Model processing method and apparatus, communication device, and storage medium

Abstract

The present application relates to the technical field of communications, and discloses a model processing method and apparatus, a communication device, and a storage medium. The model processing method in embodiments of the present application comprises: a communication device obtains at least two first models; and the communication device uses the at least two first models to obtain a second model or a part of the second model or a first data set.

Description

Model processing method, device, communication equipment and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on March 27, 2024, with application number 202410361159.X and entitled “Model processing method, device, communication equipment and storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application belongs to the field of communication technology, and specifically relates to a model processing method, apparatus, communication equipment and storage medium. Background Art

[0004] Artificial Intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. AI technology has been widely applied in various fields and has played an important role. For example, in wireless communication networks, integrating AI technology can help improve technical indicators such as throughput, latency, and user capacity.

[0005] For the same AI functionality or feature in wireless communication networks, different AI models can be trained using different methods or datasets. These models may have different parameters and input-to-output mappings. Currently, a single AI model is selected from multiple models for use. However, the performance of a single model is limited, making it adaptable to only certain scenarios or environments and unable to achieve optimal gains. Summary of the Invention

[0006] The embodiments of the present application provide a model processing method, apparatus, communication equipment, and storage medium, which can utilize multiple AI models to obtain better gain, thereby helping to improve the performance of wireless communication networks.

[0007] In a first aspect, a model processing method is provided, comprising:

[0008] The communication device obtains at least two first models;

[0009] The communication device uses the at least two first models to obtain a second model or a partial model of the second model or a first data set.

[0010] In a second aspect, a model processing device is provided, comprising:

[0011] A first obtaining module, configured to obtain at least two first models;

[0012] The second obtaining module is used to obtain the second model or a partial model of the second model or the first data set by using the at least two first models.

[0013] In a third aspect, a communication device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0014] In a fourth aspect, a communication device is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method described in the first aspect.

[0015] In a fifth aspect, a terminal is provided, which includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0016] In a sixth aspect, a terminal is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method described in the first aspect.

[0017] In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0018] In an eighth aspect, a network side device is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method described in the first aspect.

[0019] In a ninth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0020] In the tenth aspect, a wireless communication system is provided, comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the method described in the first aspect, or the network side device can be used to execute the steps of the method described in the first aspect.

[0021] In the eleventh aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method described in the first aspect.

[0022] In a twelfth aspect, a computer program / program product is provided, wherein the computer program / program product is stored in a storage medium, and the computer program / program product is executed by at least one processor to implement the steps of the method described in the first aspect.

[0023] In an embodiment of the present application, after the communication device obtains at least two first models, it uses the at least two first models to obtain a second model or a first data set, and fuses multiple first models to obtain a second model or a partial model of the second model or a first data set, thereby aligning the mapping relationship between the input and output of multiple first models. Applying the second model or the partial model of the second model or the first data set to the wireless communication network can obtain better gain and help improve the performance of the wireless communication network. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] FIG1 is a block diagram of a wireless communication system applicable to embodiments of the present application;

[0025] FIG2 is a schematic diagram of a neural network in the related art;

[0026] FIG3 is a schematic diagram of a neuron in the related art;

[0027] FIG4 is a flowchart of an implementation of a model processing method in an embodiment of the present application;

[0028] FIG5 is a schematic diagram of a unilateral model processing process in an embodiment of the present application;

[0029] FIG6 is a schematic diagram of a bilateral model processing process in an embodiment of the present application;

[0030] FIG7 is a schematic structural diagram of a model processing device according to an embodiment of the present application;

[0031] FIG8 is a schematic structural diagram of a communication device according to an embodiment of the present application;

[0032] FIG9 is a schematic structural diagram of a terminal according to an embodiment of the present application;

[0033] FIG10 is a schematic structural diagram of a network-side device according to an embodiment of the present application;

[0034] FIG11 is a schematic structural diagram of another network-side device in an embodiment of the present application. Specific embodiments

[0035] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0036] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0037] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0038] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, 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 the embodiments of the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. th Generation, 6G) communication system.

[0039] FIG1 shows a block diagram of a wireless communication system applicable to embodiments of the present application. The wireless communication system includes a terminal 11 and a network-side device 12 .

[0040] Among them, the terminal 11 can be a mobile phone, a tablet personal computer, a laptop computer, a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile Internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device, an aircraft (flight vehicle), a vehicle user equipment (VUE), a shipborne device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (PC), an ATM or a self-service machine, and other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, vehicle-mounted controller, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application.

[0041] The network-side device 12 may include an access network device or a core network device. The access network device may also be referred to as a radio access network (RAN) device, a radio access network function, or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AP), or a wireless fidelity (WiFi) node. Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the 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 (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the relevant field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0042] The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (MME), access mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), policy and charging rules function unit (PCRF), edge application service discovery function (EASDF), unified data management (UDM), unified data repository (UDR), home user server (HSS), centralized network configuration (CNC), network storage function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BSF), application function ( Function, AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), Network Data Analytics Function (NWDAF), etc. It should be noted that in the embodiment of the present application, only the core network equipment in the NR system is taken as an example to introduce, and the specific type of the core network equipment is not limited.

[0043] To facilitate understanding, the artificial intelligence (AI) related technologies and concepts involved in the embodiments of this application are first introduced.

[0044] AI technology is widely used in various fields, including communications, healthcare, and education. AI models can be implemented in a variety of ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. The present application examples primarily illustrate the AI ​​model as a neural network, but this does not limit the specific type of AI model.

[0045] FIG2 is a schematic diagram of a neural network, which includes an input layer (X1, X2, ..., X n ), hidden layer, output layer (Y). The neural network is composed of neurons, and the schematic diagram of neurons is shown in Figure 3: z=a1w1+…+a k w k +…+a K w K +b;

[0046] Among them, a1, a2, ..., a k ,…,a K is the input, 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 (tanh), and the rectified linear unit (ReLU) (also known as the linear rectification function).

[0047] Neural network parameters are optimized using a gradient optimization algorithm. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (also known as a loss function). The objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) can be constructed. Once the neural network model is obtained, the predicted output f(x) can be obtained based on the input x, and the difference between the predicted value and the true value (f(x) - Y) can be calculated. This is the loss function. The goal is to find the appropriate W and b to minimize the value of this loss function. The smaller the loss value, the closer the neural network model's predictions are to the true situation.

[0048] Currently, most common optimization algorithms are based on the back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two steps: forward propagation of signals and back propagation of errors. During forward propagation, input samples are passed from the input layer, processed layer by layer through each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the error begins to propagate backward. Back propagation involves propagating the output error back through the hidden layers to the input layer layer by layer in some form, distributing the error to all units in each layer. This error signal is then generated for each unit in each layer, which serves as the basis for adjusting the weights of each unit. This process of adjusting the weights of each layer, through forward propagation of signals and back propagation of errors, is repeated over and over again. This process of continuous weight adjustment is the network's learning and training process. This process continues until the error in the network output is reduced to an acceptable level, or until a pre-set number of learning cycles has been completed.

[0049] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method (Momentum), Nesterov (the name of the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), adaptive learning rate adjustment (Adadelta), root mean square error (RMSprop), adaptive momentum estimation (Adam), etc.

[0050] When these optimization algorithms backpropagate errors, they all calculate the derivative / partial derivative of the current neuron based on the error / loss obtained by the loss function, add the influence of the learning rate, the previous gradient / derivative / partial derivative, etc., obtain the gradient, and pass the gradient to the previous layer.

[0051] In the embodiments of the present application, the model or AI model may also be referred to as an AI unit, an AI module, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI characteristic, a neural network, a neural network function, a neural network function, etc., or the model or AI model may also refer to a processing unit or processing module that can implement specific algorithms, formulas, characteristics, processing flows, capabilities, etc. related to AI, or the model or AI model may be a processing method, algorithm, function, characteristic, module or unit for a specific data set, or the model or AI model may be a processing method, algorithm, function, characteristic, module or unit running on AI / ML-related hardware such as a graphics processing unit (GPU), a neural network processor (NPU), a tensor processing unit (TPU) or an application-specific integrated circuit (ASIC), and the embodiments of the present application do not specifically limit this.

[0052] Optionally, the identifier of a model or AI model can be understood as an AI model identifier, an AI module identifier, an AI structure identifier, an AI algorithm identifier, an AI unit identifier, or an identifier of a specific data set associated with the AI ​​model, or an identifier of a specific scenario, environment, region, cell, channel feature, or device related to AI / ML, or an identifier of a function, feature, capability, or module related to AI / ML, which is not specifically limited in this embodiment of the present application. A feature dataset may include the input or output of a model or AI model.

[0053] The above introduces the relevant technologies and concepts involved in the embodiments of the present application. Now, in combination with the accompanying drawings, the model processing method provided in the embodiments of the present application is described in detail through some embodiments and their application scenarios.

[0054] FIG4 is a flowchart illustrating an implementation of a model processing method provided in an embodiment of the present application. The method includes the following steps:

[0055] S410: The communication device obtains at least two first models;

[0056] S420: The communication device uses at least two first models to obtain a second model or a partial model of the second model or a first data set.

[0057] By applying the method provided in the embodiments of the present application, after the communication device obtains at least two first models, it uses the at least two first models to obtain the second model or a partial model of the second model or a first data set, and fuses multiple first models to obtain the second model or a partial model of the second model or a first data set, thereby aligning the mapping relationship between the input and output of multiple first models. Applying the second model or the partial model of the second model or the first data set to the wireless communication network can obtain better gain and help improve the performance of the wireless communication network.

[0058] In one embodiment, a communications device may obtain a partial model of a first model and, using the partial model of the first model and a third data set, obtain at least two first models. The obtained at least two first models may be understood as a complete first model. If the first model includes a first part and a second part, the first part is designed by the communications device itself, and only the second part needs to be obtained from another communications device or protocol. For example, if the first model is a bilateral model, the communications device obtains the encoder of the first model and then trains it based on the third data set to obtain the decoder of the first model, thereby obtaining the complete first model. For example, if the first model is a bilateral model, the communications device obtains the decoder of the first model and then trains it based on the third data set to obtain the encoder of the first model, thereby obtaining the complete first model. Optionally, the communications device may obtain the third data set by at least one of the following methods: receiving a reference signal to obtain reference signal information; protocol predefinition; or receiving data transmitted by another communications device.

[0059] In one embodiment, the communication device obtains a partial model of the second model. For example, the second model includes a first part and a second part. The first part is designed by the communication device itself, and only the second part needs to be obtained using the first model. For example, if the first model or the second model is a bilateral model, the communication device uses at least two first models to obtain a partial model of the second model, such as the encoder or decoder of the second model. For example, if the communication device is a terminal, the encoder of the second model is obtained; if the communication device is a network-side device, the decoder of the second model is obtained.

[0060] In an embodiment of the present application, the first model may be an AI model, the communication device may be a terminal, such as the terminal 11 in Figure 1, or the communication device may be a network side device, such as the network side device 12 in Figure 1.

[0061] N first models, or a model fusion method, or a data generation method may be predefined via a protocol. N is greater than or equal to 2. After obtaining at least two first models, the communication device may use the model fusion method to obtain a second model or a partial model of the second model using the at least two first models, or use the data generation method to obtain a first data set using the at least two first models.

[0062] Optionally, at least one of the following items of at least two of the first models or the second model or the partial model of the second model is predefined by the protocol:

[0063] Basic model architecture, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc.;

[0064] Model structure, such as the layers, modules, units, etc.

[0065] Parameters of each layer of the model, such as the number of neurons or convolution kernels in each layer;

[0066] Neuron coefficients, such as multiplicative or additive coefficients on neurons;

[0067] Model complexity, such as floating-point operations per second (FLOPs), floating-point operations (FLOPs), and the number of operations in the model;

[0068] Model size (size), such as model storage size;

[0069] Activation function;

[0070] Quantization method, where the quantization method can include fixed point or floating point, such as Int4, Int8, Int16, Int32, Int64, Float16, Float32, double, etc.

[0071] Optionally, the complete models of the at least two first models may be predefined by the protocol, or the parameters required to run the first models may be predefined by the protocol.

[0072] Optionally, at least two of the first models or the second models or partial models of the second models have at least one of the following in common:

[0073] Basic model architecture;

[0074] Model structure;

[0075] Activation function;

[0076] Model complexity;

[0077] The maximum value of model complexity;

[0078] Minimum model complexity;

[0079] Model size;

[0080] The maximum size of the model;

[0081] The minimum model size.

[0082] Optionally, the same parameters of at least two first models or second models or partial models of the second models may be predefined by the protocol.

[0083] Different first models can be obtained by training the same AI function or AI feature for wireless communication. The specific model parameters of different first models may differ, and the input-to-output mapping relationship may also differ. By using multiple first models to obtain a second model or a partial model of the second model or a first data set, the input-to-output mapping relationship of multiple first models can be aligned. Applying the second model or a partial model of the second model or the first data set to a wireless communication network can improve the performance of the wireless communication network.

[0084] Optionally, the second model or a portion of the second model has the same input format or output format as at least two of the first models. For example, if the input of the first model is 16-bit data, the input of the second model is also 16-bit data; or if the input of the first model is data for a single layer of 32 antennas and 13 subbands, which is a 32*13 complex matrix or a 64*13 real matrix (half of the 64 is the real part of the 32 antennas, and the other half is the imaginary part of the 32 antennas), the input of the second model is also data for a single layer of 32 antennas and 13 subbands, which is a 32*13 complex matrix or a 64*13 real matrix. The input format can be understood as the input data format or input data description form, and the output format can be understood as the output data format or output data description form.

[0085] Optionally, the second model or a partial model of the second model or the first data set can be used for at least one of the following:

[0086] Processing of reference signals;

[0087] Transmission of channel signals;

[0088] Demodulation of channel signals;

[0089] Acquisition of channel state information;

[0090] beam management;

[0091] Channel prediction;

[0092] Channel or source encoding and decoding;

[0093] Interference suppression;

[0094] position;

[0095] Forecasting of high-level business or parameters;

[0096] Management of high-level services or parameters;

[0097] Parsing of control signaling.

[0098] The processing of reference signals may include detection, filtering, equalization, etc. Reference signals include Demodulation Reference Signal (DMRS), Sounding Reference Signal (SRS), Synchronization Signal Block (SSB), Channel State Information-Reference Signal (CSI-RS), Tracking Reference Signal (TRS), Positioning Reference Signal (PRS), Phase Tracking Reference Signal (PTRS), etc.

[0099] The transmission of channel signals may include sending and receiving channel signals, etc. Channels may include Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Physical Uplink Control Channel (PUCCH), Physical Uplink Shared Channel (PUSCH), Physical Random Access Channel (PRACH), Physical Broadcast Channel (PBCH), etc.

[0100] Channel state information may include channel-related information, channel matrix-related information, channel characteristic information, channel matrix characteristic information, precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), channel quality indicator (CQI), layer indicator (LI), etc. For a frequency division duplexing (FDD) system, based on the reciprocity of the uplink and downlink parts, network-side equipment, such as a base station, can use the second model and the uplink channel to obtain angle information and delay information, and notify the terminal of the angle information and delay information through CSI-RS precoding or direct indication. The terminal reports according to the indication of the base station or selects and reports within the indication range of the base station, thereby reducing the terminal's calculation amount and the overhead of channel state information reporting.

[0101] Beam management may include beam measurement, beam reporting, beam prediction, beam failure detection, beam failure recovery, and new beam indication during beam failure recovery. Beam prediction may include spatial domain prediction or frequency domain prediction.

[0102] Channel prediction may include prediction of channel state information, beam prediction, etc.

[0103] Channel or source coding may include channel coding, channel decoding, source coding, source decoding, joint source-channel coding, joint source-channel decoding, etc.

[0104] Interference suppression can include suppression of intra-cell interference, inter-cell interference, out-of-band interference, and intermodulation interference;

[0105] Positioning can be understood as using the second model and a reference signal, such as SRS, to estimate the specific location of the terminal, such as horizontal or vertical position, or to estimate the terminal's possible future trajectory, or to obtain information to assist in position estimation or trajectory estimation, such as time of arrival (TOA), line of sight or non-line of sight, or reference signal time difference (RSTD);

[0106] High-level services or parameters may include throughput, required packet size, service requirements, mobile speed, noise information, etc.

[0107] Control signaling may include power control related signaling, beam management related signaling, etc.

[0108] The communication device uses at least two first models to obtain a second model or a partial model of the second model or a first data set. The second model or a partial model of the second model or the first data set is used for at least one of the above tasks, which can obtain better gain and improve the performance of the wireless communication network.

[0109] Optionally, the first data set can be used to train the second model or part of the second model, or to characterize applicable models or functions or characteristics, or to define performance indicators, or to define performance requirements.

[0110] In an embodiment of the present application, the communication device uses at least two first models to obtain a first data set. The first data set can then be used for model training to obtain a second model, or a partial model of the second model. The second model or the partial model of the second model can then be applied to the wireless communication network to obtain better gain.

[0111] Alternatively, the first dataset may be used to represent a model, function, or feature applicable to or working properly on the first dataset. The model, function, or feature applicable to or working properly on the first dataset may be one, multiple, or unlimited. The applicable model, function, or feature may be associated using a dataset ID, a data categorization ID, data-related information, dataset-related information, or dataset-associated signaling.

[0112] Alternatively, a performance KPI or a performance requirement may be defined by the first data set.

[0113] In some embodiments of the present application, the communication device may use at least two first models to obtain a second model or a partial model of the second model or a first data set, which may include the following steps:

[0114] Step 1: The communication device obtains a second data set;

[0115] Step 2: The communication device obtains at least one model input based on at least one data in the second data set;

[0116] Step 3: The communication device inputs at least one model input into each first model to obtain a model output or a model intermediate quantity corresponding to each model input;

[0117] Step 4: The communication device obtains the second model or a partial model of the second model or the first data set based on each model input, or the model output or model intermediate quantity corresponding to each model input.

[0118] For the convenience of description, the above four steps are combined for explanation.

[0119] In this embodiment of the present application, the communication device may obtain the second data set in at least one of the following ways:

[0120] receiving a reference signal and obtaining reference signal information;

[0121] The protocol is predefined;

[0122] Receive data transmitted by other communication devices.

[0123] The second data set may include one or more data.

[0124] After obtaining the second data set, the communication device may obtain at least one model input based on at least one data in the second data set.

[0125] Optionally, the communication device may input each data in the second data set as a model, or the communication device may process each data in the second data set and input each processed data as a model. The processing can be understood as data format conversion, mathematical operations, etc., such as converting a frequency domain channel into a time domain channel, or performing singular value decomposition on the original channel information to obtain an eigenvector, or combining multiple data or elements (such as one data including multiple elements) into a vector or matrix, or converting complex information into real information of twice the size (the real part and imaginary part are listed separately), etc.

[0126] After obtaining at least one model input, the communication device may input the at least one model input into each first model to obtain a model output or model intermediate quantity corresponding to each model input. Each model input corresponds to a different first model and has a corresponding model output or model intermediate quantity.

[0127] For example, the at least two first models obtained by the communication device include the first model 1 and the first model 2, and the at least one model input obtained by the communication device includes model input A, model input B, and model input C. The communication device can input model input A into the first model 1 and the first model 2 respectively, and obtain the model output A1' of the first model 1 corresponding to the model input A, or obtain the model intermediate quantity A1" of the first model 1 corresponding to the model input A, and obtain the model output A2' of the first model 2 corresponding to the model input A, or obtain the model intermediate quantity A2" of the first model 2 corresponding to the model input A. The communication device can input model input B into the first model 1 and the first model 2 respectively, and obtain the model output B1' of the first model 1 corresponding to the model input B, or obtain the model intermediate quantity B1" of the first model 1 corresponding to the model input B, and obtain the model output B2' of the first model 2 corresponding to the model input B, or obtain the model intermediate quantity B2" of the first model 2 corresponding to the model input B. Input the model input C into the first model 1 and the first model 2 respectively to obtain the model output C1' of the first model 1 corresponding to the model input C, or obtain the model intermediate quantity C1" of the first model 1 corresponding to the model input C, and obtain the model output C2' of the first model 2 corresponding to the model input C, or obtain the model intermediate quantity C2" of the first model 2 corresponding to the model input C.

[0128] In this way, we can obtain the mapping relationship between each model input and model output, or the mapping relationship between each model input and model intermediate quantity, or the mapping relationship between each model input and model output and model intermediate quantity, or the mapping relationship between each model input and model output and model intermediate quantity.

[0129] For example, the mapping relationship between each model input and model output or model intermediate quantity is as follows:

[0130] Model input A—model output A1'—model intermediate quantity A1";

[0131] Model input A—model output A2'—model intermediate quantity A2";

[0132] Model input B—model output B1'—model intermediate quantity B1";

[0133] Model input B—model output B2'—model intermediate quantity B2";

[0134] Model input C—model output C1'—model intermediate quantity C1";

[0135] Model input C—model output C2'—model intermediate quantity C2".

[0136] The communication device can obtain the second model or a partial model of the second model or the first data set based on each model input, or the model output or model intermediate quantity corresponding to each model input.

[0137] The communication device inputs the model input into each first model to obtain the model output or model intermediate quantity corresponding to each model input. Based on each model input, or the model output or model intermediate quantity corresponding to each model input, the second model or a partial model of the second model or the first data set can be accurately obtained.

[0138] In some embodiments of the present application, the communication device may obtain the second model or a partial model of the second model or the first data set based on each model input, or a model output or a model intermediate quantity corresponding to each model input, and may include the following steps:

[0139] The first step: the communication device determines the model final output or the model final intermediate quantity corresponding to each model input based on each model input, or the model output or the model intermediate quantity corresponding to each model input;

[0140] The second step: the communication device uses at least one model input, or the model final output or model final intermediate quantity corresponding to each model input to obtain the second model or a partial model of the second model or the first data set.

[0141] For the convenience of description, the above two steps are combined for explanation.

[0142] In an embodiment of the present application, after the communication device inputs at least one model input into each first model respectively, it can obtain the model output or model intermediate quantity corresponding to each model input. Each model input corresponds to a different first model and has a corresponding model output or model intermediate quantity.

[0143] For each model input, the communication device can determine the final model output or final model intermediate quantity corresponding to the current model input based on the current model input, or the model output or model intermediate quantity corresponding to the current model input. The final model output corresponding to the current model input can be understood as a fusion output of multiple first models corresponding to the current model input, and the final model intermediate quantity corresponding to the current model input can be understood as a fusion intermediate quantity of multiple first models corresponding to the current model input. The current model input refers to the model input targeted by the current operation.

[0144] The communication device can obtain the second model or a partial model of the second model or the first data set by using at least one model input, or the final model output or the final model intermediate quantity corresponding to each model input.

[0145] Optionally, the communication device can use at least one model input, or the final model output or final model intermediate quantity corresponding to each model input, to perform model training to obtain a second model or a partial model of the second model.

[0146] Optionally, when the second model is a one-sided model, the input of the second model is the model input, and the output of the second model is the final model output.

[0147] If the second model is a unilateral model, the output of the second model can be obtained by inputting the model input into the second model. The output of the second model is the final output of the model corresponding to the model input.

[0148] For example, the model input includes model input A, model input B, and model input C. The final model output corresponding to model input A is A0', the final model output corresponding to model input B is B0', and the final model output corresponding to model input C is C0'. During model training, the input of the second model includes model input A, model input B, and model input C. The output of the second model corresponding to model input A is the final model output A0', the output of the second model corresponding to model input B is the final model output B0', and the output of the second model corresponding to model input C is the final model output C0'.

[0149] Using the model input as the input of the second model and the model's final output as the output of the second model helps improve the training efficiency of the second model and improve the accuracy of the second model.

[0150] Optionally, when the second model is a two-sided model, the input of the encoder of the second model is the model input, the output of the encoder of the second model or the input of the decoder of the second model is the final intermediate quantity of the model, and the output of the decoder of the second model is the final output of the model.

[0151] If the second model is a bilateral model, the second model may include an encoder and a decoder. The model input may be input into the encoder of the second model. The output of the encoder of the second model is the final intermediate quantity of the model corresponding to the model input. The final intermediate quantity of the model is input into the decoder of the second model. The output of the decoder of the second model may be obtained, that is, the final output of the model corresponding to the model input.

[0152] In one embodiment, a communication device utilizes at least two first models to obtain a partial model of a second model, such as an encoder or decoder of the second model. When the communication device requires the encoder of the second model, it can be obtained using the model input and the final intermediate value of the model; when the communication device requires the decoder of the second model, it can be obtained using the final intermediate value of the model and the final output of the model.

[0153] For example, the model input includes model input A, model input B, and model input C. The final output of the model corresponding to model input A is A0', the final intermediate quantity of the model corresponding to model input A is A0", the final output of the model corresponding to model input B is B0', the final intermediate quantity of the model corresponding to model input B is B0", the final output of the model corresponding to model input C is C0', and the final intermediate quantity of the model corresponding to model input C is C0". During model training, the input of the encoder of the second model includes model input A, model input B, and model input C. The output of the encoder of the second model corresponding to model input A and the input of the decoder of the second model are the model final intermediate quantity A0", the output of the decoder of the second model corresponding to model input A is the model final output A0', the output of the encoder of the second model corresponding to model input B and the input of the decoder of the second model are the model final intermediate quantity B0", the output of the second model corresponding to model input B is the model final output B0', the output of the encoder of the second model corresponding to model input C and the input of the decoder of the second model are the model final intermediate quantity C0", and the output of the second model corresponding to model input C is the model final output C0'.

[0154] Using the model input as the input of the encoder of the second model, using the model's final intermediate quantity as the output of the encoder of the second model or the input of the decoder of the second model, and using the model's final output as the output of the decoder of the second model can help improve the training efficiency of the second model and improve the accuracy of the second model.

[0155] Optionally, the first data set may include at least one data, and each data may include a model input, or a final model output or a final model intermediate quantity corresponding to the model input.

[0156] In some embodiments, the first model is a unilateral model, and the first data set also corresponds to the unilateral model. The first data set may include one or more data, each of which may include a model input and a final model output corresponding to the model input.

[0157] In some embodiments, the first model is a bilateral model, and the first data set also corresponds to the bilateral model. The first data set may include one or more data, each of which may include a model input, a model final output corresponding to the model input, and a model final intermediate quantity.

[0158] In some embodiments, the first model is a bilateral model, and the first data set corresponds to an encoder of the bilateral model. The first data set may include one or more data, each of which may include a model input and a final intermediate quantity of the model corresponding to the model input.

[0159] In some embodiments, the first model is a bilateral model, and the first data set corresponds to a decoder of the bilateral model. The first data set may include one or more data, each of which may include a final intermediate quantity of the model corresponding to a model input and a final output of the model (without including the model input).

[0160] The communication device uses at least one model input, or the final model output or final intermediate quantity of the model corresponding to each model input, to obtain a second model or a partial model of the second model through model training, or to generate a first data set, which can ensure the accuracy of the second model or the partial model of the second model or the first data set.

[0161] In some embodiments of the present application, for each model input, the final model output corresponding to the current model input is determined based on at least one of the following:

[0162] Current model input;

[0163] A first result obtained by operating on the set of model outputs corresponding to the current model input;

[0164] The first model output in the model output set corresponding to the current model input has the highest similarity to the output label corresponding to the current model input;

[0165] The model output set includes: model outputs obtained after the current model input is input into each first model respectively.

[0166] In an embodiment of the present application, after the communication device obtains at least one model input, it can input at least one model input into each first model respectively to obtain a model output or model intermediate quantity corresponding to each model input. One model input corresponds to multiple model outputs or multiple model intermediate quantities.

[0167] For each model input, the final model output corresponding to the current model input can be determined based on at least one of the following:

[0168] 1) Current model input; in one embodiment, when the first model or the second model is a bilateral model, the current model input may be determined as the final model output corresponding to the current model input;

[0169] 2) A first result obtained by operating the model output set corresponding to the current model input; optionally, the first result may be a result obtained by performing an averaging operation on the model output set corresponding to the current model input. The model output set includes: the model outputs obtained after the current model input is input into each first model respectively. The model output set includes multiple model outputs, and the model outputs included in the model output set corresponding to the current model input may be averaged, such as by performing linear averaging, geometric averaging, harmonic averaging, square averaging, weighted averaging, minimum maximization, maximum maximization, combinations of the above or simple changes, to obtain a first result, and the first result may be determined as the final output of the model corresponding to the current model input; optionally, the first result may also be a result obtained by performing other mathematical operations on the model output set corresponding to the current model input, such as a result obtained by performing a summation operation, normalization operation, or eigenvalue decomposition operation on the model output set, which are not listed here one by one;

[0170] 3) The first model output in the model output set corresponding to the current model input has the highest similarity with the output label corresponding to the current model input; the model output set corresponding to the current model input includes multiple model outputs, and the similarity of each model output with the output label corresponding to the current model input can be determined separately to obtain the first model output corresponding to the highest similarity, and the first model output can be determined as the final output of the model corresponding to the current model input. The first model output has the highest similarity with the output label corresponding to the current model input, which can be understood as the first model output being closest to the output label corresponding to the current model input. The highest similarity can be understood as the highest correlation, cosine similarity, square of cosine similarity, etc., or as the smallest gap, difference, mean square error (NMSE), distance, Euclidean distance, etc., or as the smallest absolute value, amplitude, power, etc. of the difference.

[0171] The current model input refers to the model input targeted by the current operation.

[0172] The communication device can determine the final model output corresponding to each model input based on one of the above items, or it can determine the final model output corresponding to each model input based on a combination of the above contents. For example, after performing a mathematical operation on the current model input and the first result, the obtained result is determined as the final model output corresponding to the current model input.

[0173] Optionally, one of the above contents may be predefined through a protocol, and the communication device determines the final model output corresponding to each model input according to the predefined content of the protocol.

[0174] Optionally, the above-mentioned multiple contents can be predefined through a protocol, and the communication device selects one item according to the protocol predefinition, and determines the final model output corresponding to each model input based on the selected content.

[0175] Optionally, the above-mentioned multiple contents and combination methods can be predefined through a protocol. The communication device combines at least two contents according to the predefined protocol to determine the final model output corresponding to each model input.

[0176] Based on at least one of the above contents, the communication device can more accurately determine the final model output corresponding to each model input.

[0177] In some embodiments of the present application, for each model input, the final intermediate quantity of the model corresponding to the current model input is determined based on at least one of the following:

[0178] a second result obtained by operating on a set of model intermediate quantities corresponding to the current model input; the set of model intermediate quantities comprising: model intermediate quantities obtained by inputting the current model input into each of the first models;

[0179] A third result obtained by operating the set of model intermediate quantities and the set of model outputs corresponding to the current model input;

[0180] The first model intermediate quantity in the model intermediate quantity set, the first model intermediate quantity and the second model output are obtained using the same first model, the second model output is a model output in the model output set corresponding to the current model input, and the second model output has the highest similarity with the output label corresponding to the current model input. The model output set includes: the model output obtained after the current model input is input into each first model respectively.

[0181] In an embodiment of the present application, after the communication device obtains at least one model input, it can input at least one model input into each first model respectively to obtain a model output or model intermediate quantity corresponding to each model input. One model input corresponds to multiple model outputs or multiple model intermediate quantities.

[0182] For each model input, the final intermediate quantity of the model corresponding to the current model input can be determined based on at least one of the following:

[0183] 1) A second result obtained by operating the set of model intermediate quantities corresponding to the current model input; optionally, the second result can be the result obtained by averaging the set of model intermediate quantities corresponding to the current model input. The model intermediate quantity set includes: the model intermediate quantities obtained after the current model input is input into each first model respectively. The model intermediate quantity set includes multiple model intermediate quantities, and the model intermediate quantities included in the set of model intermediate quantities corresponding to the current model input can be averaged, such as linear averaging, geometric averaging, harmonic averaging, square averaging, weighted averaging, minimum maximization, maximum maximization, combinations of the above or simple changes, to obtain the second result, and the second result can be determined as the final model intermediate quantity corresponding to the current model input; optionally, the second result can also be the result obtained by performing other mathematical operations on the set of model intermediate quantities corresponding to the current model input, such as summing the model intermediate quantity set, or performing normalization operations, or eigenvalue decomposition operations, etc., which are not listed here one by one;

[0184] 2) A third result obtained by operating on the model intermediate quantity set and the model output set corresponding to the current model input; optionally, the third result may be a result obtained by averaging the model intermediate quantity set and the model output set corresponding to the current model input, or a result obtained by performing other mathematical operations on the model intermediate quantity set and the model output set corresponding to the current model input, such as a result obtained by performing a merging operation, a summing operation, a normalizing operation, or an eigenvalue decomposition operation on the model intermediate quantity set and the model output set corresponding to the current model input, which are not listed here one by one.

[0185] 3) The first model intermediate quantity in the model intermediate quantity set; when the first model is a bilateral model, after the current model input is input into each first model, the model output and model intermediate quantity corresponding to each first model can be obtained. The model output set corresponding to the current model input includes multiple model outputs. The similarity between each model output and the output label corresponding to the current model input can be determined separately to obtain the second model output corresponding to the highest similarity. The first model intermediate quantity corresponding to the second model output can be determined as the final model intermediate quantity corresponding to the current model input. The first model intermediate quantity and the second model output are obtained using the same first model. The second model output has the highest similarity with the output label corresponding to the current model input, which can be understood as the second model output being closest to the output label corresponding to the current model input. The highest similarity can be understood as the highest correlation, cosine similarity, square of cosine similarity, etc., or as the smallest gap, difference, mean square error (NMSE), distance, Euclidean distance, etc., or as the smallest absolute value, amplitude, power, etc. of the difference.

[0186] The current model input refers to the model input targeted by the current operation.

[0187] The communication device can determine the model final intermediate quantity corresponding to each model input based on the above item, or determine the model final intermediate quantity corresponding to each model input based on a combination of the above contents. For example, after performing a mathematical operation on the second result and the first model intermediate quantity, the obtained result is determined as the model final intermediate quantity corresponding to the current model input.

[0188] Optionally, one of the above contents may be predefined through a protocol, and the communication device determines the final intermediate quantity of the model corresponding to each model input according to the content predefined by the protocol.

[0189] Optionally, the above-mentioned multiple contents can be predefined through a protocol, and the communication device selects one item according to the protocol predefinition, and determines the final intermediate quantity of the model corresponding to each model input based on the selected content.

[0190] Optionally, the above-mentioned multiple contents and combination methods can be predefined through a protocol, and the communication device combines at least two contents according to the protocol predefinition to determine the final intermediate quantity of the model corresponding to each model input.

[0191] Based on at least one of the above contents, the communication device can more accurately determine the final intermediate quantity of the model corresponding to each model input.

[0192] In some embodiments of the present application, the communication device may use at least two first models to obtain a second model or a partial model of the second model, which may include the following steps:

[0193] The communication device combines at least two first models into a second model or a partial model of the second model.

[0194] In an embodiment of the present application, after obtaining at least two first models, the communication device may combine the at least two first models into a new large model, which serves as the second model or a partial model of the second model. Alternatively, the communication device may combine the at least two first models into the second model or a partial model of the second model according to a model fusion method predefined in the protocol. For example, the model parameters of the at least two first models may be averaged.

[0195] The communication device combines at least two first models into a second model or a partial model of the second model, which can improve the efficiency of model fusion.

[0196] For ease of understanding, the technical solutions provided in the embodiments of the present application are described below with reference to specific examples.

[0197] Example 1: The first model and the second model are unilateral models

[0198] In this example, it is assumed that the model input includes model input A, and the at least two first models include a first model 1 and a first model 2 .

[0199] As shown in FIG5 , the model input A is input into the first model 1 and the first model 2 respectively, and two model outputs are obtained, including the model output A1 ′ of the first model 1 and the model output A2 ′ of the first model 2 .

[0200] The final output (Final Output) A0' of the model corresponding to the model input A can be obtained through the above two model outputs, where A0'=F(model output A1', model output A2').

[0201] The final output of the model may be the average of the outputs of the two models; averaging methods include linear averaging, geometric averaging, harmonic averaging, square averaging, weighted averaging, maximizing the minimum, minimizing the maximum, and combinations or simple variations of at least two of the above averaging methods.

[0202] The final model output can also be the model output that is closest to the output label corresponding to the model input A among the two model outputs mentioned above; M is closest to N can be understood as: the correlation, cosine similarity, and square of cosine similarity between M and N are the highest, or the gap, difference, NMSE, distance, Euclidean distance between M and N are the smallest, or the absolute value, amplitude, and power of (MN) are the smallest.

[0203] Using the model input or the final output of the model, model fusion is performed to obtain a second model or generate a first data set.

[0204] The input of the second model is the model input A, and the output is the model final output A0';

[0205] A data of the generated first data set includes the model input A, or the model final output A0'.

[0206] Example 2: The first model and the second model are bilateral models.

[0207] In this example, it is assumed that the model input includes model input B, and the at least two first models include first model 3 and first model 4 .

[0208] As shown in Figure 6, the model input B is input into the encoder (Encoder) of the first model 3 and the encoder of the first model 4 respectively, and two model intermediate quantities (inter-data) are obtained, including the model intermediate quantity B3" of the first model 3, and the model intermediate quantity B4" of the first model 4. These two model intermediate quantities are input into the corresponding decoder (Decoder) of the first model 3 and the decoder of the first model 4 respectively, and two model outputs are obtained, including the model output B1' of the first model 3, and the model output B4' of the first model 4. Among them, the model output B3' and the model intermediate quantity B3" are obtained using the same first model, that is, the first model 3, and the model output B4' and the model intermediate quantity B4" are obtained using the same first model, that is, the first model 4.

[0209] The final intermediate quantity (Final inter-data) B0' or the final output (Final Output) B0' of the model corresponding to the model input B can be obtained through the above two model outputs.

[0210] B0'=F(model output B3', model output B4').

[0211] There are the following solutions to determine the final output B0' of the model:

[0212] Solution 1: The final output of the model B0' is the model input B;

[0213] If the second model is used for compression or recovery of channel information / CSI, such as the encoder is used to compress channel information / CSI into feedback information, and the decoder is used to restore feedback information into channel information / CSI, or the second model is used for encoding or decoding, such as source encoding and decoding, channel encoding and decoding, source-channel joint encoding and decoding, etc. (the encoder is used for encoding, and the decoder is used for decoding), then this scheme can be used to determine the final output of the model.

[0214] Solution 2: The final output of the model B0' is the average of the outputs of the above two models;

[0215] The averaging methods include linear averaging, geometric averaging, harmonic averaging, square averaging, weighted averaging, minimum maximization, maximum maximization, and combinations or simple variations of at least two of the above averaging methods.

[0216] Solution 3: The final model output B0' is the model output closest to the output label among the above two model outputs;

[0217] M is closest to N, which can be understood as: the correlation, cosine similarity, and square of cosine similarity between M and N are the highest, or the gap, difference, NMSE, distance, and Euclidean distance between M and N are the smallest, or the absolute value, amplitude, and power of (MN) are the smallest;

[0218] For the first model used for channel information / CSI compression and recovery, or for encoding and decoding (source coding, channel coding, or joint source-channel coding), the output label is the model input. The final model output B0' is the model output that is closest to the model input.

[0219] There are the following solutions for determining the final intermediate quantity B0" of the model:

[0220] Solution 1: B0″=F(model intermediate quantity B3″, model intermediate quantity B4″), optionally, the final model intermediate quantity B0″ is the average of the above two model intermediate quantities;

[0221] Solution 2: The final intermediate quantity B0" of the model is the intermediate quantity corresponding to the model output closest to the output label among the two model outputs mentioned above.

[0222] There are the following optional combinations for determining the final output of the model and the final intermediate quantity of the model:

[0223] Scheme 1 of the model's final output and schemes 1 and 2 of the model's final intermediate quantities can be combined;

[0224] Scheme 2 of the model's final output and Scheme 1 of the model's final intermediate quantity can be combined;

[0225] Scheme 3 for the final output of the model and Scheme 2 for the final intermediate quantity of the model can be combined.

[0226] Model fusion can be performed using the model input, or the final output of the model, or the final intermediate quantity of the model to obtain a second model or generate a first data set.

[0227] The input of the encoder of the second model is the model input B, the output of the encoder or the input of the decoder is the final intermediate quantity of the model B0", and the output of the decoder is the final output of the model B0';

[0228] A data of the generated first data set includes a model input B, or a final intermediate quantity of the model B0", or a final output of the model B0'.

[0229] The embodiments of the present application can fuse multiple first models into a second model or a partial model of the second model, or generate a reference data set, thereby aligning the mapping relationship from the input to the output of multiple first models. Using the second model or the partial model of the second model can improve the performance of the wireless communication system.

[0230] The model processing method provided in the embodiment of the present application can be executed by a model processing device. In the embodiment of the present application, the model processing device provided in the embodiment of the present application is described by taking the execution of the model processing method by the model processing device as an example.

[0231] As shown in FIG7 , the model processing device 700 includes the following modules:

[0232] A first obtaining module 710 is configured to obtain at least two first models;

[0233] The second obtaining module 720 is configured to obtain a second model or a partial model of the second model or a first data set using at least two first models.

[0234] By applying the device provided in the embodiment of the present application, after obtaining at least two first models, the at least two first models are used to obtain a second model or a first data set, and the multiple first models are fused to obtain a second model or a partial model of the second model or a first data set, thereby aligning the mapping relationship between the input and output of the multiple first models. Applying the second model or the partial model of the second model or the first data set to a wireless communication network can obtain better gain, which helps to improve the performance of the wireless communication network.

[0235] In some embodiments of the present application, the second obtaining module 720 includes:

[0236] A first obtaining submodule is used to obtain a second data set;

[0237] A second obtaining submodule, configured to obtain at least one model input based on at least one data in the second data set;

[0238] A third obtaining submodule is configured to input at least one model input into each first model to obtain a model output or a model intermediate quantity corresponding to each model input;

[0239] The fourth obtaining submodule is used to obtain the second model or a partial model of the second model or the first data set based on each model input, or the model output or model intermediate quantity corresponding to each model input.

[0240] In some embodiments of the present application, the fourth obtaining submodule is specifically configured to:

[0241] Determine the final model output or the final model intermediate quantity corresponding to each model input based on each model input, or the model output or the model intermediate quantity corresponding to each model input;

[0242] A second model or a partial model of the second model or the first data set is obtained by using at least one model input, or a final model output or a final model intermediate quantity corresponding to each model input.

[0243] In some embodiments of the present application, for each model input, the final model output corresponding to the current model input is determined based on at least one of the following:

[0244] Current model input;

[0245] A first result obtained by operating on the set of model outputs corresponding to the current model input;

[0246] The first model output in the model output set corresponding to the current model input has the highest similarity to the output label corresponding to the current model input;

[0247] The model output set includes: model outputs obtained after the current model input is input into each first model respectively.

[0248] In some embodiments of the present application, for each model input, the final intermediate quantity of the model corresponding to the current model input is determined based on at least one of the following:

[0249] A second result obtained by operating on the set of model intermediate quantities corresponding to the current model input;

[0250] A third result obtained by operating the model intermediate quantity set and the model output set corresponding to the current model input;

[0251] A first model intermediate quantity in the set of model intermediate quantities, where the first model intermediate quantity and the second model output are obtained using the same first model, the second model output is a model output in the set of model outputs corresponding to the current model input, and the second model output has the highest similarity to the output label corresponding to the current model input;

[0252] The model intermediate quantity set includes: model intermediate quantities obtained after inputting the current model input into each first model respectively;

[0253] The model output set includes: model outputs obtained after the current model input is input into each first model respectively.

[0254] In some embodiments of the present application, when the second model is a unilateral model, the input of the second model is the model input, and the output of the second model is the final model output.

[0255] In some embodiments of the present application, when the second model is a bilateral model, the input of the encoder of the second model is the model input, the output of the encoder of the second model or the input of the decoder of the second model is the final intermediate quantity of the model, and the output of the decoder of the second model is the final output of the model.

[0256] In some embodiments of the present application, the first obtaining module is specifically configured to:

[0257] Obtain the second dataset by at least one of the following methods:

[0258] receiving a reference signal and obtaining reference signal information;

[0259] The protocol is predefined;

[0260] Receive data transmitted by other communication devices.

[0261] In some embodiments of the present application, the second obtaining module is specifically configured to:

[0262] At least two first models are combined into a second model or a partial model of a second model.

[0263] In some embodiments of the present application, the first data set is used to train the second model or a portion of the second model, or to characterize an applicable model or function or characteristic, or to define performance indicators, or to define performance requirements.

[0264] In some embodiments of the present application, at least one of the following items of at least two first models or second models or partial models of the second models is predefined by the protocol:

[0265] Basic architecture of the model; model structure; parameters of each layer of the model; neuron coefficients; model complexity; model size; activation function; quantization method.

[0266] In some embodiments of the present application, at least two first models or second models or partial models of the second models have at least one of the following in common:

[0267] Model basic architecture; model structure; activation function; model complexity; maximum model complexity; minimum model complexity; model size; maximum model size and minimum model size.

[0268] In some embodiments of the present application, the second model or a partial model of the second model has the same input format or output format as at least two first models.

[0269] In some embodiments of the present application, the second model or a partial model of the second model or the first data set is used for at least one of the following:

[0270] Processing of reference signals;

[0271] Transmission of channel signals;

[0272] Demodulation of channel signals;

[0273] Acquisition of channel state information;

[0274] Beam management;

[0275] Channel prediction;

[0276] Channel or source encoding and decoding;

[0277] Interference suppression;

[0278] position;

[0279] Forecasting of high-level business or parameters;

[0280] Management of high-level services or parameters;

[0281] Parsing of control signaling.

[0282] In some embodiments of the present application, the first obtaining module 710 is specifically configured to:

[0283] obtaining at least two partial models of the first model;

[0284] At least two first models are obtained by using the partial models of the at least two first models and the third data set.

[0285] The model processing device 700 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 4 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0286] As shown in Figure 8, an embodiment of the present application further provides a communication device 800, including a processor 801 and a memory 802. The memory 802 stores a program or instruction that can be run on the processor 801. For example, when the communication device 800 is a terminal, the program or instruction is executed by the processor 801 to implement the various steps of the above-mentioned model processing method embodiment and can achieve the same technical effect. When the communication device 800 is a network-side device, the program or instruction is executed by the processor 801 to implement the various steps of the above-mentioned model processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0287] The present application also provides a terminal including a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is configured to execute a program or instruction to implement the steps in the method embodiment shown in FIG4 . This terminal embodiment corresponds to the above-described method embodiment, and each implementation process and implementation method of the above-described method embodiment is applicable to this terminal embodiment and can achieve the same technical effects.

[0288] Specifically, FIG9 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[0289] The terminal 900 includes but is not limited to: a radio frequency unit 901, a network module 902, an audio output unit 903, an input unit 904, a sensor 905, a display unit 906, a user input unit 907, an interface unit 908, a memory 909 and at least some of the components of the processor 910.

[0290] Those skilled in the art will appreciate that the terminal 900 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 910 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG9 does not limit the terminal. The terminal may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.

[0291] It should be understood that in an embodiment of the present application, the input unit 904 may include a graphics processing unit (GPU) 9041 and a microphone 9042, and the graphics processor 9041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 906 may include a display panel 9061, and the display panel 9061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 907 includes a touch panel 9071 and at least one of other input devices 9072. The touch panel 9071 is also called a touch screen. The touch panel 9071 may include two parts: a touch detection device and a touch controller. Other input devices 9072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0292] In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 901 may transmit the data to the processor 910 for processing. Furthermore, the RF unit 901 may send uplink data to the network-side device. Typically, the RF unit 901 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0293] The memory 909 can be used to store software programs or instructions and various data. The memory 909 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 909 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 909 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0294] Processor 910 may include one or more processing units. Optionally, processor 910 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 910.

[0295] The processor 910 is configured to obtain at least two first models;

[0296] By using at least two first models, a second model or a partial model of the second model or a first data set is obtained.

[0297] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the method embodiment and achieve the same or corresponding technical effects. To avoid repetition, it will not be described here.

[0298] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG4 . This network-side device embodiment corresponds to the above-described method embodiment, and each implementation process and implementation method of the above-described method embodiment are applicable to this network-side device embodiment and can achieve the same technical effects.

[0299] Specifically, an embodiment of the present application also provides a network-side device. As shown in Figure 10, the network-side device 1000 includes: an antenna 1001, a radio frequency device 1002, a baseband device 1003, a processor 1004, and a memory 1005. Antenna 1001 is connected to radio frequency device 1002. In the uplink direction, radio frequency device 1002 receives information via antenna 1001 and sends the received information to baseband device 1003 for processing. In the downlink direction, baseband device 1003 processes the information to be transmitted and sends it to radio frequency device 1002. Radio frequency device 1002 processes the received information and sends it through antenna 1001.

[0300] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 1003 , which includes a baseband processor.

[0301] The baseband device 1003 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 10, one of which is, for example, a baseband processor, which is connected to the memory 1005 through a bus interface to call the program in the memory 1005 and execute the network side device operations shown in the above method embodiment.

[0302] The network side device may further include a network interface 1006, which is, for example, a Common Public Radio Interface (CPRI).

[0303] Specifically, the network side device 1000 of the embodiment of the present application also includes: instructions or programs stored in the memory 1005 and executable on the processor 1004. The processor 1004 calls the instructions or programs in the memory 1005 to execute the method executed by each module in the execution model processing device 700 and achieves the same technical effect. To avoid repetition, it will not be described here.

[0304] Specifically, the embodiment of the present application further provides a network-side device. As shown in FIG11 , the network-side device 1100 includes a processor 1101, a network interface 1102, and a memory 1103. The network interface 1102 is, for example, a common public radio interface (CPRI).

[0305] Specifically, the network side device 1100 of the embodiment of the present application also includes: instructions or programs stored in the memory 1103 and executable on the processor 1101. The processor 1101 calls the instructions or programs in the memory 1103 to execute the methods executed by each module in the execution model processing device 700 and achieves the same technical effect. To avoid repetition, it will not be repeated here.

[0306] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0307] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0308] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0309] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0310] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0311] An embodiment of the present application also provides a wireless communication system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the model processing method described above, and the network side device can be used to execute the steps of the model processing method described above.

[0312] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0313] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0314] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A model processing method, wherein: include: The communication device obtains at least two first models; The communication device uses the at least two first models to obtain a second model or a partial model of the second model or a first data set.

2. The model processing method according to claim 1, wherein: The communication device obtains a second model or a partial model of the second model or a first data set by using the at least two first models, including: The communication device obtains a second data set; The communication device obtains at least one model input based on at least one data in the second data set; The communication device inputs the at least one model input into each first model respectively to obtain a model output or a model intermediate quantity corresponding to each model input; The communication device obtains the second model or a partial model of the second model or the first data set based on each model input, or the model output or model intermediate quantity corresponding to each model input.

3. The model processing method according to claim 2, wherein: The communication device obtains a second model or a partial model of the second model or a first data set based on each model input, or a model output or a model intermediate quantity corresponding to each model input, including: The communication device determines the model final output or the model final intermediate quantity corresponding to each model input based on each model input or the model output or the model intermediate quantity corresponding to each model input; The communication device uses the at least one model input, or the model final output or model final intermediate quantity corresponding to each model input to obtain the second model or a partial model of the second model or the first data set.

4. The model processing method according to claim 3, wherein: For each model input, the final model output corresponding to the current model input is determined based on at least one of the following: the current model input; a first result obtained by operating the set of model outputs corresponding to the current model input; A first model output in the model output set corresponding to the current model input, wherein the first model output has the highest similarity to the output label corresponding to the current model input; The model output set includes: model outputs obtained after the current model input is input into each first model respectively.

5. The model processing method according to claim 3 or 4, wherein: For each model input, the final intermediate quantity of the model corresponding to the current model input is determined based on at least one of the following: a second result obtained by operating the set of model intermediate quantities corresponding to the current model input; a third result obtained by operating the set of model intermediate quantities and the set of model outputs corresponding to the current model input; a first model intermediate quantity in the set of model intermediate quantities, wherein the first model intermediate quantity and a second model output are obtained using the same first model, the second model output is a model output in the set of model outputs corresponding to the current model input, and the second model output has the highest similarity to the output label corresponding to the current model input; The model intermediate quantity set includes: model intermediate quantities obtained after inputting the current model input into each first model respectively; The model output set includes: model outputs obtained after the current model input is input into each first model respectively.

6. The model processing method according to any one of claims 3 to 5, wherein: In the case where the second model is a unilateral model, the input of the second model is the model input, and the output of the second model is the final output of the model.

7. The model processing method according to any one of claims 3 to 5, wherein: In the case where the second model is a bilateral model, the input of the encoder of the second model is the model input, the output of the encoder of the second model or the input of the decoder of the second model is the final intermediate quantity of the model, and the output of the decoder of the second model is the final output of the model.

8. The model processing method according to any one of claims 2 to 7, wherein: The communication device obtains a second data set, including: The communication device obtains the second data set by at least one of the following methods: receiving a reference signal and obtaining reference signal information; The protocol is predefined; Receive data transmitted by other communication devices.

9. The model processing method according to claim 1, wherein: The communication device obtains a second model or a partial model of the second model by using the at least two first models, including: The communication device combines the at least two first models into a second model or a partial model of the second model.

10. The model processing method according to any one of claims 1 to 9, wherein: The first data set is used to train the second model or a part of the second model, or to characterize an applicable model or function or feature, or to define performance indicators, or to define performance requirements.

11. The model processing method according to any one of claims 1 to 10, wherein: At least one of the following items of the at least two first models or the second model or a partial model of the second model is predefined by the protocol: Basic architecture of the model; model structure; parameters of each layer of the model; neuron coefficients; model complexity; model size; activation function; quantization method.

12. The model processing method according to any one of claims 1 to 11, wherein: The at least two first models or the second model or a partial model of the second model have at least one of the following in common: Model basic architecture; model structure; activation function; model complexity; maximum model complexity; minimum model complexity; model size; maximum model size and minimum model size.

13. The model processing method according to any one of claims 1 to 12, wherein: The second model or a partial model of the second model has the same input format or output format as the at least two first models.

14. The model processing method according to any one of claims 1 to 13, wherein: The second model or a partial model of the second model or the first data set is used for at least one of the following: Processing of reference signals; Transmission of channel signals; Demodulation of channel signals; Acquisition of channel state information; beam management; Channel prediction; Channel or source encoding and decoding; Interference suppression; position; Forecasting of high-level business or parameters; Management of high-level services or parameters; Parsing of control signaling.

15. The model processing method according to any one of claims 1 to 14, wherein: The communication device obtains at least two first models, including: The communication device obtains at least two partial models of the first model; The communication device obtains at least two first models using the partial models of the at least two first models and the third data set.

16. A model processing device, wherein: include: A first obtaining module, configured to obtain at least two first models; The second obtaining module is used to obtain the second model or a partial model of the second model or the first data set by using the at least two first models.

17. The model processing device according to claim 16, wherein: The second obtaining module includes: A first obtaining submodule is used to obtain a second data set; a second obtaining submodule, configured to obtain at least one model input based on at least one data in the second data set; A third obtaining submodule is configured to input the at least one model input into each first model to obtain a model output or a model intermediate quantity corresponding to each model input; The fourth obtaining submodule is used to obtain the second model or a partial model of the second model or the first data set based on each model input, or the model output or model intermediate quantity corresponding to each model input.

18. The model processing device according to claim 17, wherein: The fourth obtaining submodule is specifically used to: Determine the final model output or the final model intermediate quantity corresponding to each model input based on each model input, or the model output or the model intermediate quantity corresponding to each model input; The second model or a partial model of the second model or the first data set is obtained by using the at least one model input, or the final model output or the final model intermediate quantity corresponding to each model input.

19. The model processing device according to claim 18, wherein: For each model input, the final model output corresponding to the current model input is determined based on at least one of the following: the current model input; a first result obtained by operating the set of model outputs corresponding to the current model input; A first model output in the model output set corresponding to the current model input, wherein the first model output has the highest similarity to the output label corresponding to the current model input; The model output set includes: model outputs obtained after the current model input is input into each first model respectively.

20. The model processing device according to claim 18 or 19, wherein: For each model input, the final intermediate quantity of the model corresponding to the current model input is determined based on at least one of the following: a second result obtained by operating the set of model intermediate quantities corresponding to the current model input; a third result obtained by operating the set of model intermediate quantities and the set of model outputs corresponding to the current model input; a first model intermediate quantity in the set of model intermediate quantities, wherein the first model intermediate quantity and a second model output are obtained using the same first model, the second model output is a model output in the set of model outputs corresponding to the current model input, and the second model output has the highest similarity to the output label corresponding to the current model input; The model intermediate quantity set includes: model intermediate quantities obtained after inputting the current model input into each first model respectively; The model output set includes: model outputs obtained after the current model input is input into each first model respectively.

21. The model processing device according to any one of claims 18 to 20, wherein: In the case where the second model is a unilateral model, the input of the second model is the model input, and the output of the second model is the final output of the model.

22. The model processing device according to any one of claims 18 to 20, wherein: In the case where the second model is a bilateral model, the input of the encoder of the second model is the model input, the output of the encoder of the second model or the input of the decoder of the second model is the final intermediate quantity of the model, and the output of the decoder of the second model is the final output of the model.

23. The model processing device according to any one of claims 17 to 22, wherein: The first obtaining module is specifically configured to: Obtain the second dataset by at least one of the following methods: receiving a reference signal and obtaining reference signal information; The protocol is predefined; Receive data transmitted by other communication devices.

24. The model processing device according to claim 16, wherein: The second obtaining module is specifically configured to: The at least two first models are combined into a second model or a partial model of a second model.

25. The model processing device according to any one of claims 16 to 24, wherein: The first data set is used to train the second model or a part of the second model, or to characterize an applicable model or function or feature, or to define performance indicators, or to define performance requirements.

26. The model processing device according to any one of claims 16 to 25, wherein: At least one of the following items of the at least two first models or the second model or a partial model of the second model is predefined by the protocol: Basic architecture of the model; model structure; parameters of each layer of the model; neuron coefficients; model complexity; model size; activation function; quantization method.

27. The model processing device according to any one of claims 16 to 26, wherein: The at least two first models or the second model or a partial model of the second model have at least one of the following in common: Model basic architecture; model structure; activation function; model complexity; maximum model complexity; minimum model complexity; model size; maximum model size and minimum model size.

28. The model processing device according to any one of claims 16 to 27, wherein: The second model or a partial model of the second model has the same input format or output format as the at least two first models.

29. The model processing device according to any one of claims 16 to 28, wherein: The second model or a partial model of the second model or the first data set is used for at least one of the following: Processing of reference signals; Transmission of channel signals; Demodulation of channel signals; Acquisition of channel state information; beam management; Channel prediction; Channel or source encoding and decoding; Interference suppression; position; Forecasting of high-level business or parameters; Management of high-level services or parameters; Parsing of control signaling.

30. The model processing device according to any one of claims 16 to 29, wherein: The first obtaining module is specifically configured to: obtaining at least two partial models of the first model; At least two first models are obtained by using the partial models of the at least two first models and the third data set.

31. A communication device, wherein: The method comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the model processing method according to any one of claims 1 to 15 are implemented.

32. A readable storage medium, wherein: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the model processing method according to any one of claims 1 to 15 are implemented.

Images