Communication method and communication apparatus

Abstract

The application provides a communication method and a communication device. A terminal side infers a non-linear response by a first model to obtain first information, the first information being used to indicate K second models in N second models, wherein the K second models are used to calibrate the non-linear interference, K and N are positive integers, and K is less than or equal to N. The terminal side sends the first information. The network side can calibrate the non-linear interference by the K second models. In this way, the second models are selected by the terminal side, the network side calibrates the non-linear interference by the second models based on the decision of the terminal side, and the flexibility of the non-linear interference calibration is improved.

Description

Technical Field

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

[0002] In complex and large-scale communication scenarios, nonlinear devices in communication systems, such as traveling wave tube amplifiers (TWTAs) and solid-state power amplifiers (SSPAs), often generate various disturbances. These nonlinear disturbances are diverse and have a significant impact on signal transmission and reception, leading to a degradation in system performance.

[0003] Current calibration methods are typically optimized for specific types of nonlinear distortion. For example, digital predistortion (DPD) is used to compensate for the nonlinear effects of TWTA, while linearization circuits are used to reduce gain saturation in SSPA. However, communication systems contain a wide variety of nonlinear devices, and different user equipment may face different types of interference, making it difficult for traditional single compensation schemes to cover all situations. Summary of the Invention

[0004] This application provides a communication method and communication device that can calibrate various nonlinear interferences, thereby improving the flexibility of nonlinear interference calibration.

[0005] Firstly, this application provides a communication method that can be applied to the terminal side, for example, it can be executed by a terminal device; or it can be executed by a component deployed in the terminal device, such as circuits or chips inside the terminal device (e.g., modem chips, also known as baseband chips, or system-on-chip (SoC) chips or system-in-package (SIP) chips containing modem cores, etc.); or it can be executed by a device deployed outside the terminal device (e.g., the host of an over-the-top (OTT) system or a cloud server) or a component in the device (e.g., chips, processors, or circuits inside the device); or it can be implemented by a logic module or software capable of realizing all or part of the functions of the terminal device, etc. Alternatively, the method can be executed by a first device, which can be a terminal device; it can also be a component within the terminal device, such as internal circuitry or a chip (e.g., a modem chip), or a SoC chip or SIP chip containing a modem core; it can also be a device outside the terminal device (e.g., the host of an OTT system or a cloud server) or a component within a device (e.g., internal chips, processors, or circuitry); it can also be a logic module or software capable of implementing some or all of the functionalities of the terminal side, etc. This application does not limit this.

[0006] The method may include: reasoning about the nonlinear response through a first model to obtain first information, wherein the nonlinear response indicates nonlinear interference, the first information is used to indicate K of N second models, and the K second models are used to calibrate the nonlinear interference, wherein K and N are both positive integers, and K is less than or equal to N; and sending the first information.

[0007] In this context, nonlinear response can be understood as the nonlinear response that the terminal itself can obtain. This nonlinear response indicates nonlinear interference. For example, the nonlinear response can be an inherent characteristic of the nonlinear device predetermined during manufacturing, stored in the device using a lookup table. The terminal can directly obtain the nonlinear response by consulting a pre-defined nonlinear response data table. This saves the step of measuring nonlinear interference based on a reference signal, thereby avoiding the superposition error between channel estimation and nonlinear estimation, and reducing the measurement overhead of reference information.

[0008] The function of the first model is to deduce a second model suitable for the nonlinear disturbance based on the nonlinear response. For example, the first model can be a routing model.

[0009] Based on the above technical solution, the terminal side can obtain first information through the first model, and the network side can determine K second models from N second models for nonlinear interference calibration based on the first information. Thus, by determining the second models for nonlinear interference calibration based on the first information provided by the terminal side, targeted calibration of nonlinear interference can be achieved. Furthermore, the N second models can be deployed on the network side for easy management, while the first model is deployed on the terminal side, enabling targeted nonlinear interference calibration for different types of nonlinear interference, thus improving flexibility.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the first information indicates the probabilities of K' second models and / or K' second models, the probability of one of the K' second models is related to the degree of adaptation of the second model to nonlinear disturbances, the probability of the K' second models is greater than the probability of the remaining second models among the N second models, and the K' second models include K second models.

[0011] Based on the above technical solution, the first information can indicate K' second models or the probabilities of K' second models, where the K' second models have a higher degree of adaptation to the nonlinear interference compared to other second models. The network side can determine K second models from the K' second models using the first information, and these K second models are used for nonlinear interference calibration. These K second models belong to N second models. That is, the first information can indicate multiple second models, allowing the network side to select the second models with higher adaptation and that it already possesses from these multiple second models for nonlinear interference calibration. This reduces the likelihood of the second model indicated by the terminal side not being included in the network side, and further indicates the degree of adaptation, improving the accuracy of nonlinear interference calibration.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, after sending the first information, the method further includes: receiving second information, the second information indicating calibration information, the calibration information being obtained by calibrating nonlinear interference using K second models, and the calibration information being used to adjust the power of the nonlinear device.

[0013] Based on the above technical solution, the network side can calibrate nonlinear interference through the second model to obtain calibration information. The terminal side receives the calibration information and can use it to adjust the power of nonlinear devices, which can further reduce nonlinear interference during data transmission.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the second model and / or the first model are obtained by training on the distorted signals of different nonlinear disturbances and the corresponding original signals.

[0015] Based on the above technical solution, the first and second models can be trained using distorted signals of different nonlinear interference types and their corresponding original signals, or using distorted signals of different degrees of nonlinear interference and their corresponding original signals. This allows the second model to be divided into multiple types based on different training data, adapting to various nonlinear interference conditions. When training the second model, the first model can be trained simultaneously, making the first and second models more compatible.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the second model is related to the type of nonlinear disturbance.

[0017] Based on the above technical solution, different second models can be trained according to different types of nonlinear interference, thus providing a targeted second model for each type of nonlinear interference. This, in turn, can improve the accuracy of nonlinear interference calibration.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: sending capability information, the capability information indicating support for the first model.

[0019] Based on the above technical solution, by reporting the capability information on the terminal side, the network side can determine whether the terminal side supports the first model. Thus, based on the capability of each terminal device, the selection of nonlinear interference calibration method is beneficial to improving the signal transmission efficiency and performance between the network side and the terminal side.

[0020] Secondly, a communication method is provided, which can be applied to the terminal side. For example, it can be executed by a terminal device; or it can be executed by a component deployed in the terminal device, such as internal circuits or chips (e.g., modem chips, also known as baseband chips, or SoC chips or SIP chips containing modem cores); or it can be executed by a device deployed outside the terminal device (e.g., the host or cloud server of an OTT system) or a component within the device (e.g., internal chips, processors, or circuits); or it can be implemented by a logic module or software capable of realizing all or part of the functions of the terminal device, etc. Alternatively, the method can be executed by a first device, which can be a terminal device; or a component within the terminal device, such as internal circuits or chips (e.g., modem chips, or SoC chips or SIP chips containing modem cores); or a device outside the terminal device (e.g., the host or cloud server of an OTT system) or a component within the device (e.g., internal chips, processors, or circuits); or a logic module or software capable of realizing some or all of the functions of the terminal side, etc. This application does not limit this.

[0021] The method may include: sending third information indicating a nonlinear device type, the nonlinear device type being associated with a second model, the second model being used to calibrate nonlinear interference.

[0022] Based on the above technical solution, the terminal side can indicate the nonlinear device type to the network side through the association between the nonlinear device type and the second model. The network side can then determine the second model based on this association. This second model can effectively calibrate the nonlinear interference generated by the nonlinear device, thus enabling targeted calibration of nonlinear interference. Furthermore, multiple second models can be deployed on the network side for easy management. The network side can indicate the nonlinear device type, providing targeted nonlinear interference calibration for different nonlinear interferences of each terminal, improving flexibility.

[0023] In conjunction with the second aspect, in some implementations of the second aspect, after sending the third information, the method further includes: receiving the second information, the second information indicating calibration information, the calibration information being obtained by calibrating the nonlinear interference using the second model, and the calibration information being used to adjust the power of the nonlinear device.

[0024] Based on the above technical solution, the network side can calibrate nonlinear interference through the second model to obtain calibration information. The terminal side receives the calibration information and can use it to adjust the power of nonlinear devices, thereby reducing nonlinear interference during data transmission.

[0025] In conjunction with the second aspect, in some implementations of the second aspect, the second model is obtained by training on the distorted signals of different nonlinear disturbances and the corresponding original signals.

[0026] Based on the above technical solution, the second model can be trained using distorted signals of different nonlinear interference types and their corresponding original signals, or it can be trained using distorted signals of different degrees of nonlinear interference and their corresponding original signals. In this way, the second model can be divided into multiple second models based on different training data to adapt to various nonlinear interference conditions.

[0027] Thirdly, a communication method is provided, which can be applied to the network side. For example, it can be executed by a network device; or it can be executed by a component deployed within the network device, such as internal circuits or chips (e.g., modem chips, also known as baseband chips, or SoC chips or SIP chips containing modem cores); or it can be implemented by a logic module or software capable of realizing all or part of the functions of the network device, etc. Alternatively, the method can be executed by a second device, which can be a network device; or a component within the network device, such as internal circuits or chips (e.g., modem chips), or SoC chips or SIP chips containing modem cores; or it can be a device outside the network device (e.g., intelligent network elements) or a component within the device (e.g., internal chips, processors, or circuits); or it can be a logic module or software capable of realizing some or all of the functions of the network side, etc. This application does not limit this.

[0028] The method may include: receiving first information, which is obtained by reasoning about a nonlinear response through a first model, the nonlinear response indicating nonlinear interference, the first information being used to indicate K second models out of N second models, the second models being used to calibrate the nonlinear interference, wherein K and N are both positive integers, and K is less than or equal to N; and determining K second models based on the first information.

[0029] In conjunction with the third aspect, in some implementations of the third aspect, the first information indicates the probabilities of K' second models and / or K' second models, the probability of one of the K' second models is related to the degree of adaptation of a second model to nonlinear disturbances, the probability of the K' second models is greater than the probability of the remaining second models among the N second models, and the K' second models include K second models.

[0030] In conjunction with the third aspect, in some implementations of the third aspect, determining K second models based on the first information includes: determining K second models based on the probabilities of K' second models and / or K' second models.

[0031] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: sending second information, the second information indicating calibration information, the calibration information being obtained by calibrating the nonlinear interference using K second models, and the calibration information being used to adjust the power of the nonlinear device.

[0032] In conjunction with the third aspect, in some implementations of the third aspect, the second model and / or the first model are obtained by training the distorted signal with different degrees of nonlinear interference with the corresponding original signal.

[0033] In conjunction with the third aspect, in some implementations of the third aspect, the second model is related to the type of nonlinear disturbance.

[0034] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: receiving capability information, which indicates support for the first model.

[0035] It should be understood that the beneficial effects and possible designs of the third aspect can be referred to the description of any of the first or second aspects, and will not be repeated here.

[0036] Fourthly, a communication method is provided, which can be applied to the network side. For example, it can be executed by a network device; or it can be executed by a component deployed within the network device, such as internal circuits or chips (e.g., modem chips, also known as baseband chips, or SoC chips or SIP chips containing modem cores); or it can be implemented by a logic module or software capable of realizing all or part of the functions of the network device, etc. Alternatively, the method can be executed by a second device, which can be a network device; or a component within the network device, such as internal circuits or chips (e.g., modem chips), or SoC chips or SIP chips containing modem cores; or it can be a device outside the network device (e.g., intelligent network elements) or a component within the device (e.g., internal chips, processors, or circuits); or it can be a logic module or software capable of realizing some or all of the functions of the network side, etc. This application does not limit this.

[0037] The method may include: receiving third information indicating a nonlinear device type, the nonlinear device type being associated with a second model, the second model being used to calibrate nonlinear interference; and determining the second model based on the third information.

[0038] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes: sending second information, the second information indicating calibration information, the calibration information being obtained by calibrating the nonlinear interference using the second model, and the calibration information being used to adjust the power of the nonlinear device.

[0039] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the second model is obtained by training on the distorted signals of different nonlinear disturbances and the corresponding original signals.

[0040] Combining aspects one through four, in some implementations of aspects one through four, the first model is a routing model and the second model is an expert model.

[0041] It should be understood that the beneficial effects and possible designs of the fourth aspect can be referred to the description of any of the first or second aspects, and will not be repeated here.

[0042] Fifthly, an apparatus is provided. This apparatus may include functional modules corresponding to each of the methods / operations / steps / actions described in any possible implementation of the first or second aspect, or may include functional modules corresponding to each of the methods / operations / steps / actions described in any of the third or fourth aspects. The module may be hardware circuitry, software, or a combination of hardware circuitry and software implementation.

[0043] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions performed by the terminal side in the methods described in the first or second aspect above, while the processing module is used to perform processing-related actions performed by the terminal side in the methods described in the first or second aspect above.

[0044] In one design, the device can be a terminal device, or a device, module, circuit, or chip configured in the terminal device, or a device that can be used in conjunction with the terminal device, such as an OTT host or cloud server.

[0045] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions performed by the network side in the methods described in the third or fourth aspect above, while the processing module is used to perform processing-related actions performed by the network side in the methods described in the third or fourth aspect above.

[0046] In one design, the device can be a network device, or a device, module, circuit, or chip configured in the network device, or a device that can be used in conjunction with the network device, such as an intelligent network element with a radio access network (RAN) intelligent controller (RIC) deployed thereon.

[0047] A sixth aspect provides an apparatus comprising a processor and a storage medium storing instructions which, when executed by the processor, cause a method as in any possible implementation of the first or second aspect to be implemented, or a method as in any possible implementation of the third or fourth aspect to be implemented.

[0048] A seventh aspect provides an apparatus comprising a processing circuit for processing data and / or information such that a method as in any possible implementation of the first or second aspect is implemented, or a method as in any possible implementation of the third or fourth aspect is implemented.

[0049] The processing circuit may include one or more processors, or all or part of the circuitry in one or more processors used for control or processing functions.

[0050] Optionally, the apparatus may further include a memory for storing programs or instructions, and the processor for running the programs or instructions to implement the methods in any possible implementation of the first or second aspect, or to implement the methods in any possible implementation of the third or fourth aspect.

[0051] Optionally, the device may also include the transceiver circuit, or an input / output interface.

[0052] Eighthly, a chip is provided, including processing circuitry for running a program or instructions to cause the method in any possible implementation of the first or second aspect to be implemented, or to cause the method in any possible implementation of the third or fourth aspect to be implemented.

[0053] Optionally, the chip may further include a memory for storing programs or instructions.

[0054] Optionally, the chip may also include transceiver circuitry, or input / output interfaces.

[0055] A ninth aspect provides a computer-readable storage medium comprising instructions that, when executed by a processor, cause a method as in any possible implementation of the first or second aspect to be implemented, or a method as in any possible implementation of the third or fourth aspect to be implemented.

[0056] In a tenth aspect, a computer program product is provided, the computer program product comprising computer program code or instructions that, when the computer program code or instructions are executed, cause the methods of the first or second aspect and any possible implementation thereof to be implemented, or cause the methods of the third or fourth aspect and any possible implementation thereof to be implemented.

[0057] Eleventhly, a communication system is provided, the communication system including means for performing the first aspect or the second aspect and any possible implementation thereof, or including means for performing the third aspect or the fourth aspect and any possible implementation thereof.

[0058] It should be understood that aspects five to eleven of this application correspond to the technical solutions of aspects one to four of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be repeated here. Attached Figure Description

[0059] Figure 1 This is a schematic diagram of a communication system applicable to the communication method in the embodiments of this application.

[0060] Figure 2 This is a schematic diagram of another communication system applicable to the communication method of the embodiments of this application.

[0061] Figure 3 This is a schematic diagram of a possible application framework in a communication system.

[0062] Figure 4 This is a schematic diagram of another possible application framework in a communication system.

[0063] Figure 5 This is a schematic flowchart of a communication method provided in an embodiment of this application.

[0064] Figure 6 This is a schematic diagram of the model workflow provided in the embodiments of this application.

[0065] Figure 7 This is a schematic diagram of the model training method provided in the embodiments of this application.

[0066] Figure 8 This is a schematic flowchart illustrating another communication method provided in an embodiment of this application.

[0067] Figure 9 This is a schematic flowchart illustrating another communication method provided in an embodiment of this application.

[0068] Figure 10 This is a schematic flowchart illustrating another communication method provided in an embodiment of this application.

[0069] Figure 11 This is a schematic block diagram of a communication device provided in an embodiment of this application.

[0070] Figure 12 This is a schematic diagram of another communication device provided in an embodiment of this application.

[0071] Figure 13 This is a schematic diagram of the structure of an artificial intelligence (AI) processor provided in an embodiment of this application. Detailed Implementation

[0072] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0073] To facilitate understanding of the embodiments of this application, the following points will be explained first:

[0074] First, in this application, the terminal side can also be referred to as the user equipment (UE) side, terminal-side equipment, etc., including: terminal equipment (or user equipment, terminal, etc.), components deployed in the terminal equipment (such as circuits or chips inside the terminal equipment), equipment deployed outside the terminal equipment (such as the host or cloud server of an over-the-top (OTT) system, hereinafter referred to as the OTT system server), or components deployed in equipment outside the terminal equipment (such as circuits or chips inside the equipment). The network side (NW side) can also be referred to as network-side equipment, including: network equipment that communicates with the terminal equipment, components deployed in the network equipment (such as circuits or chips inside the network equipment with near real-time radio access network (RAN) intelligent control functions), equipment deployed outside the network equipment (such as intelligent network elements, for example, intelligent network elements with near real-time RAN intelligent control functions), or components deployed in the intelligent network element (such as circuits or chips inside the intelligent network element). Network equipment may include: access network equipment, core network equipment, or operation administration and maintenance (OAM) equipment.

[0075] Second, in this application, the indication includes direct indication (also known as explicit indication) and indirect indication (also known as implicit indication). Directly indicating information A means including information A; indirectly indicating information A can mean indicating information A through the correspondence between information A and information B and by directly indicating information B; or by indicating information A through a preset rule that can be used to determine A based on B and by directly indicating information B. The correspondence between information A and information B, and the preset rule, can be predefined, pre-stored, pre-burned, or pre-configured.

[0076] Third, in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the preceding and following related objects, but it does not exclude the possibility of indicating an "and" relationship; the specific meaning can be understood in context. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Here, a, b, and c can be single or multiple.

[0077] Fourth, the use of prefixes such as "first" and "second" in this application is merely for the purpose of distinguishing and describing different things belonging to the same name category, and does not constrain the order, size, or quantity of things. For example, "first dataset" and "second dataset" are simply different datasets, and do not limit the number, size, or priority of the datasets; similarly, "first model" and "second model" are simply different models, and do not limit the number, size, or priority of the models; furthermore, "first information" and "second information" are simply different indicative information, and do not limit the quantity, chronological order, size, or priority of the information.

[0078] Fifth, in this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to a terminal device" can be understood as the destination of the information being the terminal device, which may include direct transmission via the air interface or indirect transmission by other units or modules via the air interface. "Receive information from a network device" can be understood as the source of the information being the network device, which may include direct reception from the network device via the air interface or indirect reception from the network device by other units or modules via the air interface. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between a terminal device and a computing node, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0079] Sixth, in the embodiments of this application, "when," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a time, nor do they require the device to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0080] Seventh, in this application, the words "example," "exemplarily," "for example," or "such as" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "example," "exemplarily," "for example," or "such as" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "example," "exemplarily," "for example," or "such as" is intended to present the relevant concepts in a specific manner.

[0081] The communication system to which this application applies is described below.

[0082] The technical solutions provided in this application can be applied to various communication systems, such as 5th generation (5G) or new radio (NR) systems, frequency division duplex (FDD) systems, 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.

[0083] In a communication system, one network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This disclosure uses a network element 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 network element, and the network device can be replaced by a second network element, both performing the corresponding methods described in this disclosure.

[0084] Figure 1 This is a schematic diagram of a communication system applicable to the communication method in the embodiments of this application. For example... Figure 1 As shown, the communication system 100A may include at least one access network device, such as Figure 1 The access network device 110 shown; the communication system 100A may also include at least one terminal device, such as Figure 1 Terminal devices 120 and 130 are shown. Access network device 110 can communicate with terminal devices (such as terminal devices 120 and 130) via a wireless link. Communication devices in this communication system, for example, between access network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0085] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, thus requiring increasingly diverse demands. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming (BF), and supporting beam management, network energy efficiency has become a hot research topic. These new demands, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (AI) technology can be introduced into wireless communication networks to achieve network intelligence. To support AI technology in wireless networks, AI nodes may also be introduced. AI nodes can be AI network elements or AI modules.

[0086] AI can endow machines with human-like intelligence, for example, allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) a model using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0087] This document explains some basic concepts in the field of AI, which does not limit the scope of protection of the embodiments of this application.

[0088] (1) Machine learning (ML)

[0089] Machine learning is a crucial technological approach to achieving AI. AI endows machines with human-like intelligence, using computer hardware and software to simulate certain intelligent human behaviors, including machine learning and other methods. Machine learning refers to learning models or rules from raw data, such as neural networks, decision trees, and support vector machines. Machine learning can be categorized into supervised learning, unsupervised learning, and reinforcement learning.

[0090] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and expresses this learned mapping relationship using a machine learning model. The process of training the machine learning model is the process of learning this mapping relationship. For example, in signal detection, the noisy received signal is the sample, and the corresponding real constellation point is the label. Machine learning aims to learn the mapping relationship between samples and labels through training, that is, to enable the machine learning model to learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted values ​​and the real labels. Once the mapping relationship is learned, it can be used to predict the sample label of each new sample. The mapping relationship learned in supervised learning can include linear mappings and nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0091] Unsupervised learning relies solely on collected sample values, using algorithms to discover inherent patterns within the samples. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals; that is, the model learns the mapping relationship from sample to sample, which is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0092] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each terminal device based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and the optimal decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0093] Deep neural networks (DNNs) are a specific implementation of machine learning. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while DNN-based deep learning communication systems can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0094] Based on their construction method, DNNs can be divided into feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). FNNs can be neural networks where neurons in adjacent layers are completely connected pairwise, which makes FNNs typically require a large amount of storage space and have high computational complexity.

[0095] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (discrete sampling along the time axis) and image data (two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (such as people and objects in an image representing different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0096] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0097] AI models refer to function models that map inputs of a certain dimension to outputs of a certain dimension, and their parameters 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 correspond to the parameters of this model and can be obtained through machine learning training. In machine learning, the data used for model training, validation, and / or testing can form a dataset or training dataset. The quantity and / or quality of data in the dataset or training dataset will affect the effectiveness of machine learning. Model training involves selecting an appropriate loss function (which measures the difference between the model's predictions and the true values) and using optimization algorithms to train the model parameters to minimize the loss function value. Model testing involves evaluating the model's performance using test data after training. Model application involves using the trained model to solve real-world problems.

[0098] A neural network, or artificial neural network, is a mathematical model that mimics the behavioral characteristics of animal neural networks to perform distributed parallel information processing. It is a special form of AI model.

[0099] (2) Model Training

[0100] Model training involves selecting an appropriate function (such as a loss function) and using optimization algorithms to train the model parameters so that the difference between the model's predicted values ​​and the ground truth (or target values, labels) tends to be minimized.

[0101] For example, model training methods include, but are not limited to, supervised learning, self-supervised learning, and knowledge distillation.

[0102] (3) Model files and model parameters

[0103] Model files and / or model parameters can be used to determine the model. Optionally, the model in this application may refer to the model itself, or it may refer to the model files and / or model parameters used to determine the model.

[0104] The model file can be used to indicate the model structure, which may include, but is not limited to, FNN, CNN, or RNN. The model file can have a fixed format, such as a standard predefined format, or a format pre-negotiated by both ends of the interface. Model parameters can refer to parameters in the neural network model, such as, but not limited to, the number of layers in the neural network, the type and weights of neurons in each layer, etc. This application does not limit the method of distributing model parameters.

[0105] Take DNN as an example. The idea behind DNN comes from the neuronal structure of the brain. Each neuron can perform a weighted summation operation on its inputs and then use the result of the weighted summation operation to generate the output through a non-linear function. For example, the input of a neuron is x = [x0, x1, ..., x...]. N-1The weights corresponding to the inputs are w = [w0, w1, ..., w] N-1 The bias of the weighted summation is b. The nonlinear function f() can take many forms; for example, the nonlinear function f() can be the maximum value function max{0, x}. Then the effect of a neuron's execution is... Where N is a positive integer, and n is a positive integer greater than or equal to 0 and less than or equal to (N-1). The weights of the weighted summation operation of neurons in a neural network and the nonlinear function are called the parameters of the neural network. The parameters of all neurons in a neural network constitute the parameters of the neural network.

[0106] A DNN typically has multiple neural network layers, including an input layer, one or more hidden layers, and an output layer. Generally, the first layer is the input layer, the last layer is the output layer, and the layers in between are hidden layers. Each layer contains multiple neurons. Layers are fully connected; that is, any neuron in the i-th layer is connected to any neuron in the (i+1)-th layer. The input layer processes the received values ​​(i.e., the DNN's input) through neurons and then passes them to the hidden layers. Similarly, the hidden layers pass the computation results to the final output layer, producing the DNN's output. This application does not limit the structure and parameters used in the AI ​​model.

[0107] One of the model structure or model parameters can be predefined, while the other can be provided by the sender (e.g., the network side). Alternatively, both the model structure and model parameters can be provided by the sender (e.g., the network side). This application does not impose any limitations on this.

[0108] The transmitting model can refer to sending model files and / or model parameters, while the receiving model can refer to receiving model files and / or model parameters. Currently, AI technology is being introduced into wireless communication systems. AI technology can be used for wireless channel information compression and reconstruction, beam management, and positioning enhancement, improving wireless communication performance based on trained AI models. A wireless AI framework can include multiple modules such as data collection, model training, model management, model inference, and model storage.

[0109] Figure 2 This is a schematic diagram of another communication system applicable to the communication method in the embodiments of this application. Compared to Figure 1 Regarding the communication system 100A shown, Figure 2 The communication system 100B shown also includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building datasets or AI models. The AI ​​network element can also be simply referred to as an intelligent network element. In this disclosure, the AI ​​model can be simply referred to as a model.

[0110] In one possible implementation, access network device 110 can send data related to the training of the AI ​​model to AI network element 140, whereby AI network element 140 constructs a dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by terminal devices. AI network element 140 can send the results of operations related to the AI ​​model to access network device 110, and then forward them to terminal devices via access network device 110. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results, etc. Exemplarily, a portion of the trained AI model may be deployed on access network device 110, and another portion on terminal devices 120 and / or 130. Alternatively, the trained AI model may be deployed on access network device 110. Or, the trained AI model may be deployed on terminal devices 120 and / or 130.

[0111] It should be understood that Figure 2 This explanation only uses the direct connection between AI network element 140 and access network device 110 as an example. In other scenarios, AI network element 140 can also be connected to terminal devices. Alternatively, AI network element 140 can be connected to both access network device 110 and terminal devices simultaneously. Alternatively, AI network element 140 can also be connected to access network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between AI network element and other network elements. For example, AI network element 140 can also be configured as a module in access network device and / or terminal device, for example, configured in... Figure 1 In the access network device 110 or terminal device shown.

[0112] It should be noted that, Figure 1 and Figure 2 This is a simplified illustration for ease of understanding only. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices. Figure 1 and Figure 2 The figures are not shown. In practical applications, this communication system may include multiple access network devices or multiple terminal devices. This application does not limit the number of access network devices and terminal devices included in the communication system.

[0113] In the embodiments of this application, the terminal device may also be referred to as 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 equipment.

[0114] 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.

[0115] 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.

[0116] 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. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. 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 solution of this embodiment.

[0117] The network device in this application embodiment can be a device for communicating with a terminal device. This network device may include an access network device, a core network device, or other devices in the communication system. The access network device may be, for example, a base station. In this application embodiment, the access network device may 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 such as: 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), radio unit (RU), positioning node, 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. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in V2X technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technology or equipment form used in the access network equipment.

[0118] 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.

[0119] In some deployments, the access network equipment mentioned in the embodiments of this application may be a device including a CU, or a DU, or a device including both CU and DU, or a device with a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the access network equipment may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0120] 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.

[0121] 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, it moves some downlink and / or uplink baseband functions—for example, for downlink, precoding, digital beamforming, or one or more of inverse fast Fourier transform (IFFT) / adding a cyclic prefix (CP)—from the DU to the RU; and for uplink, digital beamforming, or one or more of fast Fourier transform (FFT) / removing CP—from the DU to the RU. In one possible implementation, this interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting methods between DU and RU are different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0122] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. The DU is configured to implement one or more functions preceding layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping itself), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming, or one or more of IFFT / CP addition) are implemented in the RU. For uplink transmission, de-RE mapping is used as the dividing line. The DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping itself), while other functions following de-mapping (e.g., digital BF or FFT / CP removal) are implemented in the RU. It is understood that descriptions of the functions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol and will not be elaborated upon here.

[0123] 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.

[0124] 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 open RAN (ORAN) architecture, CU can also be called open CU (open-CU, O-CU), DU can also be called open DU (open-DU, O-DU), CU-CP can also be called open CU-CP (open-CU-CP) O-CU-CP, CU-UP can also be called open CU-UP (open-CU-UP, O-CU-UP), and RU can also be called open RU (open-RU, 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.

[0125] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0126] Network devices and / or 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, or software functions running on dedicated hardware or 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.

[0127] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network equipment, terminal equipment, or core network elements. Alternatively, the AI ​​node can also 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 OTT system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: access network equipment, terminal equipment, or core network elements.

[0128] 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.

[0129] 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.

[0130] Figure 3 This is a schematic diagram of a possible application framework in a communication system. For example... Figure 3As shown, network elements in a communication system are connected via interfaces (such as next-generation (NG) interfaces or Xn interfaces) or air interfaces. The NG interface is the interface between the radio access network and the 5G core network. The Xn interface is the interface between access network devices, and the air interface is the interface between access network devices and terminal devices. These network element nodes, such as core network devices, RAN nodes, terminal devices, or one or more devices in the OAM, are equipped with one or more AI modules (for clarity, ...). Figure 3 (Only one is shown in the image). The access network node can be a single RAN node or can include multiple RAN nodes, such as CU and DU. The CU and / or DU can also be configured with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are configured in CU-CP and / or CU-UP.

[0131] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0132] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0133] The network device can be a network device equipped with one or more AI modules. The network device may include... Figure 3 This refers to one or more devices within the core network, RAN, or OAM. For example, the AI ​​module could be... Figure 4The RAN intelligent controller (RIC) shown can be a near-real-time (near-RT) RIC or a non-real-time (non-RT) RIC. For example, a near-real-time RIC is located in a RAN node (e.g., in a CU or DU), while a non-real-time RIC is located in an OAM, a cloud server, a core network device, or other access network devices. The RIC can obtain subsets from multiple terminal devices from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble them into a dataset, and train based on the dataset. Exemplarily, near-real-time and non-real-time RICs can also be set up as separate network elements, and access network devices can be either near-real-time or non-real-time RICs.

[0134] Figure 4 This is a schematic diagram of another possible application framework in a communication system. Figure 4 The communication system shown includes access network nodes (CU, DU, and RU shown in the figure) and terminals, as well as a RIC. For example, the RIC could be... Figure 3 The AI ​​module shown can be used to implement AI-related functions. The RIC includes near real-time RIC and non-real-time RIC. Non-real-time RIC primarily processes non-real-time information, such as data that is not sensitive to latency, with latency on the order of seconds. Real-time RIC primarily processes near real-time information, such as data that is relatively sensitive to latency, with latency on the order of tens of milliseconds.

[0135] The near real-time RIC is used for model training and inference. For example, it is 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 the inference results 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 near real-time RIC delivers the inference results to the DU, and the DU sends them to the RU.

[0136] 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., one or more of CU, CU-CP, CU-UP, DU, 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.

[0137] The near real-time RIC and non-real-time RIC can also be set up 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 the OAM, cloud server, core network device, or other network device.

[0138] To facilitate understanding of the embodiments of this application, the terms involved in this application will be briefly explained below.

[0139] 1. Nonlinear Interference: Nonlinear interference refers to output distortion (or noise) in a system caused by nonlinear factors that is not linearly proportional to the amplitude or characteristics of the input signal. This interference is usually caused by nonlinear devices or nonlinear effects in the system; for example, the nonlinear distortion that TWTA may produce under high-power signal drive. Nonlinear interference can lead to signal distortion, in-band intermodulation, or out-of-band spurious signals, affecting the overall performance of the system. It should be understood that nonlinear interference can also be called nonlinear disturbance, and this application does not limit the terminology.

[0140] 2. Nonlinear Interference Calibration: Nonlinear interference calibration refers to taking compensation and calibration measures to reduce the impact of nonlinear distortion on signal quality and system performance by addressing output distortion (or noise) caused by nonlinear factors in the system. In this application, nonlinear interference calibration can be performed using a second model. It should be understood that nonlinear interference calibration can also be called nonlinear interference compensation, nonlinear calibration, nonlinear compensation, etc., and this application does not limit the name.

[0141] 3. Nonlinear Response: This refers to the nonlinear behavior of a system or device in response to an input signal, meaning that the change in the output signal is no longer proportional to the change in the input signal. Common nonlinear responses include distortion caused by TWTA, SSPA, and clipping. For example, with TWTA, under high power input, its gain gradually saturates as the input power increases, leading to nonlinear distortion of the output signal.

[0142] 4. Mixture of Experts (MoE): MoE is a deep learning model architecture typically used to handle large-scale tasks and improve the model's generalization ability. MoE works by dividing the task among multiple expert models, each expert handling a different subset of data or a sub-part of the task. In this application, the task refers to handling multiple nonlinear compensation tasks. Its design theory is based on the following fundamental principles:

[0143] 1) Definition of an expert: In the MoE architecture, an "expert" refers to an independent model that learns and optimizes specifically for different subspaces of the dataset. Each expert model may focus on solving a certain class of problems or processing a specific type of data, which allows the model to perform better on local data.

[0144] 2) Gating Mechanism: The MoE architecture includes a gating network, which determines which experts should process a given input, or the degree of contribution of each expert to the final output. The gating network dynamically assigns weights to different experts based on the characteristics of the input data, thus enabling adaptive processing of the input.

[0145] 3) Sparsity Principle: MoE leverages the sparsity of knowledge, meaning that not all experts need to participate in processing every input. In practice, only a few experts are activated, which helps reduce computation and improve efficiency. This conditional computation allows the model to scale to very large sizes without sacrificing performance;

[0146] 4) Parallelization and Distributed Training: The MoE architecture natively supports parallelization and distributed training because expert models can be trained independently and then combined during the inference phase. This is especially useful for large-scale models and large datasets, as it can effectively utilize hardware resources such as multiple GPUs or TPUs;

[0147] 5) Learning and Optimization: The learning process of the MoE model involves joint optimization of expert models and gating networks. Expert models are typically updated using traditional gradient descent methods, while the gating network needs to learn how to correctly allocate inputs to the experts. The loss function of the entire system considers the outputs of all experts and the decisions of the gating network.

[0148] 6) Scalability and Flexibility: Another advantage of the MoE architecture is its scalability and flexibility. The complexity and expressive power of the model can be enhanced by adding more expert models, while keeping the computational cost within a controllable range.

[0149] 5. Routing Model: This refers to a mechanism for selecting and routing input data flows to different models or sub-models. It is similar to the gating mechanism in MoE, but focuses more on intelligent selection and allocation among multiple models based on input characteristics. In this application, it refers to instructing a specific expert model in MoE through the inference results of the routing model.

[0150] 6. Inference Data: This refers to the data input into the model for prediction or inference. Inference data typically originates from real-time or historical data, which is preprocessed before being used as input to the model. The quality of the inference data directly affects the accuracy and reliability of the inference results. In communication systems, inference data may include various information such as CSI, channel parameters, and network load.

[0151] 7. Inference Results: This refers to the output generated by the model based on the inference data. This output is typically used for decision support, helping the system make real-time decisions in dynamic environments. In communication tasks, inference results may include predicted CSI values, channel quality estimates, and interference detection; these results are crucial for network management and optimization.

[0152] Nonlinear devices are widely used in communication technologies, including transceivers, solid-state power amplifiers (SSPAs), and clipping devices. These nonlinear devices introduce different types of nonlinear distortion, which significantly affect the signal transmission and reception of the system.

[0153] TWTA (Transient Wave Amplifier) ​​devices introduce various types of nonlinear distortion, significantly impacting signal transmission and reception. They are characterized by high gain and a wide frequency response. The nonlinearity of TWTA is primarily manifested in saturation effects and harmonic distortion: when the input signal power is high, the amplifier enters the saturation region, and the output signal is no longer proportionally amplified, leading to waveform distortion and harmonic generation. To address these nonlinear distortions, digital predistortion (DPD) technology is commonly used. This involves preprocessing the signal before transmission to reduce the amplifier's nonlinear effects.

[0154] Solid-state power amplifiers (SSPAs) are based on solid-state semiconductor technology and are used in communication systems such as mobile communications, wireless LANs, and satellite communications. The nonlinear characteristics of SSPAs manifest as nonlinear gain and saturation effects. Particularly when the input signal approaches saturation power, the output signal gain is no longer proportional to the input, resulting in distortion. SSPAs typically aim for high efficiency and often operate near saturation, thus increasing nonlinear distortion. To mitigate this effect, distributed power amplifiers (DPDs) or linearization circuits can be used to optimize system performance.

[0155] Clipping is a common signal processing technique in orthogonal frequency division multiplexing (OFDM) systems. It involves truncating the signal strength to a set threshold when the signal amplitude exceeds that threshold. This process leads to signal distortion, particularly in the peak signal range, resulting in nonlinear distortion. Clipping also introduces high-frequency components, causing spectral spread and harmonic distortion, affecting the efficient use of the signal. Furthermore, clipping increases the bit error rate (BER), impacting signal quality in digital communication systems. Clipping is often used in situations where signal power is limited, such as to prevent equipment damage or reduce interference with other signals.

[0156] To address the different types of nonlinear distortion mentioned above, targeted compensation methods are typically employed. For example, DPDs are primarily used to compensate for the nonlinear effects of power amplifiers, while linearization circuits can be used to reduce gain saturation distortion in SSPAs. However, in practical communication systems, signals are often affected by a combination of nonlinear distortions, including but not limited to: gain compression: after a power amplifier enters the saturation region, its gain characteristics deviate from a linear response, leading to signal distortion; harmonic distortion: power amplifiers generate harmonic components in the nonlinear operating region, resulting in spectrum broadening and affecting system performance; and cross-channel interference: due to the interaction of multiple signals, severe nonlinear cross-interference may occur between signals under high-frequency bandwidth conditions.

[0157] These nonlinear disturbances have complex interactions, making it difficult for a single compensation method to address them comprehensively. In traditional schemes, different nonlinear distortions often require independent compensation strategies or multiple complex algorithms, which not only increases computational complexity but may also limit the system's real-time performance and compensation accuracy.

[0158] Based on this, this application provides a communication method that can indicate a suitable second model through the inference results of a first model, and use the second model to handle different types of nonlinear interference, thereby improving the flexibility of nonlinear interference calibration and thus enhancing system performance.

[0159] The methods provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings. The embodiments provided by this application can be applied to the scenarios shown in the above figures and are not limited thereto. In addition, the terms used below can be referred to the foregoing explanations and will not be repeated hereafter. Furthermore, for ease of description, the terminal side and network side are used as examples for illustrative purposes. As an example, the terminal side method can be executed by a terminal device, or by a component of the terminal device (e.g., a chip, chip system, circuit, or communication module), or by a device deployed outside the terminal device (e.g., the host or cloud server of an OTT system) or a component within the device (e.g., a chip, processor, or circuit inside the device). As an example, the network side method can be executed by a network device, or by a component of the network device (e.g., a chip, chip system, circuit, or communication module), or by a device outside the network device (e.g., a smart network element on the network side) or a component within the device (e.g., a chip, processor, or circuit inside the device). Furthermore, the steps described below as being executed by a single execution entity can also be divided into being executed by multiple execution entities, which can be logically and / or physically separated.

[0160] Figure 5 This is a schematic flowchart of the communication method 500 provided in the embodiments of this application.

[0161] Figure 6 This is a schematic diagram of the model workflow provided in the embodiments of this application.

[0162] Figure 5 The method shown illustrates the flow of method 500 from the perspective of interaction between the terminal side and the network side. More detailed explanations regarding the terminal side and the network side can be found above and will not be repeated here. Figure 5 The method shown includes S510 to S530.

[0163] S510, the terminal side infers the nonlinear response through the first model to obtain the first information.

[0164] In S520, the terminal sends the first information, and the network receives the first information accordingly.

[0165] In this context, the first model is used to infer the nonlinear response and obtain the first information. Inferring the first information from the nonlinear response using the first model can be described as obtaining the first information based on the first model and the nonlinear response; it can also be described as inputting the nonlinear response into the first model to obtain the first information; or it can be described as the inference data of the first model being the nonlinear response, and the inference result being the first information.

[0166] For example, the first model can be a routing model, that is, the terminal side can use the nonlinear response as inference data and obtain the inference result through the routing model. This inference result is the first information.

[0167] The nonlinear response can refer to the nonlinear response of the terminal side itself. For an explanation of the nonlinear response, please refer to the above text. It will not be repeated here. The nonlinear response can also be called nonlinear characteristic. This application does not limit the name.

[0168] The following examples illustrate several ways to obtain nonlinear responses.

[0169] Method 1: One possible way to implement nonlinear response is through pre-stored modeling. Specifically, during the manufacturing process, the radio frequency (RF) front-end of the terminal device is calibrated and modeled to measure its nonlinear characteristics. These nonlinear characteristics (such as gain compression, phase distortion, intermodulation distortion, etc.) are stored in the device and used for subsequent DPD or adaptive power control.

[0170] Method 2: Another possible implementation of nonlinear response is based on real-time feedback measurement. Specifically, for example, the RF link of the terminal device typically includes a power detection circuit (e.g., a root mean square (RMS) detector) to measure whether the transmit power enters the nonlinear region. As another example, in multi-carrier or high-power transmission scenarios, the terminal device can detect out-of-band distortion components (e.g., third-order intermodulation (IM3) components and fifth-order intermodulation (IM5) components) to assess the nonlinearity of its power amplifier.

[0171] It should be noted that the nonlinear response in this application mainly refers to the nonlinear characteristics that the terminal device can obtain. The above-mentioned methods for obtaining the nonlinear response are only examples, and other methods may also be used.

[0172] The first information is used to indicate K of the N second models, where K and N are both positive integers, and K is less than or equal to N.

[0173] In other words, the first information can be used to indicate the models that can be used on the network side (i.e., K second models), which can be calibrated for the corresponding nonlinear interference on the terminal side. That is, these models are used to calibrate signals subjected to nonlinear interference.

[0174] Since the terms N, K, and K' second models appear repeatedly in the text, the relationship between these three will be explained below. Nonlinear interference can include various types; taking the nonlinear interference #A on the terminal side in Method 500 as an example, we will discuss it further.

[0175] The term "N second models" indicates that there can be multiple models used for nonlinear interference calibration on the network side. In this application, the models that can be deployed on the network side for nonlinear interference calibration are represented by N second models.

[0176] K second models represent one or more second models used on the network side to calibrate nonlinear interference #A, where N and K are related as follows: K is less than or equal to N.

[0177] K' second models represent the models that the terminal side suggests the network side can use to calibrate nonlinear interference #A. K' is a positive integer. The relationship between K' second models and K second models is that K' second models include K second models, that is, K is less than or equal to K'.

[0178] In one implementation, the first information can indicate the probabilities of K' second models and / or K' second models. The following example illustrates this with N=5.

[0179] Example 1 of the implementation of the first information: The first information can indicate K' second models. There can be multiple ways to implement the first information indicating K' second models. In one implementation, the first information can indicate the identifiers (also called serial numbers, sequences, activation sequences, etc.) of the K' second models. In other words, the first information can indicate the activation index of the second models. For example, the identifiers of the 5 second models are: 0001 for model #1, 0002 for model #2, 0003 for model #3, 0004 for model #4, and 0005 for model #5.

[0180] For example, when K' is 1, the first information can indicate one second model, such as the second model identified as 0001. As another example, when K' is 2, the first information can indicate two second models, such as the two second models identified as 0002 and 0003 respectively.

[0181] Example 2 of the implementation of the first information: The first information can indicate the probabilities of K' second models. In other words, the first information can indicate the probabilities of K' second models in a Top-K form. In one implementation, the first information can indicate the probabilities of the K' second models in the form of a sequence. For example, the first information can indicate the probabilities of the 5 second models as [0.8, 0.17, 0.76, 0.95, 0.20].

[0182] It should be understood that in this example, K' is equal to N. Specifically, the network side includes 5 second models, and the terminal side knows these 5 second models. If the first information is a sequence of length 5, then the first information can represent the probabilities of these 5 second models as follows: the probability of model #1 is 0.8, the probability of model #2 is 0.17, the probability of model #3 is 0.76, the probability of model #4 is 0.95, and the probability of model #5 is 0.20.

[0183] Example 3 of the implementation of the first information: The first information can indicate K' second models and the probabilities of the K' second models. For example, when K' is 1, the first information can indicate the probability of the 1 second model. Or, when K' is 2, the first information can indicate the probability of the 2 second models. In this example, the first information can be indicated by a sequence, for example, the first information indicating the probability of the 2 second models can be [(0001, 0.91), (0003, 0.64)], or it can be indicated by a table. This application does not limit the scope of the first information.

[0184] In this context, the probability of one of the K' second models is related to its fit to nonlinear disturbances. The fit can represent the ability to calibrate against nonlinear disturbances, or it can represent the weight given to the nonlinear disturbance during calibration. In other words, the probability of a second model can represent its ability to calibrate against nonlinear disturbance #A, or it can be said that the probability of a second model represents the weight given to the nonlinear disturbance #A. An example is provided below, using N=5 as an example.

[0185] Example 1: The first information can indicate the probabilities of K' second models. In one implementation, the first information indicates the probabilities of N second models in a sequential manner. For example, the first information can indicate the probabilities of the 5 second models as [0.8, 0.17, 0.76, 0.95, 0.20]. In this example, the fit between model #1 and the nonlinear interference #A on the terminal side is 0.8, or it means that model #1's processing capability for the nonlinear interference #A on the terminal side is 0.8; the fit between model #2 and the nonlinear interference #A on the terminal side is 0.17, or it means that model #1's processing capability for the nonlinear interference #A on the terminal side is 0.17, and so on.

[0186] Example 2: The first information can indicate the probabilities of K' second models and K' second models. When K' is 1, the first information indicates that the probability of the 1 second model is 0.8. For example, the probability of model #1 is 0.8, which means that the adaptability of model #1 to the nonlinear interference #A on the terminal side is 0.8, or that the processing capability of model #A to the nonlinear interference #A on the terminal side is 0.8.

[0187] Example 3: The first information can indicate the probabilities of K' second models and K' second models. When K' is 2, the first information can indicate that the probability of model #1 is 0.8 and the probability of model #3 is 0.76. This means that model #1 has a fit of 0.8 to the nonlinear interference #A on the terminal side, and model #3 has a fit of 0.76 to the nonlinear interference #A on the terminal side; or it means that model #1 has a processing capability of 0.8 to the nonlinear interference #A on the terminal side, and model #3 has a processing capability of 0.76 to the nonlinear interference #A on the terminal side. In this example, since the probabilities of model #1 and model #3 are relatively close, the network side can choose to calibrate the nonlinear interference #A using model #1, or it can choose to calibrate the nonlinear interference #A using both model #1 and model #3. In this case, the model probabilities can be used as weights for the calibration operation on the nonlinear interference #A. The specific implementation method can be found in the description in S530 below.

[0188] Among them, the probability of K' second models is greater than the probability of the remaining second models among N second models. That is, the model indicated by the first information has a higher degree of fit for the nonlinear disturbance #A compared to the other models.

[0189] S530, the network side determines K second models based on the first information.

[0190] K second models are used to calibrate the nonlinear disturbance #A. In one implementation, the second model can be an expert model. For an explanation of nonlinear disturbance calibration and expert models, please refer to the above introduction; it will not be repeated here.

[0191] The first information is used to indicate K second models out of N second models. Specifically, the first information can indicate the probabilities of K' second models and / or K' second models. Depending on the implementation of the first information, there are multiple ways for the network to determine the K second models based on the first information. The following sections describe in detail the different ways the network determines the K second models based on the first information.

[0192] Method 1: When the first information indicates K' second models, the network side determines K second models based on the K' second models.

[0193] When K' is 1, for example, the first information can indicate the second model identified as 0001. Then, the network side determines K second models based on the first information, namely the second model identified as 0001. At this time, the network side can use the second model identified as 0001 to calibrate the nonlinear interference #A.

[0194] When K' is 2, for example, if the first information indicates a second model identified as 0001 and a second model identified as 0002, the network can select one or more second models to calibrate the nonlinear interference #A according to predefined rules. For example, if the predefined rule is that the two models indicated by the first information are sorted from high to low according to their fit, then the network determines K second models as: the second model identified as 0001. As another example, if the predefined rule is that both models indicated by the first information are used to calibrate the nonlinear interference #A, then the network uses the second models identified as 0001 and 0002 to calibrate the nonlinear interference.

[0195] It should be understood that in this approach, some of the K' second models may not belong to the N second models. In this case, the network side can choose the intersection of the K' second models and the N second models as the K second models.

[0196] Method 2: When the first information indicates the probabilities of K' second models, the network side determines K second models based on the probabilities of K' second models.

[0197] In one implementation, the network side can select the second model with the highest probability to calibrate the nonlinear interference #A. For example, when the network side includes 5 second models (N equals 5), and the first information indicates that the probabilities of the 5 second models are [0.8, 0.17, 0.76, 0.95, 0.20], the network side can select the second model with the fourth model corresponding to model 0004 to calibrate the nonlinear interference #A.

[0198] In another implementation, the network can calibrate the nonlinear interference #A based on K second models with probabilities greater than or equal to a certain threshold. For example, when the threshold is 0.8, the network can calibrate the nonlinear interference #A based on a second model with a probability of 0.8 and a second model with a probability of 0.95. Specifically, the probabilities can be used as weights to calibrate the nonlinear interference. For example, the probabilities of the two second models can be normalized and used as weights to calibrate the nonlinear interference #A based on the two second models.

[0199] Method 3: When the first information indicates the probabilities of K' second models and K' second models, the network side determines K second models based on the probabilities of K' second models and K' second models.

[0200] When K' is 1, for example, the first information can indicate that the second model identified as 0001 and the probability of the second model identified as 0001 is 0.8. Then, the network side determines K second models based on the first information, namely the second model identified as 0001. At this time, the network side can use the second model identified as 0001 to calibrate the nonlinear interference #A.

[0201] When K' is 2, for example, the first information can indicate that the second model identified as 0001 has a probability of 0.8 and the second model identified as 0002 has a probability of 0.95, then the network can select one or more second models to calibrate the nonlinear interference #A according to predefined rules. For example, if the predefined rule is to select the second model with the highest probability to calibrate the nonlinear interference #A, then the network determines K second models as: the second model identified as 0001. Another example is that if the predefined rule is that the network can calibrate the nonlinear interference #A based on K second models with probabilities greater than or equal to a certain threshold, for example, when the threshold is 0.8, the network can calibrate the nonlinear interference #A based on the second model with a probability of 0.8 and the second model with a probability of 0.95. Specifically, probabilities can be used as weights to calibrate the nonlinear interference; for example, the probabilities of the two second models can be normalized and used as weights to calibrate the nonlinear interference #A.

[0202] It should be understood that in this approach, some of the K' second models may not belong to the N second models. In this case, the network side can choose the intersection of the K' second models and the N second models as the K second models.

[0203] The above describes how the network side can determine the second model for calibrating the nonlinear disturbance #A based on the first and second models. The training methods of the first and / or second models are described below.

[0204] Based on the embodiment provided by method 500, according to the first model and the nonlinear response, the terminal side can indicate K' second models applicable to its own nonlinear interference, and then the network side determines K second models for calibrating the nonlinear interference. In this way, targeted K second models can more accurately calibrate the nonlinear interference, eliminating the need for measurement steps based on reference signals, thereby reducing resource overhead and improving real-time performance. Furthermore, the N second models deployed on the network side can calibrate various types of nonlinear devices, which is easier to manage than setting multiple nonlinear interference compensation models on the network side, and also reduces system complexity.

[0205] Figure 7 This is a schematic diagram of the model training method provided in the embodiments of this application.

[0206] The first and / or second models can be trained using the distorted signals of different nonlinear disturbances and their corresponding original signals. That is, the first and / or second models use the distorted signals of different nonlinear disturbances and their corresponding original signals as training data. The first and / or second models can be trained using the distorted signals of different nonlinear disturbances and their corresponding original signals. Different nonlinear disturbances can be implemented in various ways, as illustrated in the examples below.

[0207] In one implementation, different nonlinear disturbances can include different nonlinear disturbance types. The second model is related to the type of nonlinear disturbance. In other words, each second model can correspond to one type of nonlinear disturbance. Specifically, for example, second model #1 (including second model #1.1, second model #1.2, ..., second model #1.n) can correspond to the nonlinear disturbance type clipping, second model #2 (including second model #2.1, second model #2.2, ..., second model #2.n) can correspond to the nonlinear disturbance type TWTA, and second model #3 (including second model #3.1, second model #3.2, ..., second model #3.n) can correspond to the nonlinear disturbance type SSPA.

[0208] In another implementation, different nonlinear interferences can include nonlinear interferences generated by different types of nonlinear interference devices. The second model is related to the type of nonlinear device. In other words, each second model can correspond to a type of nonlinear interference device. Specifically, for example, second model #1 (including second model #1.1, second model #1.2, ..., second model #1.n) can correspond to a high-power amplifier as the nonlinear interference device type, second model #2 (including second model #2.1, second model #2.2, ..., second model #2.n) can correspond to a traveling wave tube (TWT) as the nonlinear interference device type, and second model #3 (including second model #3.1, second model #3.2, ..., second model #3.n) can correspond to transistors as the nonlinear interference device type.

[0209] In the above implementation, different nonlinear interferences can refer to different types of nonlinear interferences, or to nonlinear interferences generated by different nonlinear devices. As the communication environment changes, different nonlinear interferences can also be classified in other ways, and this application does not limit this.

[0210] In another implementation, the different nonlinear disturbances can also include nonlinear disturbances of different degrees. That is, each second model can also train multiple second models of different degrees (or levels) based on the different degrees of nonlinear disturbances associated with that second model.

[0211] Taking the correlation between the second model and the type of nonlinear interference as an example, for instance, the second model #1 is related to clipping, the second model #2 is related to TWTA, and the second model #3 is related to SSPA.

[0212] The second model #1 may include multiple second models #1 for different degrees of clipping. These multiple second models #1 can be second model #1.1, second model #1.2, ..., second model #1.n. In one implementation, the different degrees of clipping nonlinear interference can be determined based on a shear threshold, as shown in the following formula.

[0213]

[0214] Among them, f clip (x n ,Ψ cr ) can represent nonlinear interference signals, x n Represents the original signal, Ψ cr Indicates the shear threshold. This means that if the value exceeds this threshold, it will be clipped.

[0215] The second model #2 may include multiple second models #2 for different degrees of TWTA type. The multiple second models #2 can be second model #2.1, second model #2.2, ..., second model #2.n. In one implementation, the nonlinear disturbance of different degrees of TWTA type can be determined according to the nonlinear characteristic coefficient, as shown in the following formula.

[0216] f TWTA (x n ) = x n +ηx n |x n | 2

[0217] Among them, f TWTA (x n ) can represent nonlinear interference signals, x n Let η represent the original signal and η represent the nonlinear characteristic coefficient.

[0218] The third model #3 may include multiple second models #3 for different degrees of SSPA type. The multiple second models #3 may be second model #3.1, second model #3.2, ..., second model #3.n. In one implementation, the nonlinear disturbance of different degrees of SSPA type can be determined according to the nonlinear intensity, as shown in the following formula.

[0219]

[0220] Among them, f SSPA (x n ) can represent nonlinear interference signals, x n Let ξ represent the original signal, and ξ represent the nonlinear intensity.

[0221] The above, combined with Figures 5-7 This application introduces a model management method for nonlinear interference calibration provided by an embodiment. The following section combines... Figure 8 Introduction based on Figure 5 The specific procedure for nonlinear interference calibration is described.

[0222] Figure 8 This is a schematic flowchart of the communication method 800 provided in the embodiments of this application. Figure 8 The method shown illustrates the flow of method 800 from the perspective of interaction between the terminal side and the network side. More detailed explanations regarding the terminal side and the network side can be found above and will not be repeated here.

[0223] Method 800 may include S802, S803, S804, S810, S820, S830, S831, and S832. Optionally, method 800 may also include S801, S832, and S833.

[0224] S802, the terminal side sends capability information, and correspondingly, the network side receives capability information.

[0225] Among them, capability information can indicate whether the first model is supported.

[0226] For example, the terminal sends capability information to the network, indicating that it supports a first model; based on this capability information, the network determines the measurement configuration for sending nonlinear interference to the terminal. As another example, the terminal sends capability information to the network, indicating that it does not support the first model; based on this capability information, the network determines the measurement configuration for not sending nonlinear interference to the terminal.

[0227] As an example, capability information can be implemented using at least one bit. For instance, capability information can be implemented using 1 bit. For example, if the 1-bit value is a first value, it indicates that the terminal supports the first model; if the 1-bit value is a second value, it indicates that the terminal does not support the first model. The first and second values ​​are different; for example, the first value is "0" and the second value is "1"; or, the first value is "1" and the second value is "0".

[0228] Optionally, prior to S802, method 800 may further include S801, whereby the network side sends first model confirmation configuration information, and correspondingly, the terminal side receives the first model confirmation configuration information. The first model confirmation configuration information is used to inquire whether the terminal side supports the first model.

[0229] S803, the network side sends nonlinear interference measurement configuration information, and correspondingly, the terminal side receives the nonlinear interference measurement configuration information.

[0230] S804, the nonlinear response is obtained by measurement on the terminal side.

[0231] S810 uses the first model to infer the nonlinear response and obtain the first information.

[0232] In S820, the terminal sends the first information, and correspondingly, the network receives the first information.

[0233] S830, the network side determines K second models based on the first information.

[0234] S831 calibrates nonlinear disturbances using K second models.

[0235] S832, the network side sends second information, and correspondingly, the terminal side receives the second information. The second information indicates calibration information, which is obtained by calibrating the nonlinear interference using the K second models. This calibration information is used by the terminal side to adjust the power of the nonlinear devices.

[0236] Optionally, method 800 also includes S832, whereby the terminal side adjusts the power of the nonlinear device based on the second information.

[0237] Optionally, method 800 further includes S833, whereby the terminal side transmits data information based on the power of the nonlinear device, and correspondingly, the network side receives the data information.

[0238] The above method 800 provides a method for nonlinear interference calibration. The specific implementation can be found in method 500, and will not be repeated here. The following section combines... Figure 9 This application introduces another method for nonlinear interference calibration.

[0239] Figure 9 This is a schematic flowchart of another communication method 900 provided in an embodiment of this application. Figure 9 The method shown illustrates the flow of method 900 from the perspective of interaction between the terminal side and the network side. More detailed explanations regarding the terminal side and the network side can be found above and will not be repeated here. Figure 9 The methods shown include S910 and S920.

[0240] S910, the terminal side sends third information, and the network side receives the third information accordingly. The third information indicates the type of nonlinear device.

[0241] There are many types of nonlinear devices, and the classification methods can include: classifying nonlinear devices into different types according to the manufacturer, device type, and degree of nonlinearity.

[0242] The degree of nonlinearity can also be referred to as the nonlinearity level, and this application does not limit the name.

[0243] In one implementation, the type of nonlinear device can be represented by an identifier (ID), which can also be called a serial number, number, etc.

[0244] For example, as shown in Table 1 below, the type of nonlinear device from manufacturer #1, with device type α and nonlinear level 1, can correspond to 1.1.1; the type of nonlinear device from manufacturer #1, with device type α and nonlinear level 2, can correspond to 1.1.2.

[0245] Table 1

[0246] Nonlinear device manufacturers Device type nonlinear level ID A α level 1-10 1.1.1-1.1.n B β level 1-10 2.1.1-2.1.n C γ level 1-10 3.1.1-3.1.n …… …… …… ……

[0247] Among them, device types α, β, and γ can be various types of high-power amplifiers (HPA), optoelectronic nonlinear devices, nonlinear filters, etc.

[0248] The degree of nonlinearity (level) can be classified according to the nonlinearity parameters provided by the manufacturer.

[0249] It should be understood that the classification of nonlinear device types is merely an example, and can also be understood as each nonlinear device corresponding to a unique ID. It should also be understood that with technological advancements, there may be many other types of nonlinear devices, which are not fully listed here.

[0250] The type of nonlinear device is related to the second model. In other words, each nonlinear device can correspond to one or more second models.

[0251] The second model is used to calibrate nonlinear disturbances. For details on the function and training method of the second model, please refer to Method 500; it will not be elaborated upon here.

[0252] In one implementation, a nonlinear device can correspond to a second model. The nonlinear device type #1 (manufacturer A, device type is TWTA, nonlinear level is 1) corresponds to ID 1.2.1, and the associated second model is second model #2.1 (nonlinear interference type is TWTA, nonlinear level is 1).

[0253] In another implementation, a nonlinear device can correspond to multiple second models. For example, a nonlinear device can correspond to two second models. For instance, nonlinear device type #1 (manufacturer A, device type is TWTA, nonlinear level is 1) corresponds to ID 1.2.1, and the associated second model can be second model #2.1 and second model #2.2.

[0254] S920, the network side determines the second model based on third information.

[0255] In one implementation, the third information indicates a nonlinear device that is associated with the second model, and the second model can be determined based on the nonlinear device.

[0256] For example, the third information indicates that the ID of the nonlinear device is 1.2.1, and the corresponding second model is second model #2.1.

[0257] For example, the third information indicates that the ID of the nonlinear device is 1.2.1, which can correspond to the second model as second model #2.1 and second model #2.2.

[0258] Optionally, the method 900 may further include calibrating the nonlinear disturbance using a second model to obtain calibration information (or, as may be called, a calibration report).

[0259] Furthermore, method 900 may also include the network side sending second information, and correspondingly, the terminal side receiving the second information. The second information indicates calibration information. The calibration information can be used to adjust the power of the nonlinear device.

[0260] Optionally, method 900 may further include adjusting the power of the nonlinear device on the terminal side based on the second information. Then, the terminal side can transmit data at the adjusted power.

[0261] Based on the embodiments provided by method 900, according to the association between the nonlinear device type and the second model, the terminal side can indicate its own nonlinear device type, and then the network side can determine the second model for calibrating nonlinear interference. In this way, the targeted second model can calibrate nonlinear interference more accurately, eliminating the need for the measurement step of nonlinear interference, thereby reducing resource overhead and improving real-time performance.

[0262] Figure 10 This is a schematic flowchart of the communication method 1000 provided in the embodiments of this application. Figure 10 The method shown provides an interaction method for the Open RAN architecture. The flow of this method 1000 is illustrated from the perspectives of multiple terminal sides, multiple network sides, and OAM interactions. More detailed explanations regarding the terminal side, network side, and OAM can be found above and will not be repeated here. Figure 10 The provided embodiments mainly use the interaction between OAM, RAN node 1, RAN node 2, RAN node 3 and UE1, UE2, UE3 as an example for description. Method 1000 includes S1001, S1002, S1010, S1020, and S1030. Optionally, method 1000 may also include S1021 and S1031.

[0263] S1001, the RAN node sends the nonlinear measurement configuration, and the UE receives the nonlinear measurement configuration accordingly.

[0264] In one implementation, the RAN node can send nonlinear measurement configuration to the UE in its cell. For example, if UE1 is in the cell where RAN node 1 is located, RAN node 1 sends nonlinear measurement configuration to UE1; if UE2 is in the cell where RAN node 2 is located, RAN node 2 sends nonlinear measurement configuration to UE2; if UE3 is in the cell where RAN node 3 is located, RAN node 3 sends nonlinear measurement configuration to UE3.

[0265] It should be understood that this example only uses the RAN node managing one UE, but the RAN node can also send nonlinear measurement configurations to multiple UEs.

[0266] S1002, the UE performs a measurement to obtain a nonlinear response, or, as can be called, the UE measures a nonlinear response. This nonlinear response can indicate the nonlinear interference of the UE. For example, UE1 performs a measurement according to a nonlinear measurement configuration, and the obtained nonlinear response can reflect the nonlinear interference of UE1.

[0267] The nonlinear interference of different UEs may be different. For example, the nonlinear interference of UE1 is nonlinear interference #1, the nonlinear interference of UE2 is nonlinear interference #2, and the nonlinear interference of UE3 is nonlinear interference #3. Nonlinear interference #1, nonlinear interference #2 and nonlinear interference #3 may be the same, may be partially the same, or may be completely different.

[0268] S1010, the UE infers the nonlinear response through the first model and obtains the first information.

[0269] S1020, the UE sends first information, and correspondingly, the RAN node receives the first information. The first information indicates K of the N second models, which are used to calibrate nonlinear interference. Specifically, the first information indicates K' second models, which include the K second models.

[0270] For example, UE1 sends a first message, and RAN node 1 receives the first message accordingly, which indicates K' second models; UE2 sends a first message, and RAN node 2 receives the first message accordingly, which indicates K' second models; UE3 sends a first message, and RAN node 3 receives the first message accordingly, which indicates K' second models.

[0271] It should be understood that the aforementioned first information is used by the RAN node to determine K second models. Different UEs may generate different nonlinear interferences, and therefore, the corresponding first information will also be different.

[0272] S1030, RAN nodes determine K second models.

[0273] In one implementation, N second models are deployed in RAN nodes. The RAN nodes determine the second models based on the first information. For example, UE1 sends the first information, RAN node 1 receives the first information, and RAN node 1 determines the second model #1 based on the first information; UE2 sends the first information, RAN node 2 receives the first information, and RAN node 2 determines the second model #2 based on the first information; UE3 sends the first information, RAN node 3 receives the first information, and RAN node 3 determines the second model #3 based on the first information.

[0274] In another implementation, method 1000 may optionally include steps S1021 and S1031. In S1021, the RAN node sends first information to the OAM, and the corresponding OAM receives the first information. In this implementation, N second models are deployed in the OAM, and the OAM determines K second models based on the first information. In S1031, the OAM sends the model weights of the K second models, and correspondingly, the RAN node receives the model weights of the K second models. At this point, step S1030 obtains the weights of the K second models, thus determining the second models.

[0275] S1032, the RAN node performs nonlinear interference calibration. Specifically, the RAN node calibrates the nonlinear interference using K second models.

[0276] Optionally, method 1000 may further include: the RAN node calibrating the nonlinear interference using K second models; the RAN node sending a nonlinear calibration report to the UE; and the UE adjusting the power of the nonlinear device according to the nonlinear calibration report.

[0277] It should be understood that for the parts of this method not described in detail in method 1000, please refer to method 500, which will not be repeated here.

[0278] Method 1000 describes the specific implementation of the method provided in this application within an open RAN architecture. It can be seen that the method provided in this application can centrally manage the nonlinear interference calibration model deployed at the RAN node or OAM. By having the UE measure its own nonlinear response and the first model, it provides nonlinear interference information to the RAN node or OAM. Subsequently, the RAN node or OAM can determine a targeted second model to calibrate the UE's nonlinear interference. The method of this application not only improves the accuracy of nonlinear interference calibration but also eliminates the step of measuring nonlinear interference based on reference information, thereby avoiding the superposition error between channel estimation and nonlinear estimation, and reducing the measurement overhead of reference information. Furthermore, the second model provided by the method of this application is centrally deployed at the RAN node or OAM, facilitating management.

[0279] It should be understood that in the various embodiments shown above in conjunction with the accompanying drawings, the sequence number of each step does not imply the order of execution. The execution order of each step should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0280] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0281] In the above embodiments, exemplary descriptions are mainly based on devices in the current network architecture (such as terminal devices, network devices, OTT system servers, intelligent network elements, etc.). The specific form of the devices is not limited in the embodiments of this application. For example, devices that can achieve the same function in the future can also be applied to the methods provided in the embodiments of this application.

[0282] It is understood that in the above-described method embodiments, the methods and operations implemented by a device (such as a terminal device or a network device) can also be implemented by components of the device (such as chips or circuits). They can also be executed by devices or components deployed outside the terminal device or network device. For example, they can be executed by devices deployed outside the terminal device (such as the host or cloud server of an OTT system) or by components within the device (such as chips, processors, or circuits inside the device); or, for another example, they can be executed by devices outside the network device (such as intelligent network elements) or by components within the device (such as chips, processors, or circuits inside the device).

[0283] The above combination Figures 5 to 10 Methods 500, 800, 900, and 1000 are described below. The apparatus provided in the embodiments of this application will now be described with reference to the accompanying drawings.

[0284] Figure 11 and Figure 12 This is a schematic block diagram of possible apparatuses provided in the embodiments of this application. These apparatuses can be used to implement the functions on the terminal side or network side in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0285] Figure 11 This is a schematic block diagram of a communication device provided in an embodiment of this application. Figure 11 The device 1100 shown may include a processing module 1110 and a communication module 1120.

[0286] In one possible design, device 1100 can be used to implement Figures 5 to 10The communication method is implemented on the terminal side in any of the embodiments shown. For example, the processing module 1110 is used to implement the model inference steps executed on the terminal side in each method embodiment, such as inferring the nonlinear response through the first model to obtain the first information; the communication module 1120 is used to implement the sending and / or receiving steps executed on the terminal side in each method embodiment, such as sending the first information.

[0287] For example, the processing module 1110 infers the nonlinear response using a first model to obtain first information. The communication module 1120 can be used to send the first information.

[0288] Optionally, the communication module 1120 can be used to receive second information, which indicates calibration information.

[0289] Optionally, the communication module 1120 can be used to send capability information indicating support for the first model.

[0290] For example, the communication module 1120 can be used to send third information, which indicates the type of nonlinear device.

[0291] Optionally, the communication module 1120 can be used to receive second information, which indicates calibration information.

[0292] For a more detailed description of the processing module 1110 and the communication module 1120 mentioned above, please refer to [link / reference]. Figures 5 to 10 The relevant descriptions in the method embodiments shown are directly obtained and will not be repeated here.

[0293] In another possible design, device 1100 can be used to achieve Figures 5 to 10 The communication method is implemented by the network side in any of the embodiments shown. For example, the processing module 1110 is used to implement the steps related to inference and training of the second model executed by the network side in each method embodiment; the communication module 1120 is used to implement the sending and / or receiving steps executed by the network side in each method embodiment, such as receiving first information, sending second information, etc.

[0294] For example, the communication module 1120 can be used to receive first information, which indicates K second models out of N second models; the processing module 1110 can be used to determine K second models based on the first information.

[0295] Optionally, the processing module 1110 can be used to determine K second models based on K' second models and / or the probabilities of K' second models.

[0296] Optionally, the communication module 1120 can be used to send a second message indicating calibration information.

[0297] Optionally, the communication module 1120 can be used to receive capability information indicating support for the first model.

[0298] For example, third information is received, indicating the type of nonlinear device. A second model is determined based on the third information.

[0299] Optionally, the communication module 1120 can be used to send a second message indicating calibration information.

[0300] For a more detailed description of the processing module 1110 and the communication module 1120 mentioned above, please refer to [link / reference]. Figures 5 to 10 The relevant descriptions in the method embodiments shown are directly obtained and will not be repeated here.

[0301] It should be noted that the communication module can also be called a transceiver module, transceiver unit, transceiver, transceiver device, or transceiver apparatus, etc. The processing module can also be called a processor, processing board, processing unit, or processing apparatus, etc. Optionally, the communication module is used to execute the sending and receiving operations of the first or second communication device in the above method. The device in the communication module that implements the receiving function can be considered as the receiving module, and the device in the communication module that implements the sending function can be considered as the sending module; that is, the communication module can include both a receiving module and a sending module.

[0302] It should also be noted that, in one possible design, the aforementioned processing module and / or communication module can be implemented through virtual modules. For example, the processing module can be implemented through software functional units or virtual devices, and the communication module can be implemented through software functions or virtual devices. In another possible design, the processing module or communication module can also be implemented through physical devices. For example, if the device is implemented using a chip / chip circuit, the communication module can be an input / output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operation) and output operations (corresponding to the aforementioned sending operation); the processing module can be an integrated processor, a microprocessor, or an integrated circuit.

[0303] The module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional modules in the various examples of this embodiment can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0304] Figure 12 This is a schematic diagram of another communication device provided in an embodiment of this application. Figure 12As shown, the device 1200 includes a processing circuit 1210 and a communication circuit 1220. The processing circuit 1210 and the communication circuit 1220 are coupled to each other.

[0305] It can be understood that the processing circuit 1210 can be one or more processors, or it can be all or part of the processing functions of one or more processors.

[0306] It is understandable that the communication circuit 1220 can be a transceiver or an input / output interface.

[0307] Optionally, the device 1200 may further include a memory 1230 for storing instructions executed by the processing circuit 1210, or storing input data required for the running instructions of the processing circuit 1210, or storing data generated after the running instructions of the processing circuit 1210.

[0308] It is understood that the memory 1230 may be located outside the processing circuit 1210 or inside the processing circuit 1210.

[0309] As an example, the processing circuit 1210 is used to implement the functions of the processing module 1110, and the communication circuit 1220 is used to implement the functions of the communication module 1120.

[0310] As an example, device 1200 can be a communication device or a chip used in a communication device.

[0311] When device 1200 is a communication device, the communication circuit can be a transceiver; when device 1200 is a chip, the communication circuit can be an input / output circuit, a bus, pins, or other types of communication interfaces. The input circuit in the input / output circuit can be used for receiving, and the output interface can be used for transmitting.

[0312] For example, one possible implementation of a processor for AI could be... Figure 12 The AI ​​processor 1200 shown. Figure 12 This is a schematic diagram of the structure of the AI ​​processor provided in the embodiments of this application.

[0313] Figure 13 This is a schematic diagram of the structure of an AI processor provided in an embodiment of this application. Figure 13As shown, the AI ​​processor 1300 may include one or more of the following: an AI core, a digital vision pre-processing (DVPP) module, a task scheduler (TS), an L3 cache, an AI CPU, a control CPU, an L2 cache, a universal serial bus (USB) interface, a network interface card (NIC), a peripheral component interconnect express (PCIe) interface (PCIe is a high-speed serial computer expansion bus standard), a double data rate (DDR) / high bandwidth memory (HBM) interface, a general purpose input / output (GPIO) / inter-integrated circuit (I2C) bus, etc. It is understood that the specific meanings of these terms are well known to those skilled in the art and will not be elaborated upon here.

[0314] This application also provides a computer program product that, when run on a processor, can implement the communication method executed by the terminal side or the communication method executed by the network side in the above method embodiments.

[0315] This application also provides a computer-readable storage medium containing computer instructions that, when executed on a processor, can implement the communication method executed by the terminal side or the communication method executed by the network side in the above method embodiments.

[0316] This application also provides a communication system, including the aforementioned terminal side and network side. The terminal side can be used to implement the communication method implemented by the terminal side in the above method embodiments, and the network side can be used to implement the communication method implemented by the network side in the above method embodiments.

[0317] It is understood that the processor in the embodiments of this application can be any of the following devices or all or part of the circuitry of the following devices used for processing functions: a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), graphics processing units (GPUs), neural network processing units (NPUs), artificial intelligence processors, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, any conventional processor, or one or more integrated circuits used to control the execution of a program for controlling the method provided in any of the above embodiments. The memory mentioned above can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM), etc. Some or all steps of the communication method in the embodiments of this application can be implemented by a GPU, AI processor, or NPU, or by a GPU, AI processor, or NPU in conjunction with other processors.

[0318] The terms “unit”, “module”, etc., used in this specification may be used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution.

[0319] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0320] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0321] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, 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 coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0322] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0323] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0324] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0325] 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 in that, include: The nonlinear response is inferred using a first model to obtain first information, which indicates nonlinear interference. The first information is used to indicate K second models out of N second models, which are used to calibrate the nonlinear interference. Here, K and N are both positive integers, and K is less than or equal to N. Send the first message.

2. The method according to claim 1, characterized in that, The first information indicates the probabilities of K' second models and / or the K' second models, wherein the probability of one of the K' second models is related to the degree of adaptation of the one second model to the nonlinear disturbance, the probability of the K' second models is greater than the probability of the remaining second models among the N second models, and the K' second models include the K second models.

3. The method according to claim 1 or 2, characterized in that, After sending the first information, the method further includes: Receive second information, the second information indicating calibration information, the calibration information being obtained by calibrating the nonlinear interference using the K second models, the calibration information being used to adjust the power of the nonlinear device.

4. The method according to any one of claims 1 to 3, characterized in that, The second model and / or the first model are obtained by training on the distorted signals of different nonlinear disturbances and the corresponding original signals.

5. The method according to any one of claims 1 to 4, characterized in that, The second model is related to the type of nonlinear disturbance.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Send capability information, which indicates support for the first model.

7. A communication method, characterized in that, include: A third message is sent, indicating the type of nonlinear device, which is associated with a second model used to calibrate nonlinear interference.

8. The method according to claim 7, characterized in that, After sending the third information, the method further includes: The system receives second information, which indicates calibration information. The calibration information is obtained by calibrating the nonlinear interference using the second model, and is used to adjust the power of the nonlinear device.

9. The method according to claim 7 or 8, characterized in that, The second model is obtained by training on the distorted signals of different nonlinear disturbances and the corresponding original signals.

10. A communication method, characterized in that, include: Receive first information, which is obtained by reasoning the nonlinear response through a first model. The nonlinear response indicates nonlinear interference. The first information is used to indicate K of the N second models. The second models are used to calibrate the nonlinear interference. Here, K and N are both positive integers, and K is less than or equal to N. The K second models are determined based on the first information.

11. The method according to claim 10, characterized in that, The first information indicates the probabilities of K' second models and / or the K' second models, wherein the probability of one of the K' second models is related to the degree of adaptation of the one second model to the nonlinear disturbance, the probability of the K' second models is greater than the probability of the remaining second models among the N second models, and the K' second models include the K second models.

12. The method according to claim 11, characterized in that, Based on the first information, the K second models are determined, including: The K second models are determined based on the K' second models and / or the probabilities of the K' second models.

13. The method according to any one of claims 10 to 12, characterized in that, The method further includes: Send a second message, which indicates calibration information. The calibration information is obtained by calibrating the nonlinear interference using the K second models. The calibration information is used to adjust the power of the nonlinear device.

14. The method according to any one of claims 10 to 13, characterized in that, The second model and / or the first model are obtained by training the distorted signals of the nonlinear interference of different degrees with the corresponding original signals.

15. The method according to any one of claims 10 to 14, characterized in that, The second model is related to the type of nonlinear disturbance.

16. The method according to any one of claims 10 to 15, characterized in that, The method further includes: Receive capability information, which indicates support for the first model.

17. A communication method, characterized in that, include: Receive third information, the third information indicating the type of nonlinear device, the type of nonlinear device being associated with a second model, the second model being used to calibrate nonlinear interference; The second model is determined based on the third information.

18. The method according to claim 17, characterized in that, The method further includes: A second message is sent, which indicates calibration information. The calibration information is obtained by calibrating the nonlinear interference using the second model, and the calibration information is used to adjust the power of the nonlinear device.

19. The method according to claim 17 or 18, characterized in that, The second model is obtained by training on the distorted signals of different nonlinear disturbances and the corresponding original signals.

20. The method according to any one of claims 1 to 19, characterized in that, The first model is a routing model, and the second model is an expert model.

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 configured to cause the communication device to perform the method of any one of claims 1 to 20.

23. 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 as described in any one of claims 1 to 20.

24. A computer program product, characterized in that, The computer program product includes a computer program or instructions that, when executed on a communication device, cause the communication device to perform the method as described in any one of claims 1 to 20.

Images