Wireless communication method and apparatus, and device

Abstract

The present application belongs to the field of communications. Disclosed are a wireless communication method and apparatus, and a device. The wireless communication method comprises: a first device coding source information on the basis of at least two coding modes, so as to acquire target information, wherein the at least two coding modes comprise at least two of a first coding mode, a second coding mode and a third coding mode, the first coding mode is SSCC, the second coding mode is bit-level JSCC, and the third coding mode is symbol-level JSCC; and the first device sending the target information to a second device.

Description

Wireless communication methods, apparatus and equipment

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411213697.0, filed on August 30, 2024, entitled "Wireless Communication Method, Apparatus and Device", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of communication technology, specifically relating to a wireless communication method, apparatus, and device. Background Technology

[0004] In related technologies, terminal or network-side devices can employ Separate Source Channel Coding (SSCC) for information transmission, such as for Channel State Information (CSI) feedback, or Joint Source Channel Coding (JSCC). In Separate Source Channel Coding, at the transmitting end, source coding (e.g., encoding the Precoding Matrix Indicator (PMI) using a codebook-based method) is first used to compress the data to reduce redundancy. Then, channel coding (e.g., using Polar codes) is used to increase redundancy to combat transmission errors caused by channel fluctuations during CSI transmission. In contrast, Joint Source Channel Coding requires simultaneous consideration of source and channel characteristics, optimizing the entire coding process through joint design to ensure optimal data transmission under given channel conditions.

[0005] For the separate source channel coding method, when the actual transmission channel conditions deteriorate slightly, the channel decoding may not be able to effectively correct errors, resulting in decoding failure and a sharp decline in source transmission performance.

[0006] The joint source-channel coding method has certain errors and cannot guarantee the completely accurate transmission of the source.

[0007] Therefore, how to improve the feedback performance of encoded information while ensuring the accuracy of the feedback is a problem that needs to be solved. Summary of the Invention

[0008] This application provides a wireless communication method, apparatus, and device that can solve the problems of insufficient feedback performance of encoded information in separate source channel coding and the inability to guarantee the complete and accurate transmission of the source in joint source channel coding.

[0009] Firstly, a wireless communication method is provided, comprising:

[0010] The first device encodes source information according to at least two encoding methods to obtain target information; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC.

[0011] The first device sends the target information to the second device.

[0012] Secondly, a wireless communication method is provided, including:

[0013] The second device receives target information from the first device; wherein the target information is obtained by encoding source information based on at least two encoding methods, the at least two encoding methods include at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-level JSCC;

[0014] The second device decodes the target information to obtain the decoded information.

[0015] Thirdly, a wireless communication device is provided, comprising:

[0016] The processing module is used to encode source information according to at least two encoding methods to obtain target information; wherein the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC.

[0017] The sending module is used to send the target information to the second device.

[0018] Fourthly, a wireless communication device is provided, comprising:

[0019] A receiving module is configured to receive target information from a first device; wherein the target information is obtained by encoding source information based on at least two encoding methods, the at least two encoding methods including at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method being Separate Source Channel Coding (SSCC), the second encoding method being Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method being Symbol-Level JSCC;

[0020] The processing module is used to decode the target information to obtain the decoded information.

[0021] Fifthly, a wireless communication device is provided, the device being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0022] In a sixth aspect, a first device is provided, the first device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0023] In a seventh aspect, a first device is provided, including a processor and a communication interface;

[0024] The processor is used to encode source information according to at least two encoding methods to obtain target information; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC.

[0025] The communication interface is used to send the target information to the second device.

[0026] In an eighth aspect, a second device is provided, the second device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect.

[0027] In a ninth aspect, a second device is provided, including a processor and a communication interface;

[0028] The communication interface is used to receive target information from the first device; wherein the target information is obtained by encoding source information based on at least two encoding methods, the at least two encoding methods include at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-level JSCC;

[0029] The processor is used to decode the target information to obtain decoded information.

[0030] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0031] Eleventhly, a wireless communication system is provided, comprising: a first device and a second device, wherein the first device is configured to perform the steps of the method as described in the first aspect, and the second device is configured to perform the steps of the method as described in the second aspect.

[0032] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0033] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the wireless communication method as described in the first aspect, or to implement the steps of the wireless communication method as described in the second aspect.

[0034] In this embodiment, the first device encodes source information according to at least two encoding methods to obtain target information. The at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method. The first encoding method is SSCC, the second encoding method is bit-level JSCC, and the third encoding method is symbol-level JSCC. The first device sends the target information to the second device. Specifically, this embodiment can achieve flexible source information encoding and feedback through hybrid encoding (at least two of the first, second, and third encoding methods). For content with high accuracy requirements, SSCC is used to ensure the accuracy of the feedback. For content with high real-time requirements, and / or for content with low feedback accuracy requirements, JSCC (bit-level JSCC and / or symbol-level JSCC) is used to improve feedback efficiency. Attached Figure Description

[0035] Figure 1 is a schematic diagram of a communication system architecture provided in an embodiment of this application.

[0036] Figure 2 is a schematic diagram of a CSI compression process based on an AI model provided in an embodiment of this application.

[0037] Figure 3 is a schematic flowchart of a wireless communication method provided according to an embodiment of this application.

[0038] Figure 4 is a schematic block diagram of a wireless communication device according to an embodiment of this application.

[0039] Figure 5 is a schematic block diagram of another wireless communication device provided according to an embodiment of this application.

[0040] Figure 6 is a schematic block diagram of a communication device provided according to an embodiment of this application.

[0041] Figure 7 is a schematic diagram of the hardware structure of a terminal according to an embodiment of this application.

[0042] Figure 8 is a schematic block diagram of a network-side device provided according to an embodiment of this application.

[0043] Figure 9 is a schematic block diagram of another network-side device provided according to an embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0045] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0046] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0047] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0048] Figure 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application. Specifically, the wireless communication system includes a terminal 11 and a network-side device 12.

[0049] Terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipborne equipment, pedestrian user equipment (PUE), smart home device (home device with wireless communication function, such as refrigerator, television, washing machine or furniture), game console, personal computer (PC), ATM or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart earphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in the embodiments of this application.

[0050] Among them, network-side equipment 12 may include access network equipment or core network equipment.

[0051] Alternatively, access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, wireless local area network (WLAN) access points (APs), or wireless Fidelity (WiFi) nodes, etc. The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0052] Optionally, core network equipment may also be referred to as core network nodes, core network functions, or core network elements, and includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support. The core network functions include: BSF (Block Network Function), Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), and Network Data Analytics Function (NWDAF). It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0053] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0054] To better understand the technical solution of this application, the following explains the relevant CSI information.

[0055] In an NR system, CSI information may include at least one of the following: CSI-RS Resource Indicator (CRI), SS / PBCH Block Resource Indicator (SSBRI), Layer Indicator (LI), Rank Indication (RI), Layer 1 Reference Signal Received Power (L1-RSRP), Layer 1 Signal to Interference plus Noise Ratio (L1-SINR), and Time-Domain Channel Probing (TDCP).

[0056] Regarding CRI and SSBRI: These are resource indication identifiers. For this type of information, during CSI feedback, events identified by CRI or SSBRI are typically considered to be of equal probability and cannot be further compressed, thus requiring no source coding of resource indication identifiers.

[0057] RI: Indicates the number of transport layers supported by the UE. RI is less than or equal to the number of UE antenna ports. The UE calculates RI based on channel measurements indicated by CRI. RI has low overhead; for example, 2 bits of information can identify 1 to 4 transport layers.

[0058] LI: Indicates the column of the PMI corresponding to the strongest signal in the report; the UE calculates LI based on the Channel Quantity Indicator (CQI), PMI, RI and CRI; LI has low overhead, such as a 4-bit bitmap that can identify any of the four strongest transport layers.

[0059] L1-RSRP source coding: When the higher-layer parameter nrofReportedRS is configured to 1, the value of L1-RSRP is quantized into a 7-bit value with a step size of 1dB in the range [-140, 44]dBm. When the higher-layer parameter nrofReportedRS is configured to be greater than 1 or the higher-layer parameter groupBasedBeamReporting is enabled, the maximum value in L1-RSRP is quantized into a 7-bit value with a step size of 1dB in the range [-140, 44]dBm, and the remaining L1-RSRP values ​​are differentially quantized with the maximum L1-RSRP into 4-bit values ​​with a step size of 2dB.

[0060] L1-SINR is used for source coding: When the higher-layer parameter nrofReportedRS is configured to 1, the L1-SINR value is quantized into a 7-bit value with a step size of 0.5dB in the range [-23, 40]dB. When the higher-layer parameter nrofReportedRS is configured to be greater than 1 or the higher-layer parameter groupBasedBeamReporting is enabled, the maximum value in L1-SINR is quantized into a 7-bit value with a step size of 0.5dB in the range [-23, 40]dB, and the remaining L1-SINR values ​​are differentially quantized with the maximum L1-SINR into 4-bit values ​​with a step size of 1dB.

[0061] TDCP performs source coding: The higher-layer parameter `reportQuantity` is configured to 'tdcp' and `Y` is greater than or equal to 1, indicating that Y time-domain delays are configured; the amplitude value of each delay is represented by 4 bits. If the higher-layer parameter `phase` is configured, the phase of each delay is represented as... c i ∈{0,1,…,15}, represented by 4 bits.

[0062] CQI coding: CQI is calculated based on PMI, RI, and CRI.

[0063] Broadband CQI: Uses 4 bits of information to identify the broadband CQI index.

[0064] Subband CQI: If the higher-layer parameter cqi-BitsPerSubband is not configured, 2 bits are used to identify the interpolation of subband CQI and wideband CQI; if the higher-layer parameter cqi-BitsPerSubband is configured, 4 bits are used to identify the subband CQI index.

[0065] PMI coding: Channel estimation is performed on CRI measurement resources, and the estimated channel H is decomposed into SVD: H = UΣV HCodebook-based encoding is performed on some or all vectors in the V matrix (determined by RI and CRI).

[0066] Currently, the codebook types that can be used for CSI feedback are: Type I, Type II, Enhanced Type II, and Further Enhanced Type II. The feedback amount and feedback accuracy of the four codebooks for CSI feedback types increase from small to large.

[0067] To better understand the technical solution of this application, the following explains the CSI feedback method of the separated source channel coding related to this application.

[0068] The terminal (UE) concatenates and aggregates some or all of the encoded CSI information according to the reporting instructions configured on the network (NW). Based on the uplink channel quality sent by the NW, it adds a Cyclic Redundancy Check (CRC) to the encoded CSI information and performs channel coding, modulation, and mapping to transmit symbols. The NW side performs corresponding demapping, demodulation, channel decoding, CSI information partitioning, and source decoding, performs CRC checks, and obtains the original CSI information.

[0069] As 6G demands higher transmission rates, the number of antenna ports will increase further, leading to a greater feedback quantity in the CSI feedback method with separate source channel coding, which reduces the spectrum utilization of uplink transmission.

[0070] To better understand the technical solution of this application, the following explains the CSI feedback enhancement based on the artificial intelligence (AI) model related to this application.

[0071] The CSI compression process based on the AI ​​model can be illustrated in Figure 2. The bilateral AI model includes an AI-based CSI generation model and an AI-based CSI reconstruction model. The AI-based CSI generation model is placed on the terminal side to generate CSI feedback information; the AI-based CSI reconstruction model is placed on the network side to reconstruct the CSI from the received CSI feedback information. To generate the input for the CSI generation model, further preprocessing of the measured channel may be required, such as SVD decomposition. Further post-processing can also be performed on the output of the CSI reconstruction model. The CSI generated by the AI ​​model on the terminal side needs to be quantized before output. Quantization can be achieved using AI-based quantization methods or existing quantization methods. After receiving the quantized CSI feedback, the gNB performs dequantization processing, which can also be achieved using AI-based dequantization methods or existing quantization methods. Quantization / dequantization processing may be integrated into the CSI generation / reconstruction process. AI-based CSI feedback enhancement is still considered part of source coding.

[0072] In the CSI feedback of the NR system, PMI feedback accounts for the majority of the CSI feedback overhead. Simulations compare the AI ​​CSI feedback scheme based on PMI and the NR CSI feedback scheme. Simulation results show that, compared with the NR system's CSI feedback scheme, the AI ​​model-based feedback scheme achieves better performance gains in Square Generalized Cosine Similarity (SGCS) (a key performance indicator, representing the quality of PMI feedback) and throughput (a system-level KPI).

[0073] While AI-based CSI feedback can achieve better performance gains than codebook-based CSI feedback, it relies on a separate source channel coding architecture and cannot benefit from the additional performance gains of joint source channel coding. Furthermore, when transient channel jitter occurs, separate source channel coding requires a Hybrid Automatic Repeat reQuest (HARQ) mechanism to ensure transmission accuracy. This mechanism inevitably introduces CSI transmission delay, leading to problems such as CSI aging and failure.

[0074] To better understand the technical solution of this application, the following describes the joint source-channel coding based on the AI ​​model (also known as the CSI feedback method of joint source-channel coding) related to this application.

[0075] In 5G NR communication systems, CSI feedback is performed using a separate source-channel coding approach. Specifically, at the transmitting end, source coding is first used to compress data to reduce redundancy; for example, a codebook-based coding method is used to encode the PMI. Then, channel coding is used to increase redundancy to combat transmission errors caused by channel fluctuations during transmission; for example, the NR system uses Polar codes for channel coding.

[0076] Compared to separate source-channel coding, joint source-channel coding considers both source and channel characteristics during the CSI feedback process. It optimizes the entire coding process through joint design, ensuring data is transmitted optimally under given channel conditions. However, joint source-channel coding design faces numerous challenges, including complex joint optimization problems and matching diverse source and channel characteristics. Through end-to-end learning, AI technology can directly learn the optimal joint source-channel coding scheme from specific sources and channels, reducing the design complexity and enabling its application in wireless communication systems.

[0077] Compared to separate source channel coding, joint source channel coding achieves higher overall transmission efficiency, with its performance advantages being more significant under low signal-to-noise ratio and low bandwidth conditions. Furthermore, separate source channel coding faces a "cliff effect" when the actual transmission channel conditions mismatch with the coding design conditions: when the actual transmission channel conditions deteriorate slightly, channel decoding may fail to effectively correct errors, leading to decoding failure and a sharp decline in transmission performance. Joint source channel coding, on the other hand, better utilizes the redundancy of the source and the characteristics of the channel, improving the overall system robustness and mitigating the "cliff effect" (such as the slow decline in transmission performance as channel quality deteriorates).

[0078] Although joint source channel coding has better performance than separate source channel coding and can overcome the "cliff effect" that is common in separate source channel coding, and can fully exploit the transmission performance of the instantaneous channel, joint source channel coding can hardly provide the guarantee of "accurate transmission" of separate source channel coding.

[0079] When channel conditions vary significantly, the CSI feedback scheme based on separate source channel coding encounters a "cliff effect," leading to CSI feedback failure. In such cases, it is necessary to reduce spectrum utilization to ensure successful CSI feedback under the separate source channel coding scheme. Based on the information type contained in the CSI, CSI information can be divided into CSI information requiring accurate feedback (such as CRI) and CSI information usable even with feedback errors (such as PMI). This application embodiment adopts a hybrid coding approach, allowing different coding methods to be used for different information types in the CSI for transmission. Specifically, separate source channel coding can be used for CSI information with high feedback accuracy requirements, while joint source channel coding can be used for CSI information with low feedback accuracy requirements. The NW and UE can flexibly configure the CSI feedback method according to the different needs of various CSI types in different scenarios and services. This application embodiment not only improves the efficiency of CSI feedback but also limits the impact of feedback failure to one or a few CSI types, effectively solving the problems of low feedback efficiency and the "cliff effect" leading to the unavailability of all CSIs in the separate source channel coding CSI feedback scheme.

[0080] The wireless communication method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0081] Figure 3 is a schematic flowchart of a wireless communication method 200 according to an embodiment of this application. As shown in Figure 3, the wireless communication method 200 may include at least some of the following:

[0082] S210, the first device encodes the source information according to at least two encoding methods to obtain the target information; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method is SSCC, the second encoding method is bit-level JSCC, and the third encoding method is symbol-level JSCC;

[0083] S220, the first device sends the target information to the second device;

[0084] S230, the second device receives the target information from the first device;

[0085] S240, the second device decodes the target information to obtain the decoded information.

[0086] It should be understood that Figure 3 illustrates the steps or operations of the wireless communication method 200, but these steps or operations are merely examples, and other operations or variations of the operations shown in Figure 3 may also be performed in this application.

[0087] The embodiments of this application can achieve flexible source information encoding feedback through hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method); for content with high accuracy requirements, SSCC is used for encoding to ensure the accuracy of the feedback; for content with high real-time requirements, and / or for content with low requirements for feedback precision or accuracy, JSCC (bit-level JSCC and / or symbol-level JSCC) is used for encoding to improve feedback efficiency.

[0088] The acquisition described in the embodiments of this application can be understood as or replaced by generation or determination, and this application does not limit it in this way.

[0089] The separate source channel coding described in the embodiments of this application can also be called source channel independent coding, or similar names, and this application is not limited to this.

[0090] The AI ​​model described in this application embodiment may also be referred to as an AI unit, AI model / AI unit, machine learning (ML) model, ML unit, AI structure, AI function, AI characteristic, neural network, neural network function, neural network functionality, etc. Alternatively, the AI ​​model described in this application may also refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc. related to AI. Alternatively, the AI ​​model described in this application may be a processing method, algorithm, function, module, or unit for a specific dataset. Alternatively, the AI ​​model described in this application may be a processing method, algorithm, function, module, or unit running on AI / ML related hardware such as a graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), or application-specific integrated circuit (ASIC). This application does not specifically limit this. Optionally, the specific dataset includes data related to the AI ​​model input or data related to the AI ​​model output.

[0091] The identifier of the AI ​​model described in the embodiments of this application may be an AI unit identifier, an AI structure identifier, an AI parameter identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​model described in this application, or an identifier of a specific scenario, environment, channel characteristics, or device related to the AI ​​model described in this application, or an identifier of a function, characteristic, capability, or module related to the AI ​​model described in this application. This application does not make any specific limitations on these.

[0092] In some embodiments, the first device is a terminal, an access network device, a core network device, or a third-party server; and / or, the second device is a terminal, an access network device, a core network device, or a third-party server.

[0093] For example, the first device is a first terminal, and the second device is a second terminal.

[0094] For example, the first device is a terminal, and the second device is an access network device, a core network device, or a third-party server.

[0095] For example, the first device is an access network device, a core network device, or a third-party server, and the second device is a terminal.

[0096] For example, the first device is an access network device, and the second device is a core network device or a third-party server.

[0097] For example, the first device is a core network device, and the second device is an access network device or a third-party server.

[0098] For example, the first device is a first access network device, and the second device is a second access network device.

[0099] For example, the first device is a first core network device, and the second device is a second core network device.

[0100] For example, the first device is a first third-party server, and the second device is a second third-party server.

[0101] In some embodiments, the target information may be information obtained by hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) of source information. Optionally, the target information may be information obtained by hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) of CSI; or, the target information may be information obtained by hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) of image information containing a source; or, the target information may be information obtained by hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) of video information containing a source; or, the target information may be information obtained by hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) of audio information containing a source; or, the target information may be information obtained by hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) of uplink control information (UCI), downlink control information (DCI), or sidelink control information (SCI).

[0102] For example, UCI information includes at least one of the following: uplink data scheduling requests, downlink data response information, and channel state information. When the above information is transmitted simultaneously, mixed coding (at least two of the first coding method, the second coding method, and the third coding method) can be used.

[0103] For example, DCI information contains different information fields (the content of each information field may be: carrier information, modulation and coding scheme, power control information, etc.), and different information fields can be mixed and coded (at least two of the first coding method, the second coding method, and the third coding method).

[0104] The CSI described in the embodiments of this application can also be referred to as or replaced with channel information. For example, CSI can be obtained by measuring the Channel State Information Reference Signal (CSI-RS).

[0105] In some embodiments, when the source information is CSI, a hybrid coding scheme (at least two of the first coding scheme, the second coding scheme, and the third coding scheme) can be used for coding CSI Part 1 and / or CSI Part 2.

[0106] In the embodiments of this application, the information obtained after encoding based on the first encoding method can be bit information (such as a bit sequence), the information obtained after encoding based on the second encoding method can be bit information (such as a bit sequence), and the information obtained after encoding based on the third encoding method can be symbol information (such as a symbol sequence).

[0107] In some embodiments, the encoding method used in the first part of the source information is different from the encoding method used in the second part of the source information.

[0108] In this embodiment, the encoding method used in the first part is different from that used in the second part, thereby improving the flexibility of encoding and feedback of the source information. For example, the first part contains content with high accuracy requirements; the second part contains content with high real-time requirements, and / or, the second part contains content with low feedback accuracy or precision requirements. As another example, the first part contains content with high real-time requirements, and / or, the first part contains content with low feedback accuracy or precision requirements; the second part contains content with high accuracy requirements. Specifically, for content with high accuracy requirements, SSCC is used for encoding to ensure the accuracy of the feedback; for content with high real-time requirements, and / or for content with low feedback accuracy or precision requirements, JSCC (bit-level JSCC and / or symbol-level JSCC) is used for encoding to improve feedback efficiency.

[0109] In some embodiments, the encoding method used for the source information corresponding to the first service or scenario is different from the encoding method used for the source information corresponding to the second service or scenario.

[0110] For example, the encoding method used for source information corresponding to periodic business or scenarios is different from the encoding method used for source information corresponding to non-periodic business or scenarios.

[0111] For example, the encoding method used for source information corresponding to time-delay-sensitive services or scenarios is different from the encoding method used for source information corresponding to non-time-delay-sensitive services or scenarios.

[0112] For example, the encoding method used for the source information of Ultra-Reliable and Low Latency Communication (URLLC) service is different from that used for the source information of Enhanced Mobile Broadband (eMBB) service.

[0113] For example, the encoding method used for the source information of 5G or 6G services is different from that used for the source information of 4G services.

[0114] For example, the encoding method used for source information in the eMBB scenario is different from that used for source information in the URLLC scenario.

[0115] In some embodiments, where the encoding method used in the first part includes the first encoding method and / or the second encoding method, and the encoding method used in the second part is the third encoding method, the target information is obtained by splicing or merging the encoded information corresponding to the first part after being modulated by the target modulation method with the encoded information corresponding to the second part.

[0116] For example, the first part is encoded by the first encoding method to obtain a bit sequence, and the second part is encoded by the third encoding method to obtain a symbol sequence. In this case, the target information is formed by splicing or combining the symbol sequence obtained by modulating the bit sequence obtained by encoding the first part's corresponding encoding information by the first encoding method with the target modulation method and the symbol sequence obtained by encoding the second part's corresponding encoding information by the third encoding method.

[0117] For example, the first part is encoded by the second encoding method to obtain a bit sequence, and the second part is encoded by the third encoding method to obtain a symbol sequence. In this case, the target information is formed by splicing or combining the symbol sequence obtained by modulating the bit sequence obtained by encoding the first part's corresponding encoded information by the second encoding method with the target modulation method and the symbol sequence obtained by encoding the second part's corresponding encoded information by the third encoding method.

[0118] For example, the first part is encoded by the first encoding method and the second encoding method to obtain a bit sequence, and the second part is encoded by the third encoding method to obtain a symbol sequence. In this case, the target information is formed by splicing or combining the symbol sequence obtained by modulating the bit sequence obtained by the first encoding method and the second encoding method with the target modulation method, and the symbol sequence obtained by encoding the corresponding encoded information of the second part with the third encoding method.

[0119] In some embodiments, when the encoding method used in the first part is the first encoding method and the encoding method used in the second part is the second encoding method, the target information is obtained by directly splicing or merging the encoding information corresponding to the first part with the encoding information corresponding to the second part, and then modulating it with the target modulation method.

[0120] For example, the first part is encoded by the first encoding method to obtain a bit sequence, and the second part is encoded by the second encoding method to obtain a bit sequence. In this case, the target information is obtained by directly splicing or combining the bit sequence obtained by encoding the first part's corresponding encoding information by the first encoding method with the bit sequence obtained by encoding the second part's corresponding encoding information by the second encoding method, and then modulating it by the target modulation method.

[0121] In some embodiments, the target information may further include a third part, a fourth part, etc. Optionally, each part of the target information may employ its own encoding method, wherein some parts may employ the same encoding method. If the encoding methods are the same, the encoded information can be directly concatenated or merged. If the encoded information obtained by the adopted encoding method contains bit information and symbol information, then the bit information needs to be modulated before being concatenated or merged with the symbol information.

[0122] For example, the first part is encoded by the first encoding method to obtain a bit sequence, the second part is encoded by the second encoding method to obtain a bit sequence, and the third part is encoded by the third encoding method to obtain a symbol sequence. In this case, the target information is obtained by splicing or combining the bit sequence obtained by encoding the first part's corresponding encoding information by the first encoding method and the bit sequence obtained by encoding the second part's corresponding encoding information by the second encoding method and modulating it by the target modulation method, and then splicing or combining the symbol sequence obtained by encoding the third part's corresponding encoding information by the third encoding method.

[0123] In some embodiments, different parts of the source information employing the first coding scheme and / or the second coding scheme employ their respective target modulation schemes.

[0124] In some embodiments, the target modulation method includes, but is not limited to, at least one of the following:

[0125] Binary Phase Shift Keying (BPSK);

[0126] pi / 2-BPSK;

[0127] Quadrature Phase Shift Keying (QPSK);

[0128] 16. Quadrature Amplitude Modulation (QAM);

[0129] 64QAM;

[0130] 256QAM;

[0131] 1024QAM;

[0132] 4096QAM;

[0133] Modulation based on AI models.

[0134] Optionally, the AI-based modulation can be indicated by at least one of the following:

[0135] The identifier (model ID) of the AI ​​model used to implement the modulation function;

[0136] The AI ​​function ID corresponding to the AI ​​model used to implement modulation function;

[0137] The dataset ID corresponding to the AI ​​model used to implement the modulation function;

[0138] The model pairing ID is used to identify the AI ​​model used to implement the modulation function.

[0139] Optionally, the modulation scheme corresponding to the first part and the modulation scheme corresponding to the second part may be the same or different, and this application does not limit this.

[0140] In some embodiments, the source information is CSI;

[0141] The information source information includes at least one of the following:

[0142] CQI;

[0143] At least one of the following: mean, variance, bias, and product factor of CQI normalization;

[0144] PMI;

[0145] At least one of the following: mean, variance, bias, and product factor of PMI normalization;

[0146] CRI;

[0147] At least one of the following: mean, variance, bias, and product factor of CRI normalization;

[0148] SSBRI;

[0149] At least one of the following: mean, variance, bias, and product factor of SSBRI normalization;

[0150] LI;

[0151] At least one of the following: mean, variance, bias, and product factor of LI normalization;

[0152] RI;

[0153] At least one of the following: mean, variance, bias, and product factor of RI normalization;

[0154] L1-RSRP;

[0155] At least one of the following: mean, variance, bias, and product factor of L1-RSRP normalization;

[0156] L1-SINR;

[0157] At least one of the following: mean, variance, bias, and product factor of L1-SINR normalization;

[0158] CSI reports the corresponding Capability Index;

[0159] CSI reports at least one of the following: the mean, variance, bias, and product factor of the corresponding capability index normalization.

[0160] TDCP;

[0161] At least one of the following: mean, variance, bias, and product factor of TDCP normalization;

[0162] Raw channel information;

[0163] At least one of the following: mean, variance, bias, and product factor of the normalized raw channel information;

[0164] Processed channel information (such as transforming spatial frequency domain channel information to angle delay domain channel information, and / or truncating spatial frequency domain channel information to achieve the effect of channel information compression);

[0165] The normalized mean, variance, bias, and product factor of the processed channel information;

[0166] The PMI corresponds to the information source (such as the V matrix after channel SVD decomposition);

[0167] At least one of the following: mean, variance, bias, and product factor of the source normalization corresponding to PMI;

[0168] The monitoring results of PMI.

[0169] It should be noted that the content of the first part of the source information and the content of the second part of the source information may be the same or different, and this application embodiment does not limit this.

[0170] Specifically, the capability index corresponding to CSI reporting represents the capability of the first device to report CSI.

[0171] Optionally, at least one of the mean, variance, bias, and product factor of the CQI normalization can be used by a second device to perform denormalization processing for the CQI.

[0172] In this embodiment, at least one of the mean, variance, bias, and product factor of the CQI normalization can be fed back through separate source-channel coding.

[0173] Optionally, at least one of the mean, variance, bias, and product factor of the PMI normalization can be used by a second device to perform denormalization processing on the PMI.

[0174] In this embodiment, at least one of the mean, variance, bias, and product factor of the PMI normalization can be fed back through separate source-channel coding.

[0175] Optionally, at least one of the mean, variance, bias, and product factor of the CRI normalization can be used by a second device to perform denormalization processing for the CRI.

[0176] In this embodiment, at least one of the mean, variance, bias, and product factor of the CRI normalization can be fed back through separate source-channel coding.

[0177] Optionally, at least one of the mean, variance, bias, and product factor of the SSBRI normalization can be used by a second device to perform denormalization of the SSBRI.

[0178] In this embodiment, at least one of the mean, variance, bias, and product factor of the SSBRI normalization can be fed back through separate source channel coding.

[0179] Optionally, at least one of the mean, variance, bias, and product factor of the LI normalization can be used by the second device to perform denormalization processing on the LI.

[0180] In this embodiment, at least one of the mean, variance, bias, and product factor of the LI normalization can be fed back through separate source-channel coding.

[0181] Optionally, at least one of the mean, variance, bias, and product factor of the RI normalization can be used by the second device to perform denormalization of the RI.

[0182] In this embodiment, at least one of the mean, variance, bias, and product factor of the RI normalization can be fed back through separate source-channel coding.

[0183] Optionally, at least one of the mean, variance, bias, and product factor of the L1-RSRP normalization can be used by a second device to perform denormalization processing for L1-RSRP.

[0184] In this embodiment, at least one of the mean, variance, bias, and product factor of the L1-RSRP normalization can be fed back through separate source-channel coding.

[0185] Optionally, at least one of the mean, variance, bias, and product factor of the L1-SINR normalization can be used by the second device to perform denormalization processing for L1-SINR.

[0186] In this embodiment, at least one of the mean, variance, bias, and product factor of L1-SINR normalization can be fed back through separate source channel coding.

[0187] Optionally, at least one of the mean, variance, bias, and product factor of the normalized capability index corresponding to the CSI report can be used by the second device to perform denormalization processing on the capability index corresponding to the CSI report.

[0188] In this embodiment, at least one of the mean, variance, bias, and product factor of the capability index normalized corresponding to the CSI report can be fed back through separate source channel coding.

[0189] Optionally, at least one of the mean, variance, bias, and product factor of the TDCP normalization can be used by the second device to perform denormalization processing for TDCP.

[0190] In this embodiment, at least one of the mean, variance, bias, and product factor of the TDCP normalization can be fed back through separate source-channel coding.

[0191] Optionally, at least one of the mean, variance, bias, and product factor of the normalized original channel information can be used by the second device to perform denormalization processing on the original channel information.

[0192] In this embodiment, at least one of the mean, variance, bias, and product factor of the normalized original channel information can be fed back through separate source channel coding.

[0193] Optionally, at least one of the mean, variance, bias, and product factor of the normalized channel information can be used by the second device to perform denormalization processing on the processed channel information.

[0194] In this embodiment, at least one of the normalized mean, variance, bias, and product factor of the processed channel information can be fed back through separate source channel coding.

[0195] Optionally, at least one of the mean, variance, bias, and product factor of the source normalization corresponding to PMI can be used by the second device to perform denormalization processing on the source corresponding to PMI.

[0196] In this embodiment, at least one of the mean, variance, bias, and product factor of the source normalization corresponding to PMI can be fed back through separate source channel coding.

[0197] In some embodiments, different portions of the source information using the first encoding method employ their respective source coding methods or channel coding methods. For example, the first portion or the second portion includes CQI and PMI, wherein CQI and PMI correspond to independent source coding or joint source coding, and / or, CQI and PMI correspond to independent channel coding or joint channel coding. Specifically, the first device may perform independent source coding or joint source coding on the first portion or the second portion based on the first encoding method, and / or, the first device may perform independent channel coding or joint channel coding on the first portion or the second portion based on the first encoding method.

[0198] In some embodiments, different portions of the source information employing the second encoding method use their respective bit-level joint source-channel coding methods. For example, the first portion or the second portion includes CQI and PMI, wherein CQI and PMI correspond to independent bit-level joint source-channel coding or joint bit-level joint source-channel coding. Specifically, the first device can perform independent bit-level joint source-channel coding or joint bit-level joint source-channel coding on the first portion or the second portion based on the second encoding method.

[0199] In some embodiments, different portions of the source information employing the third coding method use their respective symbol-level joint source-channel coding methods. For example, the first portion or the second portion includes CQI and PMI, wherein CQI and PMI correspond to independent symbol-level joint source-channel coding or joint symbol-level joint source-channel coding. Specifically, the first device can perform independent symbol-level joint source-channel coding or joint symbol-level joint source-channel coding on the first portion or the second portion based on the third coding method.

[0200] In some embodiments, the source coding in the first encoding method includes, but is not limited to, at least one of the following:

[0201] Huffman coding, arithmetic coding, LZ coding, quantization coding, differential coding, codebook-based coding, Cyclic Redundancy Check (CRC) coding, and AI model-based source coding.

[0202] Optionally, the AI ​​model-based source coding can be indicated by at least one of the following:

[0203] The identifier (model ID) of the AI ​​model used to implement source coding function;

[0204] The AI ​​function ID corresponding to the AI ​​model used to implement source coding function;

[0205] The dataset ID is used to identify the AI ​​model that implements source coding.

[0206] The model pairing ID is used to identify the AI ​​model that implements the source coding function.

[0207] In some embodiments, the channel coding in the first encoding method includes, but is not limited to, at least one of the following:

[0208] Low-density parity check (LDPC) codes, Polar codes, Turbo codes, repeat codes, Simplex codes, RM codes, TBCC codes, and channel coding based on AI models.

[0209] Optionally, the AI ​​model-based channel coding can be indicated by at least one of the following:

[0210] The identifier (model ID) of the AI ​​model used to implement channel coding functions;

[0211] AI function ID corresponding to the AI ​​model used to implement channel coding function;

[0212] The dataset ID is used to identify the AI ​​model that implements channel coding.

[0213] The model pairing ID is used to identify the AI ​​model used to implement channel coding.

[0214] In some embodiments, the second encoding method includes, but is not limited to, at least one of the following:

[0215] Bit-level joint source-channel coding based on AI models, and bit-level joint source-channel coding not based on AI models.

[0216] It should be noted that the second coding method can also be called bit-level joint source-channel coding.

[0217] Optionally, the bit-level joint source-channel coding based on the AI ​​model can be indicated by at least one of the following:

[0218] The identifier (model ID) of the AI ​​model used to implement bit-level joint source-channel coding;

[0219] AI function ID corresponding to the AI ​​model used to implement bit-level joint source-channel coding;

[0220] Data set ID is used to identify the AI ​​model that implements bit-level joint source-channel coding.

[0221] The model pairing ID is used to implement bit-level joint source-channel coding for AI models.

[0222] In some embodiments, the third encoding method includes, but is not limited to, at least one of the following:

[0223] Symbol-level joint source-channel coding based on AI models, and symbol-level joint source-channel coding not based on AI models.

[0224] It should be noted that the third coding method can also be called symbol-level joint source-channel coding.

[0225] Optionally, the symbol-level joint source-channel coding based on the AI ​​model can be indicated by at least one of the following:

[0226] The identifier (model ID) of the AI ​​model used to implement symbol-level joint source-channel coding;

[0227] AI function ID corresponding to the AI ​​model used to implement symbol-level joint source-channel coding;

[0228] The dataset ID corresponding to the AI ​​model used to implement symbol-level joint source-channel coding;

[0229] The model pairing ID is used to implement symbol-level joint source-channel coding for AI models.

[0230] In some embodiments, the second and third encoding methods may also be defined or described in the following ways:

[0231] The input and output of an AI model; or,

[0232] Signal processing flow; or,

[0233] Input / output information mapping.

[0234] In some implementations, the input and output definitions or descriptions of the AI ​​model, including the second and third encoding methods, may include at least one of the following:

[0235] (1) Encoding methods based on AI models include:

[0236] a. AI / ML encoding unit;

[0237] b. AI / ML decoding unit;

[0238] (2) The input to the AI / ML coding unit is CSI source information, including:

[0239] a.CQI;

[0240] b. PMI;

[0241] c.CRI;

[0242] d.SSBRI;

[0243] e.LI;

[0244] f.RI;

[0245] g.L1-RSRP;

[0246] h.L1-SINR;

[0247] i. CSI reports the corresponding Capability Index;

[0248] j.TDCP;

[0249] k. Raw channel information;

[0250] l. Processed channel information;

[0251] The information source corresponding to m.PMI;

[0252] n. Various combinations of the above information;

[0253] (3) The output of the AI / ML coding unit is the result of joint source-channel coding:

[0254] a. Bit sequence (bit-level joint source-channel coding);

[0255] b. Symbol sequence (symbol-level joint source-channel coding);

[0256] (4) The output of the AI / ML coding unit cannot use channel coding;

[0257] (5) Input to the AI / ML decoding unit:

[0258] a. The bit sequence received by NW that is related to the output of the AI / ML coding unit;

[0259] b. The symbol sequence received by NW that is associated with the output of the AI / ML coding unit;

[0260] (6) The output of the AI / ML decoding unit is the recovered CSI source information, including: a. CQI;

[0261] b. PMI;

[0262] c.CRI;

[0263] d.SSBRI;

[0264] e.LI;

[0265] f.RI;

[0266] g.L1-RSRP;

[0267] h.L1-SINR;

[0268] i. CSI reports the corresponding Capability Index;

[0269] j.TDCP;

[0270] k. Raw channel information;

[0271] l. Processed channel information;

[0272] The information source corresponding to m.PMI;

[0273] n. Various combinations of the above information.

[0274] In some implementations, defining or describing the second and third encoding methods based on the signal processing flow may include at least one of the following:

[0275] (1) A processing flow for joint source-channel coding oriented to CSI information feedback, including

[0276] a. A joint source channel coding and processing module, located on the first device side (e.g., UE);

[0277] b. A joint source-channel decoding and processing module, located on the second device side (such as gNB);

[0278] (2) Perform channel estimation on CSI-RS to obtain CSI information, which includes:

[0279] a.CQI;

[0280] b. PMI;

[0281] c.CRI;

[0282] d.SSBRI;

[0283] e.LI;

[0284] f.RI;

[0285] g.L1-RSRP;

[0286] h.L1-SINR;

[0287] i. CSI reports the corresponding Capability Index;

[0288] j.TDCP;

[0289] k. Raw channel information;

[0290] l. Processed channel information;

[0291] The information source corresponding to m.PMI;

[0292] n. Various combinations of the above information;

[0293] (3) The first device uses the joint source channel coding processing module to process the CSI information to obtain coded information, wherein the coded information may be:

[0294] a. Bit sequence (corresponding to bit-level joint source coding); or,

[0295] b. Symbol sequence (corresponding to symbol-level joint source coding);

[0296] (4) The second device uses a joint source channel decoding processing module to process the encoded bit sequence or symbol sequence containing channel interference and noise to obtain the recovered CSI information.

[0297] In some implementations, defining or describing a second or third encoding method based on input / output information mapping may include at least one of the following:

[0298] (1) A mapping on the first device side (such as joint source channel coding), wherein the mapping maps CSI information to a bit sequence after joint source channel coding (corresponding to bit-level joint source channel coding), or the mapping maps CSI information to a symbol sequence after joint source channel coding (corresponding to symbol-level joint source channel coding);

[0299] (2) A mapping on the second device side (such as joint source-channel decoding mapping), wherein the mapping maps a bit sequence of coded output containing channel interference and noise (corresponding to bit-level joint source-channel coding) to recovered CSI information, or the mapping maps a symbol sequence of coded output containing channel interference and noise (corresponding to symbol-level joint source-channel coding) to recovered CSI information.

[0300] In some embodiments, the source information is CSI, the first part further includes first metadata, and the second part further includes second metadata;

[0301] Wherein, if the encoding method used in the first part or the second part includes the first encoding method, the first metadata or the second metadata includes at least one of the following:

[0302] CSI information type, CSI information length, CSI information source coding method, CSI information channel coding method, CSI information modulation method, encoded CSI information length, and CSI information associated sequence splicing order;

[0303] Wherein, if the encoding method used in the first part or the second part includes the second encoding method, the first metadata or the second metadata includes at least one of the following:

[0304] CSI information type, CSI information length, bit-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information;

[0305] Wherein, if the encoding method used in the first part or the second part includes the third encoding method, the first metadata or the second metadata includes at least one of the following:

[0306] CSI information type, CSI information length, symbol-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information.

[0307] In some embodiments, the above-mentioned S240 may specifically include:

[0308] The second device decodes the target information based on the first metadata and the second metadata to obtain the decoded information.

[0309] In this embodiment, the second device can obtain relevant information about the first part based on the first metadata, and thus the second device can execute the decoding process corresponding to the first part based on the obtained relevant information about the first part; and / or, the second device can obtain relevant information about the second part based on the second metadata, and thus the second device can execute the decoding process corresponding to the second part based on the obtained relevant information about the second part.

[0310] In some embodiments, the first part and the first meta-information are encoded using a first encoding method and / or a second encoding method to obtain a bit sequence A1; the second part and the second meta-information are encoded using a third encoding method to obtain a symbol sequence A2; then, the bit sequence A1 is modulated and concatenated or merged with the symbol sequence A2 to obtain the target information.

[0311] In some embodiments, the first part and the first meta-information are encoded using a first encoding method to obtain bit sequence B1; the second part and the second meta-information are encoded using a second encoding method to obtain bit sequence B2; then, bit sequence B1 is directly concatenated or merged with bit sequence B2, and after modulation, the target information is obtained.

[0312] In some embodiments, the first metadata is combined or concatenated with the first part to obtain the first combined or concatenated information. Then, the first combined or concatenated information is encoded using a first encoding method and / or a second encoding method to obtain the bit sequence C1. The second metadata is combined or concatenated with the second part to obtain the second combined or concatenated information. Then, the second combined or concatenated information is encoded using a third encoding method to obtain the symbol sequence C2. Finally, the bit sequence C1 is modulated and concatenated or merged with the symbol sequence C2 to obtain the target information.

[0313] In some embodiments, the first metadata is combined or concatenated with the first part to obtain the first combined or concatenated information. Then, the first combined or concatenated information is encoded using the first encoding method to obtain the bit sequence D1. The second metadata is combined or concatenated with the second part to obtain the second combined or concatenated information. Then, the second combined or concatenated information is encoded using the second encoding method to obtain the bit sequence D2. Then, the bit sequence D1 is directly concatenated or merged with the bit sequence D2 and modulated to obtain the target information.

[0314] In some embodiments, the wireless communication method 200 further includes:

[0315] The first device acquires at least one of the following:

[0316] The first encoding method;

[0317] The second encoding method;

[0318] The third encoding method;

[0319] The type of the first part;

[0320] The type of the second part;

[0321] The type of the first metadata;

[0322] The type of the second element information.

[0323] In this embodiment, the first device (such as a terminal, access network device, core network device, third-party server, etc.) can directly obtain at least one of the following: a first encoding method, a second encoding method, a third encoding method, the type of the first part, the type of the second part, the type of the first metadata, and the type of the second metadata. Thus, the first device can implement hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) based on the obtained information.

[0324] In some embodiments, the wireless communication method 200 further includes:

[0325] The first device receives the second information from the second device, or the first device sends the second information to the second device;

[0326] The second information is used to indicate at least one of the following:

[0327] The first encoding method;

[0328] The second encoding method;

[0329] The third encoding method;

[0330] The type of the first part;

[0331] The type of the second part;

[0332] The type of the first metadata;

[0333] The type of the second element information.

[0334] For example, prior to S210 above, the first device receives the second information from the second device, or the first device sends the second information to the second device.

[0335] Optionally, when the first device is a first terminal and the second device is a second terminal, the first device receives the second information from the second device.

[0336] Optionally, when the first device is a terminal and the second device is an access network device, a core network device, or a third-party server, the first device receives the second information from the second device.

[0337] Optionally, when the first device is an access network device, a core network device, or a third-party server, and the second device is a terminal, the first device sends the second information to the second device.

[0338] Optionally, when the first device is an access network device and the second device is a core network device or a third-party server, the first device receives the second information from the second device.

[0339] Optionally, when the first device is a core network device and the second device is an access network device or a third-party server, the first device receives the second information from the second device.

[0340] In this embodiment, the first device receives second information from the second device. The first device can acquire at least one of the following: a first encoding method, a second encoding method, a third encoding method, the type of the first part, the type of the second part, the type of the first metadata, and the type of the second metadata. Therefore, the first device can implement hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method) based on the acquired information.

[0341] In this embodiment, the first device sends second information to the second device. The second device can obtain at least one of the following: a first encoding method, a second encoding method, a third encoding method, the type of the first part, the type of the second part, the type of the first metadata, and the type of the second metadata. Thus, the second device can know the hybrid encoding used by the first device (at least two of the first, second, and third encoding methods).

[0342] It should be noted that the first device may also receive the second information from other devices besides the first device and the second device, and this application embodiment does not limit this.

[0343] In some embodiments, the content indicated by the second information may also be determined by the first device based on its implementation.

[0344] Optionally, the first device is a first terminal and the second device is a second terminal. In this case, the second information can be carried by at least one of the following: Sidelink Control Information (SCI) and Media Access Control Element (MAC CE).

[0345] Optionally, the first device is a terminal, and the second device is an access network device or a core network device. In this case, the second information can be carried by at least one of the following: Radio Resource Control (RRC) signaling, Downlink Control Information (DCI), or MAC CE.

[0346] Optionally, the first device is an access network device or a core network device, and the second device is a terminal. In this case, the second information can be carried by at least one of the following: Uplink Control Information (UCI), RRC signaling, or MAC CE.

[0347] Optionally, the second information can also be information agreed upon in the agreement.

[0348] In some embodiments, the wireless communication method 200 further includes:

[0349] The first device sends a third message to the second device;

[0350] The third information is used to indicate at least one of the following:

[0351] The first device supports joint source-channel coding feedback;

[0352] The first device supports separate source channel coding feedback;

[0353] The first device supports CSI feedback based on an AI model;

[0354] The first device supports CSI feedback based on a non-AI model.

[0355] For example, prior to S210 above, the first device sends the third information to the second device.

[0356] Optionally, when the first device is a first terminal and the second device is a second terminal, the first device sends the third information to the second device.

[0357] Optionally, when the first device is a terminal and the second device is an access network device, a core network device, or a third-party server, the first device sends the third information to the second device.

[0358] In this embodiment, the first device sends third information to the second device, so that the second device can know at least one of the following based on the third information: the first device supports joint source channel coding feedback, the first device supports separate source channel coding feedback, the first device supports CSI feedback based on an AI model, and the first device supports CSI feedback based on a non-AI model, so that the second device can determine the aforementioned second information.

[0359] In some embodiments, the wireless communication method 200 further includes:

[0360] The second device monitors the performance of joint source-channel coding based on the decoded information.

[0361] In this embodiment, the second device can monitor the performance of joint source-channel coding based on the decoded information.

[0362] For example, the second device decodes the target information to obtain a lossless PMI (source with separate source-channel coding) and a lossy PMI for joint channel coding transmission. The second device then uses the lossless and lossy PMIs to monitor the performance of the joint source-channel coding.

[0363] In some embodiments, the wireless communication method 200 further includes:

[0364] The second device trains the target AI model based on the decoded information, or the second device monitors the performance of the target AI model based on the decoded information;

[0365] The target AI model is used to implement joint source-channel decoding.

[0366] In this embodiment, the second device can train the target AI model based on the decoded information, or the second device can monitor the performance of the target AI model based on the decoded information.

[0367] For example, the second device decodes the source-channel coded portion of the mixed coded sequence to obtain a lossless PMI (source-channel coded source). The second device then uses the lossless PMI (label of the target AI model) and the received joint source-channel coded output information (input to the target AI model) to train the target AI model; alternatively, the second device uses the lossless PMI (label of the target AI model) and the received joint source-channel coded output information (input to the target AI model) to monitor the performance of the target AI model.

[0368] Therefore, in this embodiment, the first device encodes the source information according to at least two encoding methods to obtain the target information; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method being SSCC, the second encoding method being bit-level JSCC, and the third encoding method being symbol-level JSCC; the first device sends the target information to the second device. Specifically, this embodiment can achieve flexible source information encoding and feedback through hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method); for content with high accuracy requirements, SSCC is used for encoding to ensure the accuracy of the feedback; for content with high real-time requirements, and / or for content with low feedback accuracy requirements, JSCC (bit-level JSCC and / or symbol-level JSCC) is used for encoding to improve feedback efficiency.

[0369] The technical solution of this application is described in detail below through specific embodiments.

[0370] Example 1 uses a first device as a terminal (UE) and a second device as an access network device (such as a gNB) as an example. In Example 1, CSI information such as CRI, RI, LI, PMI, and CQI is fed back. The specific process may include some or all of S1-1 to S1-8.

[0371] S1-1. UE Capability Reporting: Supports separate source channel coding, supports joint source channel coding, supports CSI feedback based on AI model, and supports CSI feedback based on non-AI model.

[0372] S1-2.gNB configures the CSI information group and corresponding feedback method for the UE, as detailed below:

[0373] CRI, a non-AI model, separates source and channel coding; source coding: none; channel coding: Polar.

[0374] RI, a non-AI model, separates source and channel coding; source coding: none; channel coding: repetition code.

[0375] LI, non-AI model, separate source and channel coding; source coding: none; channel coding: Polar.

[0376] CQI, AI model, bit-level joint source-channel coding, AI model model ID: 123;

[0377] PMI, AI model, symbol-level joint source-channel coding, AI model model ID: 456.

[0378] For CRI, a non-AI model-based CSI feedback and separate source channel coding is adopted; where, for CRI, source coding is not performed, and the channel coding method is Polar.

[0379] For RI, CSI feedback and separate source channel coding based on a non-AI model are adopted; where, for RI, source coding is not performed, and the channel coding method is a repeating code.

[0380] For LI, CSI feedback and separate source channel coding based on a non-AI model are adopted; where, for LI, source coding is not performed, and the channel coding method is Polar.

[0381] For CQI, CSI feedback based on AI model and bit-level joint source-channel coding are adopted; among them, for CQI, bit-level joint source-channel coding can be performed based on AI model 123.

[0382] For PMI, CSI feedback and symbol-level joint source-channel coding based on an AI model are adopted; among them, symbol-level joint source-channel coding can be performed based on AI model 456 for PMI.

[0383] S1-3. The UE performs source channel coding for CRI, RI, and LI, specifically including:

[0384] (1) The UE does not perform source coding for CRI, RI, and LI;

[0385] (2) The UE uses a repeating code to perform channel coding on RI, and the UE uses a Polar code to perform channel coding on CRI and RI to obtain bit sequence 1.

[0386] S1-4. The UE uses the AI ​​model with model ID 123 to perform bit-level joint source-channel coding on the CQI to obtain bit sequence 2.

[0387] S1-5.UE uses the AI ​​model with model ID 456 to perform symbol-level joint source-channel coding on PMI to obtain symbol sequence 1.

[0388] S1-6. The UE concatenates or combines bit sequence 1 and bit sequence 2 to form bit information 3, and uses 16QAM modulation to output symbol sequence 2.

[0389] S1-7. The UE concatenates or combines symbol sequence 1 and symbol sequence 2 to form symbol sequence 3; and the UE sends symbol sequence 3 to the NW.

[0390] S1-8.NW decodes mixed coded sequences (such as symbol sequence 3) to obtain CSI information such as CRI, RI, LI, PMI, and CQI.

[0391] Example 2 uses a first device as a terminal (UE) and a second device as an access network device (such as a gNB). In Example 2, the UE simultaneously reports the PMI monitoring results and the PMI feedback of joint source channel coding. The specific process may include some or all of S2-1 to S2-7.

[0392] S2-1. UE Capability Reporting: Supports separate source channel coding, supports joint source channel coding, supports CSI feedback based on AI model, and supports CSI feedback based on non-AI model.

[0393] S2-2.gNB configures the CSI information group and corresponding feedback method for the UE, as detailed below:

[0394] PMI monitoring results (such as SGCS of PMI monitoring results), non-AI model, separate source and channel coding, source coding: none, channel coding: Polar;

[0395] CQI, AI model, symbol-level joint source-channel coding, AI model model ID: 456.

[0396] For PMI monitoring results, CSI feedback and separate source channel coding based on a non-AI model are used; however, for PMI monitoring results, source coding is not performed, and the channel coding method is Polar.

[0397] For CQI, CSI feedback and symbol-level joint source-channel coding based on an AI model are adopted; among them, for CQI, symbol-level joint source-channel coding can be performed based on AI model 456.

[0398] S2-3. The UE performs source channel coding separation on the PMI monitoring results, specifically including:

[0399] (1) The UE does not perform source coding on the PMI monitoring results;

[0400] (2) The UE uses Polar code to encode the PMI monitoring results to obtain bit sequence 1.

[0401] S2-4. The UE uses the AI ​​model with model ID 456 to perform symbol-level joint source-channel coding on CQI to obtain symbol sequence 1.

[0402] S2-5.UE modulates bit sequence 1 using QPSK and outputs symbol sequence 2.

[0403] S2-6. The UE concatenates or combines symbol sequence 1 with symbol sequence 2 to form symbol sequence 3; and the UE sends symbol sequence 3 to the NW.

[0404] S2-7.NW decodes the mixed coded sequence (such as symbol sequence 3) to obtain CQI information and the UE's monitoring results of PMI.

[0405] Example 3 uses a first device as a terminal (UE) and a second device as an access network device (such as a gNB). In Example 3, the NW monitors the PMI of the joint source channel coding, and the specific process may include some or all of S3-1 to S3-8.

[0406] S3-1. UE Capability Reporting: Supports separate source channel coding, supports joint source channel coding, supports CSI feedback based on AI model, and supports CSI feedback based on non-AI model.

[0407] S3-2.gNB configures the CSI information group and corresponding feedback method to the UE, as detailed below:

[0408] PMI, a non-AI model, uses separate source and channel coding: Huffman coding and Polar coding.

[0409] PMI, AI model, symbol-level joint source-channel coding, AI model model ID: 456.

[0410] For PMI, a non-AI model-based CSI feedback and separate source-channel coding are adopted; specifically, for PMI, the source coding uses Huffman coding and the channel coding uses Polar coding.

[0411] For PMI, CSI feedback and symbol-level joint source-channel coding based on an AI model are adopted; among them, symbol-level joint source-channel coding can be performed based on AI model 456 for PMI.

[0412] S3-3. The UE performs source channel coding separation on the PMI, specifically including:

[0413] (1) The UE performs Huffman source coding on the PMI;

[0414] (2) The UE uses Polar code to channel code the output of PMI source coding to obtain bit sequence 1.

[0415] S3-4. The UE uses the AI ​​model with model ID 456 to perform symbol-level joint source channel coding on the PMI to obtain symbol sequence 1.

[0416] S3-5.UE modulates bit sequence 1 using QPSK and outputs symbol sequence 2.

[0417] S3-6. The UE concatenates or combines symbol sequence 1 and symbol sequence 2 to form symbol sequence 3; and the UE sends symbol sequence 3 to the NW.

[0418] S3-7.NW decodes the mixed coded sequence (such as symbol sequence 3) to obtain the lossless PMI (source coded by separate source and channel coding) and the lossy PMI for joint channel coding transmission.

[0419] S3-8.NW uses lossless and lossy PMI to monitor the performance of joint source-channel coding.

[0420] Example 4 uses a first device as a terminal (UE) and a second device as an access network device (such as a gNB). In Example 4, the NW performs joint training on the joint source channel coding using the actual channel. The specific process may include some or all of S4-1 to S4-8.

[0421] S4-1. UE Capability Reporting: Supports separate source channel coding, supports joint source channel coding, supports CSI feedback based on AI model, and supports CSI feedback based on non-AI model.

[0422] S4-2.gNB configures the CSI information group and corresponding feedback method for the UE, as detailed below:

[0423] PMI, a non-AI model, uses separate source and channel coding: Huffman coding and Polar coding.

[0424] PMI, AI model, symbol-level joint source-channel coding, AI model model ID: 456.

[0425] For PMI, a non-AI model-based CSI feedback and separate source-channel coding are adopted; specifically, for PMI, the source coding uses Huffman coding and the channel coding uses Polar coding.

[0426] For PMI, CSI feedback and symbol-level joint source-channel coding based on an AI model are adopted; among them, symbol-level joint source-channel coding can be performed based on AI model 456 for PMI.

[0427] S4-3. The UE performs source channel coding separation on the PMI, specifically including:

[0428] (1) The UE performs Huffman source coding on the PMI;

[0429] (2) The UE uses Polar code to channel code the output of PMI source coding to obtain bit sequence 1.

[0430] S4-4.UE uses the AI ​​model with model ID 456 to perform symbol-level joint source channel coding on PMI to obtain symbol sequence 1.

[0431] S4-5.UE modulates bit sequence 1 using QPSK and outputs symbol sequence 2.

[0432] S4-6. The UE concatenates or combines symbol sequence 1 and symbol sequence 2 to form symbol sequence 3; and the UE sends symbol sequence 3 to the NW.

[0433] S4-7.NW decodes the source-channel coded portion of the hybrid coded sequence to obtain a lossless PMI (source-channel coded source).

[0434] S4-8.NW trains the joint source-channel codec decoder using lossless PMI (label of the joint source-channel decoder) and received joint source-channel coding output information (input of the joint source-channel decoder); or, NW monitors the performance of the joint source-channel codec decoder using lossless PMI (label of the joint source-channel decoder) and received joint source-channel coding output information (input of the joint source-channel decoder).

[0435] It should be noted that the joint source-channel decoder can be the aforementioned target AI model.

[0436] The wireless communication method provided in this application can be executed by a wireless communication device. This application uses an example of a wireless communication device executing the wireless communication method to illustrate the wireless communication device provided in this application.

[0437] This application provides a wireless communication device. As an example, the wireless communication device may be a communication equipment or a component within a communication equipment, such as a chip. The communication equipment may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0438] The wireless communication device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0439] Specifically, referring to Figure 4, when the wireless communication device is the first device or a component of the first device, the wireless communication device 300 includes:

[0440] Processing module 301 is used to encode source information according to at least two encoding methods to obtain target information; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC.

[0441] The sending module 302 is used to send the target information to the second device.

[0442] In some embodiments, the encoding method used in the first part of the source information is different from the encoding method used in the second part of the source information.

[0443] In some embodiments, the encoding method used for the source information corresponding to the first service or scenario is different from the encoding method used for the source information corresponding to the second service or scenario.

[0444] In some embodiments, where the encoding method used in the first part includes the first encoding method and / or the second encoding method, and the encoding method used in the second part is the third encoding method, the target information is obtained by splicing or merging the encoding information corresponding to the first part after being modulated by the target modulation method with the encoding information corresponding to the second part.

[0445] or,

[0446] When the encoding method used in the first part is the first encoding method and the encoding method used in the second part is the second encoding method, the target information is obtained by directly splicing or merging the encoding information corresponding to the first part with the encoding information corresponding to the second part, and then modulating it with the target modulation method.

[0447] In some embodiments, the source information is channel state information (CSI), the first part further includes first metadata, and the second part further includes second metadata;

[0448] Wherein, if the encoding method used in the first part or the second part includes the first encoding method, the first metadata or the second metadata includes at least one of the following:

[0449] CSI information type, CSI information length, CSI information source coding method, CSI information channel coding method, CSI information modulation method, encoded CSI information length, and CSI information associated sequence splicing order;

[0450] Wherein, if the encoding method used in the first part or the second part includes the second encoding method, the first metadata or the second metadata includes at least one of the following:

[0451] CSI information type, CSI information length, bit-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information;

[0452] Wherein, if the encoding method used in the first part or the second part includes the third encoding method, the first metadata or the second metadata includes at least one of the following:

[0453] CSI information type, CSI information length, symbol-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information.

[0454] In some embodiments, different parts of the source information employing the first coding scheme and / or the second coding scheme employ their respective target modulation schemes.

[0455] In some embodiments, the target modulation scheme includes at least one of the following:

[0456] Binary Phase Shift Keying (BPSK);

[0457] pi / 2-BPSK;

[0458] Quadrature Phase Shift Keying (QPSK)

[0459] 16 Quadrature Amplitude Modulation (QAM);

[0460] 64QAM;

[0461] 256QAM;

[0462] 1024QAM;

[0463] 4096QAM;

[0464] Modulation based on artificial intelligence (AI) models.

[0465] In some embodiments, the source information is CSI;

[0466] The information source information includes at least one of the following:

[0467] Channel Quality Indicator (CQI);

[0468] At least one of the following: mean, variance, bias, and product factor of CQI normalization;

[0469] Precoding matrix indicates PMI;

[0470] At least one of the following: mean, variance, bias, and product factor of PMI normalization;

[0471] Channel State Information Reference Signal Resource Indicator (CRI);

[0472] At least one of the following: mean, variance, bias, and product factor of CRI normalization;

[0473] Synchronization Signal Block Resource Indicator (SSBRI);

[0474] At least one of the following: mean, variance, bias, and product factor of SSBRI normalization;

[0475] Layer indicator LI;

[0476] At least one of the following: mean, variance, bias, and product factor of LI normalization;

[0477] Rank indicator RI;

[0478] At least one of the following: mean, variance, bias, and product factor of RI normalization;

[0479] Layer 1 reference signal received power L1-RSRP;

[0480] At least one of the following: mean, variance, bias, and product factor of L1-RSRP normalization;

[0481] Layer 1 signal interference-to-noise ratio (L1-SINR);

[0482] At least one of the following: mean, variance, bias, and product factor of L1-SINR normalization;

[0483] CSI reports the corresponding capability index;

[0484] At least one of the following: mean, variance, bias, and product factor of the capability index normalization;

[0485] Time-domain channel characteristics (TDCP);

[0486] At least one of the following: mean, variance, bias, and product factor of TDCP normalization;

[0487] Raw channel information;

[0488] At least one of the following: mean, variance, bias, and product factor of the normalized raw channel information;

[0489] Processed channel information;

[0490] The normalized mean, variance, bias, and product factor of the processed channel information;

[0491] The information source corresponding to PMI;

[0492] At least one of the following: mean, variance, bias, and product factor of the source normalization corresponding to PMI;

[0493] The monitoring results of PMI.

[0494] In some embodiments, different portions of the source information that use the first coding method employ their respective source coding methods or channel coding methods; and / or,

[0495] Different portions of the source information using the second encoding method employ their respective bit-level joint source-channel coding methods; and / or,

[0496] Different parts of the source information that use the third coding method employ their respective symbol-level joint source-channel coding methods.

[0497] In some embodiments, the source coding in the first coding method includes at least one of the following: Huffman coding, arithmetic coding, LZ coding, quantization coding, differential coding, codebook-based coding, cyclic redundancy check (CRC) coding, and AI model-based source coding.

[0498] The channel coding in the first coding method includes at least one of the following: low-density parity-check (LDPC) code, Polar code, Turbo code, repeat code, Simplex code, RM code, TBCC code, and channel coding based on an AI model.

[0499] The second encoding method includes at least one of the following: bit-level joint source-channel coding based on an AI model, and bit-level joint source-channel coding not based on an AI model;

[0500] The third coding method includes at least one of the following: symbol-level joint source-channel coding based on an AI model, and symbol-level joint source-channel coding not based on an AI model.

[0501] In some embodiments, the wireless communication device 300 further includes: a receiving module 303;

[0502] The receiving module 303 is used to receive second information from the second device, and the sending module 302 is also used to send the second information to the second device;

[0503] The second information is used to indicate at least one of the following:

[0504] The first encoding method;

[0505] The second encoding method;

[0506] The third encoding method;

[0507] The type of the first part;

[0508] The type of the second part;

[0509] The type of the first metadata;

[0510] The type of the second element information.

[0511] In some embodiments, the processing module 301 is further configured to obtain at least one of the following:

[0512] The first encoding method;

[0513] The second encoding method;

[0514] The third encoding method;

[0515] The type of the first part;

[0516] The type of the second part;

[0517] The type of the first metadata;

[0518] The type of the second element information.

[0519] In some embodiments, the wireless communication device 300 is a first terminal and the second device is a second terminal; or, the wireless communication device 300 is a terminal and the second device is an access network device, a core network device, or a third-party server.

[0520] The sending module 302 is also used to send third information to the second device;

[0521] The third information is used to indicate at least one of the following:

[0522] The wireless communication device 300 supports joint source-channel coding feedback;

[0523] The wireless communication device 300 supports separate source channel coding feedback;

[0524] The wireless communication device 300 supports CSI feedback based on an AI model;

[0525] The wireless communication device 300 supports CSI feedback based on a non-AI model.

[0526] Referring to Figure 5, when the wireless communication device is a second device or a component of a second device, the wireless communication device 400 includes:

[0527] The receiving module 401 is used to receive target information from the first device; wherein the target information is obtained by encoding source information based on at least two encoding methods, the at least two encoding methods include at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC;

[0528] The processing module 402 is used to decode the target information to obtain the decoded information.

[0529] In some embodiments, the encoding method used in the first part of the source information is different from the encoding method used in the second part of the source information.

[0530] In some embodiments, the encoding method used for the source information corresponding to the first service or scenario is different from the encoding method used for the source information corresponding to the second service or scenario.

[0531] In some embodiments, where the encoding method used in the first part includes the first encoding method and / or the second encoding method, and the encoding method used in the second part is the third encoding method, the target information is obtained by splicing or merging the encoding information corresponding to the first part after being modulated by the target modulation method with the encoding information corresponding to the second part.

[0532] or,

[0533] When the encoding method used in the first part is the first encoding method and the encoding method used in the second part is the second encoding method, the target information is obtained by directly splicing or merging the encoding information corresponding to the first part with the encoding information corresponding to the second part, and then modulating it with the target modulation method.

[0534] In some embodiments, the source information is channel state information (CSI), the first part further includes first metadata, and the second part further includes second metadata;

[0535] The processing module 402 is specifically used for:

[0536] Based on the first metadata and the second metadata, the target information is decoded to obtain the decoded information;

[0537] Wherein, if the encoding method used in the first part or the second part includes the first encoding method, the first metadata or the second metadata includes at least one of the following:

[0538] CSI information type, CSI information length, CSI information source coding method, CSI information channel coding method, CSI information modulation method, encoded CSI information length, and CSI information associated sequence splicing order;

[0539] Wherein, if the encoding method used in the first part or the second part includes the second encoding method, the first metadata or the second metadata includes at least one of the following:

[0540] CSI information type, CSI information length, bit-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information;

[0541] Wherein, if the encoding method used in the first part or the second part includes the third encoding method, the first metadata or the second metadata includes at least one of the following:

[0542] CSI information type, CSI information length, symbol-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information.

[0543] In some embodiments, different parts of the source information employing the first coding scheme and / or the second coding scheme employ their respective target modulation schemes.

[0544] In some embodiments, the target modulation scheme includes at least one of the following:

[0545] Binary Phase Shift Keying (BPSK);

[0546] pi / 2-BPSK;

[0547] Quadrature Phase Shift Keying (QPSK)

[0548] 16 Quadrature Amplitude Modulation (QAM);

[0549] 64QAM;

[0550] 256QAM;

[0551] 1024QAM;

[0552] 4096QAM;

[0553] Modulation based on artificial intelligence (AI) models.

[0554] In some embodiments, the source information is CSI;

[0555] The information source information includes at least one of the following:

[0556] Channel Quality Indicator (CQI);

[0557] At least one of the following: mean, variance, bias, and product factor of CQI normalization;

[0558] Precoding matrix indicates PMI;

[0559] At least one of the following: mean, variance, bias, and product factor of PMI normalization;

[0560] Channel State Information Reference Signal Resource Indicator (CRI);

[0561] At least one of the following: mean, variance, bias, and product factor of CRI normalization;

[0562] Synchronization Signal Block Resource Indicator (SSBRI);

[0563] At least one of the following: mean, variance, bias, and product factor of SSBRI normalization;

[0564] Layer indicator LI;

[0565] At least one of the following: mean, variance, bias, and product factor of LI normalization;

[0566] Rank indicator RI;

[0567] At least one of the following: mean, variance, bias, and product factor of RI normalization;

[0568] Layer 1 reference signal received power L1-RSRP;

[0569] At least one of the following: mean, variance, bias, and product factor of L1-RSRP normalization;

[0570] Layer 1 signal interference-to-noise ratio (L1-SINR);

[0571] At least one of the following: mean, variance, bias, and product factor of L1-SINR normalization;

[0572] CSI reports the corresponding capability index;

[0573] At least one of the following: mean, variance, bias, and product factor of the capability index normalization;

[0574] Time-domain channel characteristics (TDCP);

[0575] At least one of the following: mean, variance, bias, and product factor of TDCP normalization;

[0576] Raw channel information;

[0577] At least one of the following: mean, variance, bias, and product factor of the normalized raw channel information;

[0578] Processed channel information;

[0579] The normalized mean, variance, bias, and product factor of the processed channel information;

[0580] The information source corresponding to PMI;

[0581] At least one of the following: mean, variance, bias, and product factor of the source normalization corresponding to PMI;

[0582] The monitoring results of PMI.

[0583] In some embodiments, different portions of the source information that use the first coding method employ their respective source coding methods or channel coding methods; and / or,

[0584] Different portions of the source information using the second encoding method employ their respective bit-level joint source-channel coding methods; and / or,

[0585] Different parts of the source information that use the third coding method employ their respective symbol-level joint source-channel coding methods.

[0586] In some embodiments, the source coding in the first coding method includes at least one of the following: Huffman coding, arithmetic coding, LZ coding, quantization coding, differential coding, codebook-based coding, cyclic redundancy check (CRC) coding, and AI model-based source coding.

[0587] The channel coding in the first coding method includes at least one of the following: low-density parity-check (LDPC) code, Polar code, Turbo code, repeat code, Simplex code, RM code, TBCC code, and channel coding based on an AI model.

[0588] The second encoding method includes at least one of the following: bit-level joint source-channel coding based on an AI model, and bit-level joint source-channel coding not based on an AI model;

[0589] The third coding method includes at least one of the following: symbol-level joint source-channel coding based on an AI model, and symbol-level joint source-channel coding not based on an AI model.

[0590] In some embodiments, the first device is a first terminal and the wireless communication device 400 is a second terminal; or, the first device is a terminal and the wireless communication device 400 is an access network device, a core network device, or a third-party server.

[0591] The receiving module 401 is also configured to receive third information from the first device;

[0592] The third information is used to indicate at least one of the following:

[0593] The first device supports joint source-channel coding feedback;

[0594] The first device supports separate source channel coding feedback;

[0595] The first device supports CSI feedback based on an AI model;

[0596] The first device supports CSI feedback based on a non-AI model.

[0597] In some embodiments, the processing module 402 is further configured to monitor the performance of joint source-channel coding based on the decoded information; and / or,

[0598] The processing module 402 is further configured to train the target AI model based on the decoded information, or the processing module 402 is further configured to monitor the performance of the target AI model based on the decoded information.

[0599] The target AI model is used to implement joint source-channel decoding.

[0600] Therefore, in this embodiment, the first device encodes the source information according to at least two encoding methods to obtain the target information; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method being SSCC, the second encoding method being bit-level JSCC, and the third encoding method being symbol-level JSCC; the first device sends the target information to the second device. Specifically, this embodiment can achieve flexible source information encoding and feedback through hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method); for content with high accuracy requirements, SSCC is used for encoding to ensure the accuracy of the feedback; for content with high real-time requirements, and / or for content with low feedback accuracy requirements, JSCC (bit-level JSCC and / or symbol-level JSCC) is used for encoding to improve feedback efficiency.

[0601] The wireless communication device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG3 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0602] As shown in Figure 6, this application embodiment also provides a communication device 500, including a processor 501 and a memory 502, wherein the memory 502 stores a program or instructions that can be run on the processor 501.

[0603] For example, when the communication device 500 is the first device, the program or instruction executed by the processor 501 implements the various steps executed by the first device in the above wireless communication method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0604] For example, when the communication device 500 is a second device, the program or instruction executed by the processor 501 implements the various steps executed by the second device in the above wireless communication method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0605] This application also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps in the method embodiment shown in FIG3. This terminal embodiment corresponds to the above-described first device-side method embodiment or second device-side method embodiment, and all implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and can achieve the same technical effect. The terminal can be the wireless communication device 300 shown in FIG4 or the wireless communication device 400 shown in FIG5. Specifically, FIG7 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application.

[0606] The terminal 600 includes, but is not limited to, at least some of the following components: radio frequency unit 601, network module 602, audio output unit 603, input unit 604, sensor 605, display unit 606, user input unit 607, interface unit 608, memory 609, and processor 610.

[0607] Those skilled in the art will understand that terminal 600 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to processor 610 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in Figure 7 does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0608] It should be understood that, in this embodiment, the input unit 604 may include a graphics processor 6041 and a microphone 6042. The graphics processor 6041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 606 may include a display panel 6061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 607 includes at least one of a touch panel 6071 and other input devices 6072. The touch panel 6071 is also called a touch screen. The touch panel 6071 may include two parts: a touch detection device and a touch controller. Other input devices 6072 may include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick, which will not be described in detail here.

[0609] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 601 can transmit it to the processor 610 for processing; in addition, the radio frequency unit 601 can send uplink data to the network-side device. Typically, the radio frequency unit 601 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0610] The memory 609 can be used to store software programs or instructions, as well as various data. The memory 609 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 609 may include volatile memory or non-volatile memory. The non-volatile memory may 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), 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). The memory 609 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0611] Processor 610 may include one or more processing units; optionally, processor 610 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 610.

[0612] In some embodiments, the first device is a terminal;

[0613] The processor 610 is used to acquire target information according to at least two encoding methods; wherein the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, wherein the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC.

[0614] The radio frequency unit 601 is used to send the target information to the second device.

[0615] In some embodiments, the second device is a terminal;

[0616] The radio frequency unit 601 is used to receive target information from the first device; wherein the target information is obtained based on at least two encoding methods, the at least two encoding methods including at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-level JSCC.

[0617] The processor 610 is used to decode the target information to obtain decoded information.

[0618] Therefore, in this embodiment, the first device acquires target information according to at least two encoding methods; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method being SSCC, the second encoding method being bit-level JSCC, and the third encoding method being symbol-level JSCC; the first device sends the target information to the second device. Specifically, this embodiment can achieve flexible source information encoding and feedback through hybrid encoding (at least two of the first encoding method, the second encoding method, and the third encoding method); for content with high accuracy requirements, SSCC is used for encoding to ensure the accuracy of the feedback; for content with high real-time requirements, and / or for content with low feedback accuracy or precision requirements, JSCC (bit-level JSCC and / or symbol-level JSCC) is used for encoding to improve feedback efficiency.

[0619] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the method embodiment and achieve the same or corresponding technical effect. To avoid repetition, it will not be described again here.

[0620] This application also provides a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiment shown in FIG3. This network-side device embodiment corresponds to the method embodiment executed by the first or second device described above. All implementation processes and methods of the above method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0621] Specifically, this application embodiment also provides a network-side device, which may be the wireless communication device 300 shown in FIG. 4 or the wireless communication device 400 shown in FIG. 5. As shown in FIG. 8, the network-side device 700 includes: an antenna 71, a radio frequency device 72, a baseband device 73, a processor 74, and a memory 75. The antenna 71 is connected to the radio frequency device 72. In the uplink direction, the radio frequency device 72 receives information through the antenna 71 and sends the received information to the baseband device 73 for processing. In the downlink direction, the baseband device 73 processes the information to be transmitted and sends it to the radio frequency device 72. The radio frequency device 72 processes the received information and transmits it through the antenna 71.

[0622] The method executed by the first or second device in the above embodiments can be implemented in the baseband device 73, which includes a baseband processor.

[0623] The baseband device 73 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG8. One of the chips is, for example, a baseband processor, which is connected to the memory 75 via a bus interface to call the program in the memory 75 to execute the operation of the first device or the second device shown in the above method embodiments.

[0624] The network-side device may also include a network interface 76, such as a Common Public Radio Interface (CPRI).

[0625] Specifically, the network-side device 700 in this application embodiment further includes: instructions or programs stored in memory 75 and executable on processor 74. Processor 74 calls the instructions or programs in memory 75 to execute the methods executed by the modules shown in FIG4 or FIG5 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0626] Specifically, this application also provides a network-side device. As shown in FIG9, the network-side device 800 includes a processor 801, a network interface 802, and a memory 803. The network-side device may be the wireless communication device 300 shown in FIG4 or the wireless communication device 400 shown in FIG5. The network interface 802 is, for example, a common public radio interface (CPRI).

[0627] Specifically, the network-side device 800 in this application embodiment further includes: instructions or programs stored in memory 803 and executable on processor 801. Processor 801 calls the instructions or programs in memory 803 to execute the methods executed by the modules shown in FIG4 or FIG5 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0628] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described wireless communication method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0629] The processor is the processor in the first or second device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0630] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described wireless communication method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0631] 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.

[0632] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described wireless communication method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0633] This application also provides a wireless communication system, including a first device and a second device. The first device can be used to perform the steps performed by the first device in the wireless communication method described above, and the second device can be used to perform the steps performed by the second device in the wireless communication method described above.

[0634] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0635] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0636] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

A wireless communication method, comprising: The first device encodes source information according to at least two encoding methods to obtain target information; wherein, the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC. The first device sends the target information to the second device. According to the method of claim 1, wherein, The encoding method used in the first part of the source information is different from the encoding method used in the second part of the source information. The method according to claim 2, wherein, In the case where the encoding method used in the first part includes the first encoding method and / or the second encoding method, and the encoding method used in the second part is the third encoding method, the target information is obtained by splicing or merging the encoding information corresponding to the first part after being modulated by the target modulation method with the encoding information corresponding to the second part. or, When the encoding method used in the first part is the first encoding method and the encoding method used in the second part is the second encoding method, the target information is obtained by directly splicing or merging the encoding information corresponding to the first part with the encoding information corresponding to the second part, and then modulating it with the target modulation method. The method according to claim 2 or 3, wherein, The source information is channel state information (CSI), the first part further includes first element information, and the second part further includes second element information; Wherein, if the encoding method used in the first part or the second part includes the first encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, CSI information source coding method, CSI information channel coding method, CSI information modulation method, encoded CSI information length, and CSI information associated sequence splicing order; Wherein, if the encoding method used in the first part or the second part includes the second encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, bit-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information; Wherein, if the encoding method used in the first part or the second part includes the third encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, symbol-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information. The method according to claim 3, wherein, The source information employs different target modulation methods for different parts of the first encoding method and / or the second encoding method. The method according to claim 3 or 5, wherein, The target modulation method includes at least one of the following: Binary Phase Shift Keying (BPSK); pi / 2-BPSK; Quadrature Phase Shift Keying (QPSK) 16 Quadrature Amplitude Modulation (QAM); 64QAM; 256QAM; 1024QAM; 4096QAM; Modulation based on artificial intelligence (AI) models. The method according to any one of claims 1 to 6, wherein, The encoding method used for the source information corresponding to the first business or scenario is different from the encoding method used for the source information corresponding to the second business or scenario. The method according to any one of claims 1 to 7, wherein, The source information is CSI; The information source information includes at least one of the following: Channel Quality Indicator (CQI); At least one of the following: mean, variance, bias, and product factor of CQI normalization; Precoding matrix indicates PMI; At least one of the following: mean, variance, bias, and product factor of PMI normalization; Channel State Information Reference Signal Resource Indicator (CRI); At least one of the following: mean, variance, bias, and product factor of CRI normalization; Synchronization Signal Block Resource Indicator (SSBRI); At least one of the following: mean, variance, bias, and product factor of SSBRI normalization; Layer indicator LI; At least one of the following: mean, variance, bias, and product factor of LI normalization; Rank indicator RI; At least one of the following: mean, variance, bias, and product factor of RI normalization; Layer 1 reference signal received power L1-RSRP; At least one of the following: mean, variance, bias, and product factor of L1-RSRP normalization; Layer 1 signal interference-to-noise ratio (L1-SINR); At least one of the following: mean, variance, bias, and product factor of L1-SINR normalization; CSI reports the corresponding capability index; At least one of the following: mean, variance, bias, and product factor of the capability index normalization; Time-domain channel characteristics (TDCP); At least one of the following: mean, variance, bias, and product factor of TDCP normalization; Raw channel information; At least one of the following: mean, variance, bias, and product factor of the normalized raw channel information; Processed channel information; The normalized mean, variance, bias, and product factor of the processed channel information; The information source corresponding to PMI; At least one of the following: mean, variance, bias, and product factor of the source normalization corresponding to PMI; The monitoring results of PMI. The method according to any one of claims 1 to 8, wherein, Different portions of the source information that use the first encoding method employ their respective source encoding methods or channel encoding methods; and / or, Different portions of the source information using the second encoding method employ their respective bit-level joint source-channel coding methods; and / or, Different parts of the source information that use the third coding method employ their respective symbol-level joint source-channel coding methods. The method according to any one of claims 1 to 9, wherein, The method further includes: The first device receives the second information from the second device, or the first device sends the second information to the second device; The second information is used to indicate at least one of the following: The first encoding method; The second encoding method; The third encoding method; The type of the first part; The type of the second part; The type of the first metadata; The type of the second element information. The method according to any one of claims 1 to 9, wherein, The method further includes: The first device acquires at least one of the following: The first encoding method; The second encoding method; The third encoding method; The type of the first part; The type of the second part; The type of the first metadata; The type of the second element information. The method according to any one of claims 1 to 11, wherein, The source coding in the first coding method includes at least one of the following: Huffman coding, arithmetic coding, LZ coding, quantization coding, differential coding, codebook-based coding, cyclic redundancy check (CRC) coding, and AI model-based source coding. The channel coding in the first coding method includes at least one of the following: low-density parity-check (LDPC) code, Polar code, Turbo code, repeat code, Simplex code, RM code, TBCC code, and channel coding based on an AI model. The second encoding method includes at least one of the following: bit-level joint source-channel coding based on an AI model, and bit-level joint source-channel coding not based on an AI model; The third coding method includes at least one of the following: symbol-level joint source-channel coding based on an AI model, and symbol-level joint source-channel coding not based on an AI model. The method according to any one of claims 1 to 12, wherein, The first device is a first terminal, and the second device is a second terminal; or, the first device is a terminal, and the second device is an access network device, a core network device, or a third-party server. The method further includes: The first device sends a third message to the second device; The third information is used to indicate at least one of the following: The first device supports joint source-channel coding feedback; The first device supports separate source channel coding feedback; The first device supports CSI feedback based on an AI model; The first device supports CSI feedback based on a non-AI model. A wireless communication method, comprising: The second device receives target information from the first device; wherein the target information is obtained by encoding source information based on at least two encoding methods, the at least two encoding methods include at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-level JSCC; The second device decodes the target information to obtain the decoded information. The method according to claim 14, wherein, The encoding method used in the first part of the source information is different from the encoding method used in the second part of the source information. The method according to claim 15, wherein, In the case where the encoding method used in the first part includes the first encoding method and / or the second encoding method, and the encoding method used in the second part is the third encoding method, the target information is obtained by splicing or merging the encoding information corresponding to the first part after being modulated by the target modulation method with the encoding information corresponding to the second part. or, When the encoding method used in the first part is the first encoding method and the encoding method used in the second part is the second encoding method, the target information is obtained by directly splicing or merging the encoding information corresponding to the first part with the encoding information corresponding to the second part, and then modulating it with the target modulation method. The method according to claim 15 or 16, wherein, The source information is channel state information (CSI), the first part further includes first element information, and the second part further includes second element information; The second device decodes the target information to obtain decoded information, including: The second device decodes the target information based on the first metadata and the second metadata to obtain the decoded information; Wherein, if the encoding method used in the first part or the second part includes the first encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, CSI information source coding method, CSI information channel coding method, CSI information modulation method, encoded CSI information length, and CSI information associated sequence splicing order; Wherein, if the encoding method used in the first part or the second part includes the second encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, bit-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information; Wherein, if the encoding method used in the first part or the second part includes the third encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, symbol-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information. The method according to any one of claims 14 to 17, wherein, The source information is CSI; The information source information includes at least one of the following: Channel Quality Indicator (CQI); At least one of the following: mean, variance, bias, and product factor of CQI normalization; Precoding matrix indicates PMI; At least one of the following: mean, variance, bias, and product factor of PMI normalization; Channel State Information Reference Signal Resource Indicator (CRI); At least one of the following: mean, variance, bias, and product factor of CRI normalization; Synchronization Signal Block Resource Indicator (SSBRI); At least one of the following: mean, variance, bias, and product factor of SSBRI normalization; Layer indicator LI; At least one of the following: mean, variance, bias, and product factor of LI normalization; Rank indicator RI; At least one of the following: mean, variance, bias, and product factor of RI normalization; Layer 1 reference signal received power L1-RSRP; At least one of the following: mean, variance, bias, and product factor of L1-RSRP normalization; Layer 1 signal interference-to-noise ratio (L1-SINR); At least one of the following: mean, variance, bias, and product factor of L1-SINR normalization; CSI reports the corresponding capability index; At least one of the following: mean, variance, bias, and product factor of the capability index normalization; Time-domain channel characteristics (TDCP); At least one of the following: mean, variance, bias, and product factor of TDCP normalization; Raw channel information; At least one of the following: mean, variance, bias, and product factor of the normalized raw channel information; Processed channel information; The normalized mean, variance, bias, and product factor of the processed channel information; The information source corresponding to PMI; At least one of the following: mean, variance, bias, and product factor of the source normalization corresponding to PMI; The monitoring results of PMI. The method according to any one of claims 14 to 18, wherein, The first device is a first terminal, and the second device is a second terminal; or, the first device is a terminal, and the second device is an access network device, a core network device, or a third-party server. The method further includes: The second device receives third information from the first device; The third information is used to indicate at least one of the following: The first device supports joint source-channel coding feedback; The first device supports separate source channel coding feedback; The first device supports CSI feedback based on an AI model; The first device supports CSI feedback based on a non-AI model. The method according to any one of claims 14 to 19, wherein, The method further includes: The second device monitors the performance of joint source-channel coding based on the decoded information; and / or, The second device trains the target AI model based on the decoded information, or the second device monitors the performance of the target AI model based on the decoded information; The target AI model is used to implement joint source-channel decoding. A wireless communication device, comprising: The processing module is used to encode source information according to at least two encoding methods to obtain target information; wherein the at least two encoding methods include at least two of a first encoding method, a second encoding method, and a third encoding method, the first encoding method is Separate Source Channel Coding (SSCC), the second encoding method is Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method is Symbol-Level JSCC. The sending module is used to send the target information to the second device. The apparatus according to claim 21, wherein, The encoding method used in the first part of the source information is different from the encoding method used in the second part of the source information. The apparatus according to claim 22, wherein, In the case where the encoding method used in the first part includes the first encoding method and / or the second encoding method, and the encoding method used in the second part is the third encoding method, the target information is obtained by splicing or merging the encoding information corresponding to the first part after being modulated by the target modulation method with the encoding information corresponding to the second part. or, When the encoding method used in the first part is the first encoding method and the encoding method used in the second part is the second encoding method, the target information is obtained by directly splicing or merging the encoding information corresponding to the first part with the encoding information corresponding to the second part, and then modulating it with the target modulation method. The apparatus according to claim 22 or 23, wherein, The source information is channel state information (CSI), the first part further includes first element information, and the second part further includes second element information; Wherein, if the encoding method used in the first part or the second part includes the first encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, CSI information source coding method, CSI information channel coding method, CSI information modulation method, encoded CSI information length, and CSI information associated sequence splicing order; Wherein, if the encoding method used in the first part or the second part includes the second encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, bit-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information; Wherein, if the encoding method used in the first part or the second part includes the third encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, symbol-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information. The apparatus according to any one of claims 21 to 24, wherein, The wireless communication device further includes: a receiving module; The receiving module is used to receive second information from the second device, or the sending module is further used to send second information to the second device; The second information is used to indicate at least one of the following: The first encoding method; The second encoding method; The third encoding method; The type of the first part; The type of the second part; The type of the first metadata; The type of the second element information. The apparatus according to any one of claims 21 to 25, wherein, The first device is a first terminal, and the second device is a second terminal; or, the first device is a terminal, and the second device is an access network device, a core network device, or a third-party server. The sending module is also used to send third information to the second device; The third information is used to indicate at least one of the following: The wireless communication device supports joint source-channel coding feedback; The wireless communication device supports separate source channel coding feedback; The wireless communication device supports CSI feedback based on an AI model; The wireless communication device supports CSI feedback based on a non-AI model. A wireless communication device, comprising: A receiving module is configured to receive target information from a first device; wherein the target information is obtained by encoding source information based on at least two encoding methods, the at least two encoding methods including at least two of a first encoding method, a second encoding method and a third encoding method, the first encoding method being Separate Source Channel Coding (SSCC), the second encoding method being Bit-Level Joint Source Channel Coding (JSCC), and the third encoding method being Symbol-Level JSCC; The processing module is used to decode the target information to obtain the decoded information. The apparatus according to claim 27, wherein, The encoding method used in the first part of the source information is different from the encoding method used in the second part of the source information. The apparatus according to claim 28, wherein, In the case where the encoding method used in the first part includes the first encoding method and / or the second encoding method, and the encoding method used in the second part is the third encoding method, the target information is obtained by splicing or merging the encoding information corresponding to the first part after being modulated by the target modulation method with the encoding information corresponding to the second part. or, When the encoding method used in the first part is the first encoding method and the encoding method used in the second part is the second encoding method, the target information is obtained by directly splicing or merging the encoding information corresponding to the first part with the encoding information corresponding to the second part, and then modulating it with the target modulation method. The apparatus according to claim 28 or 29, wherein, The source information is channel state information (CSI), the first part further includes first element information, and the second part further includes second element information; The processing module is specifically used for: Based on the first metadata and the second metadata, the target information is decoded to obtain the decoded information; Wherein, if the encoding method used in the first part or the second part includes the first encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, CSI information source coding method, CSI information channel coding method, CSI information modulation method, encoded CSI information length, and CSI information associated sequence splicing order; Wherein, if the encoding method used in the first part or the second part includes the second encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, bit-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information; Wherein, if the encoding method used in the first part or the second part includes the third encoding method, the first metadata or the second metadata includes at least one of the following: CSI information type, CSI information length, symbol-level joint source-channel coding method of CSI information, modulation method of CSI information, length of encoded CSI information, and sequence splicing order associated with CSI information. The apparatus according to any one of claims 27 to 30, wherein, The first device is a first terminal, and the wireless communication device is a second terminal; or, the first device is a terminal, and the wireless communication device is an access network device, a core network device, or a third-party server. The receiving module is also configured to receive third information from the first device; The third information is used to indicate at least one of the following: The first device supports joint source-channel coding feedback; The first device supports separate source channel coding feedback; The first device supports CSI feedback based on an AI model; The first device supports CSI feedback based on a non-AI model. The apparatus according to any one of claims 27 to 31, wherein, The processing module is also configured to monitor the performance of joint source-channel coding based on the decoded information; and / or, The processing module is also used to train the target AI model based on the decoded information, or the processing module is also used to monitor the performance of the target AI model based on the decoded information; The target AI model is used to implement joint source-channel decoding. A first device includes a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the wireless communication method as claimed in any one of claims 1 to 13. A second device includes a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the wireless communication method as claimed in any one of claims 14 to 20. A readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the wireless communication method as claimed in any one of claims 1 to 13, or implement the steps of the wireless communication method as claimed in any one of claims 14 to 20.

Images