Transmission method and apparatus, and device, readable storage medium and computer program product

Abstract

The present application relates to the technical field of communications, and specifically relates to a transmission method and apparatus, and a device, a readable storage medium and a computer program product. The method comprises: a first communication device receiving from a second communication device first data and a first identifier associated with the first data (201); and the first communication device determining a target AI model on the basis of the first data and the first identifier (202), wherein the first identifier comprises at least one of the following: a first-type identifier, which comprises an identifier of the first data; a second-type identifier, which comprises an association identifier of the first data; and a third-type identifier, which comprises a model-related identifier.

Description

Transmission methods, apparatus, devices, readable storage media, and computer program products

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411576376.7, filed in China on November 6, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of communication technology, specifically relating to a transmission method, apparatus, device, readable storage medium, and computer program product. Background Technology

[0004] Currently, data transmission occurs in artificial intelligence (AI) communication, and identifiers are carried in this process. However, the relevant technologies do not have a clear definition of the meaning and usage of these identifiers. Summary of the Invention

[0005] This application provides a transmission method, apparatus, device, readable storage medium, and computer program product that can solve the problem that the meaning and usage of the identifier carried in the data transmission process of AI communication are not clearly defined.

[0006] Firstly, a transmission method is provided, including:

[0007] The first communication device receives first data and a first identifier associated with the first data from the second communication device;

[0008] The first communication device determines the target artificial intelligence (AI) model based on the first data and the first identifier;

[0009] The first identifier includes at least one of the following:

[0010] The first type of identifier includes the identifier of the first data;

[0011] The second type of identifier includes the association identifier of the first data;

[0012] The third category of identifiers includes model-related identifiers.

[0013] Secondly, a transmission method is provided, including:

[0014] The second communication device sends first data and a first identifier associated with the first data to the first communication device;

[0015] The first data and the first identifier are used by the first communication device to determine the target AI model;

[0016] The first identifier includes at least one of the following:

[0017] The first type of identifier includes the identifier of the first data;

[0018] The second type of identifier includes the association identifier of the first data;

[0019] The third category of identifiers includes model-related identifiers.

[0020] Thirdly, a transmission device is provided, comprising:

[0021] A first receiving module is configured to receive first data and a first identifier associated with the first data from a second communication device.

[0022] The first processing module is used to determine the target AI model based on the first data and the first identifier;

[0023] The first identifier includes at least one of the following:

[0024] The first type of identifier includes the identifier of the first data;

[0025] The second type of identifier includes the association identifier of the first data;

[0026] The third category of identifiers includes model-related identifiers.

[0027] Fourthly, a transmission device is provided, comprising:

[0028] A first sending module is configured to send first data and a first identifier associated with the first data to a first communication device.

[0029] The first data and the first identifier are used by the first communication device to determine the target AI model;

[0030] The first identifier includes at least one of the following:

[0031] The first type of identifier includes the identifier of the first data;

[0032] The second type of identifier includes the association identifier of the first data;

[0033] The third category of identifiers includes model-related identifiers.

[0034] Fifthly, a transmission device is provided, the device being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0035] In a sixth aspect, a communication device is provided, the communication device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect, or implementing the steps of the method as described in the second aspect.

[0036] Seventhly, a communication device is provided, including a processor and a communication interface, wherein,

[0037] When the communication device is a first communication device, the communication interface is used for the first communication device to receive first data from the second communication device, and a first identifier associated with the first data;

[0038] The processor is used by the first communication device to determine the target artificial intelligence (AI) model based on the first data and the first identifier;

[0039] The first identifier includes at least one of the following:

[0040] The first type of identifier includes the identifier of the first data;

[0041] The second type of identifier includes the association identifier of the first data;

[0042] The third category of identifiers includes model-related identifiers.

[0043] When the communication device is a second communication device, the communication interface is used for the second communication device to send first data and a first identifier associated with the first data to the first communication device;

[0044] The first data and the first identifier are used by the first communication device to determine the target AI model;

[0045] The first identifier includes at least one of the following:

[0046] The first type of identifier includes the identifier of the first data;

[0047] The second type of identifier includes the association identifier of the first data;

[0048] The third category of identifiers includes model-related identifiers.

[0049] Eighthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0050] A ninth aspect provides a wireless communication system, comprising: a first communication device and a second communication device, wherein the first communication device is configured to perform the steps of the method described in the first aspect, and the second communication device is configured to perform the steps of the method described in the second aspect.

[0051] In a tenth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0052] Eleventhly, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect.

[0053] In this application embodiment, a specific definition and usage of identifiers in AI communication data transmission are given, clarifying the meaning and usage of data transmission, thereby improving the efficiency of the AI ​​communication system. Attached Figure Description

[0054] Figure 1a is a block diagram of a wireless communication system applicable to an embodiment of this application;

[0055] Figure 1b is a schematic diagram of a neural network for a related technology;

[0056] Figure 1c is a schematic diagram of the neural network principle of a related technology;

[0057] Figure 2 is a schematic flowchart of one of the transmission methods provided in the embodiments of this application;

[0058] Figure 3 is a second schematic flowchart of the transmission method provided in the embodiments of this application;

[0059] Figure 4 is a schematic diagram of the structure of a transmission device provided in an embodiment of this application;

[0060] Figure 5 is a second schematic diagram of the transmission device provided in an embodiment of this application;

[0061] Figure 6 is a schematic diagram of the structure of the communication device provided in an embodiment of this application;

[0062] Figure 7 is a schematic diagram of the structure of the terminal provided in an embodiment of this application;

[0063] Figure 8 is a schematic diagram of the structure of a network-side device provided in an embodiment of this application;

[0064] Figure 9 is a second schematic diagram of the network-side device provided in an embodiment of this application. Detailed Implementation

[0065] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0066] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0067] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0068] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0069] Figure 1a shows a block diagram of a wireless communication system applicable to an embodiment of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0070] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support. The core network functions include: BSF (Block Network Function), Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), and Network Data Analytics Function (NWDAF). It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0071] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0072] To better understand the technical solution of this application, the following content will be introduced first:

[0073] AI

[0074] AI has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks. AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but it does not limit the specific type of AI module.

[0075] A neural network is shown in Figure 1b.

[0076] A neural network is composed of neurons, as illustrated in the diagram below. Here, a1, a2, ..., aK are the inputs, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ() is the activation function. Common activation functions include Sigmoid, tanh, Rectified Linear Unit (ReLU), etc.

[0077] As shown in Figure 1c, the parameters of the neural network are optimized using gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (sometimes called a loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). With the model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. Our goal is to find suitable W and b that minimize the value of the above loss function. The smaller the loss value, the closer our model is to the reality.

[0078] Most common optimization algorithms are based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two parts: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error to all units in each layer, thus obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is repeated continuously. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.

[0079] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (named after the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0080] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0081] The transmission method provided in this application will be described in detail below with reference to the accompanying drawings, through some embodiments and application scenarios.

[0082] First, let's explain some of the terms and concepts involved in the technical solution of this application:

[0083] AI Unit / AI Model

[0084] The AI ​​unit / AI model described in this application may also be referred to as an AI unit, AI model, machine learning (ML) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, the AI ​​unit / AI model may refer to a processing unit capable of implementing specific algorithms, formulas, characteristics, processing flows, capabilities, etc., related to AI. Or, the AI ​​unit / AI model may be a processing method, algorithm, function, characteristic, module, or unit for a specific dataset. Alternatively, the AI ​​unit / 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), Neural Processing Unit (NPU), Tensor Processing Unit (TPU), or Application-Specific Integrated Circuit (ASIC). This application does not specifically limit its scope. Optionally, the specific dataset includes the input and / or output of the AI ​​unit / AI model.

[0085] Optionally, the identifier of the AI ​​unit / AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​unit / AI model, or an identifier of a specific scenario, environment, region, cell, channel characteristic, or device related to the AI / ML, or an identifier of a function, characteristic, capability, or module related to the AI / ML. This application does not specifically limit this.

[0086] data

[0087] Specifically, it can be data or a dataset, and the data transmission can also be a dataset transfer.

[0088] The execution entities involved in the technical solution of this application are a first communication device and a second communication device, that is, two communication devices capable of interaction and data output. The first communication device may specifically be a terminal, a network-side device, etc., and the second communication device may also be a terminal, a network-side device, etc.

[0089] Model transfer can occur when a network (NW) sends a model to a user equipment (UE), a UE sends a model to the NW, the core network sends a model to the NW, or the NW sends a model to the core network. The UE can be a UE device, a UE-side server, or a UE manufacturer; the NW can be an NW device, an NW-side server, or an NW manufacturer.

[0090] Data transmission can be from NW to UE, from UE to NW, from core network to NW, or from NW to core network.

[0091] Referring to Figure 2, this application embodiment provides a transmission method, the execution subject of which is a first communication device, and the method includes:

[0092] Step 201: The first communication device receives first data and a first identifier associated with the first data from the second communication device;

[0093] Step 202: The first communication device determines the target AI model based on the first data and the first identifier;

[0094] Understandably, the aforementioned target AI model can also be called a target model.

[0095] The first identifier includes at least one of the following:

[0096] (1) The first type of identifier, including the identifier of the first data;

[0097] Specifically, it may include data identifiers or dataset identifiers.

[0098] (2) The second type of identifier includes the associated identifier of the first data;

[0099] Specifically, it may include the associated identifiers corresponding to the data or dataset;

[0100] For example, an association identifier used to indicate the applicable data or dataset, or an association identifier used to indicate the corresponding data or dataset when it was obtained, or an association identifier used to indicate the association of the reference signal (RS) collected by the data or dataset (such as the configuration information of the RS, report configuration, resource configuration, resource set configuration, and measure configuration).

[0101] (3) The third category of identifiers includes model-related identifiers.

[0102] Specifically, it may include model-related identifiers corresponding to the data or dataset;

[0103] It should be noted that, regarding the aforementioned method of receiving the first data and the first identifier, the first identifier may be carried or indicated during data transfer (e.g., transmitted together with the data / dataset, within the data / dataset, or indicated outside the data / dataset). The first identifier includes at least one of the following: data identifier (ID), dataset identifier, associated identifier (ID), model identifier, pairing identifier (ID), encoder identifier (ID), decoder identifier (ID), UE-part model identifier (UE-part model ID), NW-part model identifier (NW-part model ID), model structure identifier, UE-part model structure identifier, and NW-part model structure identifier.

[0104] In this application embodiment, a specific definition and usage of identifiers in AI communication data transmission are given, clarifying the meaning and usage of data transmission, thereby improving the efficiency of the AI ​​communication system.

[0105] The following describes several schemes for the first communication device to use the first data and the first identifier:

[0106] Option 1:

[0107] In one optional implementation, the first communication device determines the target AI model based on first data and a first identifier, including:

[0108] (1) The first communication device uses the first data to train and obtain the first target AI model;

[0109] (2) The first communication device determines the first type of identifier or the second type of identifier as the relevant information of the first target AI model, or the first communication device determines the third type of identifier as the model identifier of the first target AI model.

[0110] In the embodiments of this application, data or datasets are used for training to obtain one or more target models. It is understood that the specific training process can be implemented based on the first communication device itself, and the embodiments of this application do not limit the training method. It should be noted that the training process specifically involves training an initial model using data or datasets. This initial model can be obtained by being provided by a second communication device, or by invoking based on other third-class identifiers. For example, the initial model corresponding to the other third-class identifier can be determined according to a protocol agreement, or the initial model can be determined from existing models on the first communication device based on the other third-class identifier.

[0111] The third type of identifier is a related identifier for the target model. That is, the trained target model is identified using the third type of identifier, so that the target model can be directly scheduled subsequently using the third type of identifier.

[0112] The third type of identifier may include: model identifier, pairing ID, encoder ID, decoder ID, UE-part model ID, and NW-part model ID.

[0113] Among them, the pairing ID, encoder ID, decoder ID, UE-part model ID, and NW-part model ID are mainly used in two-sided model use cases, such as Channel State Information (CSI) compression, CSI prediction, channel coding and decoding, source coding and decoding, and joint channel source coding and decoding.

[0114] Optionally, the first communication device may report relevant information about the first target AI model to the second communication device; the second communication device may determine the applicable scope of the first target AI model based on the relevant information of the first target model, and use it to perform or assist in the lifecycle management of the first target AI model.

[0115] Option 2:

[0116] In one optional implementation, the first communication device determines the target AI model based on first data and a first identifier, including:

[0117] (1) The first communication device determines the model-related information based on the third type of identifier;

[0118] (2) The first communication device uses the first data and model-related information to train and obtain the first target AI model.

[0119] In this application embodiment, when using data or datasets for training, it is necessary to use the corresponding model-related information;

[0120] In one alternative implementation, the third type of identifier includes at least one of the following:

[0121] (1) Model structure identification;

[0122] (2) The structural identifier of the first communication device side model;

[0123] (3) The second communication equipment side model structure identifier.

[0124] The third type of identifier refers to the identifier of model-related information, such as model structure identifier, UE-side model structure identifier, and NW-side model structure identifier.

[0125] When training with data or datasets, you need to use model structure identifiers to identify the corresponding model structure for model training.

[0126] Optionally, the first or second type of identifier can be used in the subsequent lifecycle management of the AI ​​model to indicate the model parameters.

[0127] Alternatively, the first or second type of identifier, along with the third type of identifier, can be used together to indicate the complete model.

[0128] At this point, the model parameters are indicated by the first or second type of identifier, and the model structure is indicated by the third type of identifier. The combination of the two indicates a complete model.

[0129] Option 3:

[0130] In one optional implementation, the first communication device determines the target AI model based on first data and a first identifier, including:

[0131] (1) The first communication device acquires the second target AI model corresponding to the third type of identifier;

[0132] (2) The first communication device uses the first data to train the second target AI model to obtain the third target AI model.

[0133] In this embodiment of the application, the data or dataset is used to train, update, and fine-tune the second target AI model (i.e., the initial model before training). The third type of identifier refers to the relevant identifiers of the second target AI model, such as model identifier, pairing ID, encoder ID, decoder ID, UE-part model ID, and NW-part model ID.

[0134] In one optional implementation, the first communication device acquires the second target AI model corresponding to the third type of identifier, including any one of the following:

[0135] (1.1) The first communication device receives the second target AI model from the second communication device;

[0136] Taking a scenario where the first communication device is the UE and the second communication device is the NW as an example, the target model is sent to the UE by the NW;

[0137] During model transfer / delivery, the target model carries relevant identifiers, or the NW indicates the relevant identifiers.

[0138] (1.2) The first communication device determines the second target AI model according to the third type of identifier and the protocol agreement;

[0139] Taking a scenario where the first communication device is the UE and the second communication device is the NW as an example, the target model is the reference model;

[0140] The relevant identifiers are agreed upon by the protocol, or the NW indicates the relevant identifiers used by the target model (e.g., the UE first reports support for a certain reference model, and then the NW assigns a certain identifier to the reference model);

[0141] (1.3) The first communication device determines the second target AI model from its existing models based on the third type of identifier.

[0142] Taking a scenario where the first communication device is the UE and the second communication device is the NW as an example, the target model is the UE's existing model;

[0143] The UE reports the relevant identifier of the target model in model identification / model registration, UE capability reporting, or UE model information reporting.

[0144] Regarding the use of the first data by the first communication device to train the second target AI model to obtain the third target AI model, several sub-schemes are described below.

[0145] In one alternative implementation, the first communication device uses the first data to train the second target AI model to obtain a third target AI model, including at least one of the following:

[0146] Sub-option 1:

[0147] Taking a scenario where the first communication device is the UE and the second communication device is the NW as an example;

[0148] The first communication device uses the first data to directly modify or update the model structure or model parameters of the second target AI model to obtain the third target AI model;

[0149] Using the data or dataset, (UE, UE server, or UE manufacturer) the target model can be directly trained, updated, or fine-tuned, that is, the model structure or parameters of the target model can be directly modified or updated.

[0150] Sub-option 2:

[0151] The first communication device uses the first data to train a first matching model that can match the second target AI model, and then uses at least one of the first data and the second data to train the first matching model to obtain a third target AI model, wherein the third target AI model is a model that can match the first matching model, and the second data is data that is not associated with the first identifier;

[0152] For the two-sided model use case, first use the data or dataset to train a matching model of the target model, and then use the data or dataset, and / or other data or datasets, to train a new target model based on the matching model;

[0153] Taking a scenario where the first communication device is the UE and the second communication device is the NW as an example: When the NW sends data to the UE, and the target model is the encoder, the UE, UE server, or UE manufacturer first uses the data or dataset to train a decoder that matches the encoder. Then, using the data or dataset, and / or other data or datasets (UE, UE server, or UE manufacturer's own dataset, i.e., the second data mentioned above), a new encoder is trained based on the decoder.

[0154] Taking a scenario where the first communication device is NW and the second communication device is UE as an example: When UE sends data to NW, the target model is decoder. Then (NW, NW server, or NW manufacturer) first uses the data or dataset to train an encoder that matches the decoder. Then, using the data or dataset, and / or other data or datasets (NW, NW server, or NW manufacturer, their own dataset), a new decoder is trained based on the encoder.

[0155] Sub-option 3:

[0156] The first communication device trains a second target AI model using at least one of the first data and the second data to obtain a second matching model that can match the second target AI model, and determines the second matching model as the third target AI model, wherein the second data is data that is not associated with the first identifier;

[0157] For the two-sided model use case, the data or dataset, and / or other data or datasets, are used to train the matching model of the target model.

[0158] Taking a scenario where the first communication device is the UE and the second communication device is the NW as an example: when the NW sends data to the UE, and the target model is the decoder, then the UE, UE server, or UE manufacturer uses the data or dataset, and / or other data or datasets (UE, UE server, or UE manufacturer, their own dataset) to train a new encoder based on the decoder.

[0159] Taking the scenario where the first communication device is NW and the second communication device is UE as an example: When UE sends data to NW and the target model is encoder, then (NW, NW server, or NW manufacturer) uses the data or dataset, and / or other data or datasets (NW, NW server, or NW manufacturer's own dataset) to train a new decoder based on the encoder.

[0160] Sub-option four:

[0161] The first communication device uses the second target AI model to generate the third data, and uses the first data and the third data to train the second target AI model to obtain the third target AI model.

[0162] Use the target model to generate other data or datasets, and train a new target model together with the transmitted data or datasets;

[0163] The target model is model A, the transmitted data is data A, model A is used to generate data B, and data A and data B are used together to train a new model B.

[0164] In one alternative implementation, the method further includes:

[0165] The first communication device uses at least one of the first type of identifier, the second type of identifier, and the third type of identifier to perform model lifecycle management on the target AI model.

[0166] In the embodiments of this application, subsequent AI model lifecycle management uses a first type of identifier, a second type of identifier, or a third type of identifier to indicate the model obtained based on data or datasets.

[0167] AI model lifecycle management includes at least one of the following:

[0168] Model activation, model deactivation, model switching, model selection, model rollback, model monitoring, model identification, model registration, model transmission, and model-related data transmission.

[0169] In one optional implementation, the associated ID is used to indicate condition information, that is, to indicate condition information, condition, additional condition, or assistance information on the NW side or UE side.

[0170] The condition information includes at least one of the following:

[0171] (1) Antenna pattern on the first communication device side or the second communication device side;

[0172] For example, the antenna pattern on the NW side or UE side (such as the number of antenna elements, the number of Transceiver Units (TXRUs), the arrangement of the antenna array, and the mapping relationship between antenna elements and TXRUs);

[0173] (2) Beam pattern on the first communication device side or the second communication device side;

[0174] For example, the beam pattern on the NW side or UE side (such as the number of analog beams, the main direction of each beam, the power spectrum at each angle, and the correlation between beams);

[0175] For example, the NW and / or UE may assume similar properties of downlink receive and / or uplink transmit beams or beam sets / lists associated with the same "UE-side additional conditions and / or UE-side association ID";

[0176] For example, the NW and / or UE may assume similar properties of downlink transmit and / or uplink receive beams or beam sets / lists associated with the same "NW-side additional conditions and / or NW-side association ID";

[0177] (3) At least some hardware information or configuration information of the first communication device side or the second communication device side;

[0178] For example, at least some hardware information or configuration information of the communication link on the NW side or UE side (excluding antenna pattern and beam pattern), such as hardware information or configuration information of power amplifiers, couplers, radio frequency chain (RF chain), and digital pre-distortion (DPD).

[0179] (4) Signaling configuration on the first communication device side or the second communication device side;

[0180] (5) The surrounding wireless environment or wireless signal characteristics of the first or second communication device;

[0181] (6) The transmission purpose on the first communication device side or the second communication device side;

[0182] For example, it is used by the NW or UE to select a suitable dataset for transmission. For example, the NW or UE selects a dataset with conditional information applicable to the NW or UE side for transmission based on the associated ID (UE side and / or network side), or selects a dataset collected based on the conditional information of the NW or UE side for transmission.

[0183] For example, data used by the NW or UE to collect or tag corresponding UE-side condition information. For example, the NW or UE collects data separately according to different associated IDs (UE-side and / or network-side) to form multiple datasets; or, the NW or UE collects data and tags it with associated IDs (UE-side and / or network-side).

[0184] For example, it can be used by the NW or UE to select a UE-side model or an NW-side model. For example, the NW selects a network-side model suitable for the reported associated ID (UE-side and / or network-side) based on the associated ID reported by the UE, or instructs the UE to select a UE-side model suitable for the reported associated ID. For example, the UE selects a UE-side model suitable for the reported associated ID (UE-side and / or network-side) indicated by the NW, or instructs the NW to select a network-side model suitable for the reported associated ID.

[0185] For example, this is used to ensure consistency between the UE-side model and the NW-side model during the training and inference phases. For instance, if the training data for the UE-side model or the NW-side model is collected based on certain associated IDs (UE-side and / or network-side), then during model inference, the UE selects or the NW instructs to use the model trained with said associated IDs (UE-side and / or network-side).

[0186] In one alternative implementation, the target AI model is used for at least one of the following:

[0187] (1) Reference signal processing;

[0188] Examples include signal detection, signal estimation, noise suppression, interference removal, filtering, and equalization. Other examples include demodulation reference signals (DMRS), sounding reference signals (SRS), synchronization signal blocks (SSB), channel state information reference signals (CSI-RS), tracking reference signals (TRS), positioning reference signals (PRS), and phase-tracking reference signals (PTRS).

[0189] (2) Transmission, reception, demodulation or transmission of channel signals;

[0190] These include the 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), and Physical Broadcast Channel (PBCH).

[0191] (3) Acquisition of channel state information;

[0192] include:

[0193] a) Channel state information feedback. Examples 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), and layer indicator (LI).

[0194] b) Reciprocity of uplink and downlink in FDD. For FDD systems, based on partial reciprocity, the base station obtains angle and delay information from the uplink channel. It can notify the UE of the angle and delay information through CSI-RS precoding or direct indication. The UE reports according to the base station's indication or selects and reports within the range indicated by the base station, thereby reducing the UE's computational load and the overhead of CSI reporting.

[0195] (4) Beam management;

[0196] Examples include beam measurement, beam reporting, beam prediction (spatial or frequency domain prediction), beam failure detection, beam failure recovery, and new beam indication during beam failure recovery.

[0197] (5) Channel prediction;

[0198] For example, channel state information prediction, beam prediction, cell quality prediction, etc.

[0199] (6) Channel or source encoding and decoding;

[0200] For example, channel coding, channel decoding, source coding, source decoding, joint source-channel coding, and joint source-channel decoding.

[0201] (7) Interference suppression;

[0202] For example, interference within the cell, interference between cells, out-of-band interference, and intermodulation interference.

[0203] (8) Positioning;

[0204] The specific location (including horizontal and / or vertical position) or possible future trajectory of the UE is estimated using reference signals (such as SRS), or information for auxiliary location estimation or trajectory estimation, such as Timing of Arrival (TOA), line-of-sight or non-line-of-sight, or Reference Signal Time Difference (RSTD).

[0205] (9) Forecasting and management of high-level business and parameters;

[0206] For example, throughput, required data packet size, business requirements, movement speed, noise information, etc.

[0207] (10) Encoding and parsing of control signaling.

[0208] For example, physical layer control signaling (Layer 1 signaling), medium access control (MAC) layer control signaling (Layer 2 signaling), RRC layer control signaling (Layer 3 signaling), etc.

[0209] Referring to Figure 3, this application embodiment provides a transmission method, in which a second communication device is the executing entity, and the method includes:

[0210] Step 301: The second communication device sends first data and a first identifier associated with the first data to the first communication device;

[0211] The first data and the first identifier are used by the first communication device to determine the target AI model;

[0212] The first identifier includes at least one of the following:

[0213] The first type of identifier includes the identifier of the first data;

[0214] The second type of identifier includes the associated identifier of the first data;

[0215] The third category of identifiers includes model-related identifiers.

[0216] It should be noted that, as the counterpart device that interacts with the first communication device, the execution steps and interactive information content involved in the method of the second communication device should be understood in the same way as those of the first communication device. Therefore, the understanding of the technical features in the method of the second communication device can refer to the relevant content of the first communication device. The embodiments of this application will not repeat the description here.

[0217] In one alternative implementation, the third type of identifier includes at least one of the following:

[0218] Model structure identifier;

[0219] First communication equipment side model structure identifier;

[0220] Second communication equipment side model structure identifier.

[0221] In one alternative implementation, the method further includes:

[0222] The second communication device sends the second target AI model to the first communication device.

[0223] In one alternative implementation, the method further includes:

[0224] The second communication device uses at least one of the first, second and third types of identifiers to perform model lifecycle management on the target AI model.

[0225] In one alternative implementation, the association identifier is used to indicate condition information, which includes at least one of the following:

[0226] Antenna pattern on the first communication device side or the second communication device side;

[0227] Beam pattern on the first communication device side or the second communication device side;

[0228] At least some hardware information or configuration information of the first or second communication device;

[0229] Signaling configuration on the first communication device side or the second communication device side;

[0230] The surrounding wireless environment or wireless signal characteristics of the first or second communication device;

[0231] The transmission purpose is either on the first communication device side or the second communication device side.

[0232] In one alternative implementation, the target AI model is used for at least one of the following:

[0233] Reference signal processing;

[0234] Channel signal transmission, reception, demodulation, or transmission;

[0235] Channel state information acquisition;

[0236] Beam management;

[0237] Channel prediction;

[0238] Channel or source encoding / decoding;

[0239] Interference suppression;

[0240] position;

[0241] Forecasting and management of high-level business and parameters;

[0242] Encoding and parsing of control signaling.

[0243] The transmission method provided in this application can be executed by a transmission device. This application uses an example of a transmission device executing the transmission method to illustrate the transmission device provided in this application.

[0244] This application provides a transmission device. As an example, the transmission device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0245] The transmission device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0246] Specifically, referring to Figure 4, when the transmission device is a first communication device or a component of the first communication device, the transmission device 400 includes:

[0247] The first receiving module 401 is configured to receive first data and a first identifier associated with the first data from the second communication device.

[0248] The first processing module 402 is used to determine the target AI model based on the first data and the first identifier;

[0249] The first identifier includes at least one of the following:

[0250] The first type of identifier includes the identifier of the first data;

[0251] The second type of identifier includes the association identifier of the first data;

[0252] The third category of identifiers includes model-related identifiers.

[0253] Optionally, the first processing module is configured to:

[0254] The first target AI model is obtained by training using the first data;

[0255] The first type of identifier or the second type of identifier is determined as the relevant information of the first target AI model, or the third type of identifier is determined as the model identifier of the first target AI model.

[0256] Optionally, the first processing module is configured to:

[0257] Based on the third type of identifier, determine the model-related information;

[0258] The first target AI model is obtained by training using the first data and the model-related information.

[0259] Optionally, the third type of identifier includes at least one of the following:

[0260] Model structure identifier;

[0261] First communication equipment side model structure identifier;

[0262] Second communication equipment side model structure identifier.

[0263] Optionally, the first processing module is configured to:

[0264] Obtain the second target AI model corresponding to the third type of identifier;

[0265] The first data is used to train the second target AI model to obtain the third target AI model.

[0266] Optionally, the first processing module is used for any of the following:

[0267] Receive the second target AI model from the second communication device;

[0268] The second target AI model is determined based on the third type of identifier and the protocol agreement.

[0269] Based on the third type of identifier, the second target AI model is determined from the existing models.

[0270] Optionally, the first processing module is used for at least one of the following:

[0271] The third target AI model is obtained by directly modifying or updating the model structure or model parameters of the second target AI model using the first data.

[0272] The first matching model is trained using the first data to obtain a first matching model that can match the second target AI model. Then, the first matching model is trained using at least one of the first data and the second data to obtain the third target AI model. The third target AI model is a model that can match the first matching model, and the second data is data that is not associated with the first identifier.

[0273] The second target AI model is trained using at least one of the first data and the second data to obtain a second matching model that can match the second target AI model, and the second matching model is determined as the third target AI model, wherein the second data is data that is not associated with the first identifier;

[0274] The second target AI model is used to generate third data, and the first data and the third data are used to train the second target AI model to obtain the third target AI model.

[0275] Optionally, the device further includes:

[0276] The second processing module is used to perform model lifecycle management on the target AI model using at least one of the first type of identifier, the second type of identifier, and the third type of identifier.

[0277] Optionally, the association identifier is used to indicate condition information, which includes at least one of the following:

[0278] Antenna pattern on the first communication device side or the second communication device side;

[0279] Beam pattern on the first communication device side or the second communication device side;

[0280] At least some hardware information or configuration information of the first or second communication device;

[0281] Signaling configuration on the first communication device side or the second communication device side;

[0282] The surrounding wireless environment or wireless signal characteristics of the first or second communication device;

[0283] The transmission purpose is either on the first communication device side or the second communication device side.

[0284] Optionally, the target AI model is used for at least one of the following:

[0285] Reference signal processing;

[0286] Channel signal transmission, reception, demodulation, or transmission;

[0287] Channel state information acquisition;

[0288] Beam management;

[0289] Channel prediction;

[0290] Channel or source encoding / decoding;

[0291] Interference suppression;

[0292] position;

[0293] Forecasting and management of high-level business and parameters;

[0294] Encoding and parsing of control signaling.

[0295] Referring to Figure 5, when the transmission device is a second communication device or a component of a second communication device, the transmission device 500 includes:

[0296] The first sending module 501 is used to send first data and a first identifier associated with the first data to the first communication device;

[0297] The first data and the first identifier are used by the first communication device to determine the target AI model;

[0298] The first identifier includes at least one of the following:

[0299] The first type of identifier includes the identifier of the first data;

[0300] The second type of identifier includes the association identifier of the first data;

[0301] The third category of identifiers includes model-related identifiers.

[0302] Optionally, the third type of identifier includes at least one of the following:

[0303] Model structure identifier;

[0304] The first communication device-side model structure identifier;

[0305] The second communication device side model structure identifier.

[0306] Optionally, the device further includes:

[0307] The second sending module is used to send the second target AI model to the first communication device.

[0308] Optionally, the device further includes:

[0309] The second processing module is used to perform model lifecycle management on the target AI model using at least one of the first type of identifier, the second type of identifier, and the third type of identifier.

[0310] Optionally, the association identifier is used to indicate condition information, which includes at least one of the following:

[0311] Antenna pattern on the first communication device side or the second communication device side;

[0312] Beam pattern on the first communication device side or the second communication device side;

[0313] At least some hardware information or configuration information of the first or second communication device;

[0314] Signaling configuration on the first communication device side or the second communication device side;

[0315] The surrounding wireless environment or wireless signal characteristics of the first or second communication device;

[0316] The transmission purpose is either on the first communication device side or the second communication device side.

[0317] Optionally, the target AI model is used for at least one of the following:

[0318] Reference signal processing;

[0319] Channel signal transmission, reception, demodulation, or transmission;

[0320] Channel state information acquisition;

[0321] Beam management;

[0322] Channel prediction;

[0323] Channel or source encoding / decoding;

[0324] Interference suppression;

[0325] position;

[0326] Forecasting and management of high-level business and parameters;

[0327] Encoding and parsing of control signaling.

[0328] The transmission device provided in this application embodiment can implement the various processes implemented in the method embodiments of Figures 2 to 3 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0329] As shown in Figure 6, this application embodiment also provides a communication device 600, including a processor 601 and a memory 602. The memory 602 stores a program or instructions that can run on the processor 601. For example, when the communication device 600 is a first communication device, the program or instructions, when executed by the processor 601, implement the various steps of the above-described first communication device-side method embodiment and achieve the same technical effect. When the communication device 600 is a second communication device, the program or instructions, when executed by the processor 601, implement the various steps of the above-described second communication device-side method embodiment and achieve the same technical effect. To avoid repetition, this will not be repeated here.

[0330] This application also provides a terminal, including 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 in the method embodiment shown in FIG2. This terminal embodiment corresponds to the above-described terminal-side method embodiment, and all implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and can achieve the same technical effect. The terminal may be the transmission device shown in FIG4. Specifically, FIG7 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application.

[0331] The terminal 700 includes, but is not limited to, at least some of the following components: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.

[0332] Those skilled in the art will understand that the terminal 700 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to the processor 7710 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in Figure 7 does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0333] It should be understood that, in this embodiment, the input unit 704 may include a graphics processor 7041 and a microphone 7042. The graphics processor 7041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0334] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 701 can transmit it to the processor 710 for processing; in addition, the radio frequency unit 701 can send uplink data to the network-side device. Typically, the radio frequency unit 701 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0335] The memory 709 can be used to store software programs or instructions, as well as various data. The memory 709 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 709 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 709 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0336] Processor 710 may include one or more processing units; optionally, processor 710 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 710.

[0337] Processor 710 is configured to receive first data from a second communication device, and a first identifier associated with the first data;

[0338] Processor 710 is configured to determine a target AI model based on the first data and the first identifier;

[0339] The first identifier includes at least one of the following:

[0340] The first type of identifier includes the identifier of the first data;

[0341] The second type of identifier includes the association identifier of the first data;

[0342] The third category of identifiers includes model-related identifiers.

[0343] Optionally, the processor 710 is configured to:

[0344] The first target AI model is obtained by training using the first data;

[0345] The first type of identifier or the second type of identifier is determined as the relevant information of the first target AI model, or the third type of identifier is determined as the model identifier of the first target AI model.

[0346] Optionally, the processor 710 is configured to:

[0347] Based on the third type of identifier, determine the model-related information;

[0348] The first target AI model is obtained by training using the first data and the model-related information.

[0349] Optionally, the third type of identifier includes at least one of the following:

[0350] Model structure identifier;

[0351] First communication equipment side model structure identifier;

[0352] Second communication equipment side model structure identifier.

[0353] Optionally, the processor 710 is configured to:

[0354] Obtain the second target AI model corresponding to the third type of identifier;

[0355] The first data is used to train the second target AI model to obtain the third target AI model.

[0356] Optionally, the processor 710 is used for any of the following:

[0357] Receive the second target AI model from the second communication device;

[0358] The second target AI model is determined based on the third type of identifier and the protocol agreement.

[0359] Based on the third type of identifier, the second target AI model is determined from the existing models.

[0360] Optionally, the processor 710 is used for at least one of the following:

[0361] The third target AI model is obtained by directly modifying or updating the model structure or model parameters of the second target AI model using the first data.

[0362] The first matching model is trained using the first data to obtain a first matching model that can match the second target AI model. Then, the first matching model is trained using at least one of the first data and the second data to obtain the third target AI model. The third target AI model is a model that can match the first matching model, and the second data is data that is not associated with the first identifier.

[0363] The second target AI model is trained using at least one of the first data and the second data to obtain a second matching model that can match the second target AI model, and the second matching model is determined as the third target AI model, wherein the second data is data that is not associated with the first identifier;

[0364] The second target AI model is used to generate third data, and the first data and the third data are used to train the second target AI model to obtain the third target AI model.

[0365] Optionally, the processor 710 is configured to perform model lifecycle management on the target AI model using at least one of the first type of identifier, the second type of identifier, and the third type of identifier.

[0366] Optionally, the association identifier is used to indicate condition information, which includes at least one of the following:

[0367] Antenna pattern on the first communication device side or the second communication device side;

[0368] Beam pattern on the first communication device side or the second communication device side;

[0369] At least some hardware information or configuration information of the first or second communication device;

[0370] Signaling configuration on the first communication device side or the second communication device side;

[0371] The surrounding wireless environment or wireless signal characteristics of the first or second communication device;

[0372] The transmission purpose is either on the first communication device side or the second communication device side.

[0373] Optionally, the target AI model is used for at least one of the following:

[0374] Reference signal processing;

[0375] Channel signal transmission, reception, demodulation, or transmission;

[0376] Channel state information acquisition;

[0377] Beam management;

[0378] Channel prediction;

[0379] Channel or source encoding / decoding;

[0380] Interference suppression;

[0381] position;

[0382] Forecasting and management of high-level business and parameters;

[0383] Encoding and parsing of control signaling.

[0384] It is 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 effect. To avoid repetition, it will not be described again here.

[0385] This application also provides a network-side device, including a processor and a communication interface. 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 embodiment shown in FIG3. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0386] Specifically, this application embodiment also provides a network-side device, which can be the transmission device shown in FIG5. As shown in FIG8, the network-side device 800 includes: an antenna 81, a radio frequency device 82, a baseband device 83, a processor 84, and a memory 85. The antenna 81 is connected to the radio frequency device 82. In the uplink direction, the radio frequency device 82 receives information through the antenna 81 and sends the received information to the baseband device 83 for processing. In the downlink direction, the baseband device 83 processes the information to be transmitted and sends it to the radio frequency device 82. The radio frequency device 82 processes the received information and transmits it through the antenna 81.

[0387] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 83, which includes a baseband processor.

[0388] The baseband device 83 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG8. One of the chips is, for example, a baseband processor, which is connected to the memory 85 via a bus interface to call the program in the memory 85 and execute the network device operation shown in the above method embodiment.

[0389] The network-side device may also include a network interface 86, such as a Common Public Radio Interface (CPRI).

[0390] Specifically, the network-side device 800 in this application embodiment further includes: instructions or programs stored in memory 85 and executable on processor 84. Processor 84 calls the instructions or programs in memory 85 to execute the methods executed by each module shown in FIG5 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0391] Specifically, this application also provides a network-side device. As shown in FIG9, the network-side device 900 includes a processor 901, a network interface 902, and a memory 903. The network-side device can be the device shown in FIG5. The network interface 902 is, for example, a Common Public Radio Interface (CPRI).

[0392] Specifically, the network-side device 900 in this application embodiment further includes: instructions or programs stored in memory 903 and executable on processor 901. Processor 901 calls the instructions or programs in memory 903 to execute the methods executed by each module shown in FIG5 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0393] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0394] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0395] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0396] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0397] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0398] This application also provides a wireless communication system, including: a first communication device and a second communication device, wherein the first communication device can be used to perform the steps of the first communication device-side method as described above, and the second communication device can be used to perform the steps of the second communication device-side method as described above.

[0399] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0400] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0401] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A transmission method, comprising: The first communication device receives first data and a first identifier associated with the first data from the second communication device; The first communication device determines the target artificial intelligence (AI) model based on the first data and the first identifier; The first identifier includes at least one of the following: The first type of identifier includes the identifier of the first data; The second type of identifier includes the association identifier of the first data; The third category of identifiers includes model-related identifiers.

2. The method according to claim 1, wherein, The first communication device determines the target AI model based on the first data and the first identifier, including: The first communication device uses the first data to train and obtain a first target AI model; The first communication device determines the first type of identifier or the second type of identifier as relevant information of the first target AI model, or the first communication device determines the third type of identifier as the model identifier of the first target AI model.

3. The method according to claim 1, wherein, The first communication device determines the target AI model based on the first data and the first identifier, including: The first communication device determines model-related information based on the third type of identifier; The first communication device uses the first data and the model-related information to train and obtain a first target AI model.

4. The method according to claim 3, wherein, The third type of identifier includes at least one of the following: Model structure identifier; The first communication device-side model structure identifier; The second communication device side model structure identifier.

5. The method according to claim 1, wherein, The first communication device determines the target AI model based on the first data and the first identifier, including: The first communication device acquires the second target AI model corresponding to the third type of identifier; The first communication device uses the first data to train the second target AI model to obtain the third target AI model.

6. The method according to claim 5, wherein, The first communication device acquires the second target AI model corresponding to the third type of identifier, including any one of the following: The first communication device receives the second target AI model from the second communication device; The first communication device determines the second target AI model based on the third type of identifier and protocol agreement; The first communication device determines the second target AI model from its existing models based on the third type of identifier.

7. The method according to claim 5, wherein, The first communication device uses the first data to train the second target AI model to obtain a third target AI model, which includes at least one of the following: The first communication device uses the first data to directly modify or update the model structure or model parameters of the second target AI model to obtain the third target AI model; The first communication device uses the first data to train a first matching model that can match the second target AI model, and then uses at least one of the first data and the second data to train the first matching model to obtain the third target AI model, wherein the third target AI model is a model that can match the first matching model, and the second data is data that is not associated with the first identifier; The first communication device trains the second target AI model using at least one of the first data and the second data to obtain a second matching model that can match the second target AI model, and determines the second matching model as the third target AI model, wherein the second data is data that is not associated with the first identifier; The first communication device uses the second target AI model to generate third data, and uses the first data and the third data to train the second target AI model to obtain the third target AI model.

8. The method according to claim 1, further comprising: The first communication device uses at least one of the first type of identifier, the second type of identifier, and the third type of identifier to perform model lifecycle management on the target AI model.

9. The method according to claim 1, wherein, The association identifier is used to indicate condition information, which includes at least one of the following: Antenna pattern on the first communication device side or the second communication device side; Beam pattern on the first communication device side or the second communication device side; At least some hardware information or configuration information from the first communication device side or the second communication device side; Signaling configuration on the first communication device side or the second communication device side; The surrounding wireless environment or wireless signal characteristics of the first communication device side or the second communication device side; The transmission destination is on the first communication device side or the second communication device side.

10. The method according to claim 1, wherein, The target AI model is used for at least one of the following: Reference signal processing; Channel signal transmission, reception, demodulation, or transmission; Channel state information acquisition; Beam management; Channel prediction; Channel or source encoding / decoding; Interference suppression; position; Forecasting and management of high-level business and parameters; Encoding and parsing of control signaling.

11. A transmission method, comprising: The second communication device sends first data and a first identifier associated with the first data to the first communication device; The first data and the first identifier are used by the first communication device to determine the target AI model; The first identifier includes at least one of the following: The first type of identifier includes the identifier of the first data; The second type of identifier includes the association identifier of the first data; The third category of identifiers includes model-related identifiers.

12. The method according to claim 11, wherein, The third type of identifier includes at least one of the following: Model structure identifier; The first communication device-side model structure identifier; The second communication device side model structure identifier.

13. The method according to claim 11, further comprising: The second communication device sends the second target AI model to the first communication device.

14. The method according to claim 11, further comprising: The second communication device uses at least one of the first type of identifier, the second type of identifier, and the third type of identifier to perform model lifecycle management on the target AI model.

15. The method according to claim 11, wherein, The association identifier is used to indicate condition information, which includes at least one of the following: Antenna pattern on the first communication device side or the second communication device side; Beam pattern on the first communication device side or the second communication device side; At least some hardware information or configuration information from the first communication device side or the second communication device side; Signaling configuration on the first communication device side or the second communication device side; The surrounding wireless environment or wireless signal characteristics of the first communication device side or the second communication device side; The transmission destination is on the first communication device side or the second communication device side.

16. The method according to claim 11, wherein, The target AI model is used for at least one of the following: Reference signal processing; Channel signal transmission, reception, demodulation, or transmission; Channel state information acquisition; Beam management; Channel prediction; Channel or source encoding / decoding; Interference suppression; position; Forecasting and management of high-level business and parameters; Encoding and parsing of control signaling.

17. A transmission device, comprising: A first receiving module is configured to receive first data and a first identifier associated with the first data from a second communication device. The first processing module is used to determine the target AI model based on the first data and the first identifier; The first identifier includes at least one of the following: The first type of identifier includes the identifier of the first data; The second type of identifier includes the association identifier of the first data; The third category of identifiers includes model-related identifiers.

18. The apparatus according to claim 17, wherein, The first processing module is used for: The first target AI model is obtained by training using the first data; The first type of identifier or the second type of identifier is determined as the relevant information of the first target AI model, or the third type of identifier is determined as the model identifier of the first target AI model.

19. The apparatus according to claim 17, wherein, The first processing module is used for: Based on the third type of identifier, determine the model-related information; The first target AI model is obtained by training using the first data and the model-related information.

20. The apparatus according to claim 19, wherein, The third type of identifier includes at least one of the following: Model structure identifier; First communication equipment side model structure identifier; Second communication equipment side model structure identifier.

21. The apparatus according to claim 17, wherein, The first processing module is used for: Obtain the second target AI model corresponding to the third type of identifier; The first data is used to train the second target AI model to obtain the third target AI model.

22. The apparatus according to claim 21, wherein, The first processing module is used for any one of the following: Receive the second target AI model from the second communication device; The second target AI model is determined based on the third type of identifier and the protocol agreement. Based on the third type of identifier, the second target AI model is determined from the existing models.

23. The apparatus according to claim 21, wherein, The first processing module is used for at least one of the following: The third target AI model is obtained by directly modifying or updating the model structure or model parameters of the second target AI model using the first data. The first matching model is trained using the first data to obtain a first matching model that can match the second target AI model. Then, the first matching model is trained using at least one of the first data and the second data to obtain the third target AI model. The third target AI model is a model that can match the first matching model, and the second data is data that is not associated with the first identifier. The second target AI model is trained using at least one of the first data and the second data to obtain a second matching model that can match the second target AI model, and the second matching model is determined as the third target AI model, wherein the second data is data that is not associated with the first identifier; The second target AI model is used to generate third data, and the first data and the third data are used to train the second target AI model to obtain the third target AI model.

24. The apparatus of claim 17, further comprising: The second processing module is used to perform model lifecycle management on the target AI model using at least one of the first type of identifier, the second type of identifier, and the third type of identifier.

25. The apparatus according to claim 17, wherein, The association identifier is used to indicate condition information, which includes at least one of the following: Antenna pattern on the first communication device side or the second communication device side; Beam pattern on the first communication device side or the second communication device side; At least some hardware information or configuration information of the first or second communication device; Signaling configuration on the first communication device side or the second communication device side; The surrounding wireless environment or wireless signal characteristics of the first or second communication device; The transmission purpose is either on the first communication device side or the second communication device side.

26. The apparatus according to claim 17, wherein, The target AI model is used for at least one of the following: Reference signal processing; Channel signal transmission, reception, demodulation, or transmission; Channel state information acquisition; Beam management; Channel prediction; Channel or source encoding / decoding; Interference suppression; position; Forecasting and management of high-level business and parameters; Encoding and parsing of control signaling.

27. A transmission device, comprising: A first sending module is configured to send first data and a first identifier associated with the first data to a first communication device. The first data and the first identifier are used by the first communication device to determine the target AI model; The first identifier includes at least one of the following: The first type of identifier includes the identifier of the first data; The second type of identifier includes the association identifier of the first data; The third category of identifiers includes model-related identifiers.

28. The apparatus according to claim 27, wherein, The third type of identifier includes at least one of the following: Model structure identifier; First communication equipment side model structure identifier; Second communication equipment side model structure identifier.

29. The apparatus of claim 27, further comprising: The second sending module is used to send the second target AI model to the first communication device.

30. The apparatus of claim 27, further comprising: The second processing module is used to perform model lifecycle management on the target AI model using at least one of the first type of identifier, the second type of identifier, and the third type of identifier.

31. The apparatus according to claim 27, wherein, The association identifier is used to indicate condition information, which includes at least one of the following: Antenna pattern on the first communication device side or the second communication device side; Beam pattern on the first communication device side or the second communication device side; At least some hardware information or configuration information of the first or second communication device; Signaling configuration on the first communication device side or the second communication device side; The surrounding wireless environment or wireless signal characteristics of the first or second communication device; The transmission purpose is either on the first communication device side or the second communication device side.

32. The apparatus according to claim 27, wherein, The target AI model is used for at least one of the following: Reference signal processing; Channel signal transmission, reception, demodulation, or transmission; Channel state information acquisition; Beam management; Channel prediction; Channel or source encoding / decoding; Interference suppression; position; Forecasting and management of high-level business and parameters; Encoding and parsing of control signaling.

33. A communication device comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the transmission method as claimed in any one of claims 1 to 10, or implementing the steps of the transmission method as claimed in any one of claims 11 to 16.

34. A readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the transmission method as claimed in any one of claims 1 to 10, or implement the steps of the transmission method as claimed in any one of claims 11 to 16.

35. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the transmission method as claimed in any one of claims 1 to 10, or implement the steps of the transmission method as claimed in any one of claims 11 to 16.

Images