Channel state information processing method, and communication device

Abstract

The present application relates to a channel state information (CSI) processing method, and a communication device. The method comprises: a first communication device receiving first indication information, wherein the first indication information is used for indicating that the first communication device performs joint encoding on CSI; and the first communication device performing joint encoding on the CSI. In the embodiments of the present application, by means of performing joint encoding on CSI, the transmission performance of the CSI can be improved.

Description

Channel state information processing methods and communication equipment Technical Field

[0001] This application relates to the field of communications, and more specifically, to a channel state information processing method and a communication device. Background Technology

[0002] In traditional grammar communication systems, source coding and channel coding are separate. Feedback methods for Channel State Information (CSI) in communication systems typically assume that the CSI reporting process is error-free. However, in real-world communication systems, the ideal assumption of uplink CSI cannot be achieved, and rapid channel changes can negatively impact downlink transmission performance.

[0003] Summary of the Invention

[0004] This application provides a channel state information processing method and a communication device, which can improve CSI transmission performance.

[0005] This application provides a channel state information processing method, including:

[0006] The first communication device receives a first indication information, which instructs the first communication device to perform joint encoding of Channel State Information (CSI).

[0007] The first communication device performs joint encoding of the CSI.

[0008] This application provides a channel state information processing method, including:

[0009] The second communication device sends a first instruction message, which instructs the first communication device to perform joint encoding of CSI.

[0010] This application provides a first communication device, including:

[0011] A first receiving unit is configured to receive first indication information, which instructs the first communication device to perform joint encoding of CSI.

[0012] The processing unit is used to perform joint encoding on the CSI.

[0013] This application provides a second communication device, including:

[0014] The first transmitting unit is configured to transmit first indication information, which instructs the first communication device to perform joint encoding of CSI.

[0015] This application provides a communication device, including a transceiver, a processor, and a memory. The memory stores a computer program, the transceiver communicates with other devices, and the processor calls and runs the computer program stored in the memory to enable the communication device to perform the channel state information processing method described above.

[0016] This application provides a chip for implementing the channel state information processing method described above.

[0017] Specifically, the chip includes a processor for calling and running a computer program from a memory, causing a device equipped with the chip to perform the aforementioned channel state information processing method.

[0018] This application provides a computer-readable storage medium for storing a computer program, which, when run by a device, causes the device to execute the aforementioned channel state information processing method.

[0019] This application provides a computer program product, including computer program instructions that cause a computer to execute the channel state information processing method described above.

[0020] This application provides a computer program that, when run on a computer, causes the computer to execute the aforementioned channel state information processing method.

[0021] In this embodiment of the application, CSI transmission performance can be improved by jointly encoding CSI. Attached Figure Description

[0022] Figure 1 is a schematic diagram of an application scenario according to an embodiment of this application.

[0023] Figure 2 is a schematic diagram of the AI-based CSI autoencoder framework.

[0024] Figure 3 is a schematic diagram of AI-based spatial-frequency-time joint CSI compressed feedback.

[0025] Figure 4 is a schematic diagram of AI-based joint CSI prediction and compression.

[0026] Figure 5 is a schematic diagram of the first working method of CSI feedback in source-channel joint coding.

[0027] Figure 6 is a schematic diagram of the second working method of CSI feedback in source-channel joint coding.

[0028] Figure 7 is a schematic flowchart of a channel state information processing method according to an embodiment of this application.

[0029] Figure 8 is a schematic flowchart of a channel state information processing method according to another embodiment of this application.

[0030] Figure 9 is a schematic flowchart of a channel state information processing method according to another embodiment of this application.

[0031] Figure 10 is a schematic flowchart of a channel state information processing method according to another embodiment of this application.

[0032] Figure 11 is a schematic flowchart of a channel state information processing method according to an embodiment of this application.

[0033] Figure 12 is a schematic flowchart of a channel state information processing method according to another embodiment of this application.

[0034] Figure 13 is a schematic flowchart of a channel state information processing method according to another embodiment of this application.

[0035] Figure 14 is a schematic flowchart of a channel state information processing method according to another embodiment of this application.

[0036] Figure 15 is a flowchart of the configuration method on the user side.

[0037] Figure 16 is a flowchart of the network-side configuration method.

[0038] Figure 17 is a flowchart of a periodic CSI feedback configuration process.

[0039] Figure 18 is a flowchart of the two-step semi-continuous CSI feedback configuration process.

[0040] Figure 19 is a flowchart of a one-step semi-continuous CSI feedback configuration process.

[0041] Figure 20 is a flowchart of the non-periodic CSI feedback configuration method.

[0042] Figure 21 is a schematic block diagram of a first communication device according to an embodiment of the present application.

[0043] Figure 22 is a schematic flowchart of a first communication device according to another embodiment of this application.

[0044] Figure 23 is a schematic block diagram of a second communication device according to an embodiment of the present application.

[0045] Figure 24 is a schematic flowchart of a second communication device according to another embodiment of this application.

[0046] Figure 25 is a schematic block diagram of a communication device according to an embodiment of this application.

[0047] Figure 26 is a schematic block diagram of a chip according to an embodiment of this application.

[0048] Figure 27 is a schematic block diagram of a communication system according to an embodiment of this application. Detailed Implementation

[0049] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0050] The technical solutions of this application embodiment can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, Advanced Long Term Evolution (LTE-A) systems, New Radio (NR) systems, evolution systems of NR systems, LTE-based access to unlicensed spectrum (LTE-U) systems, NR-based access to unlicensed spectrum (NR-U) systems, Non-Terrestrial Networks (NTN) systems, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), 5th-Generation (5G) systems, or other communication systems.

[0051] Traditional communication systems typically support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication but also, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to these communication systems.

[0052] In one implementation, the communication system in this application embodiment can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) network deployment scenario.

[0053] In one embodiment, the communication system in this application can be applied to unlicensed spectrum, wherein the unlicensed spectrum can also be considered as shared spectrum; or, the communication system in this application can also be applied to licensed spectrum, wherein the licensed spectrum can also be considered as non-shared spectrum.

[0054] This application describes various embodiments in conjunction with network devices and terminal devices. The terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device, etc.

[0055] Terminal devices can be stations (STAION, ST) in WLANs, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistant (PDA) devices, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, in-vehicle devices, wearable devices, terminal devices in next-generation communication systems such as NR networks, or terminal devices in future evolved Public Land Mobile Network (PLMN) networks, etc.

[0056] In the embodiments of this application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships); and it can also be deployed in the air (such as airplanes, balloons and satellites).

[0057] In the embodiments of this application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical care, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0058] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0059] In the embodiments of this application, the network device can be a device for communicating with mobile devices, such as an access point (AP) in a WLAN, an evolved Node B (eNB or eNodeB) in LTE, a relay station or access point, or a vehicle-mounted device, a wearable device, a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or an NTN network, etc.

[0060] By way of example and not limitation, in this embodiment, the network device may have mobility characteristics; for example, the network device may be a mobile device. Optionally, the network device may be a satellite or a balloon station. For example, the satellite may be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station located on land, water, or other similar locations.

[0061] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0062] Figure 1 illustrates an exemplary communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one embodiment, the communication system 100 may include multiple network devices 110, and the coverage area of ​​each network device 110 may include other numbers of terminal devices 120; this embodiment does not limit the scope of the present application.

[0063] In one embodiment, the communication system 100 may also include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which are not limited in this application.

[0064] Network equipment can be further divided into access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks used to communicate with the access network equipment. Access network equipment can be evolved NodeBs (eNBs or e-NodeBs) in Long-Term Evolution (LTE), Next-Generation Radio (NR) (mobile communication system), or Authorized Auxiliary Access Long-Term Evolution (LAA-LTE) systems, such as macro base stations, micro base stations (also called "small base stations"), pico base stations, access points (APs), transmission points (TPs), or new generation Node Bs (gNodeBs).

[0065] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Taking the communication system shown in Figure 1 as an example, the communication device may include network devices and terminal devices with communication functions. The network devices and terminal devices can be specific devices in this application embodiment, which will not be described in detail here. The communication device may also include other devices in the communication system, such as network controllers, mobility management entities, and other network entities. This application embodiment does not limit this.

[0066] It should be understood that the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0067] It should be understood that the term "instruction" mentioned in the embodiments of this application can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0068] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0069] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0070] I. Artificial Intelligence and Semantic Communication

[0071] Artificial intelligence (AI) technology, relying on the development of different types of neural networks and deep learning algorithms, has already achieved widespread application in various fields such as image, speech, and video processing. Typical neural network architectures include fully connected networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer structures with self-attention mechanisms, which can accomplish different task objectives. Drawing on the rapid development of AI technology, the combination of artificial intelligence and wireless communication technology has also attracted widespread interest from academia and industry. In the discussions of the 18th (Release 18) and 19th (Release 19) versions of the 3rd Generation Partnership Project (3GPP), extensive research, evaluation, and standardization work were carried out on AI-based channel state information (CSI) feedback, beam management, and positioning technologies.

[0072] Furthermore, with the development of future wireless communication systems and the integration of AI technology, semantic communication technology has received widespread attention in recent years. In contrast, the traditional communication paradigm is called "syntactic communication," which uses traditional information theory methods such as Shannon's formula, information entropy, and the Nyquist sampling theorem to compress source information and then achieve efficient and reliable transmission through channel coding. "Semantic communication," on the other hand, primarily studies the extraction and representation of semantic information from source information, as well as the design of semantic communication systems integrated with AI, thereby coupling various modules together to achieve the transmission of semantic information.

[0073] A key difference between syntactic communication systems and semantic communication systems lies in the design of source and channel coding. In syntactic communication systems, source coding and channel coding are separate. Specifically, at the transmitter, source coding first compresses source information such as images, voice, and video into the original bitstream to be transmitted. This bitstream is then transmitted via channel coding using methods such as Low-Density Parity-Check (LDPC) and Polar coding. At the receiver, the original bitstream is first recovered through channel decoding, and then the original source is reconstructed through source decoding. This separation of source and channel coding facilitates modular optimization and design. Source coding compresses information redundancy, saving transmission bandwidth, while channel decoding enhances redundancy, improving the information's ability to resist noise and interference, and enabling error detection and correction.

[0074] In semantic communication systems, source coding and channel coding are jointly designed. Specifically, on the transmitter side (e.g., the user side), a joint source-channel encoder is designed to directly encode the original source information into the bit stream to be transmitted (joint coding output); while on the receiver side (e.g., the network side), a joint source-channel decoder is designed to directly recover the original source information from the received bit stream. This method of coupling source and channel can achieve joint optimization in source compression redundancy and channel redundancy. Furthermore, since both the encoder and decoder are designed using AI models, end-to-end training and deployment can be achieved, allowing the AI ​​model to be more adapted to the current wireless channel characteristics and noise conditions, thus optimizing system performance. Simultaneously, joint source-channel coding can further incorporate modulation and demodulation functions, further optimizing system performance.

[0075] II. CSI Feedback in NR

[0076] In NR systems, for CSI feedback schemes, a codebook-based eigenvector feedback is typically used to enable the base station to acquire downlink CSI. Specifically, the base station sends downlink channel state information-reference signal (CSI-RS) to the user (e.g., UE). The user uses the CSI-RS to estimate the downlink channel CSI and performs eigenvalue decomposition on the estimated downlink channel to obtain the corresponding eigenvector. NR provides two codebook design schemes: Type I and Type II. Type I codebooks are used for CSI feedback with standard accuracy, primarily for SU-Multiple Input Multiple Output (MIMO) scenarios. Type II codebooks are mainly used to improve MU-MIMO transmission performance. Both Type I and Type II codebooks employ a two-level codebook feedback scheme, W = W1W2. W1 describes the channel's bandwidth and long-term characteristics, defining a set of L DFT beams; W2 describes the channel's subband and short-term characteristics. For the Type I codebook, W2 selects one beam from L DFT beams; for the Type II codebook, W2 linearly combines the L DFT beams in W1, providing feedback in the form of amplitude and phase. Generally, the Type II codebook utilizes a higher number of feedback bits to achieve higher precision CSI feedback performance.

[0077] In NR, the CSI reporting process is carried by Uplink Control Information (UCI) on the Physical Uplink Control Channel (PUCCH) or the Physical Uplink Shared Channel (PUSCH). This includes periodic and semi-persistent reporting on the PUCCH, and aperiodic and semi-persistent reporting on the PUSCH. When the receiver fails to receive the UCI information correctly due to Cyclic Redundancy Check (CRC) verification, resulting in CSI feedback failure, for periodic and semi-persistent reporting, the network side does not perform any other operations, continuing to use the reporting result from the previous CSI feedback cycle and waiting for the CSI to be reported in the next cycle. For aperiodic reporting, the network side reschedules a set of CSI-RS transmission and user CSI feedback resources and re-performs CSI feedback.

[0078] III. AI-based CSI Feedback

[0079] Given the tremendous success of AI technology, especially deep learning, in computer vision and natural language processing, the communications field has begun to explore using deep learning to solve technical challenges that are difficult to address with traditional communication methods. Deep learning's commonly used neural network architectures are non-linear and data-driven, capable of extracting features from actual channel matrix data and reconstructing the compressed channel matrix information from the UE (User Equipment) at the base station side as accurately as possible. This not only ensures the reconstruction of channel information but also provides the possibility of reducing CSI (Content Support Interface) feedback overhead at the UE side. Deep learning-based CSI feedback treats channel information as an image to be compressed, using a deep learning autoencoder to compress the input channel information and then reconstructing the compressed channel image at the transmitting end, thus preserving channel information to a greater extent.

[0080] The following is an example of a main implementation framework for AI-based CSI feedback:

[0081] An AI-based CSI autoencoder method is adopted. The entire feedback system is divided into encoder and decoder parts, deployed at the user transmitter and base station receiver, respectively. After the user obtains channel information through channel estimation, it is used as input to the encoder. The encoder's neural network compresses and encodes the channel information matrix, and the compressed bitstream is fed back to the base station through the air interface feedback link. The base station uses the decoder to recover the channel information based on the feedback bitstream and outputs the complete feedback channel information. The neural networks of the encoder and decoder shown in Figure 2 can adopt deep neural networks (DNNs) composed of multiple fully connected layers, CNNs composed of multiple convolutional layers, or RNNs with structures such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs). Various neural network architectures such as residual and self-attention mechanisms can also be used to improve the performance of the encoder and decoder.

[0082] Both the CSI input and output mentioned above can be full-channel information or feature vector information obtained based on full-channel information. Deep learning-based channel information feedback methods are mainly divided into full-channel information feedback and feature vector feedback. While the former can achieve full-channel information compression and feedback, it has high feedback bitstream overhead and is not yet supported in NR systems. Feature vector-based feedback methods, on the other hand, are the feedback architecture supported by NR systems. AI-based feature vector feedback methods can achieve higher CSI feedback accuracy with the same feedback bit overhead, or significantly reduce feedback overhead while achieving the same CSI feedback accuracy.

[0083] IV. AI-based CSI Feedback

[0084] To further enhance the performance of AI-based CSI feedback, the temporal correlation between CSI responses at different times can be utilized to improve the compressed feedback performance of CSI. Specifically, use cases for different implementation methods are as follows:

[0085] (1) AI-based joint spatial-frequency-temporal CSI compression feedback, as shown in Figure 3: The encoder input on the user side includes not only the CSI measurement information at the current time (e.g., CSI at time t), but also historical CSI information from past times (e.g., historical CSI information output by the encoder based on the CSI at time t-1). This historical information can be represented by the feature output of the latent vector space of the encoder output from past times, and does not have explicit physical meaning. Similarly, the decoder input on the network side includes not only the feedback information at the current time (e.g., feedback information at time t), but also historical CSI information from past times (e.g., historical CSI information output by the decoder based on the feedback information at time t-1). This historical information can be represented by the feature output of the latent space of the decoder output from past times, and also does not have explicit physical meaning. For the feedback information at time t on the air interface, it not only implicitly represents the features of the CSI at the current time, but also includes information features from the historical CSI that help recover the CSI at the current time (e.g., recovered CSI at time t-1), which can be used by the network side to better recover the CSI at the current time (e.g., recovered CSI at time t).

[0086] (2) AI-based joint CSI prediction and compression, as shown in Figure 4: The user-side CSI prediction model takes the CSI measurement information within the measurement window as input and outputs the predicted CSI information at least one time step. This is preprocessed (e.g., if the predicted CSI information is full-channel information, Singular Value Decomposition (SVD) can be used to extract feature vectors from different layers for the CSI compression process) and used as the encoder input. When the encoder input is CSI information from multiple time steps, the encoder output is joint feedback information, and the decoder can simultaneously recover CSI information from multiple prediction time steps. By extracting the correlation information of CSI from multiple time steps, the performance of CSI feedback can be further enhanced with priority given to air interface feedback overhead. Simultaneously, the user-side CSI prediction and CSI encoding compression processes can be either separated as shown in Figure 4 or coupled, i.e., completed through a single AI model, as indicated by the dashed box.

[0087] The above use cases can all use AI models to extract, compress, and utilize the correlation of CSI at multiple moments, in order to further improve CSI feedback performance.

[0088] V. CSI Feedback Method Based on Source-Channel Joint Coding

[0089] In addition to the AI-based CSI feedback mentioned above, we can also draw on the semantic communication approach and adopt a joint source-channel CSI feedback method.

[0090] Figure 5 illustrates the first working method: On the transmitter side (e.g., the user side), a joint source-channel encoder is designed to directly encode the measured CSI as the original source information into the bit stream to be transmitted (joint encoding output), and then maps it onto physical resources through traditional modulation modules (e.g., Quadrature Phase Shift Keying (QPSK), Quadrature Amplitude Modulation (QAM), 64QAM, etc.). On the receiver side, a joint source-channel decoder is designed to directly recover the original source information from the demodulated log-likelihood ratio, i.e., recover the CSI. This method of coupling source and channel coding can achieve joint optimization in source compression redundancy and channel redundancy. Furthermore, since both the encoder and decoder are designed using AI models, end-to-end training and deployment can be achieved, making the AI ​​model more adaptable to the current wireless channel characteristics and noise conditions. This further optimizes the performance of the CSI encoder and decoder against noise and fading channels under non-ideal channel conditions, achieving optimal system performance.

[0091] Furthermore, joint source-channel coding can also include modulation and demodulation functions, as shown in Figure 6, which illustrates the second working method. At the transmitting end (e.g., the user side), the output of the joint source-channel encoder is not a bitstream, but rather complex symbols (e.g., complex sequences) that can be directly mapped to physical resources. Power constraints are applied to the complex symbols to satisfy certain conditions. At the receiving end (e.g., the network side), the joint source-channel decoder directly takes the received symbols (received complex sequences) after channel equalization and symbol detection as input and directly outputs the original information. This end-to-end design method achieves a balance between source coding, channel coding, and modulation, further optimizing end-to-end link performance.

[0092] In the CSI feedback process, whether it is the codebook-based CSI feedback in NR, the AI-based spatial and frequency domain CSI compression feedback method in R18, or the joint time-space-frequency domain CSI compression feedback method in R19, the system-level and link-level performance evaluation usually assumes ideal feedback, that is, it is assumed that there is no error in the CSI reporting process, and the base station can perfectly decode the bit stream carrying CSI information and recover the CSI information.

[0093] In practical communication systems, the ideal assumption of uplink CSI cannot be realized. For codebook-based CSI feedback in NR systems and AI-based CSI feedback currently discussed by 3GPP, the original CSI is transformed into the original information bitstream after passing through a codebook or autoencoder. This bitstream then needs to be channel-coded along with other UCI or data information and transmitted via PUCCH / PUSCH. However, during this process, errors may occur when decoding PUCCH / PUSCH at the base station due to noise. Especially at cell edges or in low signal-to-noise ratio environments such as when the link is obstructed, the error rate of uplink feedback may be high. In such cases, for periodic and semi-persistent CSI feedback, the base station cannot obtain the current CSI feedback and can only use the previous CSI feedback result. This can affect downlink transmission performance when the channel changes rapidly. For aperiodic CSI feedback, the base station may need to schedule CSI-RS measurement resources and re-feedback once or multiple times before decoding the correct downlink CSI information for downlink transmission. This introduces significant measurement resource overhead, feedback delay, and feedback overhead.

[0094] CSI feedback based on joint source-channel coding can significantly improve the performance of CSI feedback under non-ideal uplink feedback conditions. Combining joint CSI compression feedback based on the time, spatial, and frequency domains, and AI-based joint CSI prediction and compression methods, the embodiments of this application can not only provide feedback based on the CSI measured at the current moment, but also extract the correlation between CSI at multiple moments based on joint source-channel coding, thus achieving the function of joint compression feedback of CSI at multiple moments and further enhancing CSI feedback.

[0095] Figure 7 is a schematic flowchart of a channel state information processing method 700 according to an embodiment of this application. This method can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes at least a portion of the following:

[0096] S710, The first communication device receives first indication information, which is used to instruct the first communication device to perform joint encoding of CSI;

[0097] S720, the first communication device performs joint encoding of the CSI.

[0098] In this embodiment, the first communication device can receive first indication information from the second communication device. In some examples, the first communication device may include a terminal device, and the second communication device may include a network device. The first indication information may instruct the first communication device to perform joint source-channel coding on the CSI at the current time. Joint source-channel coding can both compress the CSI at the current time and predict it based on the CSI at the current time and historical times. The first communication device may include an encoder required for joint source-channel coding, and the second communication device may include a decoder required for joint source-channel coding. The encoder and decoder may be built based on an AI scheme. The AI ​​scheme may include at least one of the following: AI model, AI function, AI feature, machine learning (ML) model, ML function, ML feature, etc.

[0099] In this embodiment, the first communication device uses an encoder to jointly encode the CSI at the current moment to obtain a joint encoding result. If the first implementation method shown in Figure 5 is used, a bitstream sequence can be obtained after jointly encoding the CSI at the current moment; if the second implementation method shown in Figure 6 is used, a complex sequence can be obtained after jointly encoding the CSI at the current moment. Then, the first communication device can send the joint encoding result to the second communication device. After receiving the joint encoding result, the second communication device can use a decoder to decode the joint encoding result to obtain the recovered CSI at the current moment.

[0100] The instruction information can instruct the first communication device to perform joint encoding of CSI, thereby improving the transmission performance of CSI.

[0101] In one implementation, the first indication information is further used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

[0102] In this embodiment, if the first indication information indicates that the first communication device can use historical CSI-related information to jointly encode CSI, then the first communication device can perform joint encoding based on the current CSI and the historical CSI-related information. The historical CSI-related information can also be referred to as past CSI historical information or historical CSI-related information, etc. This historical CSI-related information can be characterized by the latent space feature outputs of one or more joint encoders prior to the current time. These latent space feature outputs can be matrices, vectors, or combinations of parameters and parameter sets representing channel characteristics of a specific dimension, and may not have explicit physical meaning.

[0103] Figure 8 is a schematic flowchart of a channel state information processing method 800 according to another embodiment of this application. The method may include one or more features of the channel state information processing method described above. In one embodiment, S720 the first communication device performs joint encoding of the CSI, including:

[0104] S810, the first communication device enters the second measurement feedback process from the first measurement feedback process, and performs joint encoding on the CSI in the second measurement feedback process. In this embodiment, the joint encoding method may not be used in the first measurement feedback process (which can be referred to as the first feedback process). For example, the CSI may be fed back using a traditional NR codebook, AI spatial domain (only the current CSI), or AI spatiotemporal frequency domain (including the current CSI and related historical CSI information). The joint encoding method is used in the second measurement feedback process (which can be referred to as the second feedback process). The information used in the joint encoding may or may not include historical information related to the CSI.

[0105] In one implementation, the method further includes:

[0106] S820, the first communication device receives second indication information, which instructs the first communication device to revert from the second measurement feedback process to the first measurement feedback process. The first communication device can then revert from the second measurement feedback process to the first measurement feedback process based on the second indication information. The second indication information may be indicated by MAC CE or DCI, or by other signaling.

[0107] In one embodiment, the second measurement feedback process includes: the first communication device performing joint encoding based on first input information and second input information to obtain first output information and second output information. The first input information includes CSI (Conditional Sensor Information), the second input information includes historical information related to CSI, the first output information includes information jointly encoded based on the first and second input information, and the second output information is the historical CSI information output based on the first and second input information.

[0108] For example, a first communication device inputs first input information (CSI at the current moment) and second input information (first historical information related to CSI) into a first artificial intelligence scheme (e.g., a first AI model), and outputs first output information (joint source-channel coding result) and second output information (second historical information related to CSI). The first historical information related to CSI is CSI-related information acquired before the current moment. The second historical information related to CSI is generated based on the first historical information related to CSI. The second historical information related to CSI can be used in joint coding at the next moment after the current moment.

[0109] In one implementation, the second output information is output by the output layer or intermediate layer of the first artificial intelligence solution. For example, a first AI model is deployed on a first communication device, and a second AI model is deployed on a second communication device. The first AI model can jointly encode CSI and its related historical information. The information output by the intermediate layer or output layer of the first AI model can be stored as second historical information related to CSI, i.e., the second output information.

[0110] In one implementation, the second input information and / or the second output information are stored in the buffer of the first communication device. At the next moment (the new current moment), the second output information can be read out and used as new second input information for joint encoding with CSI, resulting in a new joint encoding result and new second output information. The buffer of the first communication device can store historical information related to each used and generated CSI, or it can store only the historical information related to the most recently generated CSI for subsequent use.

[0111] In one implementation, the first measurement feedback process includes:

[0112] The first communication device receives the first cycle of CSI-RS;

[0113] The first communication device measures the CSI-RS and obtains the CSI for the first period;

[0114] The first communication device sends first feedback information, which includes CSI quantization information for the first period.

[0115] In this embodiment of the application, for periodic CSI feedback, during the first measurement feedback process, a second communication device, such as a network device, can send downlink CSI-RS to the first communication device, such as a UE, for CSI measurement at intervals of a first period of time units. The first communication device can obtain the CSI for the current period by measuring the CSI-RS and send first feedback information to the network side. The first feedback information may include CSI quantization information for the current period. This first feedback information can be reported via PUCCH after going through the NR CSI reporting process, such as uplink channel coding, modulation, and physical resource mapping.

[0116] In the embodiments of this application, the CSI quantization information is obtained by at least one of the following methods: quantization obtained by codebook-based CSI feedback method; quantization obtained by AI-based spatial and frequency domain CSI compression; and quantization obtained by AI-based time, spatial, and frequency domain CSI compression.

[0117] In one implementation, the first indication information is further used to indicate at least one of the following:

[0118] The second cycle of the CSI-RS is sent during the second measurement feedback process;

[0119] How the first artificial intelligence solution works;

[0120] The reporting channel resources for the second feedback information include the first output information.

[0121] In this embodiment, for periodic CSI feedback, when switching to a CSI feedback mode based on joint coding is required, the second communication device can send a first indication message to the first communication device, instructing the first communication device to enter the second measurement feedback process. During the second measurement feedback process, the second communication device can send downlink CSI-RS for CSI measurement to the first communication device at intervals of a second period. This second period can be the same as or different from the first period. When the first indication message does not additionally indicate a second period, the second period can be configured to be the same as the first period by default.

[0122] In one implementation, the first artificial intelligence solution operates as follows:

[0123] Encode CSI as a bit stream or complex symbols;

[0124] Whether to use the second input information as an additional input to the second measurement feedback process.

[0125] In this embodiment, the working mode of the first artificial intelligence scheme indicated by the first indication information may include the working method adopted for joint encoding. If the first working method shown in FIG5 is used for joint encoding, a bit stream can be obtained; if the second working method shown in FIG6 is used for joint encoding, complex symbols can be obtained.

[0126] In this embodiment, the operation of the first artificial intelligence scheme indicated by the first indication information may include using second input information, namely CSI-related historical information, as an additional input to the second measurement feedback process. If the first working method shown in FIG5 is used, a bit stream can be obtained by joint encoding based on CSI and CSI-related historical information; if the second working method shown in FIG6 is used, complex symbols can be obtained by joint encoding based on CSI and CSI-related historical information.

[0127] In the embodiments of this application, when the first AI scheme is used for joint coding of CSI feedback, it is not necessary to go through the reporting process of UCI such as channel coding and / or modulation. Therefore, the reporting channel resources can use the PUCCH occupied by the first feedback information for the reporting of the second feedback information, or it can be indicated that dedicated uplink physical channel resources are used for the reporting of the second feedback information.

[0128] In this embodiment, the first indication information may be indicated by MAC CE or DCI, or by other signaling. After receiving the first indication information, the first communication device adopts the operating mode of the first AI scheme indicated by the first indication information and reports the second feedback information on the corresponding reporting channel resource. The second communication device receives the second feedback information on the corresponding reporting channel resource and selects the corresponding second AI scheme to restore the CSI information of the current period. If the second communication device instructs the second communication device to adopt the first or second operating mode of the first AI scheme, the second communication device may also select the first or second operating mode of the matching second AI scheme.

[0129] In this embodiment, both the first and second communication devices can extract the correlation of CSI at multiple time points (e.g., historical information related to CSI). However, considering that the second communication device can optimize the second AI scheme based on its implementation, it is not required that the second and first communication devices simultaneously extract the correlation of CSI at multiple time points. For example, when the second communication device instructs the first communication device to use the second input information as an additional input for extracting the correlation of CSI at multiple time points, the second communication device can flexibly choose whether to use the fourth input information as an additional input. When the second communication device instructs the first communication device not to use the second input information as an additional input, the second communication device can also flexibly choose whether to use the fourth input information as an additional input.

[0130] In this embodiment, the second indication information can be used not only to exit the second measurement feedback process, but also to indicate the updated first cycle. By default, the current configuration is used.

[0131] In one implementation, the first measurement feedback process further includes:

[0132] The first communication device receives M third-cycle CSI-RS;

[0133] The first communication device measures the CSI-RS of the M third periods, obtains the CSI of the M third periods within the measurement window, and predicts the CSI of the N third periods within the prediction window based on the CSI of the M third periods within the measurement window.

[0134] The first communication device sends first feedback information, which includes CSI quantization information for the M third periods within the measurement window and CSI quantization information for the N third periods within the prediction window.

[0135] In this embodiment, for periodic joint CSI prediction and feedback, a complete prediction and feedback process can include M+N cycles of CSI-RS measurement and CSI prediction. The first M cycles constitute a measurement window. The second communication device periodically sends CSI-RS data to the first communication device at intervals of a set periodic time unit. The first communication device measures and reports the CSI for each cycle. Simultaneously, the first communication device needs to store the measurement results of the M CSIs within the measurement window for CSI prediction. The latter N cycles constitute a prediction window. The second communication device does not configure CSI-RS measurements. The first communication device directly predicts the N CSI results within the prediction window based on the M CSI measurement results of the measurement window and performs joint compression before reporting. The values ​​of M and N can be configured by the second communication device according to actual conditions, and M and N are greater than or equal to 1.

[0136] For periodic joint CSI prediction and feedback, during the first measurement feedback process, the second communication device can send downlink CSI-RS to the first communication device for CSI measurement at intervals of three period time units, for a duration of M1 periods, and then not send downlink CSI-RS for the subsequent N1 periods.

[0137] The first communication device measures the CSI-RS for M1 cycles and sends first feedback information to the second communication device. The first feedback information may include: quantized CSI information for the M1 cycles within the measurement window and quantized CSI information for the N1 cycles within the prediction window. The quantized CSI information for the N1 cycles within the prediction window can be predicted first using a non-AI method (e.g., autoregressive algorithm, Wiener filtering, etc.) or an AI method (CSI predictor) based on the CSI information for the M1 cycles within the measurement window, and then quantized using a codebook-based CSI feedback method in NR (e.g., the eType II codebook in Rel-16, or the Doppler-based codebook in Rel-18), or it can be obtained through AI-based spatial-frequency domain CSI compression quantization, or AI-based time-spatial-frequency domain CSI compression quantization. This information can be reported via PUCCH through NR's CSI reporting process, such as uplink channel coding, modulation, and physical resource mapping.

[0138] In one implementation, the first indication information is further used to indicate at least one of the following:

[0139] The fourth cycle of the CSI-RS is sent during the second measurement feedback process;

[0140] The duration of the first input information in the first artificial intelligence solution;

[0141] How the first artificial intelligence solution works;

[0142] The reporting channel resources for the second feedback information include the first output information.

[0143] In this embodiment, for periodic joint CSI prediction and feedback, when switching to a joint coding-based CSI prediction and feedback mode is required, the second communication device can send a first indication message to the first communication device, indicating entry into the second measurement feedback process. During the second measurement feedback process, the second communication device can send downlink CSI-RS for CSI measurement to the first communication device at intervals of four periods, lasting for M2 periods, and then not send downlink CSI-RS for the subsequent N2 periods. The fourth period can be the same as or different from the third period. The number of measurement windows M2 in the second measurement feedback process can be the same as or different from the number of measurement windows M1 in the first measurement feedback process. The number of prediction windows N2 in the second measurement feedback process can be the same as or different from the number of prediction windows N1 in the first measurement feedback process. When the first indication message does not additionally indicate the above time-related parameters, the default configuration can be the same as in the first measurement feedback process.

[0144] In this embodiment, for periodic joint CSI prediction and feedback, the length T of the first input information of the first AI scheme indicated by the first indication information satisfies the requirement 1 ≤ T ≤ N2. When T > 1, the first AI scheme can jointly compress CSI at multiple time points and provide feedback. If the first indication information does not additionally indicate the length of the first input information, the default value is T = N2, meaning the first AI scheme can jointly compress all predicted CSI results within the prediction window. If T < N2 indicated by the first indication information, then N2 must be an integer multiple of T. In this case, the first communication device can sequentially call the first AI scheme N2 / T times to complete the joint compression feedback of CSI at N2 time points.

[0145] In the embodiments of this application, for periodic joint CSI prediction and feedback, the first indication information indicates the working mode of the first AI scheme and the reporting channel resources of the second feedback information, as described above.

[0146] In this embodiment, the second indication information can be used not only to exit the second measurement feedback process, but also to indicate the updated third cycle, the number of cycles for the measurement window, and the number of cycles for the prediction window. By default, the current configuration is used.

[0147] Figure 9 is a schematic flowchart of a channel state information processing method 900 according to another embodiment of this application. The method may include one or more features of the channel state information processing method described above. In one embodiment, the method further includes:

[0148] S910, the first communication device receives third indication information, which includes an activation indication reported by the CSI. This step can be performed before S810 or S820.

[0149] In one implementation, the third indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0150] In this embodiment, semi-persistent CSI reporting, or semi-persistent combined CSI prediction and feedback reporting, falls between periodic and aperiodic CSI reporting. CSI reporting occurs at certain intervals after activation and before deactivation. Here, CSI reported via PUSCH can be activated and deactivated by DCI signaling, and CSI reported via PUCCH can be activated and deactivated by MAC CE.

[0151] In this embodiment, for semi-persistent CSI reporting, or semi-persistent combined CSI prediction and feedback reporting, the third indication information sent by the second communication device to the first communication device may include an activation indication for CSI reporting. Upon receiving the activation indication, the first communication device can activate CSI reporting. When CSI reporting is activated, a first measurement feedback process begins; upon receiving the first indication information from the second communication device, a second measurement feedback process begins; upon receiving the second indication information from the second communication device, the first communication device reverts to the first measurement feedback process. When CSI reporting is deactivated, the CSI feedback process ends.

[0152] If the CSI reporting activation is DCI signaling, the first feedback information can be reported via PUSCH. When entering the second measurement feedback process, the second feedback information is transmitted by default on the PUSCH dynamically indicated by the previous activation signaling, unless the first indication information specifically indicates the uplink physical channel resources used for reporting the second feedback information. If the CSI reporting activation is MAC CE signaling, the first feedback information can be reported via PUCCH. When entering the second measurement feedback process, the second feedback information is reported by default on the configured PUCCH resources, unless the first indication information specifically indicates the uplink physical channel resources used for reporting the second feedback information.

[0153] In some examples, the second communication device can instruct the first communication device to report deactivation information via CSI during the second measurement feedback process. When the first communication device receives the CSI report deactivation information, it can exit the CSI reporting process without requiring additional second instruction information.

[0154] In one implementation, the third indication information further includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

[0155] In this embodiment of the application, for semi-persistent CSI reporting, the third indication information sent by the second communication device to the first communication device may include not only an activation indication for CSI reporting, but also an indication of the CSI reporting method adopted by the first communication device.

[0156] In one implementation, the CSI reporting method includes at least one of the following:

[0157] After CSI reporting is activated, the first measurement feedback process begins.

[0158] After the CSI report is activated, the second measurement feedback process begins.

[0159] How the first artificial intelligence solution works.

[0160] In the embodiments of this application, CSI reporting methods may include non-jointly coded methods (such as the coding method used in the first measurement feedback process described above), for example, NR-based codebook feedback methods, AI-based spatial-frequency domain feedback methods, and AI-based time-spatial-frequency domain feedback methods. CSI reporting methods may also include jointly coded methods (such as the coding method used in the second measurement feedback process described above). For example, a CSI feedback method based on a first AI scheme and a second AI scheme. Furthermore, jointly coding may be performed using either the first or second working method. Additionally, it may indicate whether the first AI scheme uses second input information as additional input to extract the correlation of CSI over multiple periods.

[0161] If the CSI reporting method indicated in the third instruction information includes entering the second measurement feedback process after CSI reporting is activated, then after receiving the third instruction information, the first communication device can first activate CSI reporting and then directly enter the second measurement feedback process. If the CSI reporting method indicated in the third instruction information includes entering the first measurement feedback process after CSI reporting is activated, then after receiving the third instruction information, the first communication device can first activate CSI reporting and then directly enter the first measurement feedback process; it will then wait to receive the first instruction information before entering the second measurement feedback process.

[0162] If the CSI reporting method indicated in the third instruction information includes entering the second measurement feedback process after CSI reporting is activated, and indicates that the second input information is used as an additional input, then after receiving the third instruction information, the first communication device can first activate CSI reporting and then directly enter the second measurement feedback process. Furthermore, in the second measurement feedback process, the first communication device uses the second input information as an additional input and performs joint encoding together with the first input information.

[0163] Figure 10 is a schematic flowchart of a channel state information processing method 1000 according to another embodiment of this application. The method may include one or more features of the channel state information processing method described above. In one embodiment, the method further includes:

[0164] S1010, The first communication device receives fourth indication information, which includes an activation indication reported by CSI.

[0165] In one implementation, the fourth indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0166] In one implementation, the fourth instruction information further includes:

[0167] The measurement interval of CSI-RS, the number of CSI-RS measurements within the measurement window, and the length of CSI predictions included within the prediction window;

[0168] The duration of the first input information in the first artificial intelligence solution;

[0169] CSI reporting methods;

[0170] CSI reporting cycle;

[0171] Channel resources reported by CSI.

[0172] In this embodiment, for non-periodic CSI reporting, configuration and triggering can be performed using MAC CE combined with DCI triggering, and reporting can be done via PUSCH. The second communication device can send a fourth indication message to the first communication device. The fourth indication message carries an activation indication for CSI reporting, indicating that the function of undertaking non-periodic CSI reporting is activated.

[0173] In this embodiment, for non-periodic joint CSI prediction and feedback, a MAC CE combined with DCI triggering method can be used for configuration and triggering, and reported via PUSCH. The second communication device can send a fourth indication message to the first communication device. The fourth indication message carries an activation indication for CSI reporting to indicate the activation of the function of undertaking non-periodic joint CSI prediction and feedback reporting. For example, the fourth indication message can also indicate the measurement interval k5 of CSI-RS, the number of CSI-RS measurements M3 within the measurement window, and the CSI prediction length N3 contained in the prediction window. Within the measurement window, the second communication device sends downlink CSI-RS to the first communication device for CSI measurement for a duration of M3 time units, with an interval of k5 time units, and does not send downlink CSI-RS for the subsequent N3 time units. As another example, the fourth indication message can also indicate the time length T of the first input information of the first AI scheme, where 1≤T≤N3. When T>1, the first AI scheme can jointly compress CSI at multiple times and provide feedback. If the fourth indication does not additionally indicate the length of the first input information, the default value is T = N3, meaning the first AI scheme can jointly compress all predicted CSI results within the prediction window. If the fourth indication indicates T < N3, then N3 must be an integer multiple of T. In this case, the first communication device can sequentially call the first AI scheme N3 / T times to complete the joint compression feedback of N3 CSIs.

[0174] In this embodiment, the fourth indication information may also indicate the CSI reporting method used by the first communication device, as detailed in the relevant descriptions above. The fourth indication information can be indicated via MAC CE or DCI signaling, or other dedicated signaling. Furthermore, it can be configured via MAC CE and then dynamically triggered by DCI.

[0175] Figure 11 is a schematic flowchart of a channel state information processing method 1100 according to an embodiment of this application. This method can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes at least a portion of the following:

[0176] S1110, the second communication device sends a first instruction message, which is used to instruct the first communication device to perform joint encoding of CSI.

[0177] In one implementation, the first indication information is further used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

[0178] In one embodiment, the first indication information is used to instruct the first communication device to enter a second measurement feedback process from a first measurement feedback process, in which the CSI is jointly encoded.

[0179] In one embodiment, the method further includes: the second communication device sending second indication information, the second indication information being used to instruct the first communication device to revert from the second measurement feedback process to the first measurement feedback process.

[0180] Figure 12 is a schematic flowchart of a channel state information processing method 1200 according to another embodiment of this application. The method may include one or more features of the channel state information processing method described above. In one embodiment, the method further includes:

[0181] S1210, The second communication device receives first output information; wherein, the first output information includes information jointly encoded by the first communication device based on first input information and second input information, the first input information includes CSI, and the second input information includes CSI-related information;

[0182] S1220. The second communication device obtains third output information and fourth output information based on the third input information and the fourth input information; wherein, the third input information includes the first output information, the fourth input information includes CSI-related historical information, and the fourth output information outputs CSI-related historical information based on the third input information and the fourth input information.

[0183] In one implementation, the fourth output information is output by the output layer or intermediate layer of the second artificial intelligence scheme.

[0184] In one embodiment, the fourth input information and / or the fourth output information are stored in the buffer of the second communication device.

[0185] In one implementation, during the first measurement feedback process, the second communication device performs the following steps:

[0186] The second communication device transmits a first-cycle Channel State Information Reference Signal (CSI-RS);

[0187] The second communication device receives first feedback information, which includes CSI quantization information for the first period obtained by the first communication device from measuring the CSI-RS.

[0188] In one implementation, the first indication information is further used to indicate at least one of the following:

[0189] The second cycle of the CSI-RS is sent during the second measurement feedback process;

[0190] How the first artificial intelligence solution works;

[0191] The reporting channel resources for the second feedback information include the first output information.

[0192] In one implementation, during the first measurement feedback process, the second communication device performs the following steps:

[0193] The second communication device sends M third-cycle CSI-RS;

[0194] The second communication device receives first feedback information, which includes CSI quantization information of the M third periods within the measurement window obtained by the second communication device measuring the CSI-RS of the M third periods, and CSI quantization information of the N third periods within the prediction window obtained based on the CSI prediction of the M third periods within the measurement window.

[0195] In one implementation, the first indication information is further used to indicate at least one of the following:

[0196] The fourth cycle of the CSI-RS is sent during the second measurement feedback process;

[0197] The duration of the first input information in the first artificial intelligence solution;

[0198] How the first artificial intelligence solution works;

[0199] The reporting channel resources for the second feedback information include the first output information.

[0200] Figure 13 is a schematic flowchart of a channel state information processing method 1300 according to another embodiment of this application. The method may include one or more features of the channel state information processing method described above. In one embodiment, the method further includes:

[0201] S1310, the second communication device sends a third indication message, which includes an activation indication reported by the CSI.

[0202] In one implementation, the third indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0203] In one implementation, the third indication information further includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

[0204] Figure 14 is a schematic flowchart of a channel state information processing method 1400 according to another embodiment of this application. The method may include one or more features of the channel state information processing method described above. In one embodiment, the method further includes:

[0205] S1410, the second communication device sends a fourth indication message, which includes an activation indication reported by the CSI.

[0206] In one implementation, the fourth indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0207] In one implementation, the fourth instruction information further includes:

[0208] CSI-RS measurement intervals;

[0209] The duration of the first input information in the first artificial intelligence solution;

[0210] CSI reporting methods;

[0211] CSI reporting cycle;

[0212] Channel resources reported by CSI.

[0213] In one implementation, the CSI reporting method includes at least one of the following:

[0214] After CSI reporting is activated, the first measurement feedback process begins.

[0215] After the CSI report is activated, the second measurement feedback process begins.

[0216] How the first artificial intelligence solution works.

[0217] In one implementation, the first artificial intelligence solution operates as follows:

[0218] Encode CSI as a bit stream or complex symbols;

[0219] Whether to use the second input information as an additional input to the second measurement feedback process.

[0220] In one implementation, the CSI quantization information is obtained by at least one of the following methods: quantization using a codebook-based CSI feedback method; quantization using AI-based spatial-frequency domain CSI compression; and quantization using AI-based time-spatial-frequency domain CSI compression.

[0221] Specific examples of the second communication device executing methods 1100, 1200, 1300, and 1400 in this embodiment can be found in the relevant descriptions of the second communication device in methods 700, 800, 900, and 1000 above. For the sake of brevity, they will not be repeated here.

[0222] The channel state information processing method in this application embodiment may include a CSI feedback enhancement and configuration method based on joint coding. This method may include CSI feedback signaling flows for periodic, semi-persistent, and aperiodic conditions. The method deploys a first AI scheme (which may be referred to as a first AI / ML model / function / feature) and a second AI scheme (which may be referred to as a second AI / ML model / function / feature) on the user side and the network side respectively, and employs a joint source-channel coding method to extract the correlation of CSI at multiple time points, ensuring CSI feedback performance under non-ideal uplink feedback conditions.

[0223] Example 1: A joint codec configuration method for multi-time CSI feedback

[0224] Figure 15 shows the configuration method on the user side.

[0225] Among them, the user side, such as the UE, can configure the first AI / ML model / function / feature to realize the function based on the joint source channel encoder.

[0226] The first AI / ML model / function / feature takes input as first input information and outputs first output information. This first input information contains at least T consecutive time-series CSI information, where T ≥ 1. The first output information may contain at least T consecutive time-series compressed CSI information for air interface feedback, where T ≥ 1. The form of the first output information can vary depending on the first AI / ML model / function / feature used; no specific limitations are imposed, and different implementation methods are all included within the scope of this invention. For example, if the first working method shown in Figure 5 is used, the first output information is a jointly encoded bitstream sequence; if the second implementation method shown in Figure 6 is used, the first output information is a jointly encoded complex sequence.

[0227] Optionally, the input to the first AI / ML model / function / feature may include second input information, and the output may include second output information. This second input information includes at least the second output information of the first AI / ML model / function / feature from one or more past time points; the second output information includes historical information from the current time point. This historical information can be output by the output layer of the first AI / ML model / function / feature, or by the intermediate layer of the first AI / ML model / function / feature. This second output information does not need to be reported to the network side by the user via air interface; the user only needs to set up a buffer locally to store the second output information from one or more past time points.

[0228] Correspondingly, the network-side configuration method is shown in Figure 16:

[0229] The network side is configured with a second AI / ML model / function / feature, which enables functionality based on a joint source-channel decoder. This second AI / ML model / function / feature needs to be used in conjunction with the first AI / ML model / function / feature, including the training, deployment, and model management processes.

[0230] The input to the second AI / ML model / function / feature is the third input information, and the output is the third output information. The form of this third input information varies depending on the second AI / ML model / function / feature used; no specific limitations are imposed here, and all different implementation methods are included within the scope of this invention. For example, if the first working method shown in Figure 5 is used, the third input information is the demodulated log-likelihood ratio sequence; if the second working method shown in Figure 6 is used, the third input information is the received jointly coded complex sequence after passing through the channel and noise. This third output information contains at least T consecutive time-series recovered CSI information, where T ≥ 1.

[0231] Optionally, the input to the second AI / ML model / function / feature may include fourth input information, and the output may include fourth output information. This fourth input information includes at least the fourth output information of the second AI / ML model / function / feature from one or more past time points; the fourth output information includes historical information from the current time point, and this historical information can be output by the output layer of the second AI / ML model / function / feature, or by the intermediate layer of the second AI / ML model / function / feature. This fourth output information requires the network to locally configure a buffer for storing the fourth output information from one or more past time points.

[0232] The scheme in this example can achieve CSI feedback enhancement based on joint coding. By extracting the correlation information of CSI at multiple time points (such as second input information, fourth input information, etc.) and using the joint source-channel coding method, the feedback performance of CSI under non-ideal uplink feedback can be further improved and the CSI feedback overhead can be reduced.

[0233] Example 2: A Spatiotemporal Frequency Domain CSI Feedback and Configuration Method Based on Joint Coding

[0234] This example, based on the working method of Example 1, specifically introduces a spatiotemporal frequency domain CSI feedback and configuration method based on joint coding. The first and second AI / ML models / functions / features may not include CSI prediction functionality; therefore, after the user measures the CSI-RS for the current period, the CSI needs to be fed back to the network side immediately via the uplink channel. In this working mode, the first input information of the first AI / ML model / function / feature contains the number of CSI times T = 1. Optionally, second input information and second output information are required for the first AI / ML model / function / feature to extract the correlation of CSI between multiple times. Correspondingly, the third output information of the second AI / ML model / function / feature may only contain the CSI feedback information for the current time. Optionally, fourth input information and fourth output information are required for the second AI / ML model / function / feature to extract the CSI correlation between multiple times.

[0235] Example 2.1: Periodic CSI Feedback Configuration

[0236] For periodic CSI feedback, an example signaling flow is shown in Figure 17:

[0237] This periodic CSI configuration process, by default, operates under the first feedback process, which includes:

[0238] (1) The network side sends downlink CSI-RS to the user for CSI measurement every k1 time units of the first period;

[0239] (2) The user side obtains the CSI of the current period by measuring CSI-RS and sends the first feedback information to the network side. The first feedback information includes at least the CSI quantization information of the current period. Here, the first feedback information can be obtained by quantization using the codebook-based CSI feedback method in NR, or by AI-based spatial-frequency domain CSI compression quantization, or by AI-based time-spatial-frequency domain CSI compression quantization. The first feedback information needs to go through the NR CSI reporting process, such as uplink channel coding, modulation, and physical resource mapping, and is reported through PUCCH.

[0240] In step S1701, when it is necessary to switch to the CSI feedback mode based on joint coding, step S1701 is executed, and the network sends a first indication message to the user, indicating that the second feedback process should be entered. This first indication message optionally includes the following:

[0241] (1) The second period k2 is when the network side sends downlink CSI-RS to the user for CSI measurement at intervals of k2 time units. This second period can be the same as or different from the first period; when the first indication information does not additionally indicate the second period, the default configuration is that the second period is the same as the first period.

[0242] (2) Indicate the working mode of the first AI / ML model / function / feature. Specifically, it can indicate the working mode of the first AI / ML model / function / feature. The working mode includes: the first AI / ML model / function / feature works in a first or second working method (for example, the first working method is used when the indication in the indication field corresponding to the first indication information is 0, and the second working method is used when it is 1). Whether the first AI / ML model / function / feature uses the second input information (for example, when the indication in the indication field corresponding to the first indication information is 0, the second input information is not used as an additional input, and when it is 1, the second input information is used as input).

[0243] (3) Indicate the reporting channel resources for the second feedback information. When CSI feedback is jointly coded using the first AI / ML model / function / characteristic, since there is no need to go through the reporting process of these UCIs such as channel coding and / or modulation, the reporting channel resources can be the PUCCH occupied by the first feedback information for the reporting of the second feedback information, or the dedicated uplink physical channel resources can be indicated for the reporting of the second feedback information.

[0244] The first indication information can be indicated by MAC CE or DCI, or by other signaling. After receiving the first indication information, the user side adopts the indicated first AI / ML model / function / characteristic operating mode and reports the second feedback information on the corresponding reporting channel resource.

[0245] The network receives the second feedback information on the corresponding reporting channel resources and selects the corresponding second AI / ML model / function / feature to recover the CSI information for the current period. Here, when the network instructs the user to use the first or second working mode of the first AI / ML model / function / feature, the network will also select the matching first or second working mode of the second AI / ML model / function / feature. However, regarding whether the correlation of CSI at multiple time points needs to be extracted on both the network and user sides, considering that the network can optimize the second AI / ML model / function / feature based on implementation, a one-to-one correspondence between the network and user sides is not mandatory. For example, when the network instructs the user to use the second input information as an additional input to extract the CSI correlation at multiple time points, the network can flexibly choose whether to use the fourth input information as an additional input. When the network instructs the user not to use the second input information as an additional input, the network can also flexibly choose whether to use the fourth input information as an additional input. As long as the first AI / ML model / function / feature and the second AI / ML model / feature have the ability to work in pairs, the network can instruct the user side to select the first AI / ML model / function / feature based on the second AI / ML model / function / feature to be used locally.

[0246] In step S1702, the network sends a second indication message to the user to exit the second measurement feedback process and revert to the first measurement feedback process. Optionally, the second indication message may indicate the updated k1 for the first period; by default, the current k1 value is used as the first period. This second indication message may be indicated by MAC CE or DCI, or by other signaling.

[0247] Example 2.2: Semi-persistent CSI feedback configuration

[0248] Semi-persistent CSI reporting falls between periodic and aperiodic CSI reporting. CSI reporting occurs periodically, between activation and deactivation. Here, CSI reported via PUSCH is activated and deactivated by DCI signaling, while CSI reported via PUCCH is activated and deactivated by MAC CE. Therefore, a two-step semi-persistent CSI feedback enhancement mechanism for joint coding involves reusing the periodic CSI feedback process from Example 2.1 after CSI reporting is activated.

[0249] Specifically, as shown in Figure 18, when CSI reporting is activated, the system enters the first measurement feedback process as described in Example 2.1; when the user receives the first indication information from the network side, it enters the second measurement feedback process; when the user receives the second indication information from the network side, it reverts to the first measurement feedback process. The CSI feedback process ends when CSI reporting is deactivated. It is important to note that if CSI reporting activation is via DCI signaling, the first feedback information is reported via PUSCH. When entering the second measurement feedback process, the second feedback information is transmitted by default on the PUSCH dynamically indicated by the previously activated signaling, unless the first indication information specifically specifies the uplink physical channel resource used for reporting the second feedback information. If CSI reporting activation is via MAC CE signaling, the first feedback information is reported via PUCCH. When entering the second measurement feedback process, the second feedback information is reported by default on the configured PUCCH resource, unless the first indication information specifically specifies the uplink physical channel resource used for reporting the second feedback information.

[0250] The CSI reporting deactivation process can be instructed to the user by the network during the second measurement feedback process. When the user receives the CSI reporting deactivation information, they can directly exit the CSI reporting process without needing any additional second instruction information.

[0251] Unlike the process described above, this example provides a one-step semi-continuous CSI feedback configuration process, as shown in Figure 19:

[0252] Specifically, as shown in Figure 19, in S1901, the network sends third indication information to the user. This third indication information may optionally include:

[0253] (1) Activation indication for CSI reporting; this indication is responsible for activating the function of semi-continuous CSI reporting;

[0254] (2) Indicate the CSI reporting method adopted by the user. This CSI reporting method includes non-jointly coded methods (as described in the first measurement feedback process above), namely, NR-based codebook feedback, AI-based spatial-frequency domain feedback, and AI-based time-spatial-frequency domain feedback; it also includes jointly coded methods (as described in the second measurement feedback process above), namely, CSI feedback methods based on the first and second AI / ML models / functions / features, and specifically, whether it is the first or second working method. Furthermore, it can also indicate whether the first AI / ML model / function / feature uses the second input information as an additional input to extract the correlation of CSI over multiple cycles (see Example 2.1 for a detailed description; the indication method is similar here and will not be repeated).

[0255] (3) Other CSI reporting configurations, such as CSI reporting period, reported physical channel resources and other information.

[0256] This third indication can be indicated via MAC CE or DCI signaling, or via other dedicated signaling. Furthermore, it can be configured via MAC CE and then dynamically triggered by DCI.

[0257] In S1902, if the user side uses the first AI / ML model / function / feature to encode CSI and then sends the third feedback information to the network side, the network side can use the corresponding second AI / ML model / function / feature to decode the third feedback information. When it is necessary to deactivate the semi-persistent CSI feedback process, the network can directly send a CSI reporting deactivation instruction to the user.

[0258] Example 2.3: Aperiodic CSI Feedback Configuration

[0259] For aperiodic CSI reporting, configuration and triggering are performed using MACCE combined with DCI triggering, and reporting is conducted via PUSCH. Similar to the one-step semi-persistent CSI feedback configuration process in Figure 19, aperiodic CSI feedback configuration also adopts a one-step signaling method, as shown in Figure 20:

[0260] Specifically, as shown in Figure 20, in S2001, the network sends a fourth indication message to the user. This fourth indication message may optionally include:

[0261] (1) Activation indication for CSI reporting; this indication is responsible for activating the function of non-periodic CSI reporting;

[0262] (2) Instructing the user on the CSI reporting method. This CSI reporting method includes non-jointly coded methods (as described in the first measurement feedback process above), namely, NR-based codebook feedback, AI-based spatial-frequency domain feedback, and AI-based time-spatial-frequency domain feedback; it also includes jointly coded methods (as described in the second measurement feedback process above), namely, CSI feedback methods based on the first and second AI / ML models / functions / characteristics, and specifically, either the first or second method. However, unlike periodic and semi-continuous CSI feedback, in aperiodic CSI feedback, the user side does not support a second input information as an additional input because the user side cannot obtain stable CSI information from the previous period. Similarly, the network side does not support a fourth input information as an additional input.

[0263] (3) Other CSI reporting configurations, such as the reported physical channel resources and other information.

[0264] This fourth indication can be indicated via MAC CE or DCI signaling, or via other dedicated signaling. Furthermore, it can be configured via MAC CE and then dynamically triggered by DCI.

[0265] In S2002, if the user side uses the first AI / ML model / function / feature to perform CSI encoding and then sends the fourth feedback information to the network side, the network side can use the corresponding second AI / ML model / function / feature to decode the third feedback information.

[0266] Example 3: A CSI Prediction and Feedback Configuration Method Based on Joint Coding

[0267] This example, based on the working method of Example 1, specifically introduces a CSI prediction and feedback configuration method based on joint coding.

[0268] Example 3.1: Periodic Joint CSI Forecasting and Feedback Configuration

[0269] For periodic joint CSI prediction and feedback, a complete prediction and feedback process includes M+N cycles of CSI-RS measurement and CSI prediction. The first M cycles constitute the measurement window. Every three cycles (k3 time units), the network periodically sends CSI-RS data to the user. The user measures and reports the CSI for each cycle, and simultaneously stores the measurement results of the M CSIs within the measurement window for CSI prediction. The latter N cycles constitute the prediction window. The network does not configure CSI-RS measurements; the user directly predicts the N CSI results within the prediction window based on the M CSI measurement results from the measurement window, and then performs joint compression and reporting. The values ​​of M and N can be configured by the network according to actual conditions, with M≥1 and N≥1.

[0270] This example provides a typical configuration method for periodic joint CSI prediction and feedback signaling, which can reuse the configuration method shown in Figure 17 of Example 2.1. Specifically, the main differences are as follows (other details not specifically mentioned are the same as in Example 2.1):

[0271] By default, it operates in the first measurement feedback process, which includes:

[0272] (1) The network side sends downlink CSI-RS to the user for CSI measurement at intervals of k3 time units in the third cycle, for a period of M1 cycles, and does not send downlink CSI-RS in the subsequent N1 cycles;

[0273] (2) The user side measures the CSI-RS for M1 cycles and sends the first feedback information to the network side. Optionally, this first feedback information includes at least: CSI quantization information for the M1 cycles within the measurement window and CSI quantization information for the N1 cycles within the prediction window. Here, the CSI quantization information for the N1 cycles within the prediction window is first predicted using a non-AI method (e.g., autoregressive algorithm, Wiener filtering, etc.) or an AI method (CSI predictor) based on the CSI information for the M cycles within the measurement window. Then, it is quantized using a codebook-based CSI feedback method in NR (e.g., the eType II codebook in Rel-16, or the Doppler-based codebook in Rel-18), or it can be obtained through AI-based spatial-frequency domain CSI compression quantization, or AI-based time-spatial-frequency domain CSI compression quantization. This information needs to go through the NR CSI reporting process, such as uplink channel coding, modulation, and physical resource mapping, and is reported via PUCCH.

[0274] In step S1801, when it is necessary to switch to the CSI prediction and feedback mode based on joint coding, step S1801 is executed, and the network sends a first indication message to the user, indicating that the second feedback process should be entered. This first indication message optionally includes the following:

[0275] (1) The fourth period k4, i.e., the network side sends downlink CSI-RS to the user for CSI measurement at intervals of k4 time units, lasting for M2 periods, and does not send downlink CSI-RS for the subsequent N2 periods. This fourth period k4 can be the same as or different from the third period k3; the number of periods M2 of the measurement window can be the same as or different from M1; the number of periods N2 of the prediction window can be the same as or different from N1. When the first indication information does not additionally indicate the above time-related parameters, the default configuration is the same as in the first measurement feedback process.

[0276] (2) Indicate the length T of the first input information of the first AI / ML model / function / feature. The length of the first input information satisfies the requirement 1≤T≤N2. When T>1, the first AI / ML model / function / feature can jointly compress CSI at multiple time points and provide feedback. If the first indication information does not additionally indicate the length of the first input information, the default value is T=N2, that is, the first AI / ML model / function / feature can jointly compress all predicted CSI results within the prediction window and perform joint compression. If the first indication information indicates T<N2, then N2 needs to be an integer multiple of T (e.g., N2=4, T=2). In this case, the user side needs to call the first AI / ML model / function / feature N2 / T times in sequence to complete the joint compression feedback of CSI at N2 time points.

[0277] (3) Indicates how the first AI / ML model / function / feature works. Same as Example 2.1, so it will not be repeated here.

[0278] (4) Indicate the reporting channel resources for the second feedback information. Same as Example 2.1, and will not be repeated here.

[0279] In step S1802, the network sends a second indication message to the user to exit the second measurement feedback process and revert to the first measurement feedback process. Optionally, the second indication message may indicate the updated third period k3, the number of periods M1 of the measurement window, and the number of periods N1 of the prediction window. By default, the current configuration is used as the third period. This second indication message may be indicated by MACCE or DCI, or by other signaling.

[0280] Example 3.2: Semi-persistent joint CSI prediction and feedback configuration

[0281] This example also supports semi-persistent joint CSI prediction and feedback configuration. Similar to Example 2.2, it includes both two-step and one-step configuration processes. The main process is consistent with Figures 18 and 19; the main differences are described in detail in Example 3.1 and will not be repeated here.

[0282] Example 3.3: Non-periodic joint CSI forecasting and feedback configuration

[0283] For aperiodic joint CSI prediction and feedback, a MAC CE combined with DCI triggering method is used for configuration and triggering, and reported via PUSCH. Similarly, as shown in Figure 20 of Example 2.3, a one-step signaling method is used:

[0284] Specifically, the network sends a fourth instruction message to the user. This fourth instruction message may optionally include:

[0285] (1) Activation indication for CSI reporting; this indication is responsible for activating the functions of non-periodic joint CSI forecasting and feedback reporting:

[0286] (2) The measurement interval of CSI-RS is k5, the number of CSI-RS measurements included in the measurement window is M3, and the CSI prediction length included in the prediction window is N3. Within the measurement window, the network sends downlink CSI-RS to the user for CSI measurement for a duration of M3 time units, with an interval of k5 time units, and does not send downlink CSI-RS for the subsequent N3 time units.

[0287] (3) Indicate the length T of the first input information of the first AI / ML model / function / feature. The length of the first input information satisfies the requirement 1≤T≤N3. When T>1, the first AI / ML model / function / feature can jointly compress CSI at multiple time points and provide feedback. If the fourth indication does not additionally indicate the length of the first input information, the default value is T=N3, that is, the first AI / ML model / function / feature can jointly compress all predicted CSI results within the prediction window and perform joint compression. If the fourth indication indicates T<N3, then N2 needs to be an integer multiple of T (e.g., N3=4, T=2). In this case, the user needs to call the first AI / ML model / function / feature N3 / T times in sequence to complete the joint compression feedback of N3 CSIs.

[0288] (4) Instructing the user on the CSI reporting method. This CSI reporting method includes non-jointly coded methods (as described in the first measurement feedback process above), namely, NR-based codebook feedback, AI-based spatial-frequency domain feedback, and AI-based time-spatial-frequency domain feedback; it also includes jointly coded methods (as described in the second measurement feedback process above), namely, CSI feedback methods based on the first and second AI / ML models / functions / characteristics, and specifically, either the first or second method. However, unlike periodic and semi-continuous CSI feedback, in aperiodic CSI feedback, the user side does not support a second input information as an additional input because the user side cannot obtain stable CSI information from the previous period. Similarly, the network side does not support a fourth input information as an additional input.

[0289] (5) Other CSI reporting configurations, such as the reported physical channel resources and other information.

[0290] This fourth indication can be indicated via MAC CE or DCI signaling, or via other dedicated signaling. Furthermore, it can also be configured via MAC CE and then dynamically triggered by DCI.

[0291] Example 4: Terminal capability reporting

[0292] This example provides a method for terminal capability reporting to support CSI feedback enhancement configuration based on joint coding.

[0293] The terminal's primary capabilities include supporting CSI feedback based on joint coding, supporting the deployment of the first AI / ML model / function / feature, and supporting the reception of first / second / third / fourth instruction information. Specifically, the following reporting methods are possible:

[0294] Method 1: Terminals report CSI feedback capabilities based on joint coding. Terminals with the first capability can also support the first AI / ML model / function / feature, and can also receive the first / second / third / fourth indication information.

[0295] Method 2: The terminal reports its ability to support the first AI / ML model / function / feature. Terminals with the first capability can also support receiving the first / second / third / fourth indication information, and can also support CSI feedback enhancement based on joint coding.

[0296] Method 3: The terminal reports the ability to receive first / second / third / fourth indication information. Terminals with the first capability can also support the deployment of the first AI / ML model / function / feature, and can also support CSI feedback enhancement based on joint coding.

[0297] This application proposes a method to further enhance CSI feedback based on joint coding. Specifically, it includes a spatiotemporal frequency domain CSI feedback and configuration method based on joint coding, and a CSI prediction and feedback configuration method based on joint coding. Using the above scheme, the user side and network side can achieve joint source channel coding and decoding through matched AI / ML model design. Furthermore, by utilizing historical CSI information from past moments, or by simultaneously inputting CSI information from multiple moments for joint compression, the AI / ML model can extract the correlation of CSI from multiple moments, further enhancing CSI feedback performance under non-ideal uplink feedback conditions, thereby improving downlink precoding and transmission performance.

[0298] Figure 21 is a schematic block diagram of a first communication device 2100 according to an embodiment of the present application. The first communication device 2100 may include:

[0299] The first receiving unit 2110 is configured to receive first indication information, which instructs the first communication device to perform joint encoding of CSI.

[0300] Processing unit 2120 is used to perform joint encoding on the CSI.

[0301] In one implementation, the first indication information is further used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

[0302] In one embodiment, the processing unit 2120 is used to:

[0303] The CSI is jointly encoded from the first measurement feedback process to the second measurement feedback process.

[0304] Figure 22 is a schematic flowchart of a first communication device 2200 according to another embodiment of this application. The method may include one or more features of the device described above. In one embodiment, the device further includes:

[0305] The second receiving unit 2210 is used to receive second indication information, which is used to instruct the first communication device to revert from the second measurement feedback process to the first measurement feedback process.

[0306] In one implementation, the second measurement feedback process includes:

[0307] The first communication device performs joint encoding based on the first input information and the second input information to obtain the first output information and the second output information.

[0308] The first input information includes CSI, the second input information includes historical information related to CSI, the first output information includes information jointly encoded based on the first input information and the second input information, and the second output information is historical information related to CSI output based on the first input information and the second input information.

[0309] In one implementation, the second output information is output by the output layer or intermediate layer of the first artificial intelligence scheme.

[0310] In one embodiment, the second input information and / or the second output information are stored in the buffer of the first communication device.

[0311] In one implementation, the first measurement feedback process includes:

[0312] The first communication device receives the Channel State Information Reference Signal (CSI-RS) for the first period;

[0313] The first communication device measures the CSI-RS and obtains the CSI for the first period;

[0314] The first communication device sends first feedback information, which includes CSI quantization information for the first period.

[0315] In one implementation, the first indication information is further used to indicate at least one of the following:

[0316] The second cycle of the CSI-RS is sent during the second measurement feedback process;

[0317] How the first artificial intelligence solution works;

[0318] The reporting channel resources for the second feedback information include the first output information.

[0319] In one implementation, the first measurement feedback process further includes:

[0320] The first communication device receives M third-cycle CSI-RS;

[0321] The first communication device measures the CSI-RS of the M third periods, obtains the CSI of the M third periods within the measurement window, and predicts the CSI of the N third periods within the prediction window based on the CSI of the M third periods within the measurement window.

[0322] The first communication device sends first feedback information, which includes CSI quantization information for the M third periods within the measurement window and CSI quantization information for the N third periods within the prediction window.

[0323] In one implementation, the first indication information is further used to indicate at least one of the following:

[0324] The fourth cycle of the CSI-RS is sent during the second measurement feedback process;

[0325] The duration of the first input information in the first artificial intelligence solution;

[0326] How the first artificial intelligence solution works;

[0327] The reporting channel resources for the second feedback information include the first output information.

[0328] In one embodiment, the device further includes:

[0329] The third receiving unit 2220 is used to receive third indication information, which includes an activation indication reported by CSI.

[0330] In one implementation, the third indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0331] In one implementation, the third indication information further includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

[0332] In one embodiment, the device further includes:

[0333] The fourth receiving unit 2230 is used to receive fourth indication information, which includes an activation indication reported by CSI.

[0334] In one implementation, the fourth indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0335] In one implementation, the fourth instruction information further includes:

[0336] CSI-RS measurement intervals;

[0337] The duration of the first input information in the first artificial intelligence solution;

[0338] CSI reporting methods;

[0339] CSI reporting cycle;

[0340] Channel resources reported by CSI.

[0341] In one implementation, the CSI reporting method includes at least one of the following:

[0342] After CSI reporting is activated, the first measurement feedback process begins.

[0343] After the CSI report is activated, the second measurement feedback process begins.

[0344] How the first artificial intelligence solution works.

[0345] In one implementation, the first artificial intelligence solution operates as follows:

[0346] Encode CSI as a bit stream or complex symbols;

[0347] Whether to use the second input information as an additional input to the second measurement feedback process.

[0348] In one implementation, the CSI quantization information is obtained by at least one of the following methods: quantization using a codebook-based CSI feedback method; quantization using AI-based spatial-frequency domain CSI compression; and quantization using AI-based time-spatial-frequency domain CSI compression.

[0349] The first communication devices 1700 and 1800 in this application embodiment can realize the corresponding functions of the first communication devices in the aforementioned method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the first communication devices 1700 and 1800 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the first communication devices 1700 and 1800 in the application embodiments can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0350] Figure 23 is a schematic block diagram of a second communication device 2300 according to an embodiment of the present application. The second communication device 2300 may include:

[0351] The first transmitting unit 2310 is used to transmit first indication information, which is used to instruct the first communication device to perform joint encoding of CSI.

[0352] In one implementation, the first indication information is further used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

[0353] In one embodiment, the first indication information is used to instruct the first communication device to enter a second measurement feedback process from a first measurement feedback process, in which the CSI is jointly encoded.

[0354] Figure 24 is a schematic flowchart of a second communication device 2400 according to another embodiment of this application. The method may include one or more features of the device described above. In one embodiment, the device further includes:

[0355] The second transmitting unit 2410 is used to transmit second indication information, which is used to instruct the first communication device to revert from the second measurement feedback process to the first measurement feedback process.

[0356] In one embodiment, the device further includes:

[0357] The first receiving unit 2420 is used to receive first output information; wherein, the first output information includes information jointly encoded by the first communication device based on first input information and second input information, the first input information includes CSI, and the second input information includes CSI-related information;

[0358] Processing unit 2430 is configured to obtain third output information and fourth output information based on third input information and fourth input information; wherein the third input information includes the first output information, the fourth input information includes CSI-related historical information, and the fourth output information is the CSI-related historical information output based on the third input information and the fourth input information.

[0359] In one implementation, the fourth output information is output by the output layer or intermediate layer of the second artificial intelligence scheme.

[0360] In one embodiment, the fourth input information and / or the fourth output information are stored in the buffer of the second communication device.

[0361] In one implementation, during the first measurement feedback process, the second communication device performs the following steps:

[0362] The second communication device transmits a first-cycle Channel State Information Reference Signal (CSI-RS);

[0363] The second communication device receives first feedback information, which includes CSI quantization information for the first period obtained by the first communication device from measuring the CSI-RS.

[0364] In one implementation, the first indication information is further used to indicate at least one of the following:

[0365] The second cycle of the CSI-RS is sent during the second measurement feedback process;

[0366] How the first artificial intelligence solution works;

[0367] The reporting channel resources for the second feedback information include the first output information.

[0368] In one implementation, during the first measurement feedback process, the second communication device performs the following steps:

[0369] The second communication device sends M third-cycle CSI-RS;

[0370] The second communication device receives first feedback information, which includes CSI quantization information of the M third periods within the measurement window obtained by the second communication device measuring the CSI-RS of the M third periods, and CSI quantization information of the N third periods within the prediction window obtained based on the CSI prediction of the M third periods within the measurement window.

[0371] In one implementation, the first indication information is further used to indicate at least one of the following:

[0372] The fourth cycle of the CSI-RS is sent during the second measurement feedback process;

[0373] The duration of the first input information in the first artificial intelligence solution;

[0374] How the first artificial intelligence solution works;

[0375] The reporting channel resources for the second feedback information include the first output information.

[0376] In one embodiment, the device further includes:

[0377] The third sending unit 2440 is used to send third indication information, which includes an activation indication reported by CSI.

[0378] In one implementation, the third indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0379] In one implementation, the third indication information further includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

[0380] In one embodiment, the device further includes:

[0381] The fourth sending unit 2450 is used to send fourth indication information, which includes an activation indication reported by CSI.

[0382] In one implementation, the fourth indication information is used to instruct the first communication device to enter the first measurement feedback process after CSI reporting is activated.

[0383] In one implementation, the fourth instruction information further includes:

[0384] CSI-RS measurement intervals;

[0385] The duration of the first input information in the first artificial intelligence solution;

[0386] CSI reporting methods;

[0387] CSI reporting cycle;

[0388] Channel resources reported by CSI.

[0389] In one implementation, the CSI reporting method includes at least one of the following:

[0390] After CSI reporting is activated, the first measurement feedback process begins.

[0391] After the CSI report is activated, the second measurement feedback process begins.

[0392] How the first artificial intelligence solution works.

[0393] In one implementation, the first artificial intelligence solution operates as follows:

[0394] Encode CSI as a bit stream or complex symbols;

[0395] Whether to use the second input information as an additional input to the second measurement feedback process.

[0396] In one implementation, the CSI quantization information is obtained by at least one of the following methods: quantization using a codebook-based CSI feedback method; quantization using AI-based spatial-frequency domain CSI compression; and quantization using AI-based time-spatial-frequency domain CSI compression.

[0397] The second communication devices 2300 and 2400 in this application embodiment can realize the corresponding functions of the second communication devices in the aforementioned method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the second communication devices 2300 and 2400 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the second communication devices 2300 and 2400 in the application embodiments can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0398] Figure 25 is a schematic structural diagram of a communication device 2500 according to an embodiment of this application. The communication device 2500 includes a processor 2510, which can call and run computer programs from memory to enable the communication device 2500 to implement the methods in the embodiments of this application.

[0399] In one embodiment, the communication device 2500 may further include a memory 2520. The processor 2510 can retrieve and run computer programs from the memory 2520 to enable the communication device 2500 to implement the methods described in the embodiments of this application.

[0400] The memory 2520 can be a separate device independent of the processor 2510, or it can be integrated into the processor 2510.

[0401] In one embodiment, the communication device 2500 may further include a transceiver 2530, and the processor 2510 may control the transceiver 2530 to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices.

[0402] The transceiver 2530 may include a transmitter and a receiver. The transceiver 2530 may further include an antenna, which may be one or more.

[0403] In one embodiment, the communication device 2500 may be the first communication device in the embodiments of this application, and the communication device 2500 may implement the corresponding processes implemented by the first communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0404] In one embodiment, the communication device 2500 may be a second communication device in the embodiments of this application, and the communication device 2500 may implement the corresponding processes implemented by the second communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0405] Figure 26 is a schematic structural diagram of a chip 2600 according to an embodiment of this application. The chip 2600 includes a processor 2610, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0406] In one embodiment, chip 2600 may further include memory 2620. Processor 2610 can retrieve and run computer programs from memory 2620 to implement the methods executed by the first communication device or the second communication device in this embodiment.

[0407] The memory 2620 can be a separate device independent of the processor 2610, or it can be integrated into the processor 2610.

[0408] In one embodiment, the chip 2600 may further include an input interface 2630. The processor 2610 can control the input interface 2630 to communicate with other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0409] In one embodiment, the chip 2600 may further include an output interface 2640. The processor 2610 can control the output interface 2640 to communicate with other devices or chips; specifically, it can output information or data to other devices or chips.

[0410] In one implementation, the chip can be applied to the first communication device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the first communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0411] In one implementation, the chip can be applied to the second communication device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the second communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0412] The chips used in the first communication device and the second communication device can be the same chip or different chips.

[0413] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0414] The processors mentioned above can be general-purpose processors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processors mentioned above can be microprocessors or any conventional processor.

[0415] The aforementioned memory can be volatile memory or non-volatile memory, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM).

[0416] It should be understood that the above-described memory is exemplary but not restrictive. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0417] Figure 27 is a schematic block diagram of a communication system 2700 according to an embodiment of the present application. The communication system 2700 includes a first communication device 2710 and a second communication device 2720.

[0418] The second communication device 2720 is used to send first indication information, which instructs the first communication device to perform joint encoding of CSI.

[0419] The first communication device 2710 is used to receive the first instruction information.

[0420] The first communication device 2710 can be used to implement the corresponding functions implemented by the first communication device in the above method, and the second communication device 2720 can be used to implement the corresponding functions implemented by the second communication device in the above method. For the sake of brevity, further details are omitted here.

[0421] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0422] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply 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 this application.

[0423] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0424] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A channel state information processing method, comprising: The first communication device receives a first indication information, which instructs the first communication device to perform joint encoding of Channel State Information (CSI). The first communication device performs joint encoding on the CSI.

2. The method according to claim 1, wherein, The first indication information is also used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

3. The method according to claim 1, wherein, The first communication device performs joint encoding of the CSI, including: The first communication device enters the second measurement feedback process from the first measurement feedback process, and performs joint encoding on the CSI during the second measurement feedback process.

4. The method according to claim 3, wherein, The method further includes: The first communication device receives a second instruction, which instructs the first communication device to revert from the second measurement feedback process back to the first measurement feedback process.

5. The method according to claim 3, wherein, The second measurement feedback process includes: The first communication device performs joint encoding based on the first input information and the second input information to obtain the first output information and the second output information; Wherein, the first input information includes CSI, the second input information includes historical information related to CSI, the first output information includes information jointly encoded based on the first input information and the second input information, and the second output information is historical information related to CSI output based on the first input information and the second input information.

6. The method according to claim 5, wherein, The second output information is output from the output layer or intermediate layer of the first artificial intelligence scheme.

7. The method according to claim 5 or 6, wherein, The second input information and / or the second output information are stored in the buffer of the first communication device.

8. The method according to any one of claims 3 to 7, wherein, The first measurement feedback process includes: The first communication device receives the Channel State Information Reference Signal (CSI-RS) for the first period; The first communication device measures the CSI-RS to obtain the CSI for the first period; The first communication device sends first feedback information, which includes CSI quantization information for the first period.

9. The method according to claim 8, wherein, The first indication information is also used to indicate at least one of the following: The second cycle of the CSI-RS is sent during the second measurement feedback process; How the first artificial intelligence solution works; The reporting channel resources for the second feedback information are indicated, and the second feedback information includes the first output information.

10. The method according to any one of claims 3 to 6, wherein, The first measurement feedback process also includes: The first communication device receives M third-cycle CSI-RS; The first communication device measures the CSI-RS of the M third periods, obtains the CSI of the M third periods within the measurement window, and predicts the CSI of the N third periods within the prediction window based on the CSI of the M third periods within the measurement window. The first communication device sends first feedback information, which includes CSI quantization information for the M third periods within the measurement window and CSI quantization information for the N third periods within the prediction window.

11. The method according to claim 10, wherein, The first indication information is also used to indicate at least one of the following: The fourth cycle of the CSI-RS is sent during the second measurement feedback process; The duration of the first input information in the first artificial intelligence solution; How the first artificial intelligence solution works; The reporting channel resources for the second feedback information are indicated, and the second feedback information includes the first output information.

12. The method according to any one of claims 1 to 7, wherein, The method further includes: The first communication device receives third indication information, which includes an activation indication reported by CSI.

13. The method according to claim 12, wherein, The third indication information is used to indicate that the first communication device enters the first measurement feedback process after the CSI reporting is activated.

14. The method according to claim 12, wherein, The third indication information also includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

15. The method according to any one of claims 1 to 7, wherein, The method further includes: The first communication device receives a fourth indication message, which includes an activation indication reported by the CSI.

16. The method according to claim 15, wherein, The fourth indication information is used to indicate that the first communication device enters the first measurement feedback process after the CSI reporting is activated.

17. The method according to claim 15, wherein, The fourth instruction information also includes: CSI-RS measurement intervals; The duration of the first input information in the first artificial intelligence solution; CSI reporting methods; CSI reporting cycle; Channel resources reported by CSI.

18. The method according to claim 14 or 17, wherein, The CSI reporting method includes at least one of the following: After the CSI report is activated, the first measurement feedback process begins. After the CSI report is activated, the second measurement feedback process begins. How the first artificial intelligence solution works.

19. The method according to claim 9, 11 or 17, wherein, The working method of the first artificial intelligence solution includes: Encode CSI as a bit stream or complex symbols; Whether to use the second input information as an additional input for the second measurement feedback process.

20. The method according to claim 8 or 10, wherein, The CSI quantization information is obtained in at least one of the following ways: quantization using a codebook-based CSI feedback method; quantization using AI-based spatial and frequency domain CSI compression; and quantization using AI-based time, spatial, and frequency domain CSI compression.

21. A channel state information processing method, comprising: The second communication device sends a first instruction message, which instructs the first communication device to perform joint encoding of the CSI.

22. The method according to claim 21, wherein, The first indication information is also used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

23. The method according to claim 21, wherein, The first indication information is used to instruct the first communication device to enter the second measurement feedback process from the first measurement feedback process, and to perform joint encoding of the CSI in the second measurement feedback process.

24. The method according to claim 23, wherein, The method further includes: The second communication device sends a second indication message, which instructs the first communication device to revert from the second measurement feedback process back to the first measurement feedback process.

25. The method according to claim 23, wherein, The method further includes: The second communication device receives first output information; wherein, the first output information includes information jointly encoded by the first communication device based on first input information and second input information, the first input information includes CSI, and the second input information includes CSI-related information; The second communication device obtains third output information and fourth output information based on third input information and fourth input information; wherein, the third input information includes the first output information, the fourth input information includes CSI-related historical information, and the fourth output information outputs CSI-related historical information based on the third input information and the fourth input information.

26. The method of claim 25, wherein, The fourth output information is output from the output layer or intermediate layer of the second artificial intelligence scheme.

27. The method according to claim 25 or 26, wherein, The fourth input information and / or the fourth output information are stored in the buffer of the second communication device.

28. The method according to any one of claims 23 to 27, wherein, During the first measurement feedback process, the second communication device performs the following steps: The second communication device transmits a Channel State Information Reference Signal (CSI-RS) for the first period; The second communication device receives first feedback information, which includes CSI quantization information for the first period obtained by the first communication device from measuring the CSI-RS.

29. The method according to claim 28, wherein, The first indication information is also used to indicate at least one of the following: The second cycle of the CSI-RS is sent during the second measurement feedback process; How the first artificial intelligence solution works; The reporting channel resources for the second feedback information are indicated, and the second feedback information includes the first output information.

30. The method according to any one of claims 23 to 26, wherein, During the first measurement feedback process, the second communication device performs the following steps: The second communication device sends M third-cycle CSI-RS; The second communication device receives first feedback information, which includes CSI quantization information of the M third periods within a measurement window obtained by the second communication device measuring the CSI-RS of the M third periods, and CSI quantization information of the N third periods within a prediction window obtained based on the CSI prediction of the M third periods within the measurement window.

31. The method according to claim 30, wherein, The first indication information is also used to indicate at least one of the following: The fourth cycle of the CSI-RS is sent during the second measurement feedback process; The duration of the first input information in the first artificial intelligence solution; How the first artificial intelligence solution works; Indicates the reporting channel resources for the second feedback information.

32. The method according to any one of claims 21 to 27, wherein, The method further includes: The second communication device sends a third indication message, which includes an activation indication reported by the CSI.

33. The method according to claim 32, wherein, The third indication information is used to indicate that the first communication device enters the first measurement feedback process after the CSI reporting is activated.

34. The method according to claim 32, wherein, The third indication information also includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

35. The method according to any one of claims 21 to 27, wherein, The method further includes: The second communication device sends a fourth indication message, which includes an activation indication reported by the CSI.

36. The method according to claim 35, wherein, The fourth indication information is used to instruct the first communication device to enter the first measurement feedback process after the CSI reporting is activated.

37. The method of claim 35, wherein, The fourth instruction information also includes: CSI-RS measurement intervals; The duration of the first input information in the first artificial intelligence solution; CSI reporting methods; CSI reporting cycle; Channel resources reported by CSI.

38. The method according to claim 34 or 37, wherein, The CSI reporting method includes at least one of the following: After the CSI report is activated, the first measurement feedback process begins. After the CSI report is activated, the second measurement feedback process begins. How the first artificial intelligence solution works.

39. The method according to claim 29, 31 or 37, wherein, The working method of the first artificial intelligence solution includes: Encode CSI as a bit stream or complex symbols; Whether to use the second input information as an additional input for the second measurement feedback process.

40. The method according to claim 28 or 30, wherein, The CSI quantization information is obtained in at least one of the following ways: quantization using a codebook-based CSI feedback method; quantization using AI-based spatial and frequency domain CSI compression; and quantization using AI-based time, spatial, and frequency domain CSI compression.

41. A first communication device, comprising: The first receiving unit is configured to receive first indication information, which instructs the first communication device to perform joint encoding of CSI. A processing unit is used to perform joint encoding on the CSI.

42. The device according to claim 41, wherein, The first indication information is also used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

43. The device according to claim 41, wherein, The processing unit is used for: The process transitions from the first measurement feedback process to the second measurement feedback process, during which the CSI is jointly encoded.

44. The device according to claim 43, wherein, The device also includes: The second receiving unit is configured to receive second indication information, which instructs the first communication device to revert from the second measurement feedback process to the first measurement feedback process.

45. The device according to claim 43, wherein, The second measurement feedback process includes: The first communication device performs joint encoding based on the first input information and the second input information to obtain the first output information and the second output information; Wherein, the first input information includes CSI, the second input information includes historical information related to CSI, the first output information includes information jointly encoded based on the first input information and the second input information, and the second output information is historical information related to CSI output based on the first input information and the second input information.

46. ​​The device according to claim 45, wherein, The second output information is output from the output layer or intermediate layer of the first artificial intelligence scheme.

47. The device according to claim 45 or 46, wherein, The second input information and / or the second output information are stored in the buffer of the first communication device.

48. The device according to any one of claims 43 to 47, wherein, The first measurement feedback process includes: The first communication device receives the Channel State Information Reference Signal (CSI-RS) for the first period; The first communication device measures the CSI-RS to obtain the CSI for the first period; The first communication device sends first feedback information, which includes CSI quantization information for the first period.

49. The device according to claim 48, wherein, The first indication information is also used to indicate at least one of the following: The second cycle of the CSI-RS is sent during the second measurement feedback process; How the first artificial intelligence solution works; The reporting channel resources for the second feedback information are indicated, and the second feedback information includes the first output information.

50. The device according to any one of claims 43 to 46, wherein, The first measurement feedback process also includes: The first communication device receives M third-cycle CSI-RS; The first communication device measures the CSI-RS of the M third periods, obtains the CSI of the M third periods within the measurement window, and predicts the CSI of the N third periods within the prediction window based on the CSI of the M third periods within the measurement window. The first communication device sends first feedback information, which includes CSI quantization information for the M third periods within the measurement window and CSI quantization information for the N third periods within the prediction window.

51. The device according to claim 50, wherein, The first indication information is also used to indicate at least one of the following: The fourth cycle of the CSI-RS is sent during the second measurement feedback process; The duration of the first input information in the first artificial intelligence solution; How the first artificial intelligence solution works; The reporting channel resources for the second feedback information are indicated, and the second feedback information includes the first output information.

52. The device according to any one of claims 41 to 47, wherein, The device also includes: The third receiving unit is used to receive third indication information, which includes an activation indication reported by CSI.

53. The device according to claim 52, wherein, The third indication information is used to indicate that the first communication device enters the first measurement feedback process after the CSI reporting is activated.

54. The device according to claim 52, wherein, The third indication information also includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

55. The device according to any one of claims 41 to 47, wherein, The device also includes: The fourth receiving unit is used to receive fourth indication information, which includes an activation indication reported by CSI.

56. The device according to claim 55, wherein, The fourth indication information is used to indicate that the first communication device enters the first measurement feedback process after the CSI reporting is activated.

57. The device according to claim 55, wherein, The fourth instruction information also includes: CSI-RS measurement intervals; The duration of the first input information in the first artificial intelligence solution; CSI reporting methods; CSI reporting cycle; Channel resources reported by CSI.

58. The device according to claim 54 or 57, wherein, The CSI reporting method includes at least one of the following: After the CSI report is activated, the first measurement feedback process begins. After the CSI report is activated, the second measurement feedback process begins. How the first artificial intelligence solution works.

59. The device according to claim 49, 51 or 57, wherein, The working method of the first artificial intelligence solution includes: Encode CSI as a bit stream or complex symbols; Whether to use the second input information as an additional input for the second measurement feedback process.

60. The device according to claim 48 or 50, wherein, The CSI quantization information is obtained in at least one of the following ways: quantization using a codebook-based CSI feedback method; quantization using AI-based spatial and frequency domain CSI compression; and quantization using AI-based time, spatial, and frequency domain CSI compression.

61. A second communication device, comprising: The first transmitting unit is configured to transmit first indication information, which instructs the first communication device to perform joint encoding of CSI.

62. The device according to claim 61, wherein, The first indication information is also used to indicate whether the first communication device uses historical information related to CSI during the joint encoding of CSI.

63. The device according to claim 61, wherein, The first indication information is used to instruct the first communication device to enter the second measurement feedback process from the first measurement feedback process, and to perform joint encoding of the CSI in the second measurement feedback process.

64. The device according to claim 63, wherein, The device also includes: The second sending unit is used to send second indication information, which instructs the first communication device to revert from the second measurement feedback process to the first measurement feedback process.

65. The device according to claim 63, wherein, The device also includes: The first receiving unit is configured to receive first output information; wherein the first output information includes information jointly encoded by the first communication device based on first input information and second input information, the first input information includes CSI, and the second input information includes CSI-related information. The processing unit is configured to obtain third output information and fourth output information based on third input information and fourth input information; wherein the third input information includes the first output information, the fourth input information includes CSI-related historical information, and the fourth output information is the CSI-related historical information output based on the third input information and the fourth input information.

66. The device according to claim 65, wherein, The fourth output information is output from the output layer or intermediate layer of the second artificial intelligence scheme.

67. The device according to claim 65 or 66, wherein, The fourth input information and / or the fourth output information are stored in the buffer of the second communication device.

68. The device according to any one of claims 63 to 67, wherein, During the first measurement feedback process, the second communication device performs the following steps: The second communication device transmits a Channel State Information Reference Signal (CSI-RS) for the first period; The second communication device receives first feedback information, which includes CSI quantization information for the first period obtained by the first communication device from measuring the CSI-RS.

69. The device according to claim 68, wherein, The first indication information is also used to indicate at least one of the following: The second cycle of the CSI-RS is sent during the second measurement feedback process; How the first artificial intelligence solution works; The reporting channel resources for the second feedback information are indicated, and the second feedback information includes the first output information.

70. The device according to any one of claims 63 to 66, wherein, During the first measurement feedback process, the second communication device performs the following steps: The second communication device sends M third-cycle CSI-RS; The second communication device receives first feedback information, which includes CSI quantization information of the M third periods within a measurement window obtained by the second communication device measuring the CSI-RS of the M third periods, and CSI quantization information of the N third periods within a prediction window obtained based on the CSI prediction of the M third periods within the measurement window.

71. The device according to claim 70, wherein, The first indication information is also used to indicate at least one of the following: The fourth cycle of the CSI-RS is sent during the second measurement feedback process; The duration of the first input information in the first artificial intelligence solution; How the first artificial intelligence solution works; The reporting channel resources for the second feedback information are indicated, and the second feedback information includes the first output information.

72. The device according to any one of claims 61 to 67, wherein, The device also includes: The third sending unit is used to send third indication information, which includes an activation indication reported by CSI.

73. The device according to claim 72, wherein, The third indication information is used to indicate that the first communication device enters the first measurement feedback process after the CSI reporting is activated.

74. The device according to claim 72, wherein, The third indication information also includes: CSI reporting method; CSI reporting period; and channel resources for CSI reporting.

75. The device according to any one of claims 61 to 67, wherein, The device also includes: The fourth sending unit is used to send fourth indication information, which includes an activation indication reported by CSI.

76. The device according to claim 75, wherein, The fourth indication information is used to indicate that the first communication device enters the first measurement feedback process after the CSI reporting is activated.

77. The device according to claim 75, wherein, The fourth instruction information also includes: CSI-RS measurement intervals; The duration of the first input information in the first artificial intelligence solution; CSI reporting methods; CSI reporting cycle; Channel resources reported by CSI.

78. The device according to claim 74 or 77, wherein, The CSI reporting method includes at least one of the following: After the CSI report is activated, the first measurement feedback process begins. After the CSI report is activated, the second measurement feedback process begins. How the first artificial intelligence solution works.

79. The device according to claim 69, 71 or 77, wherein, The working method of the first artificial intelligence solution includes: Encode CSI as a bit stream or complex symbols; Whether to use the second input information as an additional input for the second measurement feedback process.

80. The device according to claim 68 or 70, wherein, The CSI quantization information is obtained in at least one of the following ways: quantization using a codebook-based CSI feedback method; quantization using AI-based spatial and frequency domain CSI compression; and quantization using AI-based time, spatial, and frequency domain CSI compression.

81. A communication device, comprising: A transceiver, a processor, and a memory, wherein the memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to invoke and run the computer program stored in the memory to cause the communication device to perform the method as described in any one of claims 1 to 49.

82. A chip, comprising: A processor for retrieving and running a computer program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1 to 40.

83. A computer-readable storage medium for storing a computer program that, when run by a device, causes the device to perform the method as claimed in any one of claims 1 to 40.

84. A computer program product comprising computer program instructions that cause a computer to perform the method as described in any one of claims 1 to 40.

85. A computer program that causes a computer to perform the method as claimed in any one of claims 1 to 40.

86. A communication system, comprising: A first communication device is configured to perform the method as described in any one of claims 1 to 20; A second communication device is used to perform the method as described in any one of claims 21 to 40.

Images