CSI transmission method, CSI reception method, and device

Abstract

A CSI transmission method, a CSI reception method, and an apparatus are provided. In the method, a terminal transmits CSI in a target layer to an access network device based on an instruction from the access network device, where the target layer may be any layer. Compared with conventional CSI feedback in which a terminal transmits PMI of n layers with the highest quality to an access network device, the CSI fed back by the terminal can meet the requirements of the access network device, thereby reducing the air interface overhead of transmitting unnecessary CSI by the terminal.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to Chinese Patent Application No. 202310126151.0, entitled "CSI Transmission Method, CSI Reception Method, and Apparatus," filed with the State Intellectual Property Office of the People's Republic of China on February 6, 2023, which is incorporated herein by reference in its entirety.

[0002] FIELD Embodiments of the present application relate to the field of communication technology, and in particular to a CSI transmission method, a CSI reception method, and an apparatus. [Background technology]

[0003] In wireless communication networks, e.g., mobile communication networks, the services supported by the network are becoming increasingly diverse, and therefore the requirements that need to be met are becoming increasingly diverse. For example, networks need to be able to support ultra-high-speed connections, ultra-low latency connections, and / or large-scale connections. This functionality increases the complexity of network planning, network configuration, and / or resource scheduling. Furthermore, network capabilities are becoming increasingly powerful. For example, higher and higher spectrum is supported, higher-order multiple-input multiple-output (MIMO) technology is supported, and new technologies such as beamforming and / or beam management are supported. These new requirements, scenarios, and characteristics pose unprecedented challenges to network planning, operation and maintenance, and efficient operation. To address this challenge, artificial intelligence technologies are being introduced into wireless communication networks to implement network intelligence. Therefore, how to transmit and receive channel state information (CSI) in an artificial intelligence wireless communication network is a worthy issue to consider. Summary of the Invention [Means for solving the problem]

[0004] The embodiments of the present application provide a CSI transmission method, a CSI receiving method and an apparatus to meet the requirements of an artificial intelligence wireless communication network for CSI.

[0005] According to a first aspect, there is provided a CSI transmission method. The method is applied to a first communication device. The first communication device may be a terminal, a chip or circuit used in the terminal, etc. The method includes: receiving first information from a second communication device, the first information including instruction information instructing the first communication device to transmit channel state information (CSI) in a target layer; and transmitting a first CSI report to the second communication device, the first CSI report including the CSI in the target layer.

[0006] In the above implementation, the terminal transmits CSI in a target layer to the access network device based on the instruction of the access network device, and the target layer may be any layer. Compared with conventional CSI feedback in which the terminal transmits PMI of n layers with the highest quality to the access network device, the CSI fed back by the terminal can meet the requirements of the access network device, thereby reducing the air interface overhead of transmitting unnecessary CSI by the terminal.

[0007] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix, or compression information and / or quantization information of the channel response of the target layer.

[0008] In the above implementation, the terminal transmits the eigenvector matrix of the target layer or the compressed and / or quantized information of the channel response to the access network device. Compared with the case where the terminal directly transmits the eigenvector matrix of the target layer, the channel response, etc. to the access network device, the air interface overhead for transmitting the CSI by the terminal can be reduced.

[0009] In one implementation, the CSI in the target layer further includes one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0010] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0011] In the above implementation, the CSI fed back by the terminal to the access network device in this application may be referred to as ground truth CSI, and the ground truth CSI and conventional CSI may be fed back together. For example, a new CSI reporting number may be designed. The CSI reporting may simultaneously feed back the ground truth CSI, conventional CSI, etc., and the ground truth CSI and conventional CSI may be fed back together, thereby improving CSI feedback efficiency.

[0012] In one implementation, the method further includes a step of sending a second CSI report to the second communication device, where the second CSI report includes one or more of the following indication information: RI, CQI, or PMI, and the number of layers of the PMI is determined based on the RI.

[0013] In the above-mentioned implementation, the CSI fed back by the terminal to the access network device in this application may be referred to as ground truth CSI, and the ground truth CSI and the conventional CSI may be fed back separately. For example, a new CSI type may be designed to feed back ground truth CSI, and the feedback of the ground truth CSI and the feedback of the conventional CSI do not affect each other.

[0014] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a transmission period of CSI in the target layer, or a transmission pattern of CSI in the target layer.

[0015] In one implementation, the CSI at the target layer transmitted by the first communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0016] In the above-described implementation, the first CSI report reported by the terminal to the access network device may be used for AI-related data collection, such as the above-described model training, model inference, model testing, model validation, or model monitoring. Based on the target layer indicated by the access network device, the terminal transmits CSI in the corresponding target layer to the access network device, so that the AI ​​data requirements of the access network device can be met.

[0017] In one implementation, the first information is configuration information, and the configuration information is used to configure the first communication device to transmit CSI in a target layer.

[0018] According to a second aspect, there is provided a CSI reception method. The second aspect is a peer-side method corresponding to the first aspect. For beneficial effects, please refer to the first aspect. The method is applied to a second communication device. The second communication device is an access network device, or a chip, circuit, etc. used in the access network device. The method includes: transmitting first information to the first communication device, where the first information includes instruction information instructing the first communication device to transmit channel state information (CSI) in a target layer to the first communication device; and receiving a first CSI report from the first communication device, where the first CSI report includes CSI in the target layer.

[0019] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix, or compression information and / or quantization information of the channel response of the target layer.

[0020] In one implementation, the CSI in the target layer further includes one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0021] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0022] In one implementation, the method further includes receiving a second CSI report from the first communication device, wherein the second CSI report includes one or more of the following indication information: RI, CQI, or PMI, and the number of layers of the PMI is determined based on the RI.

[0023] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a transmission period of CSI in the target layer, or a transmission pattern of CSI in the target layer.

[0024] In one implementation, the CSI in the target layer received by the second communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0025] In one implementation, the first information is configuration information, and the configuration information is used to configure the first communication device to transmit CSI in a target layer.

[0026] According to a third aspect, a CSI transmission method is provided. In one implementation, the method is applied to a first communication device. The first communication device may be a terminal, a chip or circuit used in the terminal, or the like. Alternatively, the first communication device may be an access network device, or a chip, circuit, or the like used in the access network device. The method includes: transmitting first information to a second communication device, where the first information includes instruction information instructing the first communication device to transmit channel state information (CSI) in a target layer; and transmitting a first CSI report to the second communication device, where the first CSI report includes the CSI in the target layer.

[0027] In the above implementation, the terminal can actively transmit CSI in the target layer to the access network device. For example, the terminal transmits indication information in the target layer to the access network device, and the terminal transmits CSI in the target layer to the access network device. Alternatively, the access network device may actively transmit CSI in the target layer to the terminal. For example, the access network device transmits indication information in the target layer to the terminal, and the access network device transmits CSI in the target layer to the terminal. The terminal or the access network device can use the collected CSI in the target layer for AI processing to meet AI requirements for CSI data.

[0028] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix of the target layer, or compression information and / or quantization information of the channel response of the target layer.

[0029] In one implementation, the CSI at the target layer may further include one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0030] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0031] In one implementation, the method further includes a step of sending a second CSI report to the second communication device, where the second CSI report includes one or more of the following indication information: RI, CQI, or PMI, and the number of layers of the PMI is determined based on the RI.

[0032] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following for the target layer: eigenvalues ​​or singular values ​​of an eigenvector matrix of the target layer; a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer; a transmission period of CSI in the target layer; or a transmission pattern of CSI in the target layer.

[0033] In one implementation, the CSI at the target layer transmitted by the first communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0034] In one implementation, the first information is instruction information, and the instruction information instructs the first communication device to transmit CSI in a target layer.

[0035] According to a fourth aspect, there is provided a CSI reception method. The fourth aspect is a peer side of the aforementioned third aspect. For beneficial effects, see the description of the third aspect. The method is applied to a second communication device. The second communication device may be an access network device, a chip or circuit used in the access network device, or the like. Alternatively, the second communication device may be a terminal, a chip or circuit used in the terminal, or the like. The method includes: receiving first information from a first communication device, the first information including instruction information instructing the first communication device to transmit channel state information (CSI) in a target layer; and receiving a first CSI report from the first communication device, the first CSI report including CSI in the target layer.

[0036] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix of the target layer, or compression information and / or quantization information of the channel response of the target layer.

[0037] In one implementation, the CSI at the target layer may further include one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0038] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0039] In one implementation, the method further includes receiving a second CSI report from the first communication device, wherein the second CSI report includes one or more of the following indication information: RI, CQI, or PMI, and the number of layers of the PMI is determined based on the RI.

[0040] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following for the target layer: eigenvalues ​​or singular values ​​of an eigenvector matrix of the target layer; a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer; a transmission period of CSI in the target layer; or a transmission pattern of CSI in the target layer.

[0041] In one implementation, the CSI in the target layer received by the second communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0042] In one implementation, the first information is instruction information, and the instruction information instructs the first communication device to transmit CSI in a target layer.

[0043] According to a fifth aspect, there is provided an apparatus, the apparatus including corresponding units or modules for performing the method of any one of the first to fourth aspects, the units or modules may be implemented by hardware circuits, software, or a combination of hardware circuits and software.

[0044] According to a sixth aspect, there is provided an apparatus, comprising a processor and an interface circuit, the processor configured to communicate with another apparatus via the interface circuit and to perform the method of any one of the first to fourth aspects, and there may be one or more processors.

[0045] According to a seventh aspect, an apparatus is provided, comprising a processor coupled to a memory. The processor is configured to execute a program stored in the memory to perform the method of any one of the first to fourth aspects. The memory may be located internal or external to the apparatus. Additionally, there may be one or more processors.

[0046] According to an eighth aspect, there is provided an apparatus, comprising a processor and a memory, the memory being configured to store computer instructions, the processor executing the computer instructions stored in the memory when the apparatus is operating, to enable the apparatus to perform the method of any one of the first to fourth aspects.

[0047] According to a ninth aspect, a chip system is provided, comprising a processor or circuitry configured to perform the method of any one of the first to fourth aspects.

[0048] According to a tenth aspect, there is provided a computer-readable storage medium having instructions stored thereon, the instructions, when executed on a communication device, causing the method of any one of the first to fourth aspects to be performed.

[0049] According to an eleventh aspect, there is provided a computer program product, the computer program product including a computer program or instructions, which, when executed by an apparatus, cause the computer to perform the method of any one of the first to fourth aspects.

[0050] According to a twelfth aspect, there is provided a system, comprising a first communication device performing the method of the first aspect and a second communication device performing the method of the second aspect, or comprising a first communication device performing the method of the third aspect and a second communication device performing the method of the fourth aspect. [Brief explanation of the drawings]

[0051] [Figure 1] 1 is a diagram of a communication system according to an embodiment of the present application; [Figure 2] FIG. 1 is a diagram illustrating the deployment of an AI model according to an embodiment of the present application. [Figure 3] FIG. 10 is another diagram of deploying an AI model according to an embodiment of the present application. [Figure 4] FIG. 1 is a diagram of an architecture of an access network device according to an embodiment of the present application. [Figure 5] FIG. 2 is another diagram of the architecture of an access network device according to an embodiment of the present application. [Figure 6] FIG. 1 is a diagram of an application architecture of an AI model according to an embodiment of the present application. [Figure 7] FIG. 1 is a diagram of a neuron according to an embodiment of the present application. [Figure 8] FIG. 2 is a diagram of layer relationships in a neural network according to an embodiment of the present application. [Figure 9]1 is a flowchart of transmitting and receiving CSI according to an embodiment of the present application. [Figure 10] FIG. 1 is a diagram of transmitting and receiving CSI using a model according to an embodiment of the present application. [Figure 11] 10 is another flowchart of transmitting and receiving CSI according to an embodiment of the present application. [Figure 12] 10 is yet another flowchart of transmitting and receiving CSI according to an embodiment of the present application. [Figure 13] 1 is a diagram of the structure of an apparatus according to an embodiment of the present application; [Figure 14] FIG. 10 is a diagram of another configuration of the device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0052] 1 is a diagram illustrating the architecture of a communication system 1000 to which the present application is applicable. As shown in FIG. 1, the communication system 1000 includes a radio access network 100 and a core network 200. Optionally, the communication system 1000 may further include the Internet 300.

[0053] The wireless access network 100 may include at least one access network device (e.g., 100a and 110b in FIG. 1 ) and may further include at least one terminal (e.g., 120a-120j in FIG. 1 ). The terminal is connected to the access network device wirelessly, and the access network device is connected to the core network wirelessly or wired. The core network device and the access network device may be separate physical devices, or the core network device functionality and the access network device logical functionality may be integrated into the same physical device, or some of the core network device functionality and some of the access network device functionality may be integrated into one physical device. The terminals may be connected to each other in a wired or wireless manner, and the access network devices may be connected to each other in a wired or wireless manner. FIG. 1 is merely a diagram. The communication system 1000 may further include other network devices, such as a wireless relay device or a wireless backhaul device, which are not shown in FIG. 1 .

[0054] The access network device may be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next-generation NodeB (gNB) for a fifth-generation (5G) mobile communication system, an access network device for an open radio access network (O-RAN), a next-generation base station for a sixth-generation (6G) mobile communication system, a base station for a future mobile communication system, an access node for a wireless fidelity (Wi-Fi) system, or the like. Alternatively, it may be a module or unit that completes part of the functions of a base station, such as a central unit (CU), a distributed unit (DU), a central unit control plane (CU-CP) module, or a central unit user plane (CU-UP) module. The access network device may be a macro base station (e.g., 110a in FIG. 1), a micro base station, or an indoor base station (e.g., 110b in FIG. 1), or may be a relay node, a donor node, or the like. The particular technology used by the access network devices and the particular device configuration are not limited by this application.

[0055] In the present application, an apparatus configured to perform the functions of an access network device may be an access network device, or may be an apparatus capable of supporting an access network device in performing the functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The apparatus may be incorporated into an access network device or adapted for use with an access network device. In the present application, a chip system may include a chip, or may include a chip and another discrete component. For ease of explanation, the following will describe the technical solutions provided in the present application using an example in which the apparatus configured to perform the functions of an access network device is an access network device.

[0056] (1) Protocol layer structure Communications between the access network device and the terminal conform to a specific protocol layer structure. The protocol layer structure may include a control plane protocol layer structure and a user plane protocol layer structure. For example, the control plane protocol layer structure may include protocol layer functions such as a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, and a physical layer. For example, the user plane protocol layer structure may include protocol layer functions such as a PDCP layer, an RLC layer, a MAC layer, and a physical layer. In one possible implementation, a service data adaptation protocol (SDAP) layer may be further included above the PDCP layer.

[0057] Optionally, the protocol layer structure between the access network device and the terminal may further include an artificial intelligence (AI) layer used to transmit data related to AI functions.

[0058] (2) Central Unit (CU) and Distributed Unit (DU) An access network device may include a CU and a DU. Multiple DUs may be centrally controlled by one CU. For example, the interface between a CU and a DU may be called an F1 interface. A control plane (CP) interface may be F1-C, and a user plane (UP) interface may be F1-U. The specific names of the interfaces are not limited in this application. The CU and DU may be divided based on the protocol layer of the wireless network. For example, the functions of the PDCP layer and the functions of the protocol layers above the PDCP layer are configured in the CU, and the functions of the protocol layers below the PDCP layer (e.g., the RLC layer and the MAC layer) are configured in the DU. In another example, the functions of the protocol layers above the PDCP layer are configured in the CU, and the functions of the PDCP layer and the functions of the protocol layers below the PDCP layer are configured in the DU. This is not a limitation.

[0059] The division of the processing functions of the CU and the DU based on the protocol layer is merely an example, and other division schemes may be used. For example, the CU or DU may have more protocol layer functions through division. As another example, the CU or DU may also have some processing functions of protocol layers through division. In one implementation, some of the RLC layer functions and functions of protocol layers above the RLC layer are configured on the CU, and the remaining RLC layer functions and functions of protocol layers below the RLC layer are configured on the DU. In another implementation, the division of the CU or DU functions may alternatively be performed based on service type or other system requirements. For example, the division may be performed based on latency. Functions whose processing time must meet latency requirements are configured on the DU, and functions whose processing time does not need to meet latency requirements are configured on the CU. In another design, the CU may alternatively have one or more functions of a core network. For example, the CU may be located on the network side to facilitate centralized management. In another design, the radio unit (RU) of the DU is remotely located. Optionally, the RU may have radio frequency functionality.

[0060] Optionally, the DU and the RU may be divided at the physical layer (PHY). For example, the DU may perform functions of a layer above the PHY layer, and the RU may perform functions of a layer below the PHY layer. When used for transmission, the PHY layer functions may include at least one of the following: cyclic redundancy check (CRC) code addition, channel coding, rate matching, scrambling, modulation, layer mapping, precoding, resource mapping, physical antenna mapping, or radio frequency transmission functions. When used for reception, the PHY layer functions may include at least one of CRC checking, channel decoding, de-rate matching, descrambling, demodulation, layer demapping, channel detection, resource demapping, physical antenna demapping, or radio frequency reception functions. The functions of the layer above the PHY layer may include some of the functions of the PHY layer. For example, some of the functions may be closer to the MAC layer. The functions of the layer below the PHY layer may include other parts of the functions of the PHY layer. For example, some of the functions may be closer to the radio frequency functions. For example, the functions of the upper layer of the PHY layer may include CRC code addition, channel coding, rate matching, scrambling, modulation, and layer mapping, while the functions of the lower layer of the PHY layer may include precoding, resource mapping, physical antenna mapping, and radio frequency transmission functions. Alternatively, the functions of the upper layer of the PHY layer may include CRC code addition, channel coding, rate matching, scrambling, modulation, layer mapping, and precoding. The functions of the lower layer of the PHY layer may include resource mapping, physical antenna mapping, and radio frequency transmission functions. For example, the functions of the upper layer of the PHY layer may include CRC checking, channel decoding, de-rate matching, decoding, demodulation, and layer demapping, while the functions of the lower layer of the PHY layer may include channel detection, resource demapping, physical antenna demapping, and radio frequency reception functions.Alternatively, the functions of the upper layer of the PHY layer may include CRC checking, channel decoding, de-rate matching, decoding, demodulation, layer demapping, and channel detection, and the functions of the lower layer of the PHY layer may include resource demapping, physical antenna demapping, and radio frequency receiving functions.

[0061] For example, the functions of the CU may be implemented by one entity or by separate entities. For example, the functions of the CU may be further divided. Specifically, the control plane and the user plane are separated and implemented by separate entities, i.e., a control plane CU entity (i.e., a CU-CP entity) and a user plane CU entity (i.e., a CU-UP entity). The CU-CP entity and the CU-UP entity may be coupled to the DU to jointly complete the functions of the access network device.

[0062] Optionally, any one of the DU, CU, CU-CP, CU-UP, and RU may be a software module, a hardware structure, or a combination of a software module and a hardware structure. This is not limited thereto. Different entities may exist in different forms. This is not limited thereto. For example, the DU, CU, CU-CP, and CU-UP are software modules, and the RU is a hardware structure. These modules and the methods performed by the modules also fall within the scope of protection of the embodiments of the present application.

[0063] In one possible implementation, the access network device includes a CU-CP, a CU-UP, a DU, and an RU. For example, the embodiments of the present application are performed by a DU, or a DU and an RU, or a CU-CP, a DU, and an RU, or a CU-UP, a DU, and an RU. This is not limited. Methods performed by modules also fall within the scope of protection of the embodiments of the present application.

[0064] A terminal may also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals may be widely used for communication in various scenarios, including, but not limited to, one or more of the following scenarios: device-to-device (D2D), vehicle-to-everything (V2X), machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transport, and smart city. Terminals may be mobile phones, tablet computers, computers with wireless transceiver capabilities, wearable devices, vehicles, unmanned aerial vehicles, helicopters, airplanes, ships, robots, robotic arms, smart home devices, etc. The specific technology and specific device configuration used by a terminal are not limited by this application.

[0065] In the present application, a device configured to perform the functions of a terminal may be a terminal, or may be a device capable of supporting a terminal in performing functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The device may be incorporated into a terminal or adapted for use with a terminal. For ease of explanation, the following will use an example in which the device configured to perform the functions of a terminal is a terminal to describe the technical solutions provided in the present application.

[0066] The access network devices and terminals may be in fixed locations or may be mobile. The access network devices and / or terminals may be located on land, on water, or on aircraft, balloons, and satellites, including indoor or outdoor devices, handheld devices, or vehicle-mounted devices. The application scenarios of the access network devices and terminals are not limited in this application. The access network devices and terminals may be located in the same scenario or in different scenarios. For example, the access network devices and terminals are both located on land, or the access network devices are located on land and the terminals are located on water. Examples will not be given one by one.

[0067] The roles of access network devices and terminals may be relative. For example, helicopter or unmanned aerial vehicle 120i in FIG. 1 may be configured as a mobile access network device. For terminal 120j accessing wireless access network 100 via 120i, terminal 120i is an access network device. However, with respect to access network device 110a, 120i is a terminal; that is, 110a and 120i communicate with each other according to a wireless air interface protocol. Alternatively, 110a and 120i communicate with each other using an interface protocol between access network devices. In this case, for 110a, 120i is also an access network device. Therefore, both access network devices and terminals may be collectively referred to as communication devices. 110a and 110b in FIG. 1 may be referred to as communication devices having the functionality of access network devices, and 120a to 120j in FIG. 1 may be referred to as communication devices having the functionality of terminals.

[0068] Communications between access network devices and terminals, between access network devices, or between terminals may be performed using licensed spectrum, unlicensed spectrum, or both licensed and unlicensed spectrum, may be performed using spectrum below 6 gigahertz (GHz), may be performed using spectrum above 6 GHz, or may be performed using spectrum below 6 GHz and above 6 GHz. The spectrum resources used for wireless communications are not limited in this application.

[0069] In this application, an independent network element, referred to as an AI network element, AI node, etc., may be introduced into the communication system shown in FIG. 1 to perform AI-related operations. The AI ​​network element may be directly connected to an access network device in the communication system or indirectly connected to the access network device via a third-party network element. The third-party network element may be a core network element, such as an authentication management function (AMF) or a user plane function (UPF). Alternatively, an AI function, AI module, or AI entity may be embedded in another network element in the communication system to perform AI-related operations. The other network element may be an access network device, a core network device, a network management system, etc. In this case, the network element performing AI-related operations may be a network element with built-in AI functions. Operation, administration, and maintenance (OAM) is configured to perform operations, administration, maintenance, etc. on the access network devices and / or core network devices.

[0070] As shown in FIG. 2 or 3 , an AI model may be deployed in at least one of a core network device, an access network device, a terminal device, an OAM, etc., and corresponding functions are implemented using the AI ​​model. In the present application, the AI ​​models deployed in different nodes may be the same or different. The models differ in terms of different structural parameters of the models, such as at least one of a different number of layers and / or weights of the models, different input parameters of the models, or different output parameters of the models. The different input parameters of the models and / or different output parameters of the models may be described as different functions of the models. Unlike FIG. 2 , in FIG. 3 , the functions of the access network device are separated into a CU and a DU. Optionally, the CU and DU may be the CU and DU in an O-RAN architecture. One or more AI models may be deployed in the CU and / or one or more AI models may be deployed in the DU. Optionally, the CU in FIG. 3 may further be divided into a CU-CP and a CU-UP. Optionally, one or more AI models may be deployed in the CU-CP and / or one or more AI models may be deployed in the CU-UP. Optionally, in FIG. 2 or FIG. 3, the OAM of the access network device and the OAM of the core network device may be located separately.

[0071] In this application, the access network device may use an O-RAN architecture. The following describes an example of an O-RAN architecture, which is not intended to limit the present application.

[0072] In a first design, as shown in FIG. 4, the access network devices include a near-real-time access network intelligent controller (RAN intelligent controller), a CU, a DU, an RU, etc. The near-real-time RIC is configured to perform model training and inference. For example, the near-real-time RIC can train an AI model and use the AI ​​model for inference. For example, the near-real-time RIC can obtain network-side or terminal-side information from one or more of the CU, the DU, the RU, or the terminal, and the information may be used as training data or inference data. For example, the above information may be used as training data, and the near-real-time RIC can train an AI model using the collected training data. Alternatively, the above information may be used as inference data, and the near-real-time RIC may perform model inference based on the collected inference data and the AI ​​model to determine an inference result. Optionally, the near-real-time RIC can transmit the inference result to one or more of the CU, the DU, the RU, the terminal, etc. Optionally, the CU and the DU may exchange the inference result. For example, the near-real-time RIC transmits the inference result to the CU, and the CU forwards the inference result to the DU. Optionally, the DU and the RU may exchange inference results, for example, the near-real-time RIC sends the inference results to the DU, or the near-real-time RIC sends the inference results to the CU, the CU forwards the inference results to the DU, and the DU forwards the inference results to the RU.

[0073] In the first design, the near-real-time RIC is included in the access network device. Whether the non-real-time RIC is included outside the access network device is not limited. For example, the non-real-time RIC may be included outside the access network device, or the non-real-time RIC may not be included outside the access network device.

[0074] In a second design, as shown in FIG. 4, a non-real-time RIC is included outside the access network device. For example, the non-real-time RIC may be located in an OAM or core network device. This is not limited to this. The non-real-time RIC may train an AI model and use the AI ​​model for inference. Optionally, the non-real-time RIC may collect network-side or terminal-side information from one or more of a CU, a DU, an RU, a terminal, etc., and the information may be used as training data or inference data. For example, the information is used as training data, and the non-real-time RIC may use the training data to train an AI model. Alternatively, the information is used as inference data, and the non-real-time RIC uses the inference data and the AI ​​model to determine an inference result. Optionally, the non-real-time RIC may transmit the inference result to one or more of a CU, a DU, an RU, a terminal, etc. Optionally, the CU and the DU may exchange the inference result. The DU and the RU may exchange the inference result.

[0075] In the second design, the non-real-time RIC is included outside the access network device. Whether the access network device includes a near-real-time RIC is not limited. For example, the access network device may include a near-real-time RIC, or the access network device may not include a near-real-time RIC.

[0076] In a third design, as shown in FIG. 4, the near-real-time RIC is included in the access network device and the non-real-time RIC is included outside the access network device. As in the first design, the near-real-time RIC can perform model training and inference, and / or as in the second design, the non-real-time RIC can perform model training and inference, and / or the non-real-time RIC can perform model training and the near-real-time RIC can perform model inference. For example, the non-real-time RIC can send a trained AI model to the near-real-time RIC, and the near-real-time RIC uses the AI ​​model for model inference. Optionally, the non-real-time RIC and / or the near-real-time RIC can collect network-side or terminal-side information from one or more of a CU, a DU, a RU, a terminal, etc., and the information may be used as training data or inference data. For example, the information is used as training data, and the non-real-time RIC uses the training data to train the AI ​​model. The information is used as inference data, and the near-real-time RIC uses the AI ​​model and inference data to determine an inference result. Optionally, the near-real-time RIC can send the inference result to one or more of a CU, a DU, a RU, a terminal, etc. Optionally, the CU and the DU may exchange inference results, and the DU and the RU may exchange inference results.

[0077] 5 shows another O-RAN architecture according to the present application. Compared with FIG. 4, in FIG. 5, the CU is separated into CU-CP, CU-UP, etc.

[0078] In this embodiment of the present application, the second communication device can perform AI-related operations on the received channel state information (CSI). AI techniques are described below, but these descriptions are not intended to limit the present application.

[0079] An AI model is a specific implementation of an AI function. An AI model represents a mapping relationship between the input and output of the model. The AI ​​model may be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q-learning model, another machine learning model, etc. In this application, an AI function may include one or more of data collection (collection of training data and / or inference data), data preprocessing, model training (model learning), model information release (configuration of model information), model validation, model inference, publishing inference results, etc. In this application, an AI model may be referred to as a model for short.

[0080] 6 is a diagram of an application architecture of an AI model. A data source is configured to store training data and inference data. A model training node analyzes or trains the training data provided by the data source to obtain an AI model, and deploys the AI ​​model to a model inference node. Optionally, the model training node can further update the AI ​​model deployed in the model inference node. The model inference node can further feed back related information of the deployed model to the model training node, so that the model training node performs optimization, update, etc. on the deployed AI model.

[0081] Obtaining an AI model through learning by a model training node is equivalent to obtaining a mapping relationship between the model's input and output through learning by the model training node using training data. The model inference node uses the AI ​​model to perform inference based on inference data provided by a data source and obtain an inference result. This method can alternatively be described as follows: the model inference node inputs inference data to the AI ​​model and uses the AI ​​model to obtain an output, where the output is the inference result. The inference result may indicate configuration parameters used (executed) by an actor object and / or operations performed by the actor object. The inference result may be planned by an actor entity in a unified manner and transmitted to one or more actor objects (e.g., network entities) for execution. Optionally, the actor entity or actor object may feed back parameters or measurement results of measurements collected by the actor entity or actor object to the data source. This process may be referred to as performance feedback, and the fed-back parameters may be used as training data or inference data. Optionally, feedback information related to model performance may be further determined based on the inference result output by the model inference node, and the feedback information is fed back to the model inference node, which can feed back model performance information to the model training node based on the feedback information, so that the model training node performs optimization, update, etc. on the deployed AI model. This process may be referred to as model feedback.

[0082] The AI ​​model may be a neural network or another machine learning model. A neural network is used as an example. A neural network is a specific implementation of machine learning techniques. According to the universal approximation theorem, a neural network can theoretically approximate any continuous function, and therefore, a neural network has the ability to learn any mapping. Therefore, a neural network can accurately perform abstract modeling for complex, high-dimensional problems.

[0083] The concept of neural networks comes from the neuron structure of the brain. Each neuron performs a weighted sum operation on the input neuron values ​​and outputs the weighted sum result using an activation function. Figure 7 shows the neuron structure. The input values ​​of a neuron are x = [x0, x1, ... x n ], and the weights corresponding to the input values ​​are w=[w, w1, ..., w n ] and the bias of the weighted sum is assumed to be b. The form of the activation function can be diversified. The activation function of one neuron is It is assumed that y = f(z) = max(0, z). In this case, the output of the neuron is

number

number

[0084] Neural networks typically have a multi-layer structure, with each layer containing one or more neurons. Increasing the depth and / or width of a neural network can improve the neural network's representational capabilities and provide more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network may be the number of layers contained in the neural network, and the number of neurons contained in each layer may be referred to as the layer width. Figure 8 illustrates the layer relationships of a neural network. In one implementation, a neural network includes an input layer and an output layer. After performing neuronal processing on the received input, the input layer of the neural network transfers the results to the output layer, which obtains the output result of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. After performing neuronal processing on the received input, the input layer of the neural network transfers the results to an intermediate hidden layer, which then transfers the calculation results to the output layer or an adjacent hidden layer, and finally, the output layer obtains the output result of the neural network. A neural network may include one hidden layer or multiple hidden layers connected in series. This is not limited. In the neural network training process, a loss function may be defined. The loss function describes the gap or difference between the neural network's output value and the neural network's ideal target value. The specific form of the loss function is not limited in this application. The neural network training process is a process of adjusting the neural network's parameters, such as the number of layers, the neural network width, the neuron weights, and / or the parameters of the neuron's activation function, so that the value of the loss function is less than a threshold or meets the target requirement.

[0085] In communication systems such as long term evolution (LTE) and new radio (NR), access network devices need to acquire downlink channel state information (CSI) to determine configurations such as resources, modulation and coding schemes (MCSs), and precoding for scheduling downlink data channels of terminals. In a time division duplex (TDD) system, because there is reciprocity between the uplink and downlink channels, access network devices may acquire uplink CSI by measuring an uplink reference signal to estimate downlink CSI. For example, uplink CSI is used as downlink CSI. In a frequency division duplex (FDD) system, because reciprocity between the uplink and downlink cannot be guaranteed, terminals acquire downlink CSI by measuring a downlink reference signal. For example, the terminal measures a downlink reference signal, such as a channel state information reference signal (CSI-RS) or a synchronization signal / physical broadcast channel block (SSB), to obtain the downlink CSI. In one implementation, the terminal generates a CSI report in a manner such as by predefining or configuring a protocol by an access network device, where the CSI report carries the downlink CSI measured by the terminal, and reports the CSI report to the access network device, thereby enabling the access network device to obtain the downlink CSI.

[0086] In the NR protocol, the downlink CSI feedback procedure involves an access network device transmitting a CSI-RS to a terminal. The terminal performs channel measurement, interference measurement, etc. based on the CSI-RS to obtain measurement results and determines feedback amounts such as a rank indicator (RI), a channel quality indicator (CQI), and a precoding matrix indication (PMI) based on the measurement results. The terminal reports downlink CSI to the access network device, and the downlink CSI includes information such as the RI, CQI, and PMI measured by the terminal. The RI indicates the number of layers for downlink transmission recommended by the terminal, the CQI indicates the MCS supported by the current downlink channel conditions recommended by the terminal, and the PMI indicates the precoding scheme recommended by the terminal.

[0087] 1. Field of the Invention The present application relates to precoding. Next, a precoding technique will be described.

[0088] Precoding technology is an important method for increasing communication speed. In precoding technology, the transmitter uses multiple antennas (also called antenna ports) and assigns weights to the transmission data of each antenna to achieve a beamforming effect, so that the signal transmitted by the transmitter better matches the channel conditions. For example, downlink precoding is used as an example. If the downlink signal transmitted by the access network device is X, the downlink channel is H, the downlink precoding matrix is ​​W, and the noise is N0, then the downlink signal transmitted by the access network device is S = WX, and the downlink signal received by the terminal is Y = HWX + N0.

[0089] The number of layers fed back by the PMI corresponds to the RI. For example, if the RI indicates n layers for downlink transmission, the PMI indicates n layers of a precoding matrix. For each layer of the PMI, the access network device can precode the downlink signal using the corresponding PMI, perform beamforming, and transmit the downlink signal to the terminal. In other words, the access network device performs precoding using each layer of the PMI to form a corresponding beam, and transmits the downlink signal to the terminal using the corresponding beam, so that beamforming can be performed and the transmission quality of the downlink signal can be improved.

[0090] The above-described CSI feedback mechanism is designed for downlink precoding, and the number of layers of PMI fed back by the terminal matches the number of layers indicated by the RI. For example, if the RI indicates n layers for downlink transmission, the terminal needs to feed back PMI corresponding to each of the n layers to the access network device. In other words, the terminal needs to feed back n layers of PMI to the access network device. After AI is introduced, in addition to downlink precoding, the PMI may also be used for data collection in AI, etc. In one implementation, the access network device may not require n layers of PMI. Therefore, in the above-described CSI feedback mechanism, the terminal may decide to feed back n layers of PMI with the best channel quality and may not flexibly adapt to the requirements of AI-related data collection on the access network device side.

[0091] An embodiment of the present application provides a CSI transmission method and a CSI reception method, the method including: a first communication device receiving first information from a second communication device, the first information including instruction information instructing the first communication device to transmit CSI in a target layer; the first communication device transmitting a first CSI report to the second communication device, the first CSI report including the CSI in the target layer; for example, the first communication device is a terminal, a chip or circuit used in the terminal, etc.; and the second communication device is an access network device, a chip, circuit, etc. used in the access network device. In the method of the present application, the access network device transmits instruction information of CSI in a specific layer to the terminal, and the terminal transmits CSI in the corresponding layer to the access network device based on the instruction of the access network device; and the terminal transmits CSI in the corresponding layer to the access network device based on the instruction of the access network device to meet the requirements of AI-related data collection at the access network device side.

[0092] As shown in FIG. 9, an example in which the first communication device is a terminal and the second communication device is an access network device is used to provide a procedure including the following steps:

[0093] Step 900: A terminal receives first information from an access network device, where the first information includes instruction information instructing the terminal to transmit CSI in a target layer.

[0094] For example, the first information may be configuration information, which is used to configure the terminal to transmit CSI in the target layer. The first information may be carried in an RRC message, a MAC CE, downlink control information (DCI), etc. This is not limited. In one implementation, the access network device may send an RRC message to the terminal, which is used to configure CSI reporting, and the configured CSI report may be referred to as a CSI reporting configuration. The terminal transmits a CSI report to the access network device based on the CSI reporting configuration. In this embodiment of the present application, the first information may be carried in an RRC message for configuring CSI reporting.

[0095] In another implementation, the access network device configures multiple CSI reports for the terminal, and each configured CSI report may be referred to as a CSI reporting configuration. Then, the access network device sends a MAC CE or a DCI to the terminal to activate one of the CSI reporting configurations, and the terminal transmits a CSI report to the access network device based on the activated CSI reporting configuration. The first information may be carried in the MAC CE or the DCI to activate the CSI report. In yet another implementation, the access network device may transmit a DCI to the terminal to schedule the CSI report, and upon receiving the scheduling of the DCI, the terminal transmits the CSI report to the access network device. Optionally, the CSI report may be carried on a data channel for transmission, for example, on a physical uplink shared channel (PUSCH) for transmission. This is not limited. The first information may be carried in the DCI to schedule the CSI report, etc. Alternatively, the first information may be independent information. To establish a relationship between the first information and the CSI report, i.e., to indicate a CSI report to which the first information specifically applies, an index of a CSI reporting configuration associated with the first information may be indicated in the first information, or an index of the first information, etc., may be indicated in the CSI reporting configuration. For example, the terminal transmits a CSI report to the access network device based on the CSI reporting configuration. The CSI reporting configuration may be used to configure a time-frequency resource, a manner, etc. for transmitting the CSI report by the terminal. This is not limited thereto. The access network device may instruct the terminal to transmit CSI in a target layer by using the first information in step 900. In this embodiment of the present application, a correspondence relationship between the CSI configuration report and the first information is established to indicate one specific CSI report or multiple specific CSI reports to which the terminal transmits CSI in the target layer.Alternatively, for example, the correspondence between the first information and the CSI report may be predefined, specified by a protocol, or default. For example, there are multiple types of CSI reports, and it is predefined that CSI in the target layer is transmitted in one or more specific types of CSI report. Alternatively, when the first information becomes valid, the first information may be applied to a predefined CSI report, a protocol-specified CSI report, a default CSI report, etc.

[0096] As described above, the first information includes instruction information instructing the terminal to transmit CSI in a target layer. The target layer may be any layer. For example, the target layer may be one layer or multiple layers. The multiple layers may be multiple consecutive layers, multiple discontinuous layers, etc. This is not limited thereto. The first information may use a bitmap to instruct the terminal to transmit CSI in the target layer. For example, the access network device may use N bits to instruct the terminal to transmit CSI in a specific target layer among N layers. Each bit represents one layer. For example, 1 indicates that the terminal needs to transmit CSI in the corresponding layer, and 0 indicates that the terminal does not need to transmit CSI in the corresponding layer. For example, 0 indicates that the terminal needs to transmit CSI in the corresponding layer, and 1 indicates that the terminal does not need to transmit CSI in the corresponding layer. For example, if the instruction information included in the first information transmitted by the access network device to the terminal is 1100, it indicates that the terminal needs to transmit CSI in the first layer and CSI in the second layer. The first and second layers may be considered as target layers. For the third and fourth layers, the terminal no longer transmits corresponding CSI. Alternatively, the first information may instruct the terminal to transmit CSI in the target layer in a specific manner. For example, the terminal may use N bits to transmit CSI in the target layer. NThe first information instructs the terminal to transmit CSI in a specific layer. For example, 00 indicates transmitting CSI in the first layer, 01 indicates transmitting CSI in the second layer, 10 indicates transmitting CSI in the third layer, and 11 indicates transmitting CSI in the fourth layer. Alternatively, the first information can instruct the terminal to no longer transmit CSI in a specific layer in a specific manner. The remaining layers that are not instructed are considered to be layers in which CSI needs to be transmitted, i.e., the remaining layers that are not instructed are considered to be target layers. For example, the terminal is instructed not to transmit CSI in a specific layer using two bits. For example, 00 indicates not transmitting CSI in the first layer, 01 indicates not transmitting CSI in the second layer, 10 indicates not transmitting CSI in the third layer, and 11 indicates not transmitting CSI in the fourth layer. If the first information sent to the terminal by the access network device includes 00, the terminal determines not to transmit CSI in the first layer and transmits CSI in the second to fourth layers. The second to fourth layers may be regarded as target layers. Alternatively, multiple layer combinations may be predefined, and the first information may use specific instruction information to instruct the terminal device to transmit CSI of a specific layer combination. For example, four layer combinations are predefined: the first layer, the second layer, and the third layer; the first layer, the third layer, and the fourth layer. The terminal may be instructed to transmit CSI in a specific layer combination using two bits. The layer combination indicated by the access network device and for which CSI needs to be transmitted may be regarded as the target layer. Alternatively, the access network device may indicate a layer combination for which CSI does not need to be transmitted. For a layer combination not indicated by the access network device, the terminal considers the layer combination to be the target layer for which CSI needs to be transmitted.

[0097] Step 901: A terminal sends a first CSI report to an access network device, where the first CSI report includes CSI in a target layer.

[0098] As described above, an association relationship between the first information and the CSI report may be established. For a CSI report for which an association relationship is established, CSI in the target layer is transmitted when the CSI report is transmitted. This is not limited. In this embodiment of the present application, it may be considered that an association relationship between the first information and the first CSI report is established.

[0099] In this embodiment of the present application, the CSI transmitted by the terminal to the access network device may be ground truth CSI. The ground truth CSI may be an eigenvector matrix, a channel response, compressed information and / or quantized information of the channel response, compressed information and / or quantized information of the eigenvector matrix, etc. This is not limited to this. In other words, in this embodiment of the present application, the CSI in the target layer transmitted by the terminal to the access network device includes one or more of the following indication information: a channel response of the target layer, an eigenvector matrix of the target layer, compressed information and / or quantized information of the eigenvector matrix of the target layer, compressed information and / or quantized information of the channel response of the target layer, etc.

[0100] In one implementation, an access network device transmits a downlink reference signal to a terminal, and the terminal measures the downlink reference signal to determine a downlink channel response H, and performs eigendecomposition or singular value decomposition on the downlink channel response H or a covariance matrix of the downlink channel response H to obtain an eigenvector matrix V of the downlink channel response. Each row or column of the eigenvector matrix V may be referred to as an eigenvector. For example, the corresponding eigenvectors may be sorted based on their eigenvalues ​​or singular values, e.g., in descending or ascending order, to separately obtain first-layer eigenvectors, second-layer eigenvectors, third-layer eigenvectors, etc. Optionally, the frequency-domain dimension is taken into consideration. The frequency-domain dimension is added to each eigenvector to obtain a first-layer eigenvector matrix, a second-layer eigenvector matrix, a third-layer eigenvector matrix, etc. Alternatively, the frequency-domain dimension is not taken into consideration. The first-layer eigenvectors, second-layer eigenvectors, third-layer eigenvectors, etc. may also be referred to as a first-layer eigenvector matrix, a second-layer eigenvector matrix, a third-layer eigenvector matrix, etc. Optionally, the access network device and the terminal may agree in advance on the correspondence between the eigenvector matrices and the layers in a specific manner, so that the access network device and the terminal have a consistent understanding of the correspondence between the eigenvector matrices and the layers. For example, the access network device and the terminal may agree that the eigenvector matrices may be sorted in descending order based on the eigenvalues ​​or singular values, thereby separately obtaining the eigenvector matrix of the first layer, the eigenvector matrix of the second layer, the eigenvector matrix of the third layer, etc.

[0101] In another implementation, as shown in FIG. 10, after obtaining the eigenvector matrix V of the target layer, the terminal can input the eigenvector matrix V of the target layer to a CSI generator, and the output of the CSI generator is a compressed eigenvector matrix Z of the target layer. The terminal transmits the compressed eigenvector matrix Z of the target layer to an access network device. The access network device inputs the received compressed eigenvector matrix Z of the target layer to a CSI reconstructor, and the output of the CSI reconstructor is a restored eigenvector matrix V′ of the target layer. In the above implementation, the terminal does not directly transmit the eigenvector matrix of the target layer to the access network device, but transmits the compressed eigenvector matrix of the target layer, thereby reducing CSI transmission overhead. It will be understood that both the CSI generator and the CSI reconstructor are pre-trained models. The function of the CSI generator includes compressing the eigenvector matrix of the target layer, and the function of the CSI reconstructor includes restoring the compressed eigenvector matrix of the target layer. Alternatively, the terminal quantizes the eigenvector matrix of the target layer, and the terminal transmits the quantized eigenvector matrix of the target layer to the access network device. The access network device restores the quantized eigenvector matrix of the target layer to obtain the eigenvector matrix of the target layer. Quantization is a process of changing the eigenvector matrix of the target layer from continuous values ​​to discrete values. Alternatively, the terminal may perform compression and quantization processes on the eigenvector matrix of the target layer. For example, the terminal can perform compression and then quantization, or quantization and then compression, or perform compression and quantization simultaneously. This is not limited. The terminal transmits the compressed and quantized eigenvector matrix of the target layer to the access network device, and the access network device restores the original eigenvector matrix of the target layer.

[0102] In another implementation, the access network device measures a downlink reference signal to determine a downlink channel response H, and performs eigendecomposition or singular value decomposition on the downlink channel response H or the covariance matrix of the downlink channel response H to obtain the channel response of each layer. Singular value decomposition (SVD) is used as an example. SVD(H)=U, S, V, i.e., H=U*S*V, where V is the eigenvector matrix, and the channel response H of the i-th layer is (:,i)*S(i)*V(i,:). U(:,i) represents the i-th column of U, S(i) represents the i-th eigenvalue, and V(i,:) represents the i-th row of V. The terminal may transmit the channel response of the target layer to the access network device. Alternatively, the terminal may compress and / or quantize the channel response of the target layer, and the terminal transmits the compressed and / or quantized channel response of the target layer to the access network device. The access network device recovers the compressed and / or quantized channel response of the target layer.

[0103] Optionally, the CSI in the target layer transmitted by the terminal to the access network device may further include one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the channel response of the target layer, the target layer, etc.

[0104] In one implementation, if the first information includes instruction information instructing the terminal to transmit eigenvalues ​​or singular values ​​of the eigenvector matrix of the channel response of the target layer, the terminal not only transmits the eigenvector matrix of the target layer indicated by the terminal to the access network device, but also transmits the eigenvalues ​​or singular values ​​corresponding to the eigenvector matrix of the target layer to the access network device. Eigenvalues ​​are used as an example. The eigenvalues ​​corresponding to the eigenvectors in each target layer may include the eigenvalues ​​corresponding to each eigenvector in the eigenvector matrix in that layer. For example, if the eigenvector matrix in one target layer includes three eigenvectors, the terminal may transmit eigenvalues ​​corresponding to the three eigenvectors to the access network device. Alternatively, one eigenvalue may be transmitted for each eigenvector in each target layer. For example, the terminal may perform averaging or weighted averaging on the eigenvalues ​​of all eigenvectors included in the eigenvector matrix in that layer, and the terminal transmits the average calculation result of the eigenvalues ​​to the access network device. In another implementation, the layer from which the terminal transmits the eigenvalues ​​or singular values ​​may alternatively be different from the aforementioned layer from which CSI is transmitted. In other words, the eigenvalues ​​or singular values ​​transmitted by the terminal may not be the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, etc. For example, the eigenvalues ​​or singular values ​​of the eigenvector matrix at a layer transmitted by the terminal to the access network device may be predefined, specified in a protocol, or may be default. For example, it is predefined that the terminal transmits the eigenvalues, singular values, etc. of the eigenvector matrix at all layers to the access network device.

[0105] For example, the access network device may send instruction information to the terminal device to instruct the terminal to transmit eigenvalues, singular values, etc. The instruction information may be configuration information and may be described as the access network device configuring the terminal to transmit eigenvalues, singular values, etc. In this embodiment of the present application, the instruction information instructing the terminal to transmit CSI in the target layer and the instruction information instructing the terminal to transmit eigenvalues ​​or singular values ​​may be carried in the same information. For example, the first information of step 900 may further include, in addition to the instruction information instructing the terminal to transmit CSI in the target layer, instruction information instructing the terminal to transmit eigenvalues ​​or singular values ​​of the eigenvector matrix in the target layer. Alternatively, the instruction information instructing the terminal to transmit CSI in the target layer and the instruction information instructing the terminal to transmit eigenvalues ​​or singular values ​​may be independent. Furthermore, the instruction information for the eigenvalues ​​or singular values ​​may carry instruction information in the target layer, etc., to instruct the terminal to transmit the eigenvalues ​​or singular values ​​in the target layer to the access network device. Alternatively, the layer in which the terminal transmits CSI may be different from the layer in which the terminal transmits eigenvalues ​​or singular values. For example, the terminal transmits eigenvalues ​​or singular values ​​in a first layer to the access network device. The first layer is not completely the same as the target layer. For example, the first layer may be instructed by the access network device, preconfigured, specified by a protocol, or default. This is not limited. For example, the terminal transmits eigenvalues, singular values, etc. in all layers to the access network device based on a predefined configuration.

[0106] In one implementation, the access network device may further instruct the terminal to a threshold value. The threshold value instructs the terminal to transmit to the access network device an eigenvector matrix whose eigenvalues ​​or singular values ​​are greater than or equal to the threshold value. The threshold value may be carried in the first information in step 900. This is not limited. An eigenvalue is used as an example. An eigenvalue being greater than or equal to the threshold value may mean that all eigenvalues ​​corresponding to all eigenvectors of an eigenvector matrix at a certain layer are greater than or equal to the threshold value, or that eigenvalues ​​corresponding to N eigenvectors in all eigenvectors of an eigenvector matrix at a certain layer are greater than or equal to the threshold value, or that eigenvalues ​​corresponding to all eigenvectors of an eigenvector matrix at a certain layer can be calculated to obtain eigenvalues, and the eigenvalues ​​are greater than or equal to the threshold value. As described above, the access network device may instruct the terminal device to transmit CSI at a target layer. The CSI at the target layer includes an eigenvector matrix at the target layer. In one implementation, the target layer indicated by the access network device may be different from the layer calculated based on the threshold value. In this case, an intersection set between the target layer and the layer may be further obtained, and the terminal may transmit to the access network device the eigenvector matrix at the layer where the intersection set exists. For example, the access network device may instruct the terminal to transmit eigenvector matrices for the first, third, and fifth layers, where the first, third, and fifth layers are considered as target layers. The layers that satisfy the condition are determined based on a threshold instructed by the access network device and are the second, third, and sixth layers. The terminal may use the intersection set of the two to transmit the eigenvector matrix for the third layer to the access network device. In another implementation, the terminal may separately transmit the eigenvector matrix for the target layer, the eigenvector matrix that satisfies the threshold condition, etc. to the access network device. This is not limited. The previous example will continue to be used.The terminal can separately transmit to the access network device the eigenvector matrices at the (1st, 3rd, and 5th) layers in the target layer indicated by the terminal and the eigenvector matrices whose thresholds satisfy the conditions at the (2nd, 3rd, and 6th) layers.

[0107] In one implementation, the access network device can further instruct the terminal on the transmission period, transmission pattern, etc. of CSI in the target layer. The instruction information may be carried in the first information in step 900. This is not limited. The terminal transmits CSI in the target layer to the access network device based on the transmission period instructed by the access network device. Furthermore, the target layer includes at least one layer. For example, the transmission period of CSI in all layers may be the same or different. When the transmission period of CSI in all layers is the same, one transmission period may be configured for all layers in the target layer, or the transmission period of CSI in each target layer may be independently configured. The independently configured transmission period of CSI in the target layer may be the same or different. This is not limited. The transmission pattern indicates CSI in a specific layer that the terminal needs to transmit each time. For example, the transmission pattern may be {first layer, second layer and third layer, first layer and third layer, and third layer and fourth layer}. In this case, the terminal may transmit CSI in the first layer to the access network device within the first transmission period. In the second transmission period, the terminal transmits CSI in the second layer and CSI in the third layer to the access network device. Similarly, in the third and fourth transmission periods, the terminal separately transmits CSI in the first layer, CSI in the third layer, CSI in the third layer, CSI in the fourth layer, etc. to the access network device. For example, the transmission pattern may be determined based on a target layer. In each transmission period, the terminal transmits CSI in a portion of the target layer to the access network device based on the transmission pattern. For example, the target layer includes layers 1 to 4. Based on the above description, the terminal transmits CSI in a portion of the target layer within each transmission period. For example, in the third transmission period, the terminal transmits CSI in the first layer and CSI in the third layer to the access network device.

[0108] In one implementation, in addition to the instruction information instructing the terminal to transmit CSI in the target layer, the first information of step 900 further includes instruction information instructing the terminal to transmit one or more of the following: eigenvalues ​​or singular values ​​of an eigenvector matrix in the target layer, a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix in the target layer, a transmission period of CSI in the target layer, a transmission pattern of CSI in the target layer, etc.

[0109] In this embodiment of the present application, the CSI transmitted by the terminal to the access network device is a channel response, compressed information of the channel response, an eigenvector matrix, or compressed information corresponding to the eigenvector matrix. This is different from conventional CSI, which includes RI, CQI, PMI, etc. and is transmitted by the terminal to the access network device. For ease of distinction, in this embodiment of the present application, the CSI transmitted by the terminal may be referred to as ground truth CSI, and the CSI conventionally transmitted by the terminal is referred to as conventional CSI.

[0110] In one implementation, the ground truth CSI and the conventional CSI may be transmitted independently. As described above, the terminal may transmit a first CSI report to the access network device, where the first CSI includes CSI in a target layer, and the CSI in the target layer may be ground truth CSI. Furthermore, the terminal may transmit a second CSI report to the access network device, where the second CSI report includes conventional CSI, i.e., the second CSI report includes one or more of the following indication information: RI, CQI, PMI, etc., where the number of layers of the PMI is determined based on the RI. Optionally, a new CSI report quantity may be defined and used to transmit ground truth CSI, for example, cir-t CSI. In the new type of CSI report, the layer on which the CSI is transmitted is indicated by the access network device and is not affected by the RI determined by the terminal.

[0111] In another implementation, the ground truth CSI and the conventional CSI may be transmitted together, i.e., the ground truth CSI and the conventional CSI may be transmitted in one CSI report. In addition to the CSI in the target layer (ground truth CSI), the aforementioned first CSI report may further include indication information of at least one of RI, CQI, PMI, etc. The number of layers of PMI is determined based on the RI. Optionally, a new CSI reporting amount may be defined to transmit the ground truth CSI and the conventional CSI, for example, cri-RI-PMI-CQI-tCSI, cri-RI-CQI-tCSI, cri-RI-LI-PMI-CQI-tCSI, cri-RSRP-tCSI, or cri-SINR-tCSI.

[0112] In the procedure of FIG. 9, the terminal transmits CSI in a target layer to an access network device. The target layer may be any layer, and is not limited to the n-th layer having the highest quality in conventional CSI transmission. Upon receiving the CSI in the target layer, the access network device can use the CSI in the target layer as AI-related data. For example, the CSI in the target layer can be used for one or more of model training, model inference, model testing, model validation, or model monitoring.

[0113] In one implementation, the access network device can use the CSI in the target layer as training data for performing model training. Model training is an important part of machine learning. The essence of machine learning is to learn some features of a training set (including training data) so that the difference between the model output and an ideal target value is as small as possible under training on the training set. Typically, even if the same network structure is used, the weights and / or outputs of models trained using different training sets may be different. Therefore, the configuration and selection of the training set determine the performance of the model to some extent. Additionally / alternatively, the access network device can use the CSI in the target layer as inference data for performing model inference. For example, the CSI in the target layer is input to a model as inference data, and an output is obtained using the model. The output is the inference result. Additionally / alternatively, the access network device can use the CSI in the target layer as test data for performing model testing. For example, after model training is completed, the test set (including test data) can be used to test the trained model, for example, to evaluate the model's generalization ability, determine whether the model performance meets requirements, or determine whether the model is usable. Alternatively, the access network device can use the CSI in the target layer as validation data to validate the model. Model validation is typically performed during model training. For example, each time a model is trained through one or more epochs, a validation set (including validation data) can be used to validate the current model and monitor the training status of the model, for example, to verify whether underfitting, overfitting, or convergence has occurred, and determine whether to terminate training. Optionally, in the model validation process, hyperparameters of the model can be further adjusted. The hyperparameters can refer to at least one of the following parameters of the model: the number of layers of a neural network, the number of neurons, an activation function, a loss function, etc.Additionally / alternatively, the access network device can use the CSI in the target layer as monitoring data for monitoring the model. For example, in a model inference process, model performance can be monitored. If the accuracy of the inference result obtained by model inference is below a threshold, the information can be fed back to a model training node, which then performs optimization, update, etc. on the deployed model. This process is sometimes referred to as model feedback.

[0114] In the procedure of FIG. 9, the access network device may need to perform AI-related operations only for the target layer. For example, if the performance of the target layer for a model is poor, the access network device can collect CSI in the target layer as training data and perform model training, etc.; or, if the access network device expects to monitor model performance, etc. only in the target layer, the access network device can collect CSI in the target layer as monitoring data to perform model monitoring, etc. The access network device may send first information to the terminal to instruct the terminal to transmit CSI in the target layer. The terminal transmits CSI in the target layer to the access network device based on the instruction of the access network device, so that the access network device flexibly collects CSI in each layer based on different requirements. Furthermore, the terminal transmits CSI in the corresponding layer based on the instruction of the access network device, so that the CSI transmitted by the terminal can meet the requirements of the access network device and reduce the air interface overhead of transmitting CSI in unnecessary layers by the terminal.

[0115] An embodiment of the present application provides another CSI transmission method and CSI reception method. For differences from the above-mentioned method, see the following description of FIG. 11. The terminal can actively transmit CSI in the target layer to the access network device. For example, the terminal transmits indication information in the target layer to the access network device, and the terminal transmits CSI in the target layer to the access network device. Alternatively, see the following description of FIG. 12. The access network device can actively transmit CSI in the target layer to the terminal. For example, the access network device transmits indication information in the target layer to the terminal, and the access network device transmits CSI in the target layer to the terminal. The method includes: a first communication device transmitting first information to a second communication device, the first information including indication information for the first communication device to transmit CSI in the target layer; and the first communication device transmitting a first CSI report to the second communication device, the first CSI report including the CSI in the target layer.

[0116] The first communication device is a terminal, or a chip or circuit used in a terminal, etc. The second communication device is an access network device, or a chip, circuit, etc. used in an access network device. An example in which the first communication device is a terminal and the second communication device is an access network device will be used to provide a procedure including the following steps, as shown in Figure 11.

[0117] Step 1100: A terminal sends first information to an access network device, where the first information includes instruction information instructing the terminal to transmit CSI in a target layer.

[0118] For example, the first information may be indication information, which instructs the terminal to transmit CSI in a target layer.

[0119] Step 1101: A terminal sends a first CSI report to an access network device, where the first CSI report includes CSI in a target layer.

[0120] In one implementation, the first information and the first CSI report may be included in the same message. For example, the first CSI report carries the first information (also referred to as indication information in the target layer). For example, the first information is carried in a first part of the first CSI report. In another implementation, the first information and the first CSI report may be included in different messages. The association relationship between the first information and the first CSI report may be established by including an index of the first CSI report in the first information or by including an index of the first information in the first CSI report. Alternatively, for example, the association relationship between the first information and the first CSI report may be predefined, specified in a protocol, or default. This is not limited. For example, it may be predefined that there are multiple types of CSI reports, and the first information indicates the layer to which CSI is transmitted in one or more types of CSI reports. Alternatively, within the validity time of the first information, the first information may indicate all CSI reporting layers, or may indicate a predefined CSI reporting layer, etc. This is not limited thereto.

[0121] The method for indicating the target layer using the first information is similar to the method for indicating the target layer in the above-described procedure of FIG. 9. For example, the target layer may be indicated using a bitmap. Alternatively, the target layer may be indicated using specific indication information. For example, two bits indicate four layers. When the specific indication information is 00, it indicates that the target layer indicated by the indication information is the first layer. Alternatively, multiple layer combinations may be pre-divided, and different layer combinations may be indicated using the indication information. For example, four layer combinations may be pre-divided: the first layer, the second layer, and the third layer; the first layer, the third layer, and the third layer, and the fourth layer. In this case, the four layer combinations may be separately indicated using two bits. For example, when the specific indication information is 10, it indicates that the layer combination indicated by the indication information is the first layer and the third layer, i.e., the target layers are the first layer and the third layer.

[0122] In this embodiment of the present application, the CSI in the target layer transmitted by the terminal to the access network device may be ground truth CSI. The CSI in the target layer includes one or more of the following indication information: channel response of the target layer, compressed information and / or quantized information of the channel response of the target layer, eigenvector matrix of the target layer, or compressed information and / or quantized information of the eigenvector matrix of the target layer. Furthermore, the CSI in the target layer may include one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or target layer, etc. For example, there may be multiple target layers, and when the terminal reports the CSI in the target layer to the access network device, the layer corresponding to each piece of CSI information may be indicated separately. For example, the CSI information is an eigenvector matrix, and the CSI information in each layer includes at least one eigenvector matrix. When transmitting the CSI in the target layer to the access network device, the terminal may indicate the layer corresponding to each eigenvector matrix separately. If all the eigenvector matrices in the CSI information correspond to the same layer, the CSI information may indicate the corresponding layer, or may not perform the indication. Alternatively, if multiple eigenvector matrices in the CSI information belong to the same layer, the multiple eigenvector matrices may indicate the corresponding layer.

[0123] Similar to the procedure of FIG. 9, the CSI in the target layer included in the first CSI report is ground truth CSI, and the ground truth CSI and conventional CSI may be transmitted together. Furthermore, the first CSI report may include conventional CSI. For example, the first CSI report may further include one or more of the following indication information: RI, CQI, or PMI, where the number of layers of the PMI is determined based on the RI. Alternatively, the CSI in the target layer and the conventional CSI may be transmitted independently. For example, the terminal may further transmit a second CSI report to the access network device. The second CSI report may include one or more of the following indication information: RI, CQI, or PMI. Similarly, for conventional CSI, the number of layers of the PMI is determined based on the RI.

[0124] In one implementation, the terminal measures a downlink reference signal to obtain measurement results, and determines CSI in different layers based on the measurement results. The terminal transmits CSI in a target layer to the access network device using the method of the procedure in FIG. 11. It can be understood that the target layer may be any layer and is not limited to the nth layer, which has the highest quality in conventional CSI transmission. Because the access network device does not instruct the terminal to transmit CSI in a specific layer, the terminal actively transmits CSI information in the target layer to the access network device, and the terminal needs to inform the access network device of the target layer in which the CSI is transmitted. In other words, the terminal needs to transmit first information to the access network device in step 1100 to ensure that the access network device correctly understands the received CSI in the target layer. Optionally, upon receiving the CSI in the target layer, the access network device can use the CSI in the target layer for one or more of the following: model training, model inference, model testing, model validation, model monitoring, etc.

[0125] The first communication device is an access network device or a chip or circuit used in an access network device. The second communication device is a terminal or a chip or circuit used in a terminal. An example in which the first communication device is an access network device and the second communication device is a terminal will be used to provide a procedure including the following steps, as shown in Figure 12.

[0126] Step 1200: The access network device sends first information to the terminal, where the first information includes instruction information instructing the access network device to transmit CSI in a target layer.

[0127] For example, the first information may be instruction information instructing the access network device to transmit CSI in a target layer. For how the first information indicates the target layer, see the description of FIG. 11.

[0128] Step 1201: The access network device sends CSI in a target layer to the terminal.

[0129] In one implementation, the first information and the CSI in the target layer may be included in the same message. For example, the first information is included in the CSI in the target layer. Alternatively, the first information and the CSI in the target layer may be included in different messages. For example, the first information may carry an indication of an associated CSI in the target layer, or the CSI in the target layer may carry an indication of an associated first information. Alternatively, for example, the association relationship between the first information and the CSI in the target layer may be predefined, specified in a protocol, or default. This is not limited. Alternatively, during the validity period of the first information, the first information may indicate all layers of CSI information transmitted by the access network device, or may indicate a predefined layer of CSI information, etc.

[0130] For example, step 1202 may also be described as follows: the access network device sends a first CSI report to the terminal, where the first CSI report carries CSI in a target layer.

[0131] For the specific content and first information included in the CSI in the target layer, please refer to the above description of Figure 11. The main difference between the embodiment of Figure 12 and the embodiment of Figure 11 is that in the procedure of Figure 11, the terminal actively transmits CSI in the target layer to the access network device. In order to enable the access network device to correctly understand the received CSI in the target layer, the terminal further needs to transmit indication information in the target layer corresponding to the CSI to the access network device. In the procedure of Figure 12, the access network device actively transmits CSI to the terminal. In order to enable the terminal to correctly understand the received CSI in the target layer, the access network device further needs to transmit indication information in the target layer corresponding to the CSI to the terminal.

[0132] As in the previous description, the CSI in the target layer is ground truth CSI. The ground truth CSI and conventional CSI may be transmitted together. The first CSI report may further include one or more of the following indication information: RI, CQI, PMI, etc., where the number of layers of the PMI is determined based on the RI. Alternatively, the ground truth CSI and conventional CSI may be transmitted separately, and the access network device may further transmit one or more of the following indication information: RI, CQI, PMI, etc. to the terminal. The number of layers of the PMI is determined based on the RI.

[0133] Optionally, the terminal uses the received CSI in the target layer for one or more of model training, model inference, model testing, model validation, model monitoring, etc. For example, in one implementation, the models are separately located on the access network device side and the terminal side, and the models on the access network device side and the terminal side need to cooperate with each other. For example, as shown in FIG. 10 , the CSI generator is located on the terminal side, and the CSI reconstructor is located on the access network device side. In this case, the access network device can use CSI collected in all or some of the layers as training data to perform model training for the CSI reconstructor. After completing the training, the access network device can select CSI in the target layer from the CSI in all layers and send the CSI in the target layer to the terminal. The terminal performs model training for the CSI generator on the terminal side using the CSI in the target layer. In another implementation, the example of FIG. 10 is still used. When the terminal monitors model performance, the access network device can send the restored CSI in the target layer (i.e., V′ in FIG. 10 ) to the terminal, and the terminal compares the restored V′ with the original V to determine model performance, etc.

[0134] In this embodiment of the present application, it can be seen that:

[0135] 1. In each step, the differences between the different steps are highlighted. Please refer to each other for the explanation of the different steps.

[0136] 2. The order of steps in each procedure is not limited. For example, in the procedure of FIG. 9, the first information and the first CSI report may be transmitted together, or the first CSI report may be transmitted first, followed by the first information.

[0137] 3. The term "indication" will be described below. The indication may explicitly indicate corresponding information or may implicitly indicate corresponding information. This is not limited to this. For example, in the description of this application, the first CSI report includes indication information of CSI in the target layer. In this case, the CSI in the target layer may be explicitly indicated. For example, the first CSI report includes the CSI in the target layer. Alternatively, the CSI in the target layer may be implicitly indicated. For example, if there is a correspondence between the CSI in the target layer and other information, the first CSI report may carry other information that has a correspondence relationship with the CSI in the target layer to indicate the CSI in the target layer.

[0138] 4. In the description of this application, unless otherwise specified, CSI refers to downlink CSI. In the above description, downlink CSI transmission is also mainly used as an example for explanation. It can be understood that this is not intended to limit the present application. In addition to downlink CSI transmission, the solutions in the embodiments of this application may also be used in other scenarios, for example, for uplink CSI transmission.

[0139] It can be understood that to implement the functions of the foregoing embodiments, the terminal and the access network device include corresponding hardware structures and / or software modules for performing the functions. Those skilled in the art should easily recognize that the units and method steps in the examples described in this application with reference to the embodiments disclosed in this application can be implemented by hardware or a combination of hardware and computer software. Whether the functions are performed by hardware or by hardware driven by computer software depends on the specific application scenario and design constraints of the technical solutions.

[0140] 13 and 14 are diagrams of possible communication device structures according to embodiments of the present application. These communication devices may be configured to perform one or more corresponding functions in the above-mentioned method embodiments, such as functions performed by one or more of a terminal, an access network device, etc. Thus, the beneficial effects of the above-mentioned method embodiments can be implemented.

[0141] 13, the communications apparatus 1300 includes a processing unit 1310 and a transceiver unit 1320. These communications apparatus 1300 may be configured to perform one or more functions in the method embodiments described above, e.g., functions performed by one or more of a terminal, an access network device, etc.

[0142] In design, the communication device 1300 may be a terminal, a chip, a circuit, or the like used in a terminal. When the communication device 1300 is configured to perform the functions of the terminal in FIG. 9 , the transceiver unit 1320 is configured to receive first information from a second communication device, where the first information includes instruction information instructing the first communication device to transmit channel state information (CSI) in a target layer. Optionally, the processing unit 1310 is configured to generate a first CSI report. The transceiver unit 1320 is further configured to transmit the first CSI report to the second communication device, where the first CSI report includes the CSI in the target layer. Optionally, the second communication device may be an access network device, or a chip, a circuit, or the like used in the access network device.

[0143] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix, or compression information and / or quantization information of the channel response of the target layer.

[0144] In one implementation, the CSI in the target layer further includes one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0145] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0146] In one implementation, the transceiver unit 1320 is further configured to send a second CSI report to the second communication device, the second CSI report including one or more of the following indication information: RI, CQI, or PMI, and the number of layers of the PMI is determined based on the RI.

[0147] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a transmission period of CSI in the target layer, or a transmission pattern of CSI in the target layer.

[0148] In one implementation, the CSI at the target layer transmitted by the first communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0149] In one implementation, the first information is configuration information, and the configuration information is used to configure the first communication device to transmit CSI in a target layer.

[0150] 9 , the processing unit 1310 is configured to generate first information; the transceiver unit 1320 is configured to transmit the first information to the first communication device, the first information including instruction information instructing the first communication device to transmit channel state information (CSI) in the target layer; and receive a first CSI report from the first communication device, the first CSI report including the CSI in the target layer. Optionally, the first communication device may be a terminal, a chip or circuit used in the terminal, or the like.

[0151] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix, or compression information and / or quantization information of the channel response of the target layer.

[0152] In one implementation, the CSI in the target layer further includes one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0153] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0154] In one implementation, the transceiver unit 1320 is further configured to receive a second CSI report from the first communication device, the second CSI report including one or more of the following indication information: an RI, a CQI, or a PMI, and the number of layers of the PMI is determined based on the RI.

[0155] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, a transmission period of CSI in the target layer, or a transmission pattern of CSI in the target layer.

[0156] In one implementation, the CSI in the target layer received by the second communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0157] In one implementation, the first information is configuration information, and the configuration information is used to configure the first communication device to transmit CSI in a target layer.

[0158] In design, the communication device 1300 is a terminal, a chip or circuit used in a terminal, or the like. When the communication device is configured to perform the functions of the terminal in FIG. 11, the communication device is an access network device, or a chip or circuit used in an access network device. When the communication device is configured to perform the functions of the access network device in FIG. 12, optionally, the processing unit 1310 is configured to generate first information, and the transceiver unit 1320 is configured to send the first information to a second communication device, where the first information includes instruction information instructing the first communication device to send channel state information (CSI) in a target layer, and to send a first CSI report to the second communication device, where the first CSI report includes the CSI in the target layer. Optionally, the second communication device is an access network device, a chip or circuit used in an access network device, or the like. Alternatively, the second communication device is a terminal, or a chip or circuit used in a terminal, or the like.

[0159] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix of the target layer, or compression information and / or quantization information of the channel response of the target layer.

[0160] In one implementation, the CSI at the target layer may further include one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0161] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0162] In one implementation, the transceiver unit 1320 is further configured to send a second CSI report to the second communication device, the second CSI report including one or more of the following indication information: RI, CQI, or PMI, and the number of layers of the PMI is determined based on the RI.

[0163] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following for the target layer: eigenvalues ​​or singular values ​​of an eigenvector matrix of the target layer; a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer; a transmission period of CSI in the target layer; or a transmission pattern of CSI in the target layer.

[0164] In one implementation, the CSI at the target layer transmitted by the first communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0165] In one implementation, the first information is instruction information, and the instruction information instructs the first communication device to transmit CSI in a target layer.

[0166] In design, the communications device 1300 is an access network device, or a chip, circuit, etc. used in the access network device. When the communications device is configured to perform the functions of the access network device in FIG. 11, the communications device is a terminal, or a chip or circuit used in the terminal. When the communications device is configured to perform the functions of FIG. 12, the transceiver unit 1320 is configured to receive first information from a first communications device, the first information including instruction information instructing the first communications device to transmit channel state information (CSI) in a target layer, and receive a first CSI report from the first communications device, the first CSI report including the CSI in the target layer. Optionally, the processing unit 1310 is configured to process the first information, the first CSI report, etc.

[0167] In one implementation, the CSI for the target layer includes one or more of the following indication information: the channel response of the target layer, the eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix of the target layer, or compression information and / or quantization information of the channel response of the target layer.

[0168] In one implementation, the CSI at the target layer may further include one or more of the following indication information: eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer, or the target layer.

[0169] In one implementation, the first CSI report further includes one or more of the following indication information: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of the PMI is determined based on the RI.

[0170] In one implementation, the transceiver unit 1320 is further configured to receive a second CSI report from the first communication device, the second CSI report including one or more of the following indication information: an RI, a CQI, or a PMI, and the number of layers of the PMI is determined based on the RI.

[0171] In one implementation, the first information further includes instruction information instructing the first communication device to transmit one or more of the following for the target layer: eigenvalues ​​or singular values ​​of an eigenvector matrix of the target layer; a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer; a transmission period of CSI in the target layer; or a transmission pattern of CSI in the target layer.

[0172] In one implementation, the CSI in the target layer received by the second communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

[0173] In one implementation, the first information is instruction information, and the instruction information instructs the first communication device to transmit CSI in a target layer.

[0174] For a more detailed description of the processing unit 1310 and the transceiver unit 1320, please directly refer to the relevant descriptions of the aforementioned method embodiments, and the details will not be repeated here.

[0175] 14, the communication device 1400 includes a processor 1410 and an interface circuit 1420. The processor 1410 and the interface circuit 1420 are coupled to each other. It may be understood that the interface circuit 1420 may be a transceiver or an input / output interface. Optionally, the communication device 1400 may further include a memory 1430 configured to store instructions to be executed by the processor 1410, to store input data required for executing the instructions by the processor 1410, or to store data generated after the processor 1410 executes the instructions. Optionally, the processor 1410 may be configured to perform one or more functions in the embodiments of the aforementioned methods.

[0176] Specifically, the processor 1410 can execute instructions in the memory 1430 to enable the communications device 1400 to perform one or more functions in the above-described method embodiments, e.g., functions performed by one or more of a terminal, an access network device, etc.

[0177] When the communications device 1400 is configured to perform the method shown in FIG. 9, FIG. 11, or FIG. 12, the processor 1410 is configured to perform the functions of the processing unit 1310, and the interface circuit 1420 is configured to perform the functions of the transceiver unit 1320.

[0178] If the communication device is a terminal or a chip used in the terminal, the terminal or the chip in the terminal can implement the functions of the terminal in the above-mentioned method embodiments. The chip in the terminal receives information from another module (e.g., a radio frequency module or an antenna) in the terminal, and the information is transmitted to the terminal by the access network device. Alternatively, the chip in the terminal transmits information to another module (e.g., a radio frequency module or an antenna) of the terminal, and the information is transmitted to the access network device by the terminal.

[0179] If the aforementioned communication apparatus is an access network device or a module used in the access network device, the access network device or a module in the access network device can perform the functions of the access network device in the aforementioned method embodiments. The module in the access network device receives information from another module (e.g., a radio frequency module or an antenna) in the access network device, and the information is transmitted to the access network device by a terminal. Alternatively, the module in the access network device transmits information to another module (e.g., a radio frequency module or an antenna) in the access network device, and the information is transmitted to the terminal by the access network device. The module in the access network device in this specification may be a baseband chip of the access network device, or may be a DU or another module. The DU in this specification may be a DU in an open radio access network (O-RAN) architecture.

[0180] In addition to a device or a chip used in a device in wireless communication, such as the aforementioned access network device or terminal, it can be understood that a communication device may alternatively be a device in another communication system, such as a Wi-Fi communication system, that performs one or more functions of an access network device or terminal. This is not limited in the present application. For example, in a Wi-Fi communication system, a device performing the function of an access network device may be an access node, or a chip or circuit used in an access node. A device performing the function of a terminal may be a terminal, or a chip or circuit used in a terminal.

[0181] It may be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0182] The method steps in the embodiments of the present application may be implemented in a hardware manner or by a processor executing software instructions. The software instructions may include corresponding software modules. The software modules may be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, removable hard disk, CD-ROM, or any other form of storage medium well known in the art. For example, the storage medium is coupled to the processor such that the processor can read information from and write information to the storage medium. Of course, the storage medium may be a component of the processor. The processor and the storage medium may be located in an ASIC. In addition, the ASIC may be located in a base station or a terminal. Of course, the processor and the storage medium may alternatively be present as separate components in the data quality measurement device.

[0183] All or part of the above embodiments may be implemented using software, hardware, firmware, or any combination thereof. When software is used to implement the embodiments, all or part of the embodiments may be implemented in the form of a computer program product. This computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, all or part of the procedures or functions of the embodiments of the present application are performed. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user terminal, or another programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program or instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless method. The computer-readable storage medium may be any available medium or data storage device that can be accessed by a computer, such as a server or data center that integrates one or more available media. The available media may be magnetic media such as floppy disks, hard disks, or magnetic tapes, or optical media such as digital video disks, or semiconductor media such as solid-state drives. The computer-readable storage medium may be a volatile storage medium or a nonvolatile storage medium, or may include both types of storage media: volatile and nonvolatile storage media.

[0184] In the embodiments of the present application, unless otherwise specified or there is no logical contradiction, the terms and / or descriptions of different embodiments are consistent and can refer to each other, and the technical features of different embodiments can be combined based on their internal logical relationships to form new embodiments.

[0185] In this application, at least one means one or more, and more than one means two or more. "And / or" describes a relationship between related objects and indicates that three relationships may exist. For example, A and / or B can indicate three cases: when only A is present, when both A and B are present, and when only B is present, and A and B may be singular or plural. In the text description of this application, the character " / " usually represents an "or" relationship between related objects. In formulas of this application, the character " / " represents a "divide by" relationship between related objects. "Comprising at least one of A, B, and C" can represent including A, including B, including C, including A and B, including A and C, including B and C, and including A, B, and C.

[0186] It can be understood that various numbers in the embodiments of the present application are only used for distinction to facilitate description, and are not used to limit the scope of the embodiments of the present application. The sequence numbers of the above processes do not imply the execution order, and the execution order of the processes should be determined based on the functions and internal logic of the processes. [Explanation of symbols]

[0187] 1000 Communication Systems 100 Wireless Access Network 110a, 110b Access network devices 120a~120j terminals 200 Core Network 300 Internet 900. The terminal receives first information from the access network device, the first information including instruction information instructing the terminal to transmit CSI in the target layer. 901: The terminal sends a first CSI report to the access network device, where the first CSI report includes CSI in a target layer. 1100. The terminal sends first information to the access network device, where the first information includes instruction information instructing the terminal to send CSI in the target layer. 1101: The terminal sends a first CSI report to the access network device, where the first CSI report includes CSI in a target layer. 1200 The access network device sends first information to the terminal, the first information including instruction information instructing the access network device to transmit CSI in the target layer. 1201 The access network device transmits the CSI in the target layer to the terminal. 1300 Communication Equipment 1310 Processing Unit 1320 Transceiver Unit 1400 Communication Equipment 1410 processor 1420 Interface Circuit 1430 memory

Claims

1. A CSI transmission method applied to a first communication device, comprising: receiving first information from a second communication device, the first information including instruction information instructing the first communication device to transmit channel state information (CSI) in a target layer; transmitting a first CSI report to the second communication device, the first CSI report including the CSI in the target layer.

2. 2. The method of claim 1, wherein the CSI for the target layer includes one or more of the following indication information: a channel response of the target layer, an eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix, or compression information and / or quantization information of the channel response of the target layer.

3. The method of claim 1 or 2, wherein the CSI in the target layer further includes one or more of the following indications: eigenvalues ​​or singular values ​​of an eigenvector matrix of the target layer, or the target layer.

4. 4. The method according to claim 1, wherein the first CSI report further includes one or more of the following indications: a rank indicator (RI), a channel quality indicator (CQI), or a precoding matrix indication (PMI), and the number of layers of PMI is determined based on the RI.

5. The method comprises:

4. The method of claim 1, further comprising: transmitting a second CSI report to the second communication device, wherein the second CSI report includes one or more of the following indication information: RI, CQI, or PMI, and a number of layers of PMI is determined based on the RI.

6. 6. The method of claim 1, wherein the first information further includes instruction information instructing the first communication device to transmit one or more of the following: eigenvalues ​​or singular values ​​of an eigenvector matrix of the target layer; a threshold for the eigenvalues ​​or singular values ​​of the eigenvector matrix of the target layer; a transmission period of the CSI in the target layer; or a transmission pattern of the CSI in the target layer.

7. 7. The method of claim 1, wherein the CSI in the target layer transmitted by the first communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

8. 8. The method of claim 1, wherein the first information is configuration information used to configure the first communication device to transmit the CSI in the target layer.

9. A CSI reception method applied to a second communication device, comprising: transmitting first information to a first communication device, the first information including instruction information instructing the first communication device to transmit channel state information (CSI) in a target layer; receiving a first CSI report from the first communication device, the first CSI report including the CSI in the target layer.

10. 10. The method of claim 9, wherein the CSI for the target layer includes one or more of the following indication information: a channel response of the target layer, an eigenvector matrix of the target layer, compression information and / or quantization information of the eigenvector matrix, or compression information and / or quantization information of the channel response of the target layer.

11. 11. The method of claim 9 or 10, wherein the CSI in the target layer further includes one or more of the following indications: eigenvalues ​​or singular values ​​of an eigenvector matrix of the target layer, or the target layer.

12. 12. The method according to claim 9, wherein the first CSI report further includes one or more of the following indications: a rank indicator RI, a channel quality indicator CQI, or a precoding matrix indication PMI, and the number of layers of PMI is determined based on the RI.

13. The method comprises:

12. The method of claim 9, further comprising: receiving a second CSI report from the first communication device, the second CSI report including one or more of the following indication information: RI, CQI, or PMI, and a number of layers of PMI is determined based on the RI.

14. The first information includes the following:

14. The method of claim 9, further comprising instruction information instructing the first communication device to transmit one or more of: an eigenvalue or a singular value of an eigenvector matrix of the target layer; a threshold value for the eigenvalue or the singular value of the eigenvector matrix of the target layer; a transmission period of the CSI in the target layer; or a transmission pattern of the CSI in the target layer.

15. 15. The method of claim 9, wherein the CSI in the target layer received by the second communication device is used for one or more of the following: model training, model inference, model testing, model validation, or model monitoring.

16. 16. The method of claim 9, wherein the first information is configuration information, and the configuration information is used to configure the first communication device to transmit the CSI in the target layer.

17. A communication device comprising a unit configured to perform the method according to any one of claims 1 to 8.

18. 9. A communication device comprising a processor and an interface circuit, the interface circuit configured to receive signals from a communication device other than the communication device and to transmit the signals to the processor or to transmit signals from the processor to a communication device other than the communication device, the processor configured to perform the method of any one of claims 1 to 8 via logic circuits or by executing code instructions.

19. A communications device comprising a processor and a memory, the processor coupled to the memory, the processor configured to perform the method of any one of claims 1 to 8.

20. A communication device comprising a unit configured to perform the method according to any one of claims 9 to 16.

21. 17. A communication device comprising a processor and an interface circuit, the interface circuit configured to receive signals from a communication device other than the communication device and to transmit the signals to the processor or to transmit signals from the processor to a communication device other than the communication device, the processor configured to perform the method of any one of claims 9 to 16 via logic circuits or by executing code instructions.

22. A communications device comprising a processor and a memory, the processor coupled to the memory, the processor configured to perform the method of any one of claims 9 to 16.

23. 17. A computer-readable storage medium having stored thereon a computer program or instructions, the computer program or instructions being executed by a communication device to perform the method of any one of claims 1 to 8 or to perform the method of any one of claims 9 to 16.

24. A computer program product comprising a computer program or instructions, which, when executed, performs the method of any one of claims 1 to 8 or the method of any one of claims 9 to 16.

25. A chip including a processor, the processor coupled to a memory, the processor configured to execute computer programs or instructions stored in the memory to enable the chip to perform the method of any one of claims 1 to 8 or the method of any one of claims 9 to 16.

26. A communication system comprising a first communication device and a second communication device, the first communication device is configured to perform the method according to any one of claims 1 to 8, A communication system, wherein the second communication device is configured to perform the method of any one of claims 9 to 16.

Images