Model processing method and device, communication equipment and storage medium

Abstract

The invention discloses a model processing method and device, communication equipment and a storage medium, and belongs to the technical field of communication, and the model processing method comprises the steps that first communication equipment receives first information from second communication equipment, the first information is used for model processing of a first model, and the first model is deployed on the first communication equipment side; a second model is deployed on the second communication equipment side; and the first communication device performs model processing on the first model according to the first information.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to a model processing method, apparatus, communication equipment, and storage medium. Background Technology

[0002] In wireless communication systems, if the power amplifier (PA) at the transmitter enters the saturation region, nonlinear distortion will occur, causing the transmitted signal to become distorted. To improve the system's nonlinear distortion, power back-off can be implemented to prevent the power amplifier from entering the saturation region. Although the power back-off mechanism can reduce signal nonlinear distortion, it reduces the transmitter's transmit power, resulting in lower power amplifier efficiency and limited network coverage. Summary of the Invention

[0003] This application provides a model processing method, apparatus, communication device, and storage medium, which solves the problems of low power amplifier efficiency and limited network coverage caused by power back-off in related technologies.

[0004] Firstly, a model processing method is provided, including:

[0005] The first communication device receives first information from the second communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

[0006] The first communication device performs model processing on the first model based on the first information.

[0007] Secondly, a model processing method is provided, including:

[0008] The second communication device sends first information to the first communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

[0009] Thirdly, a model processing apparatus is provided, comprising:

[0010] A first receiving module is configured to receive first information from a second communication device. The first information is used for model processing of a first model. The first model is deployed on the first communication device side, and a second model is deployed on the second communication device side.

[0011] The first processing module is used to perform model processing on the first model based on the first information.

[0012] Fourthly, a model processing apparatus is provided, comprising:

[0013] The third sending module is used to send first information to the first communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

[0014] Fifthly, a model processing apparatus is provided, the apparatus being configured to perform the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect.

[0015] In a sixth aspect, a communication device is provided, the communication device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect, or implementing the steps of the method as described in the second aspect.

[0016] In a seventh aspect, a communication device is provided, including a processor and a communication interface, wherein the processor is used to run programs or instructions to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect, and the communication interface is used to couple with the processor.

[0017] In an eighth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method as described in the first aspect, or implement the steps of the method as described in the second aspect.

[0018] A ninth aspect provides a wireless communication system, comprising: a terminal and a network-side device, wherein the terminal is configured to perform the steps of the method as described in the first aspect, and the network-side device is configured to perform the steps of the method as described in the second aspect.

[0019] In a tenth aspect, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the method as described in the second aspect, and the terminal can be used to perform the steps of the method as described in the first aspect.

[0020] Eleventhly, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being used to run programs or instructions to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect.

[0021] In a twelfth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect.

[0022] In this embodiment of the application, a first model is deployed on the first communication device side and a second model is deployed on the second communication device side. The first communication device receives first information from the second communication device and performs model processing on the first model based on the first information. The combination of the first model and the second model can compensate for the nonlinear distortion of the power amplifier at the transmitter end, reduce the power back-off of the power amplifier, increase the transmission power of the transmitter, improve the efficiency of the power amplifier, and enhance network coverage. Attached Figure Description

[0023] Figure 1 This is a block diagram of a wireless communication system applicable to embodiments of this application;

[0024] Figure 2 This is a schematic diagram of a neural network in a related technology;

[0025] Figure 3 This is a schematic diagram of a neuron in a related technology;

[0026] Figure 4 This is a block diagram of a digital predistortion principle in related technologies;

[0027] Figure 5 This is a flowchart illustrating the implementation of a model processing method in an embodiment of this application.

[0028] Figure 6 This is a schematic diagram illustrating the processing of nonlinear distortion based on an AI model in an embodiment of this application;

[0029] Figure 7 This is a flowchart illustrating another model processing method implemented in this application.

[0030] Figure 8 In the embodiments of this application, and Figure 5 A schematic diagram of the corresponding model processing device;

[0031] Figure 9 In the embodiments of this application, and Figure 7 A schematic diagram of the corresponding model processing device;

[0032] Figure 10 This is a schematic diagram of the structure of a communication device according to an embodiment of this application;

[0033] Figure 11 This is a schematic diagram of the structure of a terminal in an embodiment of this application;

[0034] Figure 12 This is a schematic diagram of the structure of a network-side device according to an embodiment of this application;

[0035] Figure 13 This is a schematic diagram of the structure of another network-side device in an embodiment of this application. Detailed Implementation

[0036] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0037] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0038] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0039] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0040] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home devices (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game consoles, personal computers (PCs), ATMs, or self-service machines, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (AS), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0041] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized Network Configuration (CNC), and Network Storage Function (Network). The core network functions include Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), Binding Support Function (BSF), Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), and Network Data Analytics Function (NWDAF). It should be noted that this application only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0042] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0043] To facilitate understanding, the relevant technologies and concepts involved in the embodiments of this application will be introduced first.

[0044] I. Artificial Intelligence (AI)

[0045] Artificial intelligence (AI) has wide applications in various fields such as communications, healthcare, and education. Integrating AI into wireless communication networks to improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks. AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application's embodiments mainly use a neural network as an example for illustration, but this does not constitute a limitation on the specific type of AI module.

[0046] Figure 2 The diagram shown illustrates a neural network, which includes an input layer (X1, X2, ..., X...). n The neural network consists of three layers: a hidden layer (Y), ... and an output layer (Y). A neural network is composed of neurons, and a schematic diagram of a neuron is shown below. Figure 3 As shown, where:

[0047] z = a1w1 + ... + a k w k +…+a K w K +b;

[0048] Among them, a1, a2, ..., a k ... a K The input is w, where w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include the sigmoid function, the hyperbolic tangent function, and the rectified linear unit (ReLU) (or linear rectified function).

[0049] The parameters of a neural network are optimized using gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (or loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). After obtaining the neural network model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. The goal is to find suitable W and b to minimize the value of the loss function. The smaller the loss value, the closer the prediction result of the neural network model is to the reality.

[0050] Most common optimization algorithms are based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two parts: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error to all units in each layer, thus obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is repeated continuously. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.

[0051] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (named after the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), adaptive learning rate adjustment (Adadelta), root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0052] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0053] II. AI Units / AI Models

[0054] In this application embodiment, AI unit / AI model may also be referred to as AI unit, AI model, AI module, machine learning (ML) model, ML unit, ML module, AI structure, AI function, AI characteristic, neural network, neural network function, neural network functionality, etc. Alternatively, AI unit / AI model may also refer to a processing unit or processing module capable of implementing specific algorithms, formulas, processing flows, capabilities, etc. related to AI. Alternatively, AI unit / AI model may be a processing method, algorithm, function, characteristic, module, or unit for a specific dataset. Alternatively, AI unit / AI model may be a processing method, algorithm, function, characteristic, module, or unit running on AI / ML related hardware such as Graphics Processing Unit (GPU), Neural Processing Unit (NPU), Tensor Processing Unit (TPU), or Application-Specific Integrated Circuit (ASIC). This application embodiment does not specifically limit this. Optionally, the specific dataset includes the input or output of the AI ​​unit / AI model.

[0055] Optionally, the identifier of an AI unit / AI model can be understood as an AI unit identifier, AI model identifier, AI module identifier, AI structure identifier, AI algorithm identifier, or the identifier of a specific dataset associated with an AI unit / AI model, or the identifier of a specific scenario, environment, region, cell, channel characteristics, or device related to AI / ML, or the identifier of a function, characteristic, capability, or module related to AI / ML. This application embodiment does not specifically limit this.

[0056] III. Techniques to Counteract Power Amplifier (PA) Nonlinearity

[0057] In wireless communication systems, digital pre-distortion (DPD) of power amplifiers is a common technique. It aims to reduce the distortion of the output signal by introducing a nonlinear characteristic opposite to that of the amplifier. The basic principle of pre-distortion is to place a pre-distortion processing module before the power amplifier. The combined effect of the pre-distortion processing module and the power amplifier linearizes the overall input-output characteristics, ensuring full utilization of the output power. Its block diagram is shown below. Figure 4 As shown.

[0058] Where x(n) represents the system input signal, z(n) represents the system output signal, and y(n) represents the output of the predistortion processing module. Assuming the input-output transfer characteristic of the power amplifier is G() and the characteristic of the predistortion processing module is F(), then the predistortion processing principle can be expressed as:

[0059]

[0060] The composite function of g() and F() is equal to L().

[0061] Linearization requires L() to satisfy:

[0062] z(n) = L(x(n)) = g·x(n);

[0063] In the formula, the constant g is the ideal "amplitude gain" of the power amplifier (g>1).

[0064] At the receiver end, the principle of receiver compensation for nonlinearity differs from that of digital predistortion. It uses the equalized symbol X to estimate the nonlinear interference signal and feeds it back to the equalization calculation module to eliminate nonlinear distortion.

[0065] Using a digital predistortion algorithm module deployed at the transmitter end to combat the nonlinear distortion of the power amplifier places high demands on the transmitter's algorithm. In addition, the effect of deploying it at the receiver end to combat the nonlinear distortion of the power amplifier is limited.

[0066] IV. Radio Frequency Indicator Information

[0067] Radio frequency (RF) specifications may include at least one of the following:

[0068] Peak-to-average power ratio (PAPR) information;

[0069] Error Vector Magnitude (EVM) information;

[0070] Information on the Spectrum Emission Mask (SEM);

[0071] Adjacent Channel Leakage Ratio (ACLR) information.

[0072] The relevant technologies and concepts involved in the embodiments of this application have been introduced above. The model processing method provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0073] See Figure 5 The diagram shown is an implementation flowchart of a model processing method provided in this application embodiment. The method includes the following steps:

[0074] S510: The first communication device receives first information from the second communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

[0075] S520: The first communication device performs model processing on the first model based on the first information.

[0076] Applying the method provided in the embodiments of this application, a first model is deployed on the first communication device side and a second model is deployed on the second communication device side. The first communication device receives first information from the second communication device and performs model processing on the first model based on the first information. The combination of the first model and the second model can compensate for the nonlinear distortion of the power amplifier at the transmitter end, reduce the power back-off of the power amplifier, increase the transmission power of the transmitter, improve the efficiency of the power amplifier, and enhance network coverage.

[0077] In this embodiment of the application, the first communication device may be a terminal, such as... Figure 1 The terminal 11 shown can be a network-side device, such as... Figure 1 The network-side device 12 is shown. The terminal receives first information from the network-side device. The first information is used for model processing of a first model. The first model is deployed on the terminal side, and a second model is deployed on the network-side device side. The terminal performs model processing on the first model based on the first information.

[0078] Alternatively, the first communication device can be a network-side device, such as... Figure 1 The network-side device 12 shown can be a second communication device, such as a terminal. Figure 1 The terminal 11 shown. The network-side device receives first information from the terminal. The first information is used for model processing of a first model. The first model is deployed on the network-side device side, and a second model is deployed on the terminal side. The network-side device performs model processing on the first model according to the first information.

[0079] Model processing may include at least one of model training, model updating, and parameter updating.

[0080] In this application embodiment, AI models can be introduced into both the transmitter and receiver sides. In one scenario, such as a power amplifier nonlinearity scenario, deploying an AI model on the receiver side can compensate for the nonlinear distortion of the power amplifier, effectively addressing the problems caused by the nonlinear distortion of the power amplifier at the transmitter end, and helping to improve the efficiency of the transmitter's power amplifier. In another scenario, such as a smart transmitter scenario, deploying an AI model at the transmitter end can be used to implement modulation, filtering, and other related module functions at the transmitter end. In yet another scenario, such as a smart receiver scenario, deploying an AI model on the receiver side can be used to implement channel estimation, equalization, symbol detection, demapping, and other related module functions at the receiver end. In yet another scenario, such as a smart transceiver scenario, deploying AI models on both the transmitter and receiver sides can be used to implement constellation modulation / demodulation, filtering, symbol detection, and other related module functions at both the transmitter and receiver ends.

[0081] like Figure 6 As shown, this is a schematic diagram of processing nonlinear distortion based on an AI model. On the transmitter side, the signal generated by the data generator is transmitted after being processed by AI model 1, a digital to analog converter (DAC), and a power amplifier. On the receiver side, the received signal is processed by a low-noise amplifier (LNA), an analog to digital converter (ADC), and AI model 2 before reaching the data receiver.

[0082] In this embodiment, AI models are deployed on both the transmitter and receiver sides. The two models can be trained independently and jointly optimized. For example, the AI ​​model at the transmitter can be trained first, and after training, it is activated. The receiver collects data to train its own AI model. Alternatively, the two models can be trained and jointly optimized, such as training both models simultaneously, allowing the parameters of the AI ​​models at both the transmitter and receiver to be updated concurrently. Optionally, model processing of the first model, such as model training or model updating, follows model processing of the second model, such as model training or model updating. Optionally, parameter updates of the first model and parameter updates of the second model can be performed simultaneously.

[0083] In some embodiments of this application, when the first communication device is a terminal and the second communication device is a network-side device, the first information may include at least one of the following:

[0084] The first instruction information is used to instruct the first communication device to start model training or start model updating;

[0085] The second instruction information is used to indicate when the first communication device should collect data;

[0086] The third indication information is used to indicate the data error range of the second communication device;

[0087] The fourth indication information is used to indicate the tag information for the data transmitted by the second communication device;

[0088] The fifth instruction information is used to indicate information about the first model;

[0089] The sixth indication information is used to indicate the data transmission indicators of the second communication device.

[0090] The seventh indication information is used to indicate the parameter information for data transmission.

[0091] In this embodiment, the first communication device can be a terminal, and the second communication device can be a network-side device. In downlink transmission, the transmitter-side model, such as the second model, is deployed on the network-side device side, and the receiver-side model, such as the first model, is deployed on the terminal side.

[0092] Optionally, the second communication device may train the second model first, and then instruct the first communication device to train the first model. Optionally, after completing model training or updating of the second model, the second communication device may send first information to the first communication device, which receives the first information from the second communication device and performs model processing on the first model based on the first information. The data required by the second communication device for model training or updating the second model may be obtained spontaneously by the second communication device.

[0093] The first information received by the first communication device from the second communication device is used for model processing of the first model. Optionally, the first information may include at least one of the following:

[0094] 1) First instruction information, which is used to instruct the first communication device to start model training or model update. Based on the first instruction information, the first communication device can start model training or model update of the first model.

[0095] 2) Second indication information, which is used to indicate when the first communication device should collect data. The first communication device collects data based on the second indication information in order to train or update the model based on the collected data.

[0096] 3) Third indication information: This third indication information is used to indicate the data error range of the second communication device. This data error range can assist the first communication device in determining the complexity of the first model. For example, the second communication device uses the third indication information to indicate the range of the error vector magnitude, informing the first communication device how much additional error vector magnitude the first model needs to handle. Based on the third indication information, the first communication device can determine the complexity of the first model and then perform model training or model updating.

[0097] 4) Fourth indication information: The fourth indication information is used to instruct the second communication device to send data tag information. It can be understood as information sent by the second communication device for data collection during the model processing stage of the first model performed by the first communication device, such as random numbers used for downlink data generation, downlink data symbols, etc. The first communication device can collect data based on the fourth indication information and perform model processing on the first model based on the collected data.

[0098] 5) Fifth indication information, which indicates information about the first model, such as the index of the first model. Based on the fifth indication information, the first communication device can determine the first model that needs to be trained or updated, and then perform model processing on the first model.

[0099] Optionally, the second communication device can perform model processing, such as parameter updates, simultaneously with the first communication device. The second communication device can send first information to the first communication device, and the first communication device can receive the first information from the second communication device and perform model processing on the first model based on the first information.

[0100] The first information received by the first communication device from the second communication device is used for model processing of the first model. Optionally, the first information may include at least one of the following:

[0101] 1) Fourth indication information: The fourth indication information is used to instruct the second communication device to send data tag information. It can be understood as information sent by the second communication device for data collection during the model processing stage of the first model performed by the first communication device, such as random numbers used for downlink data generation, downlink data symbols, etc. The first communication device can collect data based on the fourth indication information and perform model processing on the first model based on the collected data.

[0102] 2) Sixth indication information: The sixth indication information is used to indicate the indicator information for the data transmitted by the second communication device. Based on the sixth indication information, the first communication device can determine the indicator information that needs to be considered when updating the parameters of the first model. For example, adjacent channel leakage ratio information. Exemplarily, the second communication device can include an adjacent channel leakage ratio indication field in the downlink control information (DCI) to indicate the adjacent channel leakage ratio corresponding to the Physical Downlink Shared Channel (PDSCH) scheduled by the current downlink control information.

[0103] 3) The seventh indication information is used to indicate the parameters of data transmission. For example, the data transmission channel and signal parameters. The first communication device can receive data based on these parameters for model training.

[0104] When the first communication device is a terminal and the second communication device is a network-side device, the second communication device sends first information to the first communication device. The first information includes at least one of the above-mentioned items. Based on the first information, the first communication device can perform targeted model processing on the first model to improve model processing efficiency.

[0105] In some embodiments of this application, when the first communication device is a network-side device and the second communication device is a terminal, the first information may include at least one of the following:

[0106] The first reported information is used to report the indicator information of the data transmitted by the second communication device;

[0107] The second reporting information is used to report the tag information of the data transmitted by the second communication device;

[0108] The third reporting information is used to report to the second communication device to complete the model processing of the second model.

[0109] In this embodiment, the first communication device can be a network-side device, and the second communication device can be a terminal. In uplink transmission, the transmitter-side model, such as the second model, is deployed on the terminal side, and the receiver-side model, such as the first model, is deployed on the network-side device side.

[0110] Optionally, the second communication device can perform model processing, such as parameter updates, simultaneously with the first communication device. The second communication device can send first information to the first communication device, and the first communication device can receive the first information from the second communication device and perform model processing on the first model based on the first information.

[0111] The first information received by the first communication device from the second communication device is used for model processing of the first model. Optionally, the first information may include at least one of the following:

[0112] 1) First Reporting Information: This information is used to report the metrics of the data transmitted by the second communication device. Based on this information, the first communication device can determine the metrics to be considered when updating the parameters of the first model. For example, adjacent channel leakage ratio information. Exemplarily, the second communication device can carry the adjacent channel leakage ratio information transmitted via the Physical Uplink Shared Channel (PUSCH) in the Physical Uplink Control Channel (PUCCH).

[0113] 2) Second Reporting Information: This information is used to report tag information of the data sent by the second communication device. It can be understood as information sent by the second communication device for data collection during the model processing phase of the first model by the first communication device. The first communication device can collect data based on the second reporting information and process the first model based on the collected data.

[0114] Optionally, the second communication device may train the second model first, and then instruct the first communication device to train the first model. Optionally, after completing model training or updating of the second model, the second communication device may send first information to the first communication device, which receives the first information from the second communication device and performs model processing on the first model based on the first information. The data required by the second communication device for model training or updating the second model may be obtained spontaneously by the second communication device.

[0115] The first information received by the first communication device from the second communication device is used for model processing of the first model. Optionally, the first information may include:

[0116] The third reporting information is used to report to the second communication device that it has completed model processing of the second model. Based on the third reporting information, the first communication device can initiate model processing of the first model, such as model training or model updating.

[0117] When the first communication device is a network-side device and the second communication device is a terminal, the second communication device sends first information to the first communication device. The first information includes at least one of the above-mentioned features. Based on the first information, the first communication device can perform targeted model processing on the first model to improve model processing efficiency.

[0118] In some embodiments of this application, when the first communication device is a network-side device and the second communication device is a terminal, the method may further include the following steps:

[0119] The first communication device receives second information from the second communication device. The second information is used to instruct the second communication device to perform data collection.

[0120] In this embodiment of the application, during uplink transmission, the first communication device is a network-side device, and the second communication device is a terminal. The second communication device can first train the second model and then instruct the first communication device to train the first model. Optionally, after completing the model training or model update of the second model, the second communication device can send first information to the first communication device. The first communication device receives the first information from the second communication device and performs model processing on the first model based on the first information.

[0121] The data required by the second communication device for training or updating the second model can be obtained spontaneously by the second communication device. During the training or updating phase of the second model by the second communication device, the first communication device needs to be aware of the timing for data collection to avoid the second communication device performing ineffective uplink scheduling and reception.

[0122] Optionally, before the second communication device sends the first information to the first communication device, the second communication device may send the second information to the first communication device. The second information is used to instruct the second communication device to perform data collection.

[0123] This can be understood as follows: before the first communication device sends the first information from the second communication device, the first communication device can receive the second information from the second communication device. The second information is used to instruct the second communication device to perform data collection.

[0124] Optionally, the first window information may include at least one of the following: the start position information of the first window, the end position information of the first window, and the length information of the first window.

[0125] The first communication device does not perform uplink scheduling and reception in the first window of the second information indication, which helps to save resources.

[0126] In some embodiments of this application, when the first communication device is a network-side device and the second communication device is a terminal, the method may further include the following steps:

[0127] The first communication device sends a third message to the second communication device, which is a second window message used to instruct the second communication device to collect data.

[0128] In this embodiment of the application, during uplink transmission, the first communication device is a network-side device, and the second communication device is a terminal. The second communication device can first train the second model and then instruct the first communication device to train the first model. Optionally, after completing the model training or model update of the second model, the second communication device can send first information to the first communication device. The first communication device receives the first information from the second communication device and performs model processing on the first model based on the first information.

[0129] The data required by the second communication device for model training or model updating of the second model can be obtained by the second communication device itself. The first communication device needs to know when the second communication device is collecting data in order to avoid the first communication device from performing invalid uplink scheduling and reception.

[0130] Optionally, before the first communication device receives the first information from the second communication device, the first communication device may send third information to the second communication device. This third information serves as a second window information instructing the second communication device to collect data. The second communication device may then collect data based on the third information and subsequently perform model processing on the second model based on the collected data.

[0131] Optionally, the second window information may include at least one of the following:

[0132] The starting position information of the second window;

[0133] The end position information of the second window;

[0134] The length information of the second window.

[0135] The information in the second window is indicated by the first communication device to the second communication device. The first communication device does not need to perform uplink scheduling and reception within the second window, which helps to save resources.

[0136] In some embodiments of this application, the method may further include the following steps:

[0137] The first communication device sends a fourth message to the second communication device, the fourth message being used to indicate the model processing result of the first model.

[0138] In this embodiment, after the first communication device processes the first model based on the first information, the first communication device can send fourth information to the second communication device. The fourth information indicates the model processing result of the first model. The model processing result can be understood as the model processing effect, such as the model training effect, model update effect, parameter update effect, etc. The second communication device receives the fourth information from the first communication device and can obtain the model processing result of the first model through the fourth information, facilitating further communication between the second and first communication devices.

[0139] Optionally, after the second communication device completes model training or model update of the second model, it can send first information to the first communication device. This first information assists the first communication device in model training or model update. The first communication device receives the first information from the second communication device and, based on the first information, performs model training or model update on the first model. After completing model training or model update of the first model, the first communication device can send fourth information to the second communication device. This fourth information indicates the model training result or model update result of the first model. The second communication device receives the fourth information from the first communication device and, based on this fourth information, can ascertain the model processing effect of the first communication device and perform data transmission scheduling.

[0140] Optionally, during the training of the first and second models, the second communication device sends first information to the first communication device. This first information assists the first communication device in updating the parameters of the first model. The first communication device receives the first information from the second communication device and updates the parameters of the first model based on this information. The first communication device may send fourth information to the second communication device. This fourth information indicates the parameter update result, such as the parameter update coefficients and gradients. The parameter update result assists the second communication device in updating the parameters of the second model. After multiple rounds of parameter updates, the first and second communication devices can respectively complete the model training or model update of the first and second models.

[0141] In some embodiments of this application, the method may further include the following steps:

[0142] The first communication device receives the fifth information from the second communication device;

[0143] The first communication device deploys the first model based on the fifth information.

[0144] In this embodiment of the application, before the second communication device sends the first information to the first communication device, the second communication device may send the fifth information to the first communication device. The fifth information is used for the deployment of the first model. Before the first communication device receives the fifth information from the second communication device, the first communication device may receive the fifth information from the second communication device and deploy the first model based on the fifth information.

[0145] Optionally, the fifth piece of information includes at least one of the following:

[0146] 1) Deployment information of the first model. For example, in which functional module of the first communication device the first model is deployed.

[0147] 2) Deployment information of the second model. For example, in which functional module of the second communication device the second model is deployed.

[0148] 3) Output information of the first model. For example, modulation symbols, log-likelihood ratio (LLR), channel matrix H, etc.

[0149] 4) Output information of the second model. For example, modulation symbols, log-likelihood ratio (LLR), channel matrix H, etc.

[0150] The fifth piece of information enables the synchronization of model deployment information between the first and second communication devices, which is helpful for model processing on both the sending and receiving sides.

[0151] For ease of understanding, specific examples are used to illustrate the embodiments of this application below.

[0152] Example 1: The transmitter model (second model) for downlink transmission is deployed on the network-side equipment (second communication equipment), which can be the base station or other network-side nodes, and the receiver model (first model) is deployed on the terminal (first communication equipment).

[0153] Option 1: The network-side device first trains the second model, and then instructs the terminal to train the first model. This can include the following steps:

[0154] Step 1: The network-side device trains the second model. The data used to train the second model can be obtained spontaneously by the network-side device. After the training is completed, the terminal is instructed to start training the first model.

[0155] The terminal receives signaling sent by the network-side device, and the signaling contains at least one of the following information:

[0156] The first instruction information is used to instruct the terminal to start model training or start model updating;

[0157] The second instruction information is used to instruct the terminal on when to collect data;

[0158] The third indication information is used to indicate the data error range of the network-side device. This data error range helps the terminal determine the complexity of the first model. For example, the network-side device indicates the EVM range through signaling, telling the terminal how much additional EVM error the first model needs to handle.

[0159] The fourth indication information is used to indicate the tag information of the data transmitted by the second communication device, and to indicate the downlink transmission information used by the network-side device for data collection during the first model training phase. Examples include the random numbers generated for the downlink data and the symbols used in the downlink data transmission.

[0160] The fifth indication information is used to indicate information about the first model, such as the model index, indicating the model that needs to be trained or updated.

[0161] Step 2: The terminal trains the first model.

[0162] Step 3: Optional, after the terminal completes model training, it reports the model's performance.

[0163] Option 2: Train the first and second models simultaneously, which can include the following:

[0164] Step 1: The terminal receives signaling sent by the network-side device. The signaling includes at least one of the following:

[0165] The sixth indication information is used to indicate the indicator information of the data sent by the second communication device, and to indicate the indicator information that the terminal considers when updating the model parameters, such as the signaling indication of the ACLR information of the current signal; for example, the DCI includes an ACLR indication field, which is used to indicate the ACLR corresponding to the PDSCH of the current DCI scheduling.

[0166] The fourth indication information is used to indicate the tag information of the data sent by the second communication device, and to indicate the downlink transmission information used by the network-side device for data collection during the first model training phase, such as the random number generated by the downlink data, the symbol of the downlink data, etc.

[0167] The seventh indication information is used to indicate parameter information for data transmission, such as channel or signal parameters for data set transmission.

[0168] Step 2: The terminal updates the model parameters based on the above signaling.

[0169] Step 3: The terminal reports parameter update information, such as the coefficients and gradients of the updated model parameters.

[0170] For example, after receiving the physical downlink shared channel used to transmit training data, the terminal feeds back the coefficients of the updated model parameters through the physical uplink control channel.

[0171] Example 2: The uplink transmitter model (second model) is deployed on the terminal (second communication device), and the receiver model (first model) is deployed on the network-side device (first communication device), which can be the base station side or other network-side nodes.

[0172] Option 1: The terminal first trains the second model, and then instructs the network-side device to train the first model. This can include the following steps:

[0173] Step 1: The terminal needs to acquire a dataset to train the second model. Considering that the dataset for model training is sent and received by the terminal, the network device needs to know the timing for dataset collection to avoid ineffective uplink scheduling and reception by the network device.

[0174] Method 1: The terminal reports information, indicating at least one of the following:

[0175] The window information used by the terminal to collect data, such as the starting position and length of the window.

[0176] Method 2: The terminal receives signaling sent by the network-side equipment, which indicates the timing of data collection.

[0177] Step 2: The terminal reports information, instructing the network-side devices to train or update the model.

[0178] Step 3: After the network-side device completes the training of the first model, it indicates the training effect of the model.

[0179] Option 2: Train the first and second models simultaneously, which can include the following:

[0180] Step 1: The terminal reports information to the network-side device to assist in model training. The reported information includes at least one of the following:

[0181] The terminal sends data with metrics information that indicate the metrics considered in updating network model parameters, such as ACLR information; for example, the PUCCH carries ACLR information sent by the PUSCH.

[0182] Data tagging information;

[0183] Step 2: Network-side device indicates parameter update information.

[0184] This application proposes deploying models simultaneously on both the network-side device and the terminal side, as well as signaling interaction for model training. This supports model training and inference on both ends, which helps to improve the terminal's transmission power in power-constrained scenarios, thereby improving uplink transmission performance.

[0185] Corresponding to the above method embodiments, this application also provides a model processing method, such as... Figure 7 As shown, the method includes the following steps:

[0186] S710: The second communication device sends first information to the first communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

[0187] Applying the method provided in the embodiments of this application, a first model is deployed on the first communication device side and a second model is deployed on the second communication device side. The second communication device sends first information to the first communication device so that the first communication device performs model processing on the first model according to the first information. The combination of the first model and the second model can compensate for the nonlinear distortion of the power amplifier at the transmitter end, reduce the power back-off of the power amplifier, increase the transmission power of the transmitter, improve the efficiency of the power amplifier, and enhance network coverage.

[0188] In some embodiments of this application, when the first communication device is a terminal and the second communication device is a network-side device, the first information includes at least one of the following:

[0189] The first instruction information is used to instruct the first communication device to start model training or start model updating;

[0190] The second instruction information is used to indicate when the first communication device should collect data;

[0191] The third indication information is used to indicate the data error range of the second communication device;

[0192] The fourth indication information is used to indicate the tag information for the data transmitted by the second communication device;

[0193] The fifth instruction information is used to indicate information about the first model;

[0194] The sixth indication information is used to indicate the data transmission indicators of the second communication device.

[0195] The seventh indication information is used to indicate the parameter information for data transmission.

[0196] In some embodiments of this application, when the first communication device is a network-side device and the second communication device is a terminal, the first information includes at least one of the following:

[0197] The first reported information is used to report the indicator information of the data transmitted by the second communication device;

[0198] The second reporting information is used to report the tag information of the data transmitted by the second communication device;

[0199] The third reporting information is used to report to the second communication device to complete the model processing of the second model.

[0200] In some embodiments of this application, when the first communication device is a network-side device and the second communication device is a terminal, the method further includes:

[0201] The second communication device sends a second message to the first communication device. The second message is a first window message that instructs the second communication device to collect data.

[0202] In some embodiments of this application, the first window information includes at least one of the following:

[0203] The starting position information of the first window;

[0204] The end position information of the first window;

[0205] The length information of the first window.

[0206] In some embodiments of this application, when the first communication device is a network-side device and the second communication device is a terminal, the method further includes:

[0207] The second communication device receives third information from the first communication device. The third information is used to instruct the second communication device to perform data collection.

[0208] In some embodiments of this application, the second window information includes at least one of the following:

[0209] The starting position information of the second window;

[0210] The end position information of the second window;

[0211] The length information of the second window.

[0212] In some embodiments of this application, the method further includes:

[0213] The second communication device receives fourth information from the first communication device, which is used to instruct the model processing of the first model.

[0214] In some embodiments of this application, the second communication device sends first information to the first communication device, including:

[0215] After completing the training or update of the second model, the second communication device sends the first information to the first communication device.

[0216] In some embodiments of this application, the method further includes:

[0217] The second communication device sends a fifth message to the first communication device. The fifth message is used for the deployment of the first model.

[0218] In some embodiments of this application, the fifth information includes at least one of the following:

[0219] Deployment information for the first model;

[0220] Deployment information for the second model;

[0221] Output information of the first model;

[0222] The output information of the second model.

[0223] The model processing method provided in this application embodiment can achieve... Figure 5 The various processes implemented in the method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0224] The model processing method provided in this application can be executed by a model processing device. This application uses the example of a model processing device executing the model processing method to illustrate the model processing device provided in this application.

[0225] This application provides a model processing apparatus. As an example, the model processing apparatus may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0226] The model processing device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0227] For details, see Figure 8When the model processing device operates on the first communication device, or when the model processing device is the first communication device or a component of the first communication device, the model processing device 800 includes:

[0228] The first receiving module 810 is used to receive first information from the second communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

[0229] The first processing module 820 is used to perform model processing on the first model based on the first information.

[0230] The apparatus provided in this application embodiment has a first model deployed on the first communication device side and a second model deployed on the second communication device side. It receives first information from the second communication device and performs model processing on the first model based on the first information. The combination of the first model and the second model can compensate for the nonlinear distortion of the power amplifier at the transmitter end, reduce the power back-off of the power amplifier, increase the transmission power of the transmitter, improve the efficiency of the power amplifier, and enhance network coverage.

[0231] Optionally, when the first communication device is a terminal and the second communication device is a network-side device, the first information includes at least one of the following:

[0232] The first instruction information is used to instruct the first communication device to start model training or start model updating;

[0233] The second instruction information is used to indicate when the first communication device should collect data;

[0234] The third indication information is used to indicate the data error range of the second communication device;

[0235] The fourth indication information is used to indicate the tag information for the data transmitted by the second communication device;

[0236] The fifth instruction information is used to indicate information about the first model;

[0237] The sixth indication information is used to indicate the data transmission indicators of the second communication device.

[0238] The seventh indication information is used to indicate the parameter information for data transmission.

[0239] Optionally, when the first communication device is a network-side device and the second communication device is a terminal, the first information includes at least one of the following:

[0240] The first reported information is used to report the indicator information of the data transmitted by the second communication device;

[0241] The second reporting information is used to report the tag information of the data transmitted by the second communication device;

[0242] The third reporting information is used to report to the second communication device to complete the model processing of the second model.

[0243] Optionally, when the first communication device is a network-side device and the second communication device is a terminal, the first receiving module 810 is further configured to:

[0244] Receive second information from the second communication device, the second information being used to instruct the second communication device to perform data collection (first window information).

[0245] Optionally, the information in the first window includes at least one of the following:

[0246] The starting position information of the first window;

[0247] The end position information of the first window;

[0248] The length information of the first window.

[0249] Optionally, when the first communication device is a network-side device and the second communication device is a terminal, the model processing apparatus 800 further includes a first transmitting module, used for:

[0250] Send a third message to the second communication device. The third message is a second window message used to instruct the second communication device to collect data.

[0251] Optionally, the second window information includes at least one of the following:

[0252] The starting position information of the second window;

[0253] The end position information of the second window;

[0254] The length information of the second window.

[0255] Optionally, the model processing device 800 further includes a second transmitting module for:

[0256] A fourth message is sent to the second communication device, which indicates the model processing result of the first model.

[0257] Optionally, the first receiving module 810 is further configured to: receive fifth information from the second communication device;

[0258] The first processing module 820 is also used to deploy the first model based on the fifth information.

[0259] Optionally, the fifth piece of information includes at least one of the following:

[0260] Deployment information for the first model;

[0261] Deployment information for the second model;

[0262] Output information of the first model;

[0263] The output information of the second model.

[0264] The model processing device 800 provided in this embodiment of the application can achieve... Figure 5 The various processes implemented in the method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0265] See Figure 9 When the model processing device operates on the second communication device, or when the model processing device is the second communication device or a component of the second communication device, the model processing device 900 includes:

[0266] The third sending module 910 is used to send first information to the first communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

[0267] The apparatus provided in this application embodiment has a first model deployed on the first communication device side and a second model deployed on the second communication device side. First information is sent to the first communication device so that the first communication device can perform model processing on the first model according to the first information. The combination of the first model and the second model can compensate for the nonlinear distortion of the power amplifier at the transmitter end, reduce the power back-off of the power amplifier, increase the transmission power of the transmitter, improve the efficiency of the power amplifier, and enhance network coverage.

[0268] Optionally, when the first communication device is a terminal and the second communication device is a network-side device, the first information includes at least one of the following:

[0269] The first instruction information is used to instruct the first communication device to start model training or start model updating;

[0270] The second instruction information is used to indicate when the first communication device should collect data;

[0271] The third indication information is used to indicate the data error range of the second communication device;

[0272] The fourth indication information is used to indicate the tag information for the data transmitted by the second communication device;

[0273] The fifth instruction information is used to indicate information about the first model;

[0274] The sixth indication information is used to indicate the data transmission indicators of the second communication device.

[0275] The seventh indication information is used to indicate the parameter information for data transmission.

[0276] Optionally, when the first communication device is a network-side device and the second communication device is a terminal, the first information includes at least one of the following:

[0277] The first reported information is used to report the indicator information of the data transmitted by the second communication device;

[0278] The second reporting information is used to report the tag information of the data transmitted by the second communication device;

[0279] The third reporting information is used to report to the second communication device to complete the model processing of the second model.

[0280] Optionally, when the first communication device is a network-side device and the second communication device is a terminal, the third transmitting module 910 is further configured to:

[0281] Send a second message to the first communication device. The second message is a first window message used to instruct the second communication device to collect data.

[0282] Optionally, the information in the first window includes at least one of the following:

[0283] The starting position information of the first window;

[0284] The end position information of the first window;

[0285] The length information of the first window.

[0286] Optionally, when the first communication device is a network-side device and the second communication device is a terminal, the model processing apparatus 900 further includes a second receiving module, used for:

[0287] The third information is received from the first communication device. The third information is used to instruct the second communication device to collect data.

[0288] Optionally, the second window information includes at least one of the following:

[0289] The starting position information of the second window;

[0290] The end position information of the second window;

[0291] The length information of the second window.

[0292] Optionally, the model processing device 900 further includes a third receiving module for:

[0293] The fourth information is received from the first communication device, which is used to instruct the model processing of the first model.

[0294] Optionally, the third transmitting module 910 is specifically used for:

[0295] After completing the training or update of the second model, the first information is sent to the first communication device.

[0296] Optionally, the third transmitting module 910 is also used for:

[0297] Send the fifth message to the first communication device. The fifth message is used for the deployment of the first model.

[0298] Optionally, the fifth piece of information includes at least one of the following:

[0299] Deployment information for the first model;

[0300] Deployment information for the second model;

[0301] Output information of the first model;

[0302] The output information of the second model.

[0303] The model processing device 900 provided in this embodiment of the application can achieve... Figure 7 The various processes implemented in the method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0304] like Figure 10 As shown, this application embodiment also provides a communication device 1000, including a processor 1001 and a memory 1002. The memory 1002 stores a program or instructions that can run on the processor 1001. For example, when the communication device 1000 is a first communication device, the program or instructions executed by the processor 1001 implement the above-mentioned... Figure 5 The various steps of the method embodiment shown can achieve the same technical effect. When the communication device 1000 is a second communication device, the program or instructions executed by the processor 1001 implement the above-described steps. Figure 7 The steps of the method embodiment shown are the same and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0305] This application embodiment also provides a terminal, including a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement, for example... Figure 5 or Figure 7The steps in the method embodiment shown are illustrated. This terminal embodiment corresponds to the method embodiment where the first communication device is the terminal, or to the method embodiment where the second communication device is the terminal. All implementation processes and methods of the above method embodiments can be applied to this terminal embodiment and achieve the same technical effect. The terminal can be... Figure 8 The model processing device 800 shown, or Figure 9 The model processing device 900 shown. Specifically, Figure 11 A schematic diagram of the structure of a terminal to implement an embodiment of this application.

[0306] The terminal 1100 includes, but is not limited to, at least some of the following components: radio frequency unit 1101, network module 1102, audio output unit 1103, input unit 1104, sensor 1105, display unit 1106, user input unit 1107, interface unit 1108, memory 1109, and processor 1110.

[0307] Those skilled in the art will understand that the terminal 1100 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1110 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 11 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0308] It should be understood that, in this embodiment, the input unit 1104 may include a graphics processor 11041 and a microphone 11042. The graphics processor 11041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1106 may include a display panel 11061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1107 includes at least one of a touch panel 11071 and other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0309] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1101 can transmit it to the processor 1110 for processing; in addition, the radio frequency unit 1101 can send uplink data to the network-side device. Typically, the radio frequency unit 1101 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0310] The memory 1109 can be used to store software programs or instructions, as well as various data. The memory 1109 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1109 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1109 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0311] Processor 1110 may include one or more processing units; optionally, processor 1110 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1110.

[0312] The radio frequency unit 1101 is used to receive first information from the second communication device;

[0313] The processor 1110 is used to perform model processing on the first model based on the first information.

[0314] Alternatively, the radio frequency unit 1101 is used to send first information to the first communication device.

[0315] It is understood that the implementation process of each implementation method mentioned in this embodiment can be referred to Figure 5 or Figure 7 The relevant descriptions of the method embodiments shown herein, which achieve the same or corresponding technical effects, will not be repeated here to avoid duplication.

[0316] This application embodiment also provides a network-side device, including a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement, for example... Figure 5 or Figure 7 The steps of the method embodiment shown are as follows. This network-side device embodiment corresponds to the method embodiment where the first communication device is the network-side device, or to the method embodiment where the second communication device is the network-side device. All implementation processes and methods of the above method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0317] Specifically, embodiments of this application also provide a network-side device, which can be... Figure 8 The model processing device 800 shown, or Figure 9 The model processing device 900 shown is an example. Figure 12 As shown, the network-side device 1200 includes: an antenna 1201, a radio frequency (RF) device 1202, a baseband device 1203, a processor 1204, and a memory 1205. The antenna 1201 is connected to the RF device 1202. In the uplink direction, the RF device 1202 receives information through the antenna 1201 and transmits the received information to the baseband device 1203 for processing. In the downlink direction, the baseband device 1203 processes the information to be transmitted and sends it to the RF device 1202. The RF device 1202 processes the received information and transmits it through the antenna 1201.

[0318] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 1203, which includes a baseband processor.

[0319] The baseband device 1203 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG120. One of the chips is, for example, a baseband processor, which is connected to the memory 1205 via a bus interface to call the program in the memory 1205 to execute the network-side device operation shown in the above method embodiment.

[0320] The network-side device may also include a network interface 1206, such as a Common Public Radio Interface (CPRI).

[0321] Specifically, the network-side device 1200 in this application embodiment further includes: instructions or programs stored in memory 1205 and executable on processor 1204, wherein processor 1204 calls the instructions or programs in memory 1205 to execute. Figure 8 or Figure 9 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0322] Specifically, embodiments of this application also provide a network-side device. For example... Figure 13 As shown, the network-side device 1300 includes: a processor 1301, a network interface 1302, and a memory 1303. This network-side device can be... Figure 8 The model processing device 800 shown, or Figure 9 The model processing device 900 shown is described. The network interface 1302 is, for example, a common public radio interface (CPRI).

[0323] Specifically, the network-side device 1300 in this application embodiment further includes: instructions or programs stored in memory 1303 and executable on processor 1301, wherein processor 1301 calls the instructions or programs in memory 1303 to execute. Figure 8 or Figure 9 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0324] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0325] The processor is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0326] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0327] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0328] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0329] This application also provides a wireless communication system, including: a terminal and a network-side device, wherein the terminal can be used to perform the above-mentioned functions. Figure 5 The steps of the method embodiment shown above, where the first communication device is the terminal, can be performed by a network-side device. Figure 7 The steps of the method embodiment where the second communication device is a network-side device are shown.

[0330] This application also provides a wireless communication system, including: a terminal and a network-side device, wherein the terminal can be used to perform the above-mentioned functions. Figure 7 The steps of the method embodiment shown above, where the second communication device is the terminal, can be performed by the network-side device. Figure 5 The steps of the method embodiment shown are as follows: the first communication device is a network-side device.

[0331] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0332] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0333] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A model processing method, characterized in that, include: The first communication device receives first information from the second communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side. The first communication device performs model processing on the first model based on the first information.

2. The method according to claim 1, characterized in that, When the first communication device is a terminal and the second communication device is a network-side device, the first information includes at least one of the following: The first instruction information is used to instruct the first communication device to start model training or start model updating. The second indication information is used to indicate when the first communication device should collect data; The third indication information is used to indicate the data error range of the second communication device; The fourth indication information is used to indicate the tag information of the data transmitted by the second communication device; The fifth indication information is used to indicate information about the first model; The sixth indication information is used to indicate the indicator information for the data transmitted by the second communication device; The seventh indication information is used to indicate parameter information for data transmission.

3. The method according to claim 1, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the first information includes at least one of the following: The first reporting information is used to report the indicator information of the data sent by the second communication device; The second reporting information is used to report the tag information of the data sent by the second communication device; The third reporting information is used to report that the second communication device has completed the model processing of the second model.

4. The method according to claim 1 or 3, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the method further includes: The first communication device receives second information from the second communication device, the second information being used to instruct the second communication device to perform data collection, which is first window information.

5. The method according to claim 4, characterized in that, The first window information includes at least one of the following: The starting position information of the first window; The end position information of the first window; The length information of the first window.

6. The method according to any one of claims 1, 3, 4, and 5, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the method further includes: The first communication device sends a third message to the second communication device, the third message being used to instruct the second communication device to perform data collection via a second window.

7. The method according to claim 6, characterized in that, The second window information includes at least one of the following: The starting position information of the second window; The end position information of the second window; The length information of the second window.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: The first communication device sends a fourth message to the second communication device, the fourth message being used to indicate the model processing result of the first model.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: The first communication device receives the fifth information from the second communication device; The first communication device deploys the first model based on the fifth information.

10. The method according to claim 9, characterized in that, The fifth piece of information includes at least one of the following: Deployment information for the first model; Deployment information for the second model; Output information of the first model; The output information of the second model.

11. A model processing method, characterized in that, include: The second communication device sends first information to the first communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

12. The method according to claim 11, characterized in that, When the first communication device is a terminal and the second communication device is a network-side device, the first information includes at least one of the following: The first instruction information is used to instruct the first communication device to start model training or start model updating. The second indication information is used to indicate when the first communication device should collect data; The third indication information is used to indicate the data error range of the second communication device; The fourth indication information is used to indicate the tag information of the data transmitted by the second communication device; The fifth indication information is used to indicate information about the first model; The sixth indication information is used to indicate the indicator information for the data transmitted by the second communication device; The seventh indication information is used to indicate parameter information for data transmission.

13. The method according to claim 11, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the first information includes at least one of the following: The first reporting information is used to report the indicator information of the data sent by the second communication device; The second reporting information is used to report the tag information of the data sent by the second communication device; The third reporting information is used to report that the second communication device has completed the model processing of the second model.

14. The method according to claim 11 or 13, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the method further includes: The second communication device sends a second message to the first communication device, the second message being a first window message instructing the second communication device to collect data.

15. The method according to claim 14, characterized in that, The first window information includes at least one of the following: The starting position information of the first window; The end position information of the first window; The length information of the first window.

16. The method according to any one of claims 11, 13, 14, and 15, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the method further includes: The second communication device receives third information from the first communication device, the third information being used to instruct the second communication device to perform data collection via a second window.

17. The method according to claim 16, characterized in that, The second window information includes at least one of the following: The starting position information of the second window; The end position information of the second window; The length information of the second window.

18. The method according to any one of claims 11 to 17, characterized in that, The method further includes: The second communication device receives fourth information from the first communication device, the fourth information being used to instruct the model processing of the first model.

19. The method according to any one of claims 11 to 18, characterized in that, The second communication device sends first information to the first communication device, including: After completing the training or update of the second model, the second communication device sends the first information to the first communication device.

20. The method according to any one of claims 11 to 19, characterized in that, The method further includes: The second communication device sends a fifth message to the first communication device, the fifth message being used for the deployment of the first model.

21. The method according to claim 20, characterized in that, The fifth piece of information includes at least one of the following: Deployment information for the first model; Deployment information for the second model; Output information of the first model; The output information of the second model.

22. A model processing device, characterized in that, The model processing device operates on the first communication device and includes: A first receiving module is configured to receive first information from a second communication device. The first information is used for model processing of a first model. The first model is deployed on the first communication device side, and a second model is deployed on the second communication device side. The first processing module is used to perform model processing on the first model based on the first information.

23. The apparatus according to claim 22, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the first receiving module is further configured to: Receive second information from the second communication device, the second information being used to instruct the second communication device to perform data collection (first window information).

24. The apparatus according to claim 22 or 23, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the model processing device further includes a first sending module, used for: Send a third message to the second communication device, the third message being a second window message used to instruct the second communication device to collect data.

25. The apparatus according to any one of claims 22 to 24, characterized in that, The model processing device further includes a second sending module, used for: Send a fourth message to the second communication device, the fourth message being used to indicate the model processing result of the first model.

26. The apparatus according to any one of claims 22 to 25, characterized in that, The first receiving module is further configured to: receive fifth information from the second communication device; The first processing module is further configured to deploy the first model based on the fifth information.

27. A model processing device, characterized in that, The model processing device operates on a second communication device, including: The third sending module is used to send first information to the first communication device. The first information is used for model processing of the first model. The first model is deployed on the first communication device side, and the second model is deployed on the second communication device side.

28. The apparatus according to claim 27, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the third sending module is further configured to: Send a second message to the first communication device, the second message being a first window message used to instruct the second communication device to collect data.

29. The apparatus according to claim 27 or 28, characterized in that, When the first communication device is a network-side device and the second communication device is a terminal, the model processing device further includes a second receiving module, used for: The third information is received from the first communication device, and the third information is used to instruct the second communication device to perform data collection.

30. The apparatus according to any one of claims 27 to 29, characterized in that, The model processing device further includes a third receiving module, used for: The fourth information is received from the first communication device, which is used to instruct the model processing of the first model.

31. The apparatus according to any one of claims 27 to 30, characterized in that, The third sending module is specifically used for: After completing the training or update of the second model, the first information is sent to the first communication device.

32. The apparatus according to any one of claims 27 to 31, characterized in that, The third sending module is further configured to: Send a fifth message to the first communication device, the fifth message being used for the deployment of the first model.

33. A communication device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the model processing method as claimed in any one of claims 1 to 10, or to implement the steps of the model processing method as claimed in any one of claims 11 to 21.

34. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the model processing method as described in any one of claims 1 to 10, or implement the steps of the model processing method as described in any one of claims 11 to 21.

Images