry a reference signal; the resource quantity of the first resource; The number of resources reserved for an uplink shared channel UL-SCH in the first channel; The number of resources of the first channel.

44. The method according to claim 43, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N UL-SCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N UL-SCH represents the number of resources reserved for UL-SCH in the first channel, N PUSCH-1 Indicates the resource quantity of the first resource.

45. The method according to claim 43, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N PUSCH-1 Indicates the resource quantity of the first resource.

46. ​​The method according to any one of claims 41 to 45, It is characterized in that If the second resources include remaining resources except the resources occupied by the second part of information, the remaining resources in the second resources are used to carry UL-SCH.

47. The method according to any one of claims 41 to 46, It is characterized in that The resource quantity of the first resource is determined based on one or more of the following: The amount of resources required by the first part of information; The amount of resources required to be occupied by other information in the UCI except the CSI.

48. A method according to any one of claims 31 to 47, It is characterized in that The method further comprises: The network device sends first configuration information to the terminal device, where the first configuration information is used to indicate one or more of the following: a transmission method of the UCI; Multiplexing method of CSI on PUSCH and UL-SCH; Configuration information of the first model.

49. The method according to claim 48, It is characterized in that The configuration information of the first model is used to indicate one or more of the following: A method for determining the sequence length of the output sequence of the first model; a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

50. The method according to claim 48 or 49, It is characterized in that The method further comprises: The network device receives first capability information sent by the terminal device, where the first capability information is used to indicate that the first terminal device supports the first configuration information.

51. The method according to any one of claims 31 to 47, It is characterized in that The method further comprises: The network device receives second configuration information sent by the terminal device, where the second configuration information is used to indicate one or more of the following: a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

52. The method according to claim 51, It is characterized in that The method further comprises: The network device receives second capability information sent by the terminal device, where the second capability information is used to indicate that the first terminal device supports the second configuration information.

53. The method according to any one of claims 31 to 52, It is characterized in that The method further comprises: The network device receives third capability information sent by the terminal device, where the third capability information is used to indicate that the terminal device supports the first model.

54. The method according to any one of claims 31 to 53, It is characterized in that The switching from the first model to the first processing scheme is triggered based on one or more of the following: first condition; First timer; The first processing scheme is a second model different from the first model or the first processing scheme is a processing scheme not based on a model.

55. The method according to claim 54, It is characterized in that Whether the first condition is satisfied is monitored by the terminal device or the network device.

56. The method according to any one of claims 31 to 55, It is characterized in that The first part of information includes one or more of a rank indication RI, a channel quality indication CQI, and a layer indication LI.

57. The method according to any one of claims 31 to 56, It is characterized in that The second part of information includes a precoding matrix indicator PMI.

58. The method according to any one of claims 31 to 57, It is characterized in that The first model is a source-channel joint coding model based on artificial intelligence AI.

59. A terminal device, It is characterized in that include: A communication unit is used to send a first channel, where the first channel is used to carry uplink control information UCI, where the UCI includes channel state information CSI, and the first channel includes a first resource and a second resource, where the first resource is used to carry a first part of information in the CSI, and the second resource is used to carry a second part of information in the CSI, where the second part of information is determined based on an output sequence of a first model.

60. The terminal device according to claim 59, It is characterized in that The sequence length of the output sequence is a first length, and the first length is determined based on the resource quantity of the second resource.

61. The terminal device according to claim 60, It is characterized in that The value of the first length is less than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

62. The terminal device according to claim 61, It is characterized in that The value of the first length is a maximum value among the candidate lengths of the output sequence that is less than or equal to the first value.

63. The terminal device according to claim 60, It is characterized in that The value of the first length is greater than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

64. The terminal device according to claim 63, It is characterized in that The value of the first length is a minimum value of candidate lengths of the output sequence that is greater than or equal to the first value.

65. The terminal device according to claim 60, It is characterized in that The value of the first length is determined based on configuration information of the network device.

66. The terminal device according to claim 65, It is characterized in that The configuration information of the network device is used to configure a maximum value of a sequence length of the output sequence, and the maximum value of the sequence length of the output sequence is less than a first value, and the first value is determined based on a resource quantity of the second resource.

67. The terminal device according to any one of claims 59 to 66, It is characterized in that The first resource is also used to carry first information other than the CSI.

68. The terminal device according to claim 67, It is characterized in that The first information includes one or more of the following: Hybrid Automatic Repeat Request-Acknowledgement HARQ-ACK; Scheduling request SR.

69. The terminal device according to any one of claims 59 to 68, It is characterized in that The first channel is a physical uplink control channel PUCCH, and the resource quantity of the second resource is determined based on one or more of the following: the resource quantity of the first resource; The number of resources in the first channel used to transmit the UCI.

70. The terminal device according to claim 69, It is characterized in that The number of the second resource satisfies the following formula: N PUCCH-2 =N PUCCH -N PUCCH-1 ; Among them, N PUCCH-2 Indicates the number of resources of the second resource, N PUCCH represents the number of resources in the first channel used to transmit the UCI, N PUCCH-1 Indicates the resource quantity of the first resource.

71. The terminal device according to any one of claims 59 to 68, It is characterized in that The first channel is a physical uplink shared channel PUSCH, and the resource quantity of the second resource is determined based on one or more of the following: The number of resources in the first channel used to carry a reference signal; the resource quantity of the first resource; The number of resources reserved for an uplink shared channel UL-SCH in the first channel; The number of resources of the first channel.

72. The terminal device according to claim 71, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N UL-SCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N UL-SCH represents the number of resources reserved for UL-SCH in the first channel, N PUSCH-1 Indicates the resource quantity of the first resource.

73. The terminal device according to claim 71, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N PUSCH-1 Indicates the resource quantity of the first resource.

74. The terminal device according to any one of claims 69 to 73, It is characterized in that If the second resources include remaining resources except the resources occupied by the second part of information, the remaining resources in the second resources are used to carry UL-SCH.

75. The terminal device according to any one of claims 69 to 74, It is characterized in that The resource quantity of the first resource is determined based on one or more of the following: The amount of resources required by the first part of information; The amount of resources required to be occupied by other information in the UCI except the CSI.

76. The terminal device according to any one of claims 59 to 75, It is characterized in that The communication unit is also used for: Receive first configuration information sent by a network device, where the first configuration information is used to indicate one or more of the following: a transmission method of the UCI; Multiplexing method of CSI on PUSCH and UL-SCH; Configuration information of the first model.

77. The terminal device according to claim 76, It is characterized in that The configuration information of the first model is used to indicate one or more of the following: A method for determining the sequence length of the output sequence of the first model; a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

78. The terminal device according to claim 76 or 77, It is characterized in that The communication unit is also used for: Sending first capability information to a network device, where the first capability information is used to indicate that the first terminal device supports the first configuration information.

79. The terminal device according to any one of claims 59 to 75, It is characterized in that The communication unit is also used for: Sending second configuration information to the network device, where the second configuration information is used to indicate one or more of the following: a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

80. The terminal device according to claim 79, It is characterized in that The communication unit is also used for: Sending second capability information to the network device, where the second capability information is used to indicate that the first terminal device supports the second configuration information.

81. The terminal device according to any one of claims 59 to 80, It is characterized in that The communication unit is also used for: Send third capability information to the network device, where the third capability information is used to indicate that the terminal device supports the first model.

82. The terminal device according to any one of claims 59 to 81, It is characterized in that The switching from the first model to the first processing scheme is triggered based on one or more of the following: first condition; First timer; The first processing scheme is a second model different from the first model or the first processing scheme is a processing scheme not based on a model.

83. The terminal device according to claim 82, It is characterized in that Whether the first condition is met is monitored by the terminal device or the network device.

84. The terminal device according to any one of claims 59 to 83, It is characterized in that The first part of information includes one or more of a rank indication RI, a channel quality indication CQI, and a layer indication LI.

85. The terminal device according to any one of claims 59 to 84, It is characterized in that The second part of information includes a precoding matrix indicator PMI.

86. The terminal device according to any one of claims 59 to 85, It is characterized in that The mapping process of the information in the first resource to the first resource includes one or more of the following: code block division, adding cyclic redundancy check CRC, channel coding, rate matching, symbol modulation and resource mapping.

87. The terminal device according to any one of claims 59 to 86, It is characterized in that The mapping process of the information in the second resource to the second resource includes performing resource mapping on the output sequence of the first model.

88. The terminal device according to any one of claims 59 to 87, It is characterized in that The first model is a source-channel joint coding model based on artificial intelligence AI.

89. A network device, It is characterized in that include: A communication unit is used to receive a first channel sent by a terminal device, where the first channel is used to carry uplink control information UCI, where the UCI includes channel state information CSI, and the first channel includes a first resource and a second resource, where the first resource is used to carry a first part of information in the CSI, and the second resource is used to carry a second part of information in the CSI, where the second part of information is determined based on an output sequence of a first model.

90. The network device according to claim 89, It is characterized in that The sequence length of the output sequence is a first length, and the first length is determined based on the resource quantity of the second resource.

91. The network device according to claim 90, It is characterized in that The value of the first length is less than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

92. The network device according to claim 91, It is characterized in that The value of the first length is a maximum value among the candidate lengths of the output sequence that is less than or equal to the first value.

93. The network device according to claim 90, It is characterized in that The value of the first length is greater than or equal to a first value, and the first value is determined based on the resource quantity of the second resource.

94. The network device according to claim 93, It is characterized in that The value of the first length is a minimum value of candidate lengths of the output sequence that is greater than or equal to the first value.

95. The network device according to claim 90, It is characterized in that The value of the first length is determined based on configuration information of the network device.

96. The network device according to claim 95, It is characterized in that The configuration information of the network device is used to configure a maximum value of a sequence length of the output sequence, and the maximum value of the sequence length of the output sequence is less than a first value, and the first value is determined based on a resource quantity of the second resource.

97. The network device according to any one of claims 89 to 96, It is characterized in that The first resource is also used to carry first information other than the CSI.

98. The network device according to claim 97, It is characterized in that The first information includes one or more of the following: Hybrid Automatic Repeat Request-Acknowledgement HARQ-ACK; Scheduling request SR.

99. The network device according to any one of claims 89 to 98, It is characterized in that The first channel is a physical uplink control channel PUCCH, and the resource quantity of the second resource is determined based on one or more of the following: the resource quantity of the first resource; The number of resources in the first channel used to transmit the UCI.

100. The network device according to claim 99, It is characterized in that The number of the second resource satisfies the following formula: N PUCCH-2 =N PUCCH -N PUCCH-1 ; Among them, N PUCCH-2 Indicates the number of resources of the second resource, N PUCCH represents the number of resources in the first channel used to transmit the UCI, N PUCCH-1 Indicates the resource quantity of the first resource.

101. The network device according to any one of claims 89 to 98, It is characterized in that The first channel is a physical uplink shared channel PUSCH, and the resource quantity of the second resource is determined based on one or more of the following: The number of resources in the first channel used to carry a reference signal; the resource quantity of the first resource; The number of resources reserved for an uplink shared channel UL-SCH in the first channel; The number of resources of the first channel.

102. The network device according to claim 101, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N UL-SCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N UL-SCH represents the number of resources reserved for UL-SCH in the first channel, N PUSCH-1 Indicates the resource quantity of the first resource.

103. The network device according to claim 101, It is characterized in that The number of the second resource satisfies the following formula: N PUSCH-2 =N PUSCH -N PUSCH-1 ; Among them, N PUSCH-2 Indicates the number of resources of the second resource, N PUSCH represents the number of remaining resources in the first channel except for the resources used to carry the reference signal, N PUSCH-1 Indicates the resource quantity of the first resource.

104. The network device according to any one of claims 99 to 103, It is characterized in that If the second resources include remaining resources except the resources occupied by the second part of information, the remaining resources in the second resources are used to carry UL-SCH.

105. The network device according to any one of claims 99 to 104, It is characterized in that The resource quantity of the first resource is determined based on one or more of the following: The amount of resources required by the first part of information; The amount of resources required to be occupied by other information in the UCI except the CSI.

106. The network device according to any one of claims 89 to 105, It is characterized in that The communication unit is also used for: Sending first configuration information to the terminal device, where the first configuration information is used to indicate one or more of the following: a transmission method of the UCI; Multiplexing method of CSI on PUSCH and UL-SCH; Configuration information of the first model.

107. The network device according to claim 106, It is characterized in that The configuration information of the first model is used to indicate one or more of the following: A method for determining the sequence length of the output sequence of the first model; a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

108. The network device according to claim 106 or 107, It is characterized in that The communication unit is also used for: Receive first capability information sent by the terminal device, where the first capability information is used to indicate that the first terminal device supports the first configuration information.

109. The network device according to any one of claims 89 to 105, It is characterized in that The communication unit is also used for: Receive second configuration information sent by the terminal device, where the second configuration information is used to indicate one or more of the following: a candidate length of the output sequence of the first model; The maximum length of the output sequence of the first model; An adjustment step size of the sequence length of the output sequence of the first model; an input format of the first model; The generalization ability of the first model.

110. The network device according to claim 109, It is characterized in that The communication unit is also used for: Receive second capability information sent by the terminal device, where the second capability information is used to indicate that the first terminal device supports the second configuration information.

111. The network device according to any one of claims 89 to 110, It is characterized in that The communication unit is also used for: Receive third capability information sent by the terminal device, where the third capability information is used to indicate that the terminal device supports the first model.

112. The network device according to any one of claims 89 to 111, It is characterized in that The switching from the first model to the first processing scheme is triggered based on one or more of the following: first condition; First timer; The first processing scheme is a second model different from the first model or the first processing scheme is a processing scheme not based on a model.

113. The network device according to claim 112, It is characterized in that Whether the first condition is satisfied is monitored by the terminal device or the network device.

114. The network device according to any one of claims 89 to 113, It is characterized in that The first part of information includes one or more of a rank indication RI, a channel quality indication CQI, and a layer indication LI.

115. The network device according to any one of claims 89 to 114, It is characterized in that The second part of information includes a precoding matrix indicator PMI.

116. The network device according to any one of claims 89 to 115, It is characterized in that The first model is a source-channel joint coding model based on artificial intelligence AI.

117. A terminal device, It is characterized in that It comprises a transceiver, a memory and a processor, wherein the memory is used to store programs, and the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the terminal device executes the method as described in any one of claims 1 to 30.

118. A network device, It is characterized in that It comprises a transceiver, a memory and a processor, wherein the memory is used to store programs, and the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the network device executes the method as described in any one of claims 31 to 58.

119. A device, It is characterized in that It comprises a processor, which is used to call a program from a memory so that the apparatus executes the method as claimed in any one of claims 1 to 30, or 31 to 58.

120. A chip, It is characterized in that It comprises a processor, which is used to call a program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 30, or 31 to 58.

121. A computer-readable storage medium, It is characterized in that A program is stored thereon, the program causing a computer to execute the method according to any one of claims 1 to 30, or 31 to 58.

122. A computer program product, It is characterized in that The method comprises a program which causes a computer to execute the method as claimed in any one of claims 1 to 30, or 31 to 58.

123. A computer program, It is characterized in that The computer program enables a computer to execute the method according to any one of claims 1 to 30, or 31 to 58.

Images