Communication method and communication apparatus

Abstract

The application provides a communication method and a communication device. The method comprises: receiving first information, the first information being used to indicate that a first reference signal is used to monitor a first performance, wherein the first performance is at least one of a performance of a first model and a performance of a second model, an output of the first model being associated with a second reference signal, and the output of the first model being used as an input of the second model; and transmitting the first reference signal, wherein the first reference signal and the output of the second model are used to monitor the first performance. The embodiments of the application can directly estimate the CSI information used for performance monitoring of the AI model by using the first reference signal indicated by the first information in a communication system with reciprocity, without the need for additional feedback of the CSI information by means of transmission resources, thereby reducing the overhead of monitoring the performance of the AI model corresponding to the communication device.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0002] User equipment (UE) typically estimates channel state information (CSI) by receiving reference signals transmitted by the base station. However, with the continuous development of communication technology, the dimensionality and complexity of channel information are constantly increasing, posing significant challenges to CSI transmission and processing. Terminal-side artificial intelligence (AI) models are used to extract key features from the CSI and remove redundant information, compressing the high-dimensional CSI into a low-dimensional feedback quantity, thereby reducing the time-frequency resource overhead required for CSI feedback. After receiving the CSI from the UE, the base station can input it into the network-side AI model to recover a CSI with some accuracy loss based on the compressed feedback quantity. Furthermore, in the monitoring process, the UE can feed back the original CSI with a low compression ratio and compare it with the CSI recovered by the AI ​​model as a performance monitoring result for the model, such as channel estimation accuracy. The performance monitoring results can be used for model switching, model rollback to non-AI solutions, or initiating model training.

[0003] To obtain the raw CSI, the network device sends a downlink reference signal to the UE. The UE receives this downlink reference signal and measures the downlink channel it traverses based on the received signal. The UE then uses this measurement to obtain the downlink channel matrix to generate the CSI and feeds it back to the network device. However, sending a high-precision / low-compression CSI consumes significant channel resources, making model monitoring based on terminal-side feedback costly. Summary of the Invention

[0004] This application provides a communication method and a communication device to reduce the performance overhead of the AI ​​model corresponding to the monitoring communication device.

[0005] Firstly, a communication method is provided, which can be executed by a first communication device. The first communication device may be a terminal device, or a chip or circuit for a terminal device, or a computing network element or computing entity serving a terminal device, or a network device, or a chip or circuit for a network device, or a computing network element or computing entity serving a network device; this application does not limit the specific application to this. The method includes:

[0006] Receive first information, the first information being used to instruct a first reference signal to be used for monitoring a first performance, wherein the first performance is at least one of the performance of a first model and the performance of a second model, the output of the first model being associated with a second reference signal, and the output of the first model being used as the input of the second model; send the first reference signal, wherein the first reference signal and the output of the second model are used for monitoring the first performance.

[0007] Specifically, the input of the first model is determined based on the second reference signal, and the output of the first model is the result of mathematical operations performed on the input of the first model. Therefore, the output of the first model is associated with the second reference signal.

[0008] The embodiments of this application enable the direct estimation of CSI information for performance monitoring of AI models using a first reference signal through a first information indication in a reciprocal communication system, without the need for additional transmission resources to feed back CSI information, thereby reducing the overhead of monitoring the performance of the AI ​​model corresponding to the communication device.

[0009] In some implementations of the first aspect, the method further includes: receiving second information, the second information being used to indicate the type of output of the second model, wherein the type of output of the second model is used to send a first reference signal.

[0010] In some implementations of the first aspect, the type of the output of the second model is used to determine the spatial weight information for transmitting the first reference signal, wherein the type of the output of the second model includes at least one of the original channel information and the channel feature vector.

[0011] In this implementation, the pattern of spatial weight information can be determined according to the type or format of the output of the second model, so that the first reference signal sent according to the spatial weight information and the output of the AI ​​model form a corresponding relationship, and the performance of the AI ​​model can be monitored according to the first reference signal, thereby further reducing the overhead of monitoring the performance of the AI ​​model.

[0012] In some implementations of the first aspect, the spatial weight information for transmitting the first reference signal is determined based on at least one of the spatial weight for receiving the second reference signal and the first channel information obtained based on the second reference signal.

[0013] In this implementation, the second reference signal is used to determine the feedback information and the spatial weight information, so that the first reference signal sent according to the spatial weight information and the output of the AI ​​model form a correspondence. This allows the performance of the AI ​​model to be monitored based on the first reference signal, thereby further reducing the overhead of monitoring the performance of the AI ​​model.

[0014] In some implementations of the first aspect, the method further includes: receiving third information, wherein the third information includes first performance, any one of the first performance includes at least one of channel recovery accuracy and channel prediction accuracy.

[0015] In this implementation, the performance of the AI ​​model can simultaneously include the recovery accuracy of the measured channel and the prediction accuracy of the unmeasured channel, enabling more comprehensive monitoring of model performance.

[0016] In some implementations of the first aspect, the method further includes: receiving fourth information, the fourth information being used to indicate the frequency measurement range of the first reference signal.

[0017] In some implementations of the first aspect, the fourth information includes the frequency measurement range of the first reference signal, the fourth information being used to indicate: the first reference signal is used to monitor the channel recovery accuracy of the first performance, or the first reference signal is used to monitor the channel prediction accuracy of the first performance.

[0018] In this implementation, setting a reasonable frequency measurement range according to monitoring requirements can reduce the measurement overhead of channel measurement.

[0019] In some implementations of the first aspect, the method further includes: sending a fifth message, the fifth message being used to request monitoring of the first performance.

[0020] In this implementation, the timing and scope of monitoring the performance of the AI ​​model can be flexibly determined according to monitoring needs, so as to reduce the impact of the monitoring process on normal communication.

[0021] In some implementations of the first aspect, the first reference signal is used to determine the second channel information, and the second channel information is used to determine the first performance.

[0022] In this implementation, a first reference signal is sent based on spatial weight information, and a second channel information is determined based on the first reference signal. This approach can fully utilize the characteristics of reciprocal communication systems to reduce the performance overhead of monitoring AI models.

[0023] In some implementations of the first aspect, the first model is applied to the encoder of the communication device, and the second model is applied to the decoder of the communication device.

[0024] Secondly, a communication method is provided, which can be executed by a second communication device. The second communication device can be a terminal device, or a chip or circuit for a terminal device, or a computing network element or computing entity serving a terminal device, or a network device, or a chip or circuit for a network device, or a computing network element or computing entity serving a network device; this application does not limit the specific application to this. The method includes:

[0025] Send first information, the first information being used to instruct a first reference signal to be used for monitoring a first performance, wherein the first performance is at least one of the performance of a first model and the performance of a second model, the output of the first model being associated with a second reference signal, and the output of the first model being used as the input of the second model; receive a first reference signal, wherein the first reference signal and the output of the second model are used for monitoring the first performance.

[0026] In some implementations of the second aspect, the method further includes: sending second information, the second information being used to indicate the type of output of the second model, wherein the type of output of the second model is used to send a first reference signal.

[0027] In some implementations of the second aspect, the type of the output of the second model is used to determine the spatial weight information for transmitting the first reference signal, wherein the type of the output of the second model includes at least one of the original channel information and the channel feature vector.

[0028] In some implementations of the second aspect, the spatial weight information for transmitting the first reference signal is determined based on at least one of the spatial weight for receiving the second reference signal and the first channel information obtained based on the second reference signal.

[0029] In some implementations of the second aspect, the method further includes: sending third information, wherein the third information includes first performance, any one of the first performance includes at least one of channel recovery accuracy and channel prediction accuracy.

[0030] In some implementations of the second aspect, the method further includes: sending fourth information, the fourth information being used to indicate the frequency measurement range of the first reference signal.

[0031] In some implementations of the second aspect, the fourth information includes the frequency measurement range of the first reference signal, which is used to indicate whether the first reference signal is used to monitor the channel recovery accuracy of the first performance or the channel prediction accuracy of the first performance.

[0032] In some implementations of the second aspect, the method further includes: receiving fifth information, the fifth information being used to request monitoring of the first performance.

[0033] In some implementations of the second aspect, the first reference signal is used to determine the second channel information, and the second channel information is used to determine the first performance.

[0034] In some implementations of the second aspect, the first model is applied to the encoder of the communication device, and the second model is applied to the decoder of the communication device.

[0035] Thirdly, a communication apparatus is provided for performing the method provided in the first or second aspect. Specifically, the apparatus may include units and / or modules for performing the method provided in any implementation of the first or second aspect, such as processing units and / or communication units.

[0036] In one implementation, the device is a communication device (such as a terminal device or a network device). When the device is a communication device, the communication unit can be a transceiver or an input / output interface; the processing unit can be at least one processing circuit, such as a processor or circuitry within a processor for processing functions. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0037] In another implementation, the device is a chip, chip system, or circuit used in a communication device. When the device is a chip, chip system, or circuit used in a terminal device, the communication unit can be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; the processing unit can be at least one processor, processing circuit, or logic circuit.

[0038] Fourthly, a communication device is provided, the device comprising: at least one processing circuit for performing the method provided in any implementation of the first or second aspect described above.

[0039] In one implementation, the device is a communication device (such as a terminal device or a network device).

[0040] In another implementation, the device is a chip, chip system, or circuit used in a communication device.

[0041] The communication device may include transceiver circuits. When the device is a communication equipment, the transceiver circuit may be a transceiver. When the device is a chip, chip system, or circuit used in a communication equipment, the transceiver circuit may be an interface circuit or an input / output circuit.

[0042] Optionally, the at least one processing circuit can be used to execute a computer program or instructions stored in the memory to perform the method provided in any implementation of the first or second aspect described above. The memory can be located inside or outside the communication device.

[0043] Optionally, the communication device also includes the memory.

[0044] Fifthly, this application provides a processing circuit (or processor) for performing the methods provided in the above aspects.

[0045] Unless otherwise specified, or if it does not contradict its actual function or internal logic in the relevant description, the operations of transmission and acquisition / reception involved in the processing circuit (or processor) can be understood as the output and input operations of the processing circuit, or as the transmission and reception operations performed by the radio frequency circuit and antenna. This application does not limit them in this regard.

[0046] In a sixth aspect, a computer-readable storage medium is provided that stores program code for execution by a device, the program code including a method for performing any implementation of the first or second aspect described above.

[0047] In a seventh aspect, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the method provided by any implementation of the first or second aspect described above.

[0048] Eighthly, a chip is provided, the chip including a processing circuit and a communication interface, the processing circuit reading instructions stored in a memory through the communication interface and executing the method provided by any implementation of the first or second aspect.

[0049] Optionally, as one implementation, the chip also includes a memory storing computer programs or instructions, and a processing circuit for executing the computer programs or instructions stored in the memory. When the computer programs or instructions are executed, the processing circuit is used to perform the method provided by any of the implementations of the first or second aspect described above.

[0050] A ninth aspect provides a communication system comprising the aforementioned communication apparatus, such as a communication apparatus that performs the method provided in any implementation of the first aspect, and a communication apparatus that performs the method provided in any implementation of the second aspect. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of a wireless communication system applicable to embodiments of this application.

[0052] Figure 2This is another schematic diagram of a wireless communication system applicable to embodiments of this application.

[0053] Figure 3 This is a schematic diagram of the layer relationships in a neural network.

[0054] Figure 4 This is a schematic diagram of a communication method provided in an embodiment of this application.

[0055] Figure 5 This is a schematic diagram of a communication method provided in an embodiment of this application.

[0056] Figure 6 This is a schematic diagram of a communication device provided in an embodiment of this application.

[0057] Figure 7 This is a schematic diagram of another communication device provided in an embodiment of this application.

[0058] Figure 8 This is a schematic diagram of a chip system provided in an embodiment of this application. Detailed Implementation

[0059] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0060] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0061] In a communication system, a device can send signals to or receive signals from another device. These signals can include information, signaling, or data. The term "device" can also be replaced by an entity, network entity, communication device, mobile device, network element, communication module, node, communication node, etc. This disclosure uses a device as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this disclosure can be replaced by a first device, and the network device can be replaced by a second device, both performing the corresponding communication methods described in this disclosure. Alternatively, the corresponding communication methods in this disclosure can be applied between network devices or between terminal devices, without limitation herein.

[0062] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus.

[0063] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0064] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0065] It should be understood that in certain scenarios, terminal devices can also be used as base stations. For example, a terminal device can act as a scheduling entity, providing sidelink signals between terminal devices in scenarios such as V2X, D2D, or P2P.

[0066] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system or a chip. This device can be installed in the terminal device. In this embodiment, the chip system can consist of chips, or it can include chips and other discrete devices. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solutions of this embodiment.

[0067] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), location node, RAN intelligent controller (RIC), etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0068] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0069] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0070] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0071] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, digital beamforming (BF), or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0072] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. DU is configured to implement one or more functions preceding layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to RU. For uplink transmission, de-RE mapping is used as the dividing line. DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-mapping, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping), while other functions following de-mapping (e.g., digital BF or fast Fourier transform (FFT) / CP removal) are moved to RU. It is understandable that the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0073] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0074] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0075] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself, or it can be an apparatus capable of supporting the network device in implementing those functions, such as a chip system or a chip. This apparatus can be installed within the network device. In this embodiment, the chip system can be composed of chips, or it can include chips and other discrete devices. This embodiment only uses a network device as an example to illustrate the apparatus for implementing the functions of a network device, and does not constitute a limitation on the solutions of this embodiment.

[0076] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, software functions running on dedicated hardware, or software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0077] In addition, AI nodes may be introduced into the network to support artificial intelligence (AI) technology.

[0078] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements, etc.

[0079] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0080] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0081] AI nodes can be AI network elements or AI modules.

[0082] First, a brief introduction to the communication system applicable to the embodiments of this application will be given.

[0083] See Figure 1 , Figure 1 This is a schematic diagram of a wireless communication system applicable to embodiments of this application.

[0084] like Figure 1 As shown, the wireless communication system includes a wireless access network 100. The wireless access network 100 can be a wireless access network in a future communication network, or a traditional (e.g., 5G, 4G, 3G, or 2G) wireless access network. One or more terminal devices (120a-120j, collectively referred to as 120) can be interconnected or connected to one or more network devices (110a, 110b, collectively referred to as 110) within the wireless access network 100. Network elements in the wireless communication system are connected via interfaces (e.g., NG, Xn) or over-the-air interfaces. Furthermore, each network element in the wireless communication system may be equipped with one or more AI modules. The AI ​​modules deployed in different network elements can be the same or different.

[0085] Figure 1 This is just an illustration; the wireless communication system may also include other devices, such as core network equipment, wireless relay equipment, and / or wireless backhaul equipment. Figure 1 It is not shown in the middle.

[0086] See Figure 2 , Figure 2 This is another schematic diagram of a wireless communication system applicable to embodiments of this application.

[0087] like Figure 2 As shown, the wireless communication system includes a RAN intelligent controller (RIC). As an example, the RIC can be used to implement AI-related functions. As an example, the RIC includes near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0088] The near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0089] The non-real-time RIC is also used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0090] The near real-time RIC and non-real-time RIC can also be configured as separate network elements. Optionally, the near real-time RIC and non-real-time RIC can also be part of other devices. For example, the near real-time RIC can be set in the RAN node (e.g., in CU, DU), while the non-real-time RIC can be set in operations, administration and maintenance (OAM), cloud servers, core network devices, or other network devices.

[0091] In practical applications, this wireless communication system can include multiple network devices (also known as access network devices) and multiple terminal devices simultaneously, without limitation. A network device can serve one or more terminal devices simultaneously. A terminal device can also access one or more network devices simultaneously. This application embodiment does not limit the number of terminal devices and network devices included in the wireless communication system.

[0092] To facilitate understanding of the embodiments of this application, the terminology involved in the embodiments of this application will be briefly explained below.

[0093] 1. Artificial Intelligence (AI): This refers to enabling machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. AI can be understood as the intelligence exhibited by machines created by humans. Generally, AI refers to the technology of using computer programs to represent human intelligence. The goals of AI include understanding intelligence by constructing computer programs that demonstrate symbolic reasoning or logical reasoning.

[0094] 2. Machine Learning: This is one implementation of artificial intelligence. Machine learning is a method that endows machines with the ability to perform functions that cannot be done directly through programming. In practical terms, machine learning is a method that uses data to train a model and then uses the model to make predictions. There are many machine learning methods, such as neural networks (NNs), decision trees, and support vector machines. Machine learning theory mainly involves designing and analyzing algorithms that allow computers to learn automatically. Machine learning algorithms are a class of algorithms that automatically analyze data to obtain patterns and use these patterns to predict unknown data.

[0095] 3. Neural Networks: A specific manifestation of machine learning methods. A neural network is a mathematical model that mimics the behavioral characteristics of animal neural networks to process information. The idea behind neural networks originates from the neuronal structure of the brain. Each neuron can perform a weighted summation operation on its input values, and the result of the weighted summation operation is passed through an activation function to generate the output.

[0096] Neural networks typically consist of multiple layers, each layer containing one or more logical decision units, which are called neurons. Increasing the depth and / or width of a neural network can enhance its expressive power, providing more robust information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can be understood as the number of layers it comprises, and the number of neurons in each layer can be called the width of that layer.

[0097] See Figure 3 , Figure 3 This is a schematic diagram of the layer relationships in a neural network.

[0098] One possible implementation involves a neural network comprising an input layer and an output layer. The input layer processes the received input through neurons and then passes the results to the output layer, which obtains the output of the neural network.

[0099] Another possible implementation is a neural network consisting of an input layer, hidden layers, and an output layer, such as... Figure 3As shown, the input layer of a neural network processes the received input through neurons and then passes the results to the hidden layers. The hidden layers then pass their calculations to the output layer or adjacent hidden layers, and finally, the output layer obtains the output of the neural network. A neural network can include one or more layers of sequentially connected hidden layers, without limitation.

[0100] During the training of a neural network, a loss function can be defined. The loss function measures the difference between the model's predicted value and the true value. In the training process, the loss function describes the gap or difference between the neural network's output value and the ideal target value. The training process involves adjusting the neural network parameters so that the loss function value is less than a threshold value or meets the target requirement. The neural network parameters can include at least one of the following: the number of layers in the neural network, its width, the weights of the neurons, and the parameters in the activation functions of the neurons.

[0101] 4. Deep neural network: A neural network with multiple hidden layers.

[0102] 5. Deep learning: Machine learning that utilizes deep neural networks.

[0103] 6. AI Model: An AI model is an algorithm or computer program that enables AI functionality. It represents the mapping relationship between the model's input and output; in other words, it's a function model that maps a certain dimension of input to a certain dimension of output. The parameters of this function model can be obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be viewed as an AI model. a and b are the parameters of this AI model, and a and b can be obtained through machine learning training. For example, the AI ​​model mentioned in the following embodiments of this application is not limited to neural networks, linear regression models, decision tree models, support vector machines (SVM), Bayesian networks, Q-learning models, or other machine learning (ML) models.

[0104] The implementation of an AI model can be a hardware circuit, software, or a combination of both; there are no restrictions. Non-restrictive examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application program, or software application, etc.

[0105] Furthermore, the encoder can deploy multiple AI models, allowing it to encode information based on these models, such as compressing channel information. Similarly, the decoder can deploy multiple AI models, allowing it to decode information based on these models, such as recovering channel information from compressed data. For simplicity, the AI ​​model deployed by the encoder will be referred to as the encoder's AI model, and the AI ​​model deployed by the decoder will be referred to as the decoder's AI model.

[0106] Furthermore, in this embodiment, the encoder and decoder can be communication devices (such as terminal devices or network devices) or can be configured within a communication device. This embodiment primarily uses the encoder and decoder as communication devices as an example for illustration. The encoder can be a terminal device and the decoder a network device; or the encoder can be one terminal device and the decoder another terminal device; or the encoder can be one network device and the decoder another network device; or the encoder can be a network device and the decoder a terminal device—no limitation is imposed on this.

[0107] 7. Model Application: Use the trained model to solve practical problems.

[0108] 8. Reference Signal: Also known as pilot, reference sequence, reference signal, etc. For consistency, it will be described as reference signal below. A reference signal is a physical signal that transmits a sequence to achieve a specific function. Specifically, a reference signal is a physical signal generated by mapping a specific sequence onto corresponding resources according to a pre-defined resource mapping method.

[0109] In this application, the reference signal (RS) involved, as an example, can be any of the following: channel state information reference signal (CSI-RS), sounding reference signal (SRS), demodulation reference signal (DMRS), phase track reference signal (PT-RS), cell reference signal (CRS), etc.

[0110] It should be understood that the reference signals listed above are merely examples and should not be construed as limiting this application. This application does not preclude the possibility of defining other reference signals in future agreements to achieve the same or similar functions.

[0111] 9. Channel information: Information that reflects the characteristics and quality of the channel.

[0112] As an example, channel information includes at least one of the following: channel state information (CSI), channel time-varying information, or channel frequency offset information. The following explanation primarily uses CSI as an example of channel information; it is understood that any information reflecting channel characteristics and channel quality is applicable to the embodiments of this application.

[0113] In widely used FDD-based communication systems, uplink and downlink channels lack reciprocity. Therefore, the network side obtains the downlink CSI through uplink feedback from the terminal device. Specifically, the network side sends a downlink reference signal to the terminal device, which receives the signal. Since the terminal device knows the transmission information of the downlink reference signal, it can estimate (or measure) the downlink channel traversed by the received signal. Based on this measurement, the terminal device can obtain the downlink channel matrix, generate the CSI, and feed the CSI back to the network side.

[0114] As an example, CSI includes at least one of the following: channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), layer indicator (LI), reference signal receiving power (RSRP), or signal to interference plus noise ratio (SINR). The signal to interference plus noise ratio can also be called the signal-to-interference-plus-noise ratio. RI can be used to indicate the number of downlink transmission layers suggested by the terminal equipment; CQI can be used to indicate the modulation and coding schemes that the terminal equipment determines the current channel conditions can support; and PMI can be used to indicate the precoding suggested by the terminal equipment. The number of precoding layers indicated by PMI corresponds to RI. It should be understood that the RI, CQI, and PMI indicated in the above CSI report are only suggested values ​​for the terminal equipment. The network equipment may perform downlink transmission according to some or all of the information indicated in the CSI report. Alternatively, the network equipment may also perform downlink transmission without following the information indicated in the CSI report.

[0115] User equipment (UE) typically estimates channel state information (CSI) by receiving reference signals transmitted by the base station. However, with the continuous development of communication technology, the dimensionality and complexity of channel information are constantly increasing, posing significant challenges to CSI transmission and processing. Terminal-side artificial intelligence (AI) models are used to extract key features from the CSI and remove redundant information, compressing the high-dimensional CSI into a low-dimensional feedback quantity, thereby reducing the time-frequency resource overhead required for CSI feedback. After receiving the CSI from the UE, the base station can input it into the network-side AI model to recover a CSI with some accuracy loss based on the compressed feedback quantity. Furthermore, in the monitoring process, the UE can feed back the original CSI with a low compression ratio and compare it with the CSI recovered by the AI ​​model as a performance monitoring result for the model, such as channel estimation accuracy. The performance monitoring results can be used for model switching, model rollback to non-AI solutions, or initiating model training.

[0116] To obtain the raw CSI, the network device sends a downlink reference signal to the UE. The UE receives this downlink reference signal and measures the downlink channel it traverses based on the received signal. The UE then uses this measurement to obtain the downlink channel matrix to generate the CSI and feeds it back to the network device. However, sending a high-precision / low-compression CSI consumes significant channel resources, making model monitoring based on terminal-side feedback costly.

[0117] In view of this, this application proposes a method comprising: receiving first information, the first information being used to instruct a first reference signal to monitor a first performance, wherein the first performance is at least one of the performance of a first model and the performance of a second model, the output of the first model being associated with a second reference signal, and the output of the first model being used as the input of the second model; and transmitting the first reference signal, wherein the first reference signal and the output of the second model are used to monitor the first performance.

[0118] The embodiments of this application enable the direct estimation of CSI information for performance monitoring of AI models using a first reference signal through a first information indication in a reciprocal communication system, without the need for additional transmission resources to feed back CSI information, thereby reducing the overhead of monitoring the performance of the AI ​​model corresponding to the communication device.

[0119] It should be noted that, in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information for the purpose of instructing A, it can be understood that the instruction information carries A, directly instructs A, or indirectly instructs A.

[0120] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is a relationship between the other information and the information to be instructed. It can also indicate only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Furthermore, the information to be instructed can be sent as a whole or divided into multiple sub-information pieces, and the sending period and / or timing of these sub-information pieces can be the same or different.

[0121] It should be understood that in this application, information C is used to determine information D, including both situations where information D is determined solely based on information C and situations where it is determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, where information D is determined based on information E, and information E is determined based on information C.

[0122] Furthermore, in the embodiments of this application, "network element A sends information A to network element B" can be understood as network element B being the destination of information A or an intermediate network element in the transmission path between the destination and network element B, which may include sending information directly or indirectly to network element B. "Network element B receives information A from network element A" can be understood as network element A being the source of information A or an intermediate network element in the transmission path between the source and network element A, which may include receiving information directly or indirectly from network element A. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be understood in a similar way and will not be elaborated further here.

[0123] The communication method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. The embodiments provided in this application can be applied to the above-described embodiments. Figure 1 or Figure 2 The communication system shown is not limited.

[0124] See Figure 4 , Figure 4 This is a schematic diagram of a communication method 400 provided in an embodiment of this application. Figure 4 The method 400 shown can be performed by a first communication device (taking a terminal device as an example) and a second communication device (taking a network device as an example) in a reciprocal communication system (e.g., a time division multiplexing (TDD) system), and specifically includes the following steps.

[0125] S410, the terminal device receives first information from the network device, the first information being used to indicate that a first reference signal is used to monitor the performance of a first model and / or a second model, wherein the output of the first model is associated with a second reference signal, and the output of the first model is used as the input of the second model.

[0126] In some embodiments, the encoder and decoder of the communication system are respectively located in different communication devices. For example, if the encoder is located on the terminal side, the AI ​​model corresponding to the encoder of the terminal device is referred to as the encoder model (i.e., the first model), and if the decoder is located on the network side, the AI ​​model corresponding to the decoder of the network device is referred to as the decoder model (i.e., the second model). The terminal device can input the first channel information estimated based on the second reference signal into the encoder model to obtain channel compression information. The network device inputs the channel compression information into the decoder model to recover the channel information. The encoder model and decoder model are paired. The input of the first model is determined based on the second reference signal, and the output of the first model is the result of mathematical operations performed on the input of the first model. Therefore, the output of the first model is associated with the second reference signal.

[0127] It should also be understood that the encoder of a terminal device may correspond to multiple encoder models. For ease of explanation, this application uses a specific encoder model corresponding to the terminal device as an example to illustrate the function of the first model. Similarly, it uses a specific decoder model corresponding to the network device as an example to illustrate the function of the second model. These embodiments should not be construed as limiting the scope of protection of this application.

[0128] See Figure 5 , Figure 5 This is a flowchart illustrating a more specific embodiment of the communication method 400 provided in this application. In some embodiments, Figure 5 The process of a terminal device receiving a second reference signal and sending feedback information is illustrated.

[0129] S441, the terminal device receives a second reference signal from the network device, the second reference signal being used to determine the first channel information.

[0130] In one possible implementation, the second reference signal can be CSI-RS, a downlink measurement signal used for downlink channel measurement, etc. The terminal device performs downlink channel measurement based on the second reference signal to obtain channel matrix #1, and then obtains the first channel information (which can also be represented as channel information #1) based on channel matrix #1. The first channel information can be a low-rank approximation matrix, eigenvector matrix, or precoding matrix obtained from channel matrix #1. Low-rank approximation and eigenspace projection are methods that retain a portion of the information in the original channel matrix. The first channel information can be used as input to the first model. Other methods can be used to determine the first channel information from channel matrix #1, and this application does not limit this. Channel matrix #1 includes various information such as the channel gain and phase relationship between the transmit and receive antennas in the MIMO system, and the channel response between different transmit antennas and different receive antennas. The matrix including this type of information is called the original channel information.

[0131] In one possible implementation, singular value decomposition (SVD) is performed on a matrix of type original channel information, with the specific formula and explanation as follows.

[0132] H=UΔV H U=HVΔ -1 H eff =HV=UΔ

[0133] In this system, the singular vector matrix U represents multiple eigenvectors corresponding to the singular values ​​of the channel. These eigenvectors (i.e., the columns of matrix U) represent the main transmission directions or modes in the channel. In a MIMO system, the eigenvectors U reflect the main directions of signal propagation in space. Each eigenvector corresponds to a specific signal transmission mode, and these modes are orthogonal to each other, meaning they do not interfere with each other. The eigenvector matrix consists of one or more columns from U.

[0134] The singular value matrix Δ is a diagonal matrix composed of non-negative real numbers. The elements on the diagonal are singular values, representing the contribution of the corresponding singular vector to the matrix H. The singular values ​​are usually arranged in descending order, reflecting the energy distribution of different transmission modes in the channel. That is to say, the singular value matrix does not directly include information such as channel gain and phase relationship.

[0135] Equivalent channel matrix H eff It reflects the channel characteristics observed by the receiving equipment after the transmitting equipment has applied a specific transmission strategy.

[0136] The transformation matrix V enables the transformation between U and H. Specifically, performing an SVD operation on H yields U and V, and conversely, multiplying H by the V matrix on the right transforms H into U. Therefore, when transmitting a reference signal, the terminal device first weights the reference signal using V before transmitting it, which is equivalent to transmitting it through the equivalent channel H. eff The network device transmits a reference signal, and the channel estimated based on the reference signal is also the equivalent channel H. eff .

[0137] S442, the terminal device obtains channel compression information based on the first channel information.

[0138] S443, the network device receives the channel compression information sent by the terminal device and recovers the third channel information based on the channel compression information. The third channel information is used to determine the performance of the first model and / or the performance of the second model.

[0139] In some embodiments, the second model corresponding to the network device can recover the third channel information (which can also be represented by channel information #2) based on the channel compression information.

[0140] In one possible implementation, channel information #2 can approximate the information of channel matrix #1. If channel information #2 approximates channel matrix #1, then the type of the output of the second model, i.e., the type of channel information #2, is the original channel information; if channel information #2 approximates the eigenvector matrix of channel matrix #1, then the type of the output of the second model, i.e., the type of channel information #2, is the eigenvector matrix.

[0141] It should be understood that information #A approximates information #B, meaning that information #A and information #B have the same dimensions, each element in information #A has the same physical meaning as the corresponding element in information #B, and the difference between information #A and information #B is small. The difference can be calculated or represented by indicators such as correlation, mean squared error (MSE), and normalized mean squared error (NMSE).

[0142] In one possible implementation, channel information #2 may include an approximate representation of the information of channel matrix #1 (denoted as information #x) and an approximate representation of the information of channel matrix #2 (denoted as information #y), wherein channel matrix #2 and channel matrix #1 correspond to channel information in different frequency domains, spatial domains, or time domains. The type of channel information #2 includes the type of information #x and the type of information #y. If information #x approximates channel matrix #1, then the type of information #x is the original channel information; if information #x approximates the eigenvector matrix of channel matrix #1, then the type of information #x is the eigenvector matrix. It should be understood that information #x in the foregoing embodiments can also be information #y, and the types of information #x and information #y can be the same or different; this application does not limit this.

[0143] It should be understood that the terms "type" and "function" or "role" have similar meanings, indicating a distinction in the output of the second model, and this application does not limit this.

[0144] In some embodiments, the terminal device receives second information from the network device, the second information indicating the type of the output of the second model, wherein the type of the output of the second model is used to transmit the first reference signal. When the network device does not transmit the second information, the type of the output of the second model may be a default value, such as a channel feature vector or raw channel information.

[0145] In one possible implementation, the type of the output of the second model is used to determine the spatial weight information for transmitting the first reference signal, wherein the type of the output of the second model includes the original channel information and / or the channel feature vector.

[0146] Spatial weights are complex numerical vectors or matrices used in wireless communication systems, particularly in multiple-antenna-multiplexing (MIMO) systems, to process signals in the spatial domain. These weights optimize the spatial distribution of signals by adjusting the phase and amplitude of the transmitted or received signals from each antenna in the antenna array, thereby achieving various functions such as beamforming, spatial multiplexing, spatial diversity, and interference suppression. Spatial weights can not only focus signals in specific directions, enhancing the signal strength received by the target user, but also enable the simultaneous transmission of multiple data streams within the same frequency band, improving spectral efficiency, or enhance reliability by transmitting different copies of the same signal. Furthermore, spatial weights can be used to design spatial filters to reduce interference from other users and improve the overall system performance.

[0147] In this implementation, the second reference signal is used to determine the feedback information and the spatial weight information, so that the first reference signal sent according to the spatial weight information and the output of the AI ​​model form a correspondence. This allows the performance of the AI ​​model to be monitored based on the first reference signal, thereby further reducing the overhead of monitoring the performance of the AI ​​model.

[0148] In some embodiments, the spatial weight information for transmitting the first reference signal is determined based on the spatial weight for receiving the second reference signal and / or the first channel information obtained based on the second reference signal.

[0149] In one possible implementation, the output of the second model is of the type of raw channel information, that is, all information in the output information of the second model is of the type of raw channel information. Then the spatial weights used to transmit the first reference signal can be determined according to the spatial weights used when receiving the second reference signal.

[0150] It should be understood that determining the spatial weight information based on the spatial weight used when receiving the second reference signal may mean that the spatial weight used when receiving the second reference signal is the same as the spatial weight used to transmit the first reference signal, or that the spatial weight used when receiving the second reference signal is preprocessed to obtain the spatial weight used to transmit the first reference signal. This application does not limit this.

[0151] In one possible implementation, when the output of the second model is of the type of channel feature vector, that is, when all information in the output information of the second model is of the type of channel feature vector, the spatial weight information can be determined based on the first channel information.

[0152] In one possible implementation, the spatial weights used to transmit the first reference signal are: the transformation matrix used by the terminal device to convert the original channel information into a channel eigenvector based on the channel matrix #1. If the channel matrix #1 is denoted as H1 and the eigenvector matrix is ​​denoted as U1, then:

[0153]

[0154] V1 in the formula can be used as the spatial weight for transmitting the first reference signal. Alternatively, the matrix obtained by preprocessing V1 can be used as the spatial weight for transmitting the first reference signal.

[0155] In one possible implementation, the output of the second model (i.e., the third channel information) includes an approximate representation of the information of channel matrix #1 (denoted as information #x) and an approximate representation of the information of channel matrix #2 (denoted as information #y). When the type of information #x is a channel feature vector and the type of information #y is raw channel information, the spatial weight information is determined based on the spatial weights used to receive the second reference signal and the first channel information. Specifically, the third channel information includes information #x and information #y, the second reference signal includes reference signal #x and reference signal #y, the spatial weights of the reference signal #x used to estimate the channel information corresponding to information #x are determined based on the first channel information, and the spatial weights of the reference signal #y used to estimate the channel information corresponding to information #y are determined based on the spatial weights of the received second reference signal. Here, reference signal #x and information #x correspond to the same measurement range, and reference signal #y and information #y correspond to the same measurement range.

[0156] It should be understood that the measurement range in this embodiment may refer to the frequency domain range, port range, beam domain range, etc., covered by the reference signal, and this application does not limit this. For example, the frequency domain range may be divided into multiple frequency domain sub-bands. Range #1 may be frequency domain sub-band #1 and frequency domain sub-band #2 out of 5 frequency domain sub-bands, and range #2 may be frequency domain sub-band #3 to frequency domain sub-band #5 out of the 5 frequency domain sub-bands; the port range may include multiple antenna ports. Range #1 may be port #1 out of 4 ports, and range #2 may be port #2 to port #4 out of the 4 ports.

[0157] In one possible implementation, the channel information corresponding to information #x can be a part of the second channel information in a later embodiment (denoted as second channel information #x). The uses of information #x and second channel information #x are also detailed in a later embodiment; for example, the difference between information #x and second channel information #x can be determined. Similarly, the channel information corresponding to information #y can be a part of the second channel information in a later embodiment (denoted as second channel information #y).

[0158] In this implementation, the pattern of spatial weight information can be determined according to the type or format of the output of the second model, so that the first reference signal sent according to the spatial weight information and the output of the AI ​​model form a corresponding relationship, and the performance of the AI ​​model can be monitored according to the first reference signal, thereby further reducing the overhead of monitoring the performance of the AI ​​model.

[0159] The above embodiments can be described in two scenarios: scenario #1 and scenario #2. Scenario #1 refers to a situation where the channel compression information has already been transmitted, and the methods described in S441 to S443 are executed before S410, meaning the reception time of the channel compression information is earlier than the transmission time of the first information. Scenario #2 refers to a situation where the channel compression information has not yet been transmitted, and the methods described in S441 to S443 are executed between S410 and S420, meaning the reception time of the first information is earlier than the transmission time of the channel compression information. It should be understood that combinations of multiple embodiments formed according to different orders of transmission or reception of information are all within the scope of protection of this application.

[0160] S420, the terminal device sends a first reference signal to the network device, wherein the first reference signal and the output of the second model are used to monitor the performance of the first model and / or the performance of the second model.

[0161] In some embodiments, spatial weight information is obtained based on the type of the output of the second model, the first channel information, and / or the second reference signal, and the first reference signal is transmitted based on the spatial weight information. The specific method is described above and will not be repeated here.

[0162] In some embodiments, a first reference signal is used to determine second channel information, which in turn is used to determine the performance of a first model and / or a second model. Specifically, in conjunction with the foregoing embodiments, embodiments of this application can determine the performance of a first model and / or a second model based on the second channel information and a third channel information.

[0163] In some embodiments, a difference between second channel information and third channel information is determined, and the difference is used as at least one of the performance of a first model, the performance of a second model, and the joint performance of the first model and the second model.

[0164] In one possible implementation, the network device receives a first reference signal sent by the terminal device, and then uses a channel estimation algorithm to estimate second channel information (which can also be represented as channel information #3) based on the received first reference signal. The output of the second model is denoted as channel information #2. The difference #1 between channel information #2 and channel information #3 (e.g., correlation, MSE, NMSE) is calculated, and the performance of the second model is determined based on this difference; or the joint performance of the first and second models is determined based on this difference, or it is used as the performance of the first model.

[0165] In one possible implementation, channel information #3 is input into the proxy first model on the network device side to obtain compressed information #1. The performance of the first model is determined by calculating the difference #2 (such as MSE, NMSE, etc.) between compressed information #1 and compressed channel information fed back by the terminal device. The proxy first model is matched with a second model. Taking the output type of the second model as raw information as an example, the raw channel information is input into the proxy encoder, and then the output of the proxy encoder is input into the second model, which can recover or approximately recover the raw channel information. Alternatively, taking the output of the second model as a channel feature vector as an example, the channel feature vector is input into the proxy encoder, and then the output of the proxy encoder is input into the second model, which can recover or approximately recover the channel feature vector.

[0166] In this implementation, a first reference signal is sent based on spatial weight information, and a second channel information is determined based on the first reference signal. This approach can fully utilize the characteristics of reciprocal communication systems to reduce the performance overhead of monitoring AI models.

[0167] In some embodiments, a first measurement range of the first reference signal and a second measurement range of the second reference signal are used to determine channel recovery accuracy and channel prediction accuracy, wherein the performance of the first model and / or the performance of the second model includes at least one of channel recovery accuracy and channel prediction accuracy. Specifically, the first measurement range includes range #1 and range #2, the second channel information determined according to the first reference signal includes second channel information #1 corresponding to range #1 and second channel information #2 corresponding to range #2, and the output of the corresponding second model includes an approximate representation of the second channel information #1 (denoted as information #a) and an approximate representation of the second channel information #2 (denoted as information #b). Then, performance #a can be determined according to the second channel information #1 and information #a, and performance #b can be determined according to the second channel information #2 and information #b. If the measurement range of the second reference signal includes range #1, performance #a is used to determine the performance of channel recovery accuracy; if the measurement range of the second reference signal does not include range #1, performance #a is used to determine the performance of channel prediction accuracy. It should be understood that performance #a in the foregoing embodiments can also be performance #b, and this application does not limit it in this regard.

[0168] In one possible implementation, the performance includes channel recovery accuracy. For example, if the measurement range of the second reference signal includes range #1 and range #2, then performance #a and performance #b are used to determine the channel recovery accuracy, for example, they can be the average, summation, or weighted summation of performance #a and performance #b, or the channel recovery accuracy includes performance #a and performance #b.

[0169] In one possible implementation, the performance includes channel prediction accuracy. If the measurement range of the second reference signal does not include ranges #1 and #2, then performance #a and performance #b are used to determine the channel prediction accuracy, for example, they can be the average, sum, or weighted sum of performance #a and performance #b, or the channel prediction accuracy includes performance #a and performance #b.

[0170] In one possible implementation, the performance includes channel recovery accuracy and channel prediction accuracy. If the measurement range of the second reference signal includes range #1 but excludes range #2, then performance #a is used to determine the channel recovery accuracy, and performance #b is used to determine the channel prediction accuracy.

[0171] In one possible implementation, the first reference signal can be the SRS, which is used for uplink channel detection and quality estimation to help network devices understand uplink channel characteristics in order to perform uplink scheduling and resource allocation.

[0172] The second channel information is typically the channel matrix of the uplink channel, i.e., the true value of the uplink channel measurement. In a reciprocal system, the true value of the uplink channel measurement can be used as the true value of the downlink channel measurement. Therefore, in the embodiments of this application, the second channel information can be used as the performance monitoring of the compressed feedback model of the downlink channel information.

[0173] S430, the terminal device receives third information from the network device, wherein the third information includes the performance of the first model and / or the performance of the second model, the performance including at least one of channel recovery accuracy and channel prediction accuracy.

[0174] In one possible implementation, the performance includes channel recovery accuracy. For example, if performance #a and performance #b are used to determine channel recovery accuracy, then the third information includes channel recovery accuracy.

[0175] In one possible implementation, the performance includes channel prediction accuracy. For example, if the channel prediction accuracy includes performance #a and performance #b, then the third information includes the channel prediction accuracy.

[0176] In one possible implementation, the performance includes channel recovery accuracy and channel prediction accuracy. For example, if performance #a is used to determine channel recovery accuracy and performance #b is used to determine channel prediction accuracy, then the third information includes channel recovery accuracy and channel prediction accuracy.

[0177] In this implementation, the performance of the AI ​​model can simultaneously include the recovery accuracy of the measured channel and the prediction accuracy of the unmeasured channel, enabling more comprehensive monitoring of model performance.

[0178] In some embodiments, the terminal device receives fourth information from the network device, the fourth information indicating the frequency measurement range of the first reference signal. For example, the fourth information may directly include the frequency measurement range of the first reference signal. Specifically, the network device may determine the frequency range that needs to be monitored, which may be the frequency range of the entire channel or the frequency range of a sub-band of the entire channel specified by the network device.

[0179] In one possible implementation, the fourth information can also be used to implicitly indicate the frequency range of the first reference signal. For example, the fourth information indicates that the first reference signal is used to monitor the channel recovery accuracy of the first performance, or that the first reference signal is used to monitor the channel prediction accuracy of the first performance. For instance, when the first reference signal is used to monitor the channel recovery accuracy of the first performance according to the foregoing embodiments, the frequency range of the first reference signal can be the same as the frequency range of the second reference signal; when the first reference signal is used to monitor the channel prediction accuracy, the frequency range of the first reference signal can be different from the frequency range of the second reference signal.

[0180] In this implementation, setting a reasonable frequency measurement range according to monitoring requirements can reduce the measurement overhead of channel measurement.

[0181] In some embodiments, the terminal device sends a fifth message to the network device, wherein the fifth message is used to request monitoring of the performance of the first model and / or the performance of the second model.

[0182] In this implementation, the timing and scope of monitoring the performance of the AI ​​model can be flexibly determined according to monitoring needs, so as to reduce the impact of the monitoring process on normal communication.

[0183] It is understood that some optional features in the various embodiments of this application may not depend on other features in some scenarios, or may be combined with other features in some scenarios, without limitation.

[0184] It is also understood that in the above embodiments, terminal devices and network devices are mainly used as examples for illustrative purposes, and are not intended to be limiting. For example, the terminal device can also be replaced by components of the terminal device (such as chips or circuits), and the network device can also be replaced by components of the network device (such as chips or circuits).

[0185] It is also understood that the solutions in the various embodiments of this application can be used in reasonable combinations, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained to each other in the various embodiments, without limitation.

[0186] The above, combined with Figure 4 and Figure 5 The methods provided in the embodiments of this application are described in detail below. Figures 6 to 8 The apparatus provided in the embodiments of this application is described in detail. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, it will not be repeated here.

[0187] See Figure 6 , Figure 6 This is a schematic diagram of a communication device 1500 provided in an embodiment of this application. The device 1500 includes a transceiver unit 1510 and a processing unit 1520. The transceiver unit 1510 can be used to implement corresponding communication functions. The transceiver unit 1510 can also be referred to as a communication interface or a communication unit.

[0188] Optionally, the device 1500 may further include a storage unit for storing instructions and / or data, and the processing unit 1520 may read the instructions and / or data from the storage unit to enable the device to implement the aforementioned method embodiments.

[0189] As a design, the device 1500 can be the first communication device in the foregoing embodiments, and the device 1500 can implement the steps or processes corresponding to those performed by the communication device in the above method embodiments. The transceiver unit 1510 can be used to perform operations related to the transmission and reception of the communication device in the above method embodiments (such as sending and / or receiving data or messages), and the processing unit 1520 can be used to perform processing-related operations of the communication device in the above method embodiments, or operations other than transmission and reception (such as operations other than sending and / or receiving data or messages).

[0190] As an alternative design, the device 1500 can be a second communication device in the foregoing embodiments, which can implement the steps or processes performed by the communication device in the above method embodiments. Specifically, the transceiver unit 1510 can be used to perform operations related to the transmission and reception of the communication device in the above method embodiments (such as sending and / or receiving data or messages), and the processing unit 1520 can be used to perform processing-related operations of the communication device in the above method embodiments, or operations other than transmission and reception (such as operations other than sending and / or receiving data or messages).

[0191] It should also be understood that the device 1500 here is embodied in the form of a functional unit. The term "unit" here can refer to an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, combined logic circuitry, and / or other suitable components supporting the described functions. In an alternative example, those skilled in the art will understand that the device 1500 can be specifically a communication device (such as a first communication device, or a second communication device) in the above embodiments, and can be used to execute the various processes and / or steps corresponding to the communication device in the above method embodiments. To avoid repetition, further details are omitted here.

[0192] The apparatus 1500 of each of the above-described schemes has the function of implementing the corresponding steps performed by the communication device (such as the first communication device, the second communication device, or other devices) in the above-described methods. The function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (e.g., the transmitting unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as processing units, can be replaced by processors, respectively executing the transceiver operations and related processing operations in each method embodiment.

[0193] In addition, the transceiver unit 1510 may also be a transceiver circuit (for example, it may include a receiving circuit and a transmitting circuit), and the processing unit may be a processing circuit.

[0194] It should be pointed out that, Figure 6 The device mentioned can be the equipment described in the foregoing embodiments, or it can be a chip or a chip system, such as a system on a chip (SoC). The transceiver unit can be an input / output circuit or a communication interface; the processing unit is a processor, microprocessor, or integrated circuit integrated on the chip. No limitations are imposed here.

[0195] See Figure 7 , Figure 7 This is a schematic diagram of another communication device 1600 provided in an embodiment of this application. The device 1600 includes a processing circuit 1610, which includes circuitry for performing the methods in the above method embodiments.

[0196] Optionally, the processing circuit 1610 may be implemented by one or more processors, including the one or more processors or the processing portion of the one or more processors.

[0197] Optionally, the device 1600 further includes an interface circuit 1620 for receiving and / or transmitting signals. For example, the processing circuit 1610 controls the interface circuit 1620 to receive and / or transmit signals.

[0198] Optionally, the device 1600 also includes a memory. Processing circuitry 1610 is coupled to the memory, which stores computer programs or instructions and / or data. The processing circuitry 1610 can be used to execute the computer programs or instructions stored in the memory, or to read the data stored in the memory. Optionally, there may be one or more memories.

[0199] Optionally, the memory is located inside the processing circuit or is separately disposed outside the processing circuit.

[0200] As an example, the processing circuit 1610 may have Figure 6 The interface circuit 1620 may have the following functions as shown in the processing unit 1520: Figure 6 The function of the transceiver unit 1510 shown is illustrated.

[0201] The interface circuit 1620 may include a transceiver, input / output circuits, or a communication interface.

[0202] As one option, the device 1600 is used to implement the operations performed by the communication device (such as the first communication device, or the second communication device) in the various method embodiments described above.

[0203] For example, the processing circuit 1610 is used to perform relevant operations of the communication device (such as the first communication device or the second communication device) in the various method embodiments described above.

[0204] That is, the device 1600 can be a terminal device, a network device, or a chip or chip system for a terminal device, or a chip or chip system for a network device.

[0205] It should be understood that the processing circuit mentioned in the embodiments of this application can be one or more of the following processing devices: a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the processing function portion of the aforementioned processing devices. A general-purpose processor can be a microprocessor or any conventional processor.

[0206] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0207] It should be noted that when the processing circuit is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processing circuit.

[0208] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0209] See Figure 8 , Figure 8 This is a schematic diagram of a chip system 1700 provided in an embodiment of this application. The chip system 1700 (or may also be referred to as a processing system) includes logic circuitry 1710 and an input / output interface 1720.

[0210] The logic circuit 1710 can be a processing circuit in the chip system 1700. The logic circuit 1710, as a processing circuit in the chip system 1700, is used to perform processing functions, such as compressing channel information. The input / output interface 1720 can be an input / output circuit in the chip system 1700, outputting processed information from the chip system 1700, or inputting data or signaling information to be processed into the chip system 1700 for processing.

[0211] Alternatively, the logic circuit 1710 can be coupled to a memory to execute instructions in the memory, enabling the chip system 1700 to implement the methods and functions of the embodiments of this application.

[0212] As one option, the chip system 1700 is used to implement the operations performed by the communication device (such as the first communication device, or the second communication device) in the various method embodiments described above.

[0213] For example, logic circuit 1710 is used to implement processing-related operations performed by a communication device (such as a first communication device or a second communication device) in the above method embodiments; input / output interface 1720 is used to implement sending and / or receiving-related operations performed by a communication device (such as a first communication device or a second communication device) in the above method embodiments.

[0214] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by a communication device (such as a first communication device or a second communication device) in the above-described method embodiments.

[0215] For example, when the computer program is executed by a computer, it enables the computer to implement the methods described in the embodiments of the above methods, which are executed by a communication device (such as a first communication device or a second communication device).

[0216] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods described above that are executed by a communication device (such as a first communication device or a second communication device).

[0217] This application also provides a communication system, which includes a first communication device and a second communication device in the above embodiments.

[0218] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0219] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of apparatus or units may be electrical, mechanical, or other forms.

[0220] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. For example, the computer can be a personal computer, a server, or a network device, etc. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs). For example, the aforementioned available media include, but are not limited to, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code.

[0221] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method characterized by comprising: The method includes: Receive first information, the first information being used to instruct a first reference signal to monitor a first performance, wherein the first performance is at least one of the performance of a first model and the performance of a second model, the output of the first model being associated with a second reference signal, and the output of the first model being used as the input of the second model; The first reference signal is sent, wherein the first reference signal and the output of the second model are used to monitor the first performance.

2. The method of claim 1, wherein, The method further includes: Receive second information, the second information being used to indicate the type of output of the second model, wherein the type of output of the second model is used to send the first reference signal.

3. The method according to claim 1 or 2, characterized in that, The type of the output of the second model is used to determine the spatial weight information for transmitting the first reference signal, wherein the type of the output of the second model includes at least one of the original channel information and the channel feature vector.

4. The method according to any one of claims 1 to 3, characterized in that, The spatial weight information used to transmit the first reference signal is determined based on at least one of the spatial weights used to receive the second reference signal and the first channel information obtained from the second reference signal.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Receive third information, wherein the third information includes the first performance, and any one of the first performance includes at least one of channel recovery accuracy and channel prediction accuracy.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Receive fourth information, which is used to indicate the frequency measurement range of the first reference signal.

7. The method of claim 6, wherein, The fourth information includes the frequency measurement range of the first reference signal, and the fourth information is used to indicate that: the first reference signal is used to monitor the channel recovery accuracy of the first performance, or the first reference signal is used to monitor the channel prediction accuracy of the first performance.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Send a fifth message, which is used to request monitoring of the first performance.

9. The method according to any one of claims 1 to 8, characterized in that, The first reference signal is used to determine the second channel information, and the second channel information is used to determine the first performance.

10. The method according to any one of claims 1 to 9, characterized in that, The first model is applied to the encoder of the communication device, and the second model is applied to the decoder of the communication device.

11. A communication method, comprising: The method includes: Send first information, the first information being used to instruct a first reference signal to monitor a first performance, wherein the first performance is at least one of the performance of a first model and the performance of a second model, the output of the first model being associated with a second reference signal, and the output of the first model being used as the input of the second model; The first reference signal is received, wherein the first reference signal and the output of the second model are used to monitor the first performance.

12. The method of claim 11, wherein, The method further includes: Send a second message, the second message being used to indicate the type of output of the second model, wherein the type of output of the second model is used to send the first reference signal.

13. The method according to claim 11 or 12, characterized in that, The type of the output of the second model is used to determine the spatial weight information for transmitting the first reference signal, wherein the type of the output of the second model includes at least one of the original channel information and the channel feature vector.

14. The method according to any one of claims 11 to 13, characterized in that, The spatial weight information used to transmit the first reference signal is determined based on at least one of the spatial weights used to receive the second reference signal and the first channel information obtained from the second reference signal.

15. The method according to any one of claims 11 to 14, characterized in that, The method further includes: Send a third message, wherein the third message includes the first performance, and any one of the first performance includes at least one of channel recovery accuracy and channel prediction accuracy.

16. The method according to any one of claims 11 to 15, characterized in that, The method further includes: A fourth message is sent, which indicates the frequency measurement range of the first reference signal.

17. The method according to claim 16, characterized in that, The fourth information includes the frequency measurement range of the first reference signal, and the fourth information is used to indicate that: the first reference signal is used to monitor the channel recovery accuracy of the first performance, or the first reference signal is used to monitor the channel prediction accuracy of the first performance.

18. The method according to any one of claims 11 to 17, characterized in that, The method further includes: Receive a fifth message, which is used to request monitoring of the first performance.

19. The method according to any one of claims 11 to 18, characterized in that, The first reference signal is used to determine the second channel information, and the second channel information is used to determine the first performance.

20. The method according to any one of claims 11 to 19, characterized in that, The first model is applied to the encoder of the communication device, and the second model is applied to the decoder of the communication device.

21. A communication device, characterized in that, Includes modules or units for performing the method according to any one of claims 1 to 20.

22. A communication device, characterized in that, Includes a processor, the processor being configured to cause the communication device to perform the method of any one of claims 1 to 20.

23. The apparatus according to claim 22, characterized in that, The device further includes a memory and / or a communication interface, wherein: The communication interface is coupled to the processor, and the communication interface is used for inputting and / or outputting information; The memory is used to store computer programs or instructions executed by the processor.

24. The apparatus according to claim 22 or 23, characterized in that, The device is any of the following: a communication device, a chip, a chip system, or a circuit.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed on a communication device, cause the communication device to perform the method of any one of claims 1 to 20.

26. A computer program product, characterized in that, The computer program product includes a computer program or instructions for performing the method as described in any one of claims 1 to 20.

Images