Wireless communication method, apparatus and device

Abstract

The present application relates to the technical field of communications, and discloses a wireless communication method, apparatus and device. The wireless communication method in embodiments of the present application comprises: a first communication device receives related information of a target AI model from a second communication device; and the first communication device uses a first update mode or a second update mode to update the target AI model, wherein the first update mode is that the first communication device processes the target AI model before the target AI model is updated or used, or, the first update mode is that the first communication device directly updates or uses the target AI model, and the second update mode is that the first communication device processes the target AI model by means of a third communication device before the target AI model is updated or used, or, the second update mode is that the first communication device does not directly update or use the target AI model.

Description

Wireless communication method, apparatus and device

[0001] Cross Reference to Related Applications

[0002] This application claims priority to the Chinese patent application No. 202411073345.X, filed on August 6, 2024, and entitled "Wireless communication method, apparatus and device", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application belongs to the field of communication technology, and particularly relates to a wireless communication method, apparatus and device. BACKGROUND

[0004] In a New Radio (NR) system, specific functions such as positioning, Channel State Information (CSI) compression and recovery, channel encoding and decoding, beam prediction, channel prediction, etc. can be implemented based on an Artificial Intelligence (AI) model, however, the AI model has timeliness, and how to update the AI model is a problem to be solved. SUMMARY

[0005] Embodiments of the present application provide a wireless communication method, apparatus and device, which can solve the problem of not knowing how to update the AI model.

[0006] In a first aspect, a wireless communication method is provided, comprising:

[0007] A first communication device receives, from a second communication device, information related to a target Artificial Intelligence (AI) model; wherein the information related to the target AI model comprises at least one of the following: model parameters of the target AI model, model structure of the target AI model;

[0008] The first communication device updates the target AI model using a first update method or a second update method;

[0009] The first update method is that the first communication device processes the target AI model before or before using the target AI model is updated; or the first update method is that the first communication device directly updates or uses the target AI model;

[0010] The second update method is that the first communication device processes the target AI model through a third communication device before or before using the target AI model is updated; or the second update method is that the first communication device does not directly update or use the target AI model.

[0011] In a second aspect, a wireless communication method is provided, including:

[0012] The second communication device sends, to the first communication device, related information of a target artificial intelligence (AI) model; wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, and a model structure of the target AI model.

[0013] The second communication device receives, from the first communication device, first information.

[0014] The first information includes at least one of the following:

[0015] An update time delay of the target AI model.

[0016] A timestamp at which the target AI model is updated.

[0017] A timestamp at which the target AI model can be used.

[0018] First indication information, wherein the first indication information is used to indicate that the target AI model has been updated, or the first indication information is used to indicate that the target AI model can be used.

[0019] The update manner of the target AI model is a first update manner or a second update manner.

[0020] The first update manner is that the first communication device processes the target AI model before the target AI model is updated or used, or the first update manner is that the first communication device directly updates or uses the target AI model.

[0021] The second update manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used, or the second update manner is that the first communication device does not directly update or use the target AI model.

[0022] In a third aspect, a wireless communication apparatus is provided, including:

[0023] A receiving module, configured to receive, from a second communication device, related information of a target artificial intelligence (AI) model; wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, and a model structure of the target AI model.

[0024] A processing module, configured to update the target AI model using a first update manner or a second update manner.

[0025] The first updating manner is that the wireless communication device processes the target AI model before or before using the target AI model; or the first updating manner is that the wireless communication device directly updates or uses the target AI model.

[0026] The second updating manner is that the wireless communication device processes the target AI model through a third communication device before or before using the target AI model; or the second updating manner is that the wireless communication device does not directly update or use the target AI model.

[0027] In a fourth aspect, a wireless communication device is provided, comprising:

[0028] The sending module is configured to send related information of a target artificial intelligence (AI) model to a first communication device; wherein the related information of the target AI model comprises at least one of the following: model parameters of the target AI model, and a model structure of the target AI model.

[0029] The receiving module is configured to receive first information from the first communication device.

[0030] The first information comprises at least one of the following:

[0031] An update time delay of the target AI model;

[0032] A timestamp of completion of updating of the target AI model;

[0033] A timestamp of availability of the target AI model;

[0034] First indication information, wherein the first indication information is used to indicate that the target AI model has been updated, or the first indication information is used to indicate that the target AI model is available;

[0035] The updating manner of the target AI model is a first updating manner or a second updating manner.

[0036] The first updating manner is that the first communication device processes the target AI model before or before using the target AI model; or the first updating manner is that the first communication device directly updates or uses the target AI model.

[0037] The second updating manner is that the first communication device processes the target AI model through a third communication device before or before using the target AI model; or the second updating manner is that the first communication device does not directly update or use the target AI model.

[0038] In a fifth aspect, a wireless communication apparatus is provided, configured to perform the steps of the method of the first aspect, or implement the steps of the method of the second aspect.

[0039] In a sixth aspect, a first communication device is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method of the first aspect.

[0040] In a seventh aspect, a first communication device is provided, comprising a processor and a communication interface.

[0041] The communication interface is configured to receive, from a second communication device, related information of a target artificial intelligence (AI) model, wherein the related information of the target AI model comprises at least one of: model parameters of the target AI model, and a model structure of the target AI model.

[0042] The processor is configured to update the target AI model using a first update manner or a second update manner.

[0043] The first update manner is that, before the target AI model is updated or used, the first communication device processes the target AI model; or the first update manner is that the first communication device directly updates or uses the target AI model.

[0044] The second update manner is that, before the target AI model is updated or used, the first communication device processes the target AI model through a third communication device; or the second update manner is that the first communication device does not directly update or use the target AI model.

[0045] In an eighth aspect, a second communication device is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method of the second aspect.

[0046] In a ninth aspect, a second communication device is provided, comprising a processor and a communication interface.

[0047] The communication interface is configured to send, to a first communication device, related information of a target artificial intelligence (AI) model, wherein the related information of the target AI model comprises at least one of: model parameters of the target AI model, and a model structure of the target AI model.

[0048] The communication interface is further configured to receive, from the first communication device, first information.

[0049] The first information includes at least one of the following:

[0050] an update time delay of the target AI model;

[0051] a timestamp at which the target AI model is updated;

[0052] a timestamp at which the target AI model can be used;

[0053] first indication information, wherein the first indication information indicates that the target AI model has been updated, or the first indication information indicates that the target AI model can be used;

[0054] The update mode of the target AI model is a first update mode or a second update mode.

[0055] The first update mode is that the first communication device processes the target AI model before the target AI model is updated or used, or the first update mode is that the first communication device directly updates or uses the target AI model.

[0056] The second update mode is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used, or the second update mode is that the first communication device does not directly update or use the target AI model.

[0057] In a tenth aspect, a readable storage medium is provided, and the readable storage medium stores programs or instructions. When the programs or instructions are executed by a processor, the steps of the method according to the first aspect or the steps of the method according to the second aspect are implemented.

[0058] In an eleventh aspect, a wireless communication system is provided, and the wireless communication system includes a first communication device and a second communication device. The first communication device is configured to perform the steps of the method according to the first aspect, and the second communication device is configured to perform the steps of the method according to the second aspect.

[0059] In a twelfth aspect, a chip is provided, and the chip includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the method according to the first aspect or the method according to the second aspect.

[0060] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium, and is executed by at least one processor to implement the steps of the wireless communication method according to the first aspect, or to implement the steps of the wireless communication method according to the second aspect.

[0061] In the embodiments of the present application, the first communication device updates the target AI model using a first update manner or a second update manner; the first update manner is that the first communication device processes the target AI model before the target AI model is updated or used; or the first update manner is that the first communication device directly updates or uses the target AI model; the second update manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used; or the second update manner is that the first communication device does not directly update or use the target AI model. Thus, the target AI model can be updated using a suitable update manner, and the target AI model can be prevented from being disabled due to failure to obtain timely updates. BRIEF DESCRIPTION OF DRAWINGS

[0062] FIG. 1 is a schematic diagram of a communication system architecture according to an embodiment of the present application.

[0063] FIG. 2 is a schematic diagram of a neural network according to an embodiment of the present application.

[0064] FIG. 3 is a schematic diagram of a neuron according to an embodiment of the present application.

[0065] FIG. 4 is a schematic flowchart of a wireless communication method according to an embodiment of the present application.

[0066] FIG. 5 is a schematic block diagram of a wireless communication device according to an embodiment of the present application.

[0067] FIG. 6 is a schematic block diagram of another wireless communication device according to an embodiment of the present application.

[0068] FIG. 7 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0069] FIG. 8 is a schematic diagram of a hardware structure of a terminal according to an embodiment of the present application.

[0070] FIG. 9 is a schematic block diagram of a network-side device according to an embodiment of the present application.

[0071] FIG. 10 is a schematic block diagram of another network-side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0072] With reference to the drawings and the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly described. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art are within the scope of the present application.

[0073] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second" are generally a class, and are not limited to the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, the protection scope of "A or B" at least covers three schemes, namely, scheme one: including A and not including B; scheme two: including B and not including A; scheme three: including A and B. In addition, the terms "A and / or B", "at least one of A and B", "at least one of A or B" also at least cover the above three schemes, respectively. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0074] The term "indication" in the present application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). Among them, the direct indication can be understood as that the sender explicitly informs the receiver of specific information, operation to be performed or request result, etc. in the sent indication; the indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or judges and determines the operation to be performed or the request result according to the judgment result.

[0075] It is worth noting that the technology described in the embodiments of the present application is 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 the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems. th

[0076] Figure 1 shows a block diagram of a wireless communication system to which the embodiments of the present application can be applied. Specifically, the wireless communication system includes a terminal 11 and a network-side device 12.

[0077] ​The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palm computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home device (a home device with a wireless communication function, such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a teller machine, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothing, and the like. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application.

[0078] The network-side device 12 can include an access network device or a core network device.

[0079] Optionally, the access network device can also be referred to as a radio access network (RAN) device, a radio access network function or a radio access network unit. The access network device can include a base station, a wireless local area network (WLAN) access point (AP) or a wireless fidelity (WiFi) node, etc. Among them, the base station can be referred to as a node B (NB), an evolved node B (eNB), a next generation node B (gNB), a new radio node B (NR node B), an access point, a relay base station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home node B (HNB), a home evolved node B, a transmit / receive point (TRP), or some other suitable term in the art, as long as the same technical effect is achieved. The base station is not limited to a specific technical term, and it should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0080] Optionally, the core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), etc. It should be noted that only the core network device in the NR system is taken as an example for introduction in the embodiments of the present application, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in the subsequent protocol version (for example, 6G), it is also within the protection scope of the present application.

[0081] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices together, and the embodiments of the present application do not make specific limitations. It can be understood that the above function modules can be network elements in a hardware device, software function modules running on a special hardware, or virtualized function modules instantiated on a platform (for example, a cloud platform).

[0082] In order to better understand the embodiments of the present application, artificial intelligence (AI) is described.

[0083] Artificial intelligence (AI) has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks significantly improves technical indicators such as throughput, latency, and user capacity, which is an important task for future wireless communication networks. AI modules have various implementation methods, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. The present application takes neural networks as an example for illustration, but does not limit the specific type of AI module.

[0084] A schematic diagram of a neural network can be as shown in FIG. 2. The neural network is composed of neurons, and a schematic diagram of a neuron is shown in FIG. 3. Wherein, a1, a2, … aK are inputs, w is a weight (multiplicative coefficient), b is a bias (additive coefficient), and σ(.) is an activation function. Common activation functions include Sigmoid, tanh, rectified linear unit (ReLU), etc.

[0085] The parameters of the neural network are optimized by a gradient optimization algorithm. Gradient optimization algorithm is a class of algorithms for minimizing or maximizing an objective function (sometimes also called loss function), and the objective function 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 get the predicted output f(x) according to the input x, and can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. Our goal is to find the appropriate W, b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the true situation.

[0086] The common optimization algorithm is basically based on error back propagation (BP) algorithm. The basic idea of the BP algorithm is that the learning process is composed of two processes of forward propagation of signals and backward propagation of errors. When the forward propagation is performed, the input sample is transmitted from the input layer to the output layer through the processing of each hidden layer. If the actual output of the output layer does not match the expected output, the backward propagation of errors is performed. The error back propagation is to transmit the output error to the input layer through the hidden layer in a certain form, and distribute the error to all units of each layer, so as to obtain the error signal of each unit, which is used as the basis for correcting the weight of each unit. The weight adjustment process of each layer is repeated. The process of continuously adjusting the weight is the learning and training process of the network. The process is performed until the error of the network output is reduced to an acceptable level, or until the preset learning times are reached.

[0087] The common optimization algorithm includes gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (specifically, stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), adaptive moment estimation (Adam), etc. When the error back propagation is performed, the error / loss obtained according to the loss function is derived for the current neuron, the learning rate, the previous gradient / derivative / partial derivative, etc. are added, the gradient is obtained, and the gradient is transmitted to the previous layer.

[0088] The wireless communication method provided by the embodiments of the present application will be described in detail in combination with the accompanying drawings, some embodiments and application scenarios.

[0089] FIG. 4 is a schematic flowchart of a wireless communication method 200 according to an embodiment of the present application. As shown in FIG. 4, the wireless communication method 200 can include at least part of the following contents:

[0090] S210, the second communication device sends the related information of the target AI model to the first communication device;

[0091] The related information of the target AI model includes at least one of the following: model parameters of the target AI model, and a model structure of the target AI model.

[0092] S220, the first communication device receives, from the second communication device, the related information of the target AI model.

[0093] S230, the first communication device updates the target AI model using a first update manner or a second update manner; the first update manner is that the first communication device processes the target AI model before the target AI model is updated or used; or the first update manner is that the first communication device directly updates or uses the target AI model; the second update manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used; or the second update manner is that the first communication device does not directly update or use the target AI model.

[0094] It should be understood that FIG. 4 shows steps or operations of the wireless communication method 200, but these steps or operations are only examples, and the present application can also perform other operations or variations of each operation in FIG. 4.

[0095] In the embodiments of the present application, the first communication device updates the target AI model using the first update manner or the second update manner; the first update manner is that the first communication device processes the target AI model before the target AI model is updated or used; or the first update manner is that the first communication device directly updates or uses the target AI model; the second update manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used; or the second update manner is that the first communication device does not directly update or use the target AI model. Thus, the target AI model can be updated using a suitable update manner, and the target AI model can be prevented from being invalid due to not being updated in time.

[0096] The AI model described in the embodiments of the present application can also be referred to as an AI unit, an AI model / AI unit, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a neural network, a neural network function, a neural network function, etc. Alternatively, the AI model described in the present application can refer to a processing unit capable of implementing a specific algorithm, formula, processing flow, capability, etc. related to AI, or the AI model described in the present application can be a processing method, algorithm, function, module or unit for a specific data set, or the AI model described in the present application can be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), application specific integrated circuit (ASIC), etc. The present application does not make specific limitations. Optionally, the specific data set includes input or output of the AI model.

[0097] The identifier of the AI model described in the embodiments of the present application can be an AI unit identifier, an AI structure identifier, an AI parameter identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI model described in the present application, or an identifier of a specific scene, environment, channel feature, device related to the AI model described in the present application, or an identifier of a function, feature, capability or module related to the AI model described in the present application. The present application does not make specific limitations.

[0098] The first updating method described in the embodiments of the present application can also be referred to as real-time AI model updating or similar names, and the second updating method described in the embodiments of the present application can also be referred to as non-real-time AI model updating or similar names. For example, the first updating method has a low time delay and can complete the updating of the target AI model in real time; the second updating method has a high time delay and cannot complete the updating of the target AI model in real time.

[0099] The updating of the target AI model described in the embodiments of the present application can be understood as updating the parameters of the target AI model, and the use of the target AI model described in the embodiments of the present application can be understood as implementing a specific function based on the target AI model (see the related description of the function that can be implemented by the target AI model later).

[0100] In some embodiments, the first updating method is that the first communication device processes the target AI model before the target AI model is updated or used, which can specifically include:

[0101] After obtaining the related information of the target AI model, the first communication device performs retraining, fine-tuning, quantization, pruning, compression, or other model optimization processing on the target AI model locally before the target AI model is updated or used; or,

[0102] After obtaining the related information of the target AI model, the first communication device updates the target AI model based on the related information of the target AI model before the target AI model is used, and then the first communication device performs retraining, fine-tuning, quantization, pruning, compression, or other model optimization processing on the updated target AI model locally; or,

[0103] After obtaining the related information of the target AI model, the first communication device performs fine-tuning, quantization, pruning, compression, or other model parameter optimization processing on the related information of the target AI model before the target AI model is used, and updates the target AI model based on the related information of the target AI model after the optimization processing; or,

[0104] After obtaining the related information of the target AI model, the first communication device performs fine-tuning, quantization, pruning, compression, or other model parameter optimization processing on the combination of the related information of the target AI model and the model parameters or model structure of the target AI model before the target AI model, and updates the target AI model based on the model parameters or model structure of the target AI model after the optimization processing.

[0105] In some embodiments, the first update method is that the first communication device directly uses the target AI model, which can specifically include:

[0106] After obtaining the related information of the target AI model, the first communication device can directly use the model parameters in the related information of the target AI model.

[0107] In some embodiments, the first update method is that the first communication device directly updates the target AI model, which can specifically include:

[0108] After obtaining the related information of the target AI model, the first communication device can replace the model parameters of the target AI model before with the model parameters in the related information of the target AI model.

[0109] For example, when the obtained related information of the target AI model includes model parameters of the target AI model, the first communication device directly replaces the file or information of the model parameters of the target AI model obtained before with the file or information of the model parameters of the target AI model obtained, or the first communication device places the file or information of the model parameters of the target AI model obtained in a designated location, so that the target AI model can be used.

[0110] In some embodiments, before the target AI model is updated or used, the first communication device processes the target AI model through a third communication device, which can include the following specific operations:

[0111] After obtaining the related information of the target AI model, the first communication device needs to send the obtained related information of the target AI model to the third communication device, and the third communication device performs model optimization processing such as retraining, fine-tuning, quantization, pruning and compression on the target AI model. Then, the third communication device sends the processed related information of the target AI model to the first communication device, and the first communication device uses the processed target AI model.

[0112] In some embodiments, the first communication device is one of the following: a terminal, an access network device (such as gNB), and a core network device; and / or, the second communication device is one of the following: a terminal, an access network device (such as gNB), and a core network device.

[0113] For example, the first communication device is a terminal, and the second communication device is an access network device (such as gNB). Optionally, the third communication device is a local server or a third-party server of the terminal.

[0114] For example, the first communication device is a terminal, and the second communication device is a core network device. Optionally, the third communication device is a local server or a third-party server of the terminal.

[0115] For example, the first communication device is an access network device (such as gNB), and the second communication device is a core network device. Optionally, the third communication device is a local server or a third-party server of the access network device (such as gNB).

[0116] For example, the first communication device is a first terminal, and the second communication device is a second terminal. Optionally, the third communication device is a local server or a third-party server of the first terminal.

[0117] For example, the first communication device is a first access network device (such as gNB), and the second communication device is a second access network device (such as gNB). Optionally, the third communication device is a local server or a third-party server of the first access network device (such as gNB).

[0118] For example, the first communication device is a first core network device, and the second communication device is a second core network device. Optionally, the third communication device is a local server of the first core network device or a third-party server.

[0119] In some embodiments, the target AI model includes, but is not limited to, at least one of the following:

[0120] The AI model used by the first communication device;

[0121] The AI model used by the second communication device;

[0122] The reference AI model of the AI model used by the first communication device;

[0123] The reference AI model of the AI model used by the second communication device;

[0124] The AI model used by the first communication device in testing;

[0125] The AI model used by the second communication device in testing;

[0126] The AI model used by the testing device in testing;

[0127] The reference AI model of the AI model used by the first communication device in testing;

[0128] The reference AI model of the AI model used by the second communication device in testing;

[0129] The reference AI model of the AI model used by the testing device in testing;

[0130] The AI model used by the first communication device to match the AI model used in testing;

[0131] The AI model used by the second communication device to match the AI model used in testing;

[0132] The AI model used by the testing device to match the AI model used in testing.

[0133] In some embodiments, the input or output of the target AI model can include at least one of the following:

[0134] Reference signals, channel-borne signals, channel state information, beam information, channel prediction information, interference information, positioning information, trajectory information, codebook information, original channel information, specified prediction information and management information, and control signaling.

[0135] In some embodiments, the target AI model can implement at least one of the following functions:

[0136] Reference signal processing, including signal detection, filtering, equalization, etc., wherein the reference signal includes at least one of: a demodulation reference signal (DMRS), a sounding reference signal (SRS), a synchronization signal block (SSB), a channel state information reference signal (CSI-RS), a tracking reference signal (TRS), a positioning reference signal (PRS), a phase tracking reference signal (PT-RS);

[0137] Transmission of a channel or a signal, or reception of a channel or a signal, or demodulation of a channel or a signal, or sending of a channel or a signal, wherein the channel includes a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), a physical random access channel (PRACH), a PBCH, etc.

[0138] Channel state information acquisition; including channel state information feedback and / or uplink-downlink reciprocity on frequency division duplex (FDD); wherein the channel state information feedback includes channel related information, channel matrix related information, channel feature information, channel matrix feature information, precoding matrix indication (PMI), rank indication (RI), CSI-RS resource indication (CRI), channel quality indication (CQI), layer indication (LI), etc.; for the FDD system, according to the partial reciprocity, the base station obtains the angle and delay information according to the uplink channel, can inform the UE of the angle information and the delay information through the method of CSI-RS precoding or direct indication, and the UE reports according to the indication of the base station or selects and reports within the indication range of the base station, thereby reducing the calculation amount of the UE and the overhead of CSI reporting;

[0139] Beam management, including beam measurement, beam reporting, beam prediction, beam failure detection, beam failure recovery, new beam indication in beam failure recovery, etc.;

[0140] Channel prediction, including channel state information prediction, beam prediction, etc.

[0141] Channel / source coding, such as channel coding, channel decoding, source coding, source decoding, joint source-channel coding, joint source-channel decoding, etc.

[0142] Interference suppression, including intra-cell interference, inter-cell interference, out-of-band interference, intermodulation interference, etc.

[0143] Positioning, estimating the specific position (including horizontal position and / or vertical position) of the UE, position related information or future possible trajectory, or auxiliary position estimation or trajectory estimation information through the measurement information of the reference signal (such as SRS or PRS);

[0144] Prediction and management of high-level services and parameters, including throughput, required packet size, service demand, moving speed, noise information, etc.

[0145] Analysis of control signaling, such as power control related signaling, beam management related signaling.

[0146] In some embodiments, the model parameters of the target AI model include but are not limited to at least one of the following:

[0147] a storage size of the target AI model, a computational complexity of the target AI model, a number of operations of the target AI model, a time required for transmission of model parameters of the target AI model, and a number of data packets required for transmission of the model parameters of the target AI model.

[0148] Optionally, the number of operations of the target AI model can include, but is not limited to, at least one of the following:

[0149] a number of floating-point operations (FLOPs), a number of model multiplications and additions, a number of model multiplications, and a number of model additions.

[0150] It should be noted that a data packet carries limited data, and when the target AI model is too large, multiple data packets are required to accommodate all model parameters. It is possible to complete the transmission of multiple data packets at one time, or it is possible to complete the transmission of multiple data packets at multiple times.

[0151] In some embodiments, the model structure of the target AI model includes, but is not limited to, at least one of the following:

[0152] a number of layers of the target AI model, a number of neurons of each layer of the target AI model, a connection mode between each neuron of the target AI model, and an activation function of the target AI model.

[0153] Optionally, the connection mode between each neuron of the target AI model includes, but is not limited to, at least one of the following:

[0154] full connection, convolutional connection, and recurrent connection.

[0155] It should be noted that the connection mode between each neuron of the target AI model can realize the training and inference process of the target AI model through mechanisms such as weighted summation, activation function, attention, mixer, residual, and back propagation.

[0156] In some embodiments, the first update mode has a lower latency than the second update mode; and / or,

[0157] the latency of the first update mode is lower than or not higher than a first threshold; and / or,

[0158] the latency of the second update mode is higher than or not lower than a second threshold.

[0159] Optionally, the first threshold is agreed by a protocol, or the first threshold is configured by a network side.

[0160] Optionally, the second threshold is agreed by a protocol, or the second threshold is configured by a network side.

[0161] In some embodiments, the wireless communication method 200 further includes:

[0162] The first communication device sends first information to the second communication device;

[0163] The first information includes at least one of:

[0164] an update time delay of the target AI model;

[0165] a timestamp of completion of updating of the target AI model;

[0166] a timestamp of availability of the target AI model;

[0167] first indication information, wherein the first indication information is used to indicate that the target AI model has completed updating, or the first indication information is used to indicate that the target AI model is available.

[0168] In the present embodiment, the first communication device sends the first information to the second communication device, and accordingly, the second communication device can learn at least one of the following: the update time delay of the target AI model, the timestamp of completion of updating of the target AI model, the timestamp of availability of the target AI model, and the first indication information, so that the second communication device can learn the updating situation of the target AI model in time.

[0169] Optionally, the timestamp of completion of updating of the target AI model needs to be fed back to the second communication device within a first time length after the first communication device completes updating of the target AI model, so as to ensure that the second communication device can learn that the target AI model has completed updating in time. It should be noted that the first time length cannot be too long, so as to avoid invalidation of the target AI model within the first time length.

[0170] Optionally, the timestamp of availability of the target AI model needs to be fed back to the second communication device within a second time length after the first communication device completes updating of the target AI model, so as to ensure that the second communication device can learn that the target AI model has become available in time. It should be noted that the second time length cannot be too long, so as to avoid invalidation of the target AI model within the second time length.

[0171] Optionally, if the first indication information is used to indicate that the target AI model has completed updating, the first indication information needs to be fed back to the second communication device within a first time length after the first communication device completes updating of the target AI model, so as to ensure that the second communication device can learn that the target AI model has completed updating in time. It should be noted that the first time length cannot be too long, so as to avoid invalidation of the target AI model within the first time length.

[0172] Optionally, if the first indication information is used to indicate that the target AI model can be used, the timestamp when the target AI model can be used needs to be fed back to the second communication device within a second time length after the first communication device completes the update of the target AI model, so as to ensure that the second communication device can learn in time that the target AI model can be used. It should be noted that the second time length cannot be too long, so as to avoid that the target AI model is invalid within the second time length.

[0173] In some embodiments, the first information further includes second indication information.

[0174] The second indication information is used to indicate that the first communication device uses the first update manner to update the target AI model, or the second indication information is used to indicate that the first communication device does not use the second update manner to update the target AI model, or the second indication information is used to indicate that the first communication device uses the second update manner to update the target AI model, and the second indication information is used to indicate that the first communication device does not use the first update manner to update the target AI model.

[0175] In this embodiment, the first information further includes second indication information, and accordingly, the second communication device can learn the update manner of the target AI model used by the first communication device.

[0176] In some embodiments, the S230 can specifically include:

[0177] The first communication device updates the target AI model using the first update manner or the second update manner according to the model parameters of the target AI model.

[0178] In this embodiment, the first communication device updates the target AI model using the first update manner or the second update manner according to the model parameters of the target AI model, so that the update manner of the used target AI model can be more consistent with the actual situation of the target AI model.

[0179] In some embodiments, the first communication device updates the target AI model using the first update manner or the second update manner according to the model parameters of the target AI model, including:

[0180] In a case where the model parameters of the target AI model are less than a third threshold, or in a case where the model parameters of the target AI model are less than or equal to the third threshold, the first communication device updates the target AI model using the first update manner; and / or,

[0181] In a case where the model parameter of the target AI model is greater than a third threshold, or in a case where the model parameter of the target AI model is greater than or equal to the third threshold, the first communication device updates the target AI model using the second update manner.

[0182] Optionally, the third threshold is agreed by a protocol, or the third threshold is configured by a network side.

[0183] For example, in a case where the storage size of the target AI model is less than a third threshold, or in a case where the storage size of the target AI model is less than or equal to the third threshold, the first communication device updates the target AI model using the first update manner; otherwise, the first communication device updates the target AI model using the second update manner.

[0184] For example, in a case where the operation complexity of the target AI model is less than a third threshold, or in a case where the operation complexity of the target AI model is less than or equal to the third threshold, the first communication device updates the target AI model using the first update manner; otherwise, the first communication device updates the target AI model using the second update manner.

[0185] For example, in a case where the operation times of the target AI model is less than a third threshold, or in a case where the operation times of the target AI model is less than or equal to the third threshold, the first communication device updates the target AI model using the first update manner; otherwise, the first communication device updates the target AI model using the second update manner.

[0186] For example, in a case where the time required for transmitting the model parameter of the target AI model is less than a third threshold, or in a case where the time required for transmitting the model parameter of the target AI model is less than or equal to the third threshold, the first communication device updates the target AI model using the first update manner; otherwise, the first communication device updates the target AI model using the second update manner.

[0187] For example, in a case where the number of data packets required for transmitting the model parameter of the target AI model is less than a third threshold, or in a case where the number of data packets required for transmitting the model parameter of the target AI model is less than or equal to the third threshold, the first communication device updates the target AI model using the first update manner; otherwise, the first communication device updates the target AI model using the second update manner.

[0188] In some embodiments, the S230 can specifically include:

[0189] The first communication device updates the target AI model according to a model structure of the target AI model using the first update manner or the second update manner.

[0190] In this embodiment, the first communication device updates the target AI model according to a model structure of the target AI model using the first update manner or the second update manner, so that the update manner used for the target AI model can be more in line with the actual situation of the target AI model.

[0191] In some embodiments, the first communication device updates the target AI model according to a model structure of the target AI model using the first update manner or the second update manner, including:

[0192] In the case where the model structure of the target AI model belongs to the first AI model structure set, the first communication device updates the target AI model using the first update manner; and / or,

[0193] In the case where the model structure of the target AI model belongs to the second AI model structure set, the first communication device updates the target AI model using the second update manner.

[0194] Optionally, the first AI model structure set can be agreed by a protocol, or the first AI model structure set can be configured by a network side; and / or, the second AI model structure set can be agreed by a protocol, or the second AI model structure set can be configured by a network side.

[0195] In some embodiments, the above S230 can specifically include:

[0196] The first communication device updates the target AI model using the first update manner or the second update manner by default.

[0197] In this embodiment, the first communication device updates the target AI model using the first update manner or the second update manner by default, so that the use of the update manner of the target AI model can be simplified.

[0198] For example, when the second communication device does not make relevant indication of the update manner, and / or the first communication device does not make relevant report of the update manner, the first communication device and the second communication device both consider (such as by default) that the first communication device updates the target AI model using the first update manner or the second update manner.

[0199] Optionally, the update manner used by default can be agreed by a protocol.

[0200] The default in the embodiments of the present application can refer to that the network side does not indicate or the second communication device does not indicate.

[0201] In some embodiments, the S230 can specifically include the following steps.

[0202] The first communication device sends capability information to the second communication device.

[0203] The capability information includes at least one of the following:

[0204] The first communication device supports at least one of the following: AI model transmission, AI model update, AI model transmission based on air interface, AI model transmission based on air interface and 3rd Generation Partnership Project (3GPP) signaling (such as visible or non-transparent);

[0205] The first communication device supports the first update mode.

[0206] The first communication device supports the first update mode and does not support the second update mode.

[0207] The first communication device supports the second update mode.

[0208] The first communication device supports the second update mode and does not support the first update mode.

[0209] The first communication device supports the first update mode and the second update mode.

[0210] It should be noted that the AI model transmission in the embodiments of the present application can include transmission of model parameters of the AI model and / or transmission of model structure of the AI model.

[0211] In the present embodiment, the first communication device sends capability information to the second communication device, so that the second communication device can indicate the update mode of the target AI model to the first communication device based on the capability information sent by the first communication device, or the second communication device can determine the update mode of the target AI model used by the first communication device based on the capability information sent by the first communication device.

[0212] In some embodiments, before the first communication device updates the target AI model using the first update mode or the second update mode, the wireless communication method 200 further includes the following steps.

[0213] The first communication device receives second information or third information from the second communication device.

[0214] The second information is used to indicate that the first communication device uses the first update manner or the second update manner to update the target AI model.

[0215] The third information is used to indicate that the first communication device autonomously uses the first update manner or the second update manner to update the target AI model.

[0216] In this embodiment, the second communication device can indicate the update manner of the target AI model to the first communication device through the second information or the third information.

[0217] In some embodiments, the second information is determined based on AI model update capability of the first communication device, or the third information is determined based on the AI model update capability of the first communication device.

[0218] In some embodiments, the S230 can specifically include:

[0219] If the first communication device supports at least one of AI model transmission, AI model update, air interface-based AI model transmission, and air interface and 3GPP signaling (such as visible or non-transparent) based AI model transmission, the first communication device can use the first update manner to update the target AI model by default, or the first communication device can use the second update manner to update the target AI model by default, or the first communication device can use the first update manner or the second update manner to update the target AI model by itself, or the first communication device can use the first update manner or the second update manner to update the target AI model according to the indication (such as the second information or the third information) of the second communication device.

[0220] In this embodiment, if the first communication device supports at least one of AI model transmission, AI model update, air interface-based AI model transmission, and air interface and 3GPP signaling (such as visible or non-transparent) based AI model transmission, and does not indicate whether the first update manner is supported and does not indicate whether the second update manner is supported, the first communication device can flexibly use the update manner of the target AI model.

[0221] In some embodiments, the S230 can specifically include:

[0222] If the first communication device supports the first update manner (e.g., without indicating whether the second update manner is supported), the first communication device updates the target AI model using the first update manner, or the first communication device updates the target AI model using the first update manner by default, or the first communication device updates the target AI model using the first update manner by itself, or the first communication device updates the target AI model using the first update manner or the second update manner according to an indication (e.g., the second information or the third information) of the second communication device.

[0223] In this embodiment, if the first communication device supports the first update manner (e.g., without indicating whether the second update manner is supported), the first communication device can flexibly use the update manner of the target AI model.

[0224] In some embodiments, the S230 can specifically include:

[0225] If the first communication device supports the first update manner and does not support the second update manner, the first communication device updates the target AI model according to the first update manner.

[0226] In some embodiments, the S230 can specifically include:

[0227] If the first communication device supports the second update manner (e.g., without indicating whether the first update manner is supported), the first communication device updates the target AI model using the second update manner, or the first communication device updates the target AI model using the second update manner by default, or the first communication device updates the target AI model using the first update manner or the first update manner by itself, or the first communication device updates the target AI model using the first update manner or the second update manner according to an indication (e.g., the second information or the third information) of the second communication device.

[0228] In this embodiment, if the first communication device supports the second update manner (e.g., without indicating whether the first update manner is supported), the first communication device can flexibly use the update manner of the target AI model.

[0229] In some embodiments, the S230 can specifically include:

[0230] If the first communication device supports the second update manner and does not support the first update manner, the first communication device updates the target AI model according to the second update manner.

[0231] In some embodiments, S230 can specifically include:

[0232] If the first communication device supports the first update mode and the second update mode, the first communication device can update the target AI model using the first update mode by default, or the first communication device can update the target AI model using the second update mode by default, or the first communication device can update the target AI model using the first update mode or the first update mode by itself, or the first communication device can update the target AI model using the first update mode or the second update mode according to the indication (such as the second information or the third information) of the second communication device.

[0233] In this embodiment, if the first communication device supports the first update mode and the second update mode, the first communication device can flexibly use the update mode of the target AI model.

[0234] In some embodiments, S230 can specifically include:

[0235] If the second communication device indicates that the target AI model is updated using the first update mode or the second update mode, the first communication device updates the target AI model using the update mode indicated by the second communication device, and the first communication device does not feed back the used update mode to the second communication device; or,

[0236] If the second communication device indicates that the target AI model is updated using the first update mode or the second update mode, the first communication device updates the target AI model using the first update mode or the second update mode by itself, and the first communication device feeds back the used update mode to the second communication device; or,

[0237] If the second communication device indicates that the first communication device updates the target AI model using the first update mode or the second update mode by itself, the first communication device updates the target AI model using the first update mode or the second update mode by itself, and the first communication device feeds back the used update mode to the second communication device; or,

[0238] The first communication device updates the target AI model using the first update mode or the second update mode based on a protocol agreement, and the first communication device does not feed back the used update mode to the second communication device; or,

[0239] If the agreement stipulates that the target AI model is updated using the first update mode or the second update mode, the first communication device updates the target AI model using the first update mode or the second update mode by itself, and the first communication device feeds back the used update mode to the second communication device; or

[0240] The first communication device updates the target AI model using the first update mode or the second update mode by itself, and the first communication device feeds back the used update mode to the second communication device.

[0241] In the embodiment, the first communication device can flexibly use the update mode of the target AI model, and the first communication device can feed back the used update mode to the second communication device based on whether the implementation uses.

[0242] Therefore, in the embodiment of the application, the first communication device updates the target AI model using the first update mode or the second update mode; wherein the first update mode is that the first communication device processes the target AI model before the target AI model is updated or used; or the first update mode is that the first communication device directly updates or uses the target AI model; the second update mode is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used; or the second update mode is that the first communication device does not directly update or use the target AI model. Thus, the target AI model can be updated using a suitable update mode, and the target AI model can be prevented from being invalid due to not being updated in time.

[0243] The technical scheme of the application is described in detail through specific embodiments.

[0244] Embodiment 1 takes the first communication device as a terminal (UE), the second communication device as a network side device (NW), the first update mode as real-time AI model updating, and the second update mode as non-real-time AI model updating as an example. In embodiment 1, the relationship between UE capability reporting and real-time AI model updating or non-real-time AI model updating is described in detail.

[0245] Optionally, the UE (such as through UE capability) indicates support for "AI model transmission" or "AI model updating" or "air interface based AI model transmission" or "air interface, 3GPP signaling [visible or non-transparent] based AI model transmission". In this case, the following optional solutions can exist:

[0246] a) UE needs to use the update mode of the target AI model (it is not specified whether "non-real-time AI model update" or "real-time AI model update" is supported, only AI model update is supported), in this case, the UE updates the target AI model using real-time AI model update or non-real-time AI model update;

[0247] b) or, it indicates that the UE only supports "real-time AI model update", or the NW does not indicate real-time AI model update or non-real-time AI model update, and by default "real-time AI model update" (such as the protocol defaults to "real-time AI model update"), in this case, the UE updates the target AI model using real-time AI model update;

[0248] c) or, it indicates that the UE only supports "non-real-time AI model update", or the NW does not indicate real-time AI model update or non-real-time AI model update, and by default "non-real-time AI model update" (such as the protocol defaults to "non-real-time AI model update"), in this case, the UE updates the target AI model using non-real-time AI model update.

[0249] Optionally, the UE (such as through UE capability) indicates that it supports "real-time AI model update" (does not indicate that it does not support "non-real-time AI model update", such as the protocol does not have "non-real-time AI model update" in the UE capability, or the UE capability does not indicate whether it supports "non-real-time AI model update"), in this case, the following optional solutions can exist:

[0250] a) The UE updates the target AI model using real-time AI model update;

[0251] i. Optionally, the NW issues conditions for using the update mode of the target AI model based on the model parameters of the target AI model and / or conditions for using the update mode of the target AI model based on the model structure of the target AI model, and in the case of meeting the conditions for real-time AI model update, the UE updates the target AI model using real-time AI model update;

[0252] ii. Optionally, regardless of the conditions for using the update mode of the target AI model based on the model parameters of the target AI model and / or conditions for using the update mode of the target AI model based on the model structure of the target AI model issued by the NW, the UE updates the target AI model using real-time AI model update;

[0253] b) The UE updates the target AI model using real-time AI model update or non-real-time AI model update;

[0254] c) The NW does not indicate real-time AI model update or non-real-time AI model update, and the UE defaults to using real-time AI model update to update the target AI model.

[0255] Optionally, the UE (e.g., through UE capability) indicates support for "real-time AI model update" and indicates no support for "non-real-time AI model update", in which case there can be the following options:

[0256] The UE uses real-time AI model update to update the target AI model;

[0257] i. Optionally, the NW issues a condition for updating the model parameters of the target AI model using the target AI model and / or a condition for updating the model structure of the target AI model using the target AI model, and in the case where the condition for real-time AI model update is met, the UE uses real-time AI model update to update the target AI model;

[0258] ii. Optionally, regardless of the condition for updating the model parameters of the target AI model using the target AI model and / or the condition for updating the model structure of the target AI model using the target AI model issued by the NW, the UE uses real-time AI model update to update the target AI model.

[0259] Optionally, the UE (e.g., through UE capability) indicates support for "non-real-time AI model update" (does not indicate no support for "real-time AI model update", e.g., there is no "real-time AI model update" item in the UE capability or the UE capability does not indicate whether it supports "real-time AI model update"), in which case there can be the following options:

[0260] a) The UE uses non-real-time AI model update to update the target AI model;

[0261] i. Optionally, the NW issues a condition for updating the model parameters of the target AI model using the target AI model and / or a condition for updating the model structure of the target AI model using the target AI model, and in the case where the condition for non-real-time AI model update is met, the UE uses non-real-time AI model update to update the target AI model;

[0262] ii. Optionally, regardless of the condition for updating the model parameters of the target AI model using the target AI model and / or the condition for updating the model structure of the target AI model using the target AI model issued by the NW, the UE uses non-real-time AI model update to update the target AI model;

[0263] b) The UE uses real-time AI model update or non-real-time AI model update to update the target AI model;

[0264] c) The NW does not indicate real-time AI model update or non-real-time AI model update, and the UE defaults to using non-real-time AI model update to update the target AI model.

[0265] Optionally, the UE (such as through UE capability) indicates support for "non-real-time AI model updating" and indicates no support for "real-time AI model updating". In this case, the following options can exist:

[0266] The UE uses non-real-time AI model updating to update the target AI model.

[0267] i. Optionally, the NW issues conditions for using the target AI model for updating the model parameters of the target AI model and / or conditions for using the target AI model for updating the model structure of the target AI model. In the case where the conditions for non-real-time AI model updating are met, the UE uses non-real-time AI model updating to update the target AI model.

[0268] ii. Optionally, regardless of the conditions for using the target AI model for updating the model parameters of the target AI model and / or conditions for using the target AI model for updating the model structure of the target AI model issued by the NW, the UE uses non-real-time AI model updating to update the target AI model.

[0269] Optionally, the UE capability indicates support for "non-real-time AI model updating" and "real-time AI model updating". The UE uses real-time AI model updating or non-real-time AI model updating to update the target AI model.

[0270] Embodiment 2 takes the first communication device as a terminal (UE) and the second communication device as a network side device (NW), and takes the first updating method as real-time AI model updating and the second updating method as non-real-time AI model updating as an example. In embodiment 2, the process of using the updating method of the target AI model according to different conditions is described in detail.

[0271] Optionally, the NW issues related information of the target AI model, wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, model structure of the target AI model, and the NW indicates real-time AI model updating or non-real-time AI model updating. The UE does not need to feedback the updating method of the target AI model used by the UE (the UE needs to strictly use the updating method of the target AI model indicated by the NW).

[0272] Optionally, the NW issues related information of the target AI model, wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, model structure of the target AI model, and the NW indicates real-time AI model updating or non-real-time AI model updating. The UE does not need to feedback the updating method of the target AI model used by the UE (the UE needs to strictly use the updating method of the target AI model indicated by the NW).

[0273] Optionally, the NW issues the related information of the target AI model, wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, model structure of the target AI model, and the NW indicates the update mode of the target AI model used by the UE, and the UE feeds back the update mode of the target AI model used by the UE.

[0274] Optionally, the NW issues the related information of the target AI model, wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, model structure of the target AI model, and according to the protocol agreement, both sides know that the target AI model is updated using real-time AI model update or non-real-time AI model update, and the UE does not need to feed back the update mode of the target AI model used by the UE (the UE needs to strictly use the update mode of the target AI model according to the protocol agreement).

[0275] Optionally, the NW issues the related information of the target AI model, wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, model structure of the target AI model, and according to the protocol agreement, both sides know that the target AI model is updated using real-time AI model update or non-real-time AI model update, and the UE feeds back the update mode of the target AI model used by the UE (the UE does not need to strictly use the update mode of the target AI model according to the protocol agreement).

[0276] Optionally, the NW issues the related information of the target AI model, wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, model structure of the target AI model, and the UE feeds back the update mode of the target AI model used by the UE (the NW does not indicate, and the UE uses the update mode of the target AI model by itself).

[0277] The wireless communication method provided in the embodiments of the present application can be executed by a wireless communication device. In the embodiments of the present application, the wireless communication device is taken as an example to illustrate the wireless communication device provided in the embodiments of the present application.

[0278] The wireless communication device provided in the embodiments of the present application can be a communication device or a component in the communication device, for example, a chip. The communication device can be a terminal, a network side device, a server, or the like. Exemplarily, the terminal can include, but is not limited to, the types of the terminal 11 listed above, the network side device can include, but is not limited to, the types of the network side device 12 listed above, and the embodiments of the present application do not make specific limitations.

[0279] The wireless communication apparatus includes a receiving module, a sending module and a processing module. The receiving module, the sending module and the processing module can be implemented by software or by hardware. When implemented by hardware, the processing module can be implemented by a processor, which can include a general-purpose processor, a dedicated processor, etc., such as a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA) or other programmable logic device, a gate circuit, a transistor, a discrete hardware component, etc. The receiving module and the sending module can be implemented by a communication interface, which can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0280] Referring to FIG. 5, when the wireless communication apparatus is a first communication device or a component in the first communication device, the wireless communication apparatus 300 includes:

[0281] The receiving module 301 is configured to receive, from a second communication device, information related to a target artificial intelligent (AI) model; wherein the information related to the target AI model includes at least one of the following: a model parameter of the target AI model, a model structure of the target AI model.

[0282] The processing module 302 is configured to update the target AI model using a first update manner or a second update manner.

[0283] The first update manner is that the wireless communication apparatus 300 processes the target AI model before or before using the target AI model; or the first update manner is that the wireless communication apparatus 300 directly updates or uses the target AI model.

[0284] The second update manner is that the wireless communication apparatus 300 processes the target AI model through a third communication device before or before using the target AI model; or the second update manner is that the wireless communication apparatus 300 does not directly update or use the target AI model.

[0285] In some embodiments, the first updating manner has a lower latency than the second updating manner; and / or,

[0286] the first updating manner has a latency lower than or not higher than a first threshold; and / or,

[0287] the second updating manner has a latency higher than or not lower than a second threshold.

[0288] In some embodiments, the wireless communication apparatus 300 further comprises:

[0289] The sending module 303 is configured to send first information to the second communication device;

[0290] The first information comprises at least one of the following:

[0291] the update latency of the target AI model;

[0292] the timestamp at which the updating of the target AI model is completed;

[0293] the timestamp at which the target AI model can be used;

[0294] first indication information, wherein the first indication information indicates that the updating of the target AI model is completed, or the first indication information indicates that the target AI model can be used.

[0295] In some embodiments, the first information further comprises second indication information;

[0296] The second indication information indicates that the wireless communication apparatus 300 updates the target AI model using the first updating manner, or the second indication information indicates that the wireless communication apparatus 300 does not update the target AI model using the second updating manner, or the second indication information indicates that the wireless communication apparatus 300 updates the target AI model using the second updating manner, and the second indication information indicates that the wireless communication apparatus 300 does not update the target AI model using the first updating manner.

[0297] In some embodiments, the processing module 302 is specifically configured to:

[0298] update the target AI model using the first updating manner or the second updating manner according to the model parameters of the target AI model; or

[0299] update the target AI model using the first updating manner or the second updating manner according to the model structure of the target AI model; or

[0300] update the target AI model using the first update manner or the second update manner by default;

[0301] The model parameters of the target AI model include at least one of the following: a storage size of the target AI model, a computational complexity of the target AI model, a number of operations of the target AI model, a time required for transmission of model parameters of the target AI model, and a number of data packets required for transmission of model parameters of the target AI model.

[0302] The model structure of the target AI model includes at least one of the following: a number of layers of the target AI model, a number of neurons of each layer of the target AI model, a connection manner between each neuron of the target AI model, and an activation function of the target AI model.

[0303] In some embodiments, the processing module 302 is specifically configured to:

[0304] In a case where the model parameters of the target AI model are less than a third threshold value, or in a case where the model parameters of the target AI model are less than or equal to the third threshold value, the target AI model is updated using the first update manner; and / or,

[0305] In a case where the model parameters of the target AI model are greater than the third threshold value, or in a case where the model parameters of the target AI model are greater than or equal to the third threshold value, the target AI model is updated using the second update manner.

[0306] In some embodiments, the processing module 302 is specifically configured to:

[0307] In a case where the model structure of the target AI model belongs to a first AI model structure set, the target AI model is updated using the first update manner; and / or,

[0308] In a case where the model structure of the target AI model belongs to a second AI model structure set, the target AI model is updated using the second update manner.

[0309] In some embodiments, before the wireless communication apparatus 300 updates the target AI model using the first update manner or the second update manner, the receiving module 301 is further configured to receive second information or third information from the second communication device;

[0310] The second information is used to instruct the wireless communication apparatus 300 to update the target AI model using the first update manner or the second update manner.

[0311] The third information is used to indicate that the wireless communication apparatus 300 autonomously uses the first update manner or the second update manner to update the target AI model.

[0312] In some embodiments, the second information is determined based on an AI model update capability of the wireless communication apparatus 300; or the third information is determined based on the AI model update capability of the wireless communication apparatus 300.

[0313] In some embodiments, the processing module 302 is specifically configured to:

[0314] If the wireless communication apparatus 300 supports at least one of AI model transmission, AI model update, air interface-based AI model transmission, and air interface and third generation partnership project (3GPP) signaling-based AI model transmission, the target AI model is updated by default using the first update manner, or the target AI model is updated by default using the second update manner, or the target AI model is updated by the wireless communication apparatus 300 using the first update manner or the first update manner, or the target AI model is updated by the wireless communication apparatus 300 using the first update manner or the second update manner according to an indication of the second communication device; or,

[0315] If the wireless communication apparatus 300 supports the first update manner, the target AI model is updated using the first update manner, or the target AI model is updated by default using the first update manner, or the target AI model is updated by the wireless communication apparatus 300 using the first update manner or the first update manner, or the target AI model is updated by the wireless communication apparatus 300 using the first update manner or the second update manner according to an indication of the second communication device; or,

[0316] If the wireless communication apparatus 300 supports the first update manner and does not support the second update manner, the target AI model is updated using the first update manner; or,

[0317] If the wireless communication apparatus 300 supports the second update manner, the target AI model is updated using the second update manner, or the target AI model is updated by default using the second update manner, or the target AI model is updated by the wireless communication apparatus 300 using the first update manner or the first update manner, or the target AI model is updated by the wireless communication apparatus 300 using the first update manner or the second update manner according to an indication of the second communication device; or,

[0318] If the wireless communication device 300 supports the second updating manner and does not support the first updating manner, the target AI model is updated using the second updating manner; or

[0319] If the wireless communication device 300 supports the first updating manner and the second updating manner, the target AI model is updated using the first updating manner by default, or the target AI model is updated using the second updating manner by default, or the target AI model is updated using the first updating manner or the second updating manner by itself, or the target AI model is updated using the first updating manner or the second updating manner according to an indication of the second communication device.

[0320] In some embodiments, the processing module 302 is specifically configured to:

[0321] If the second communication device indicates that the target AI model is updated using the first updating manner or the second updating manner, the target AI model is updated using the updating manner indicated by the second communication device, and the wireless communication device 300 does not feed back the used updating manner to the second communication device; or,

[0322] If the second communication device indicates that the target AI model is updated using the first updating manner or the second updating manner, the target AI model is updated using the first updating manner or the second updating manner by itself, and the wireless communication device 300 feeds back the used updating manner to the second communication device; or,

[0323] If the second communication device indicates that the wireless communication device 300 updates the target AI model using the first updating manner or the second updating manner by itself, the target AI model is updated using the first updating manner or the second updating manner by itself, and the wireless communication device 300 feeds back the used updating manner to the second communication device; or,

[0324] The target AI model is updated using the first updating manner or the second updating manner based on a protocol agreement, and the wireless communication device 300 does not feed back the used updating manner to the second communication device; or,

[0325] If the protocol agrees that the target AI model is updated using the first updating manner or the second updating manner, the target AI model is updated using the first updating manner or the second updating manner by itself, and the wireless communication device 300 feeds back the used updating manner to the second communication device; or,

[0326] The wireless communication apparatus 300 uses the first update manner or the second update manner to update the target AI model, and feeds back the used update manner to the second communication device.

[0327] In some embodiments, the sending module 303 is further configured to send capability information to the second communication device.

[0328] The capability information comprises at least one of the following:

[0329] The wireless communication apparatus 300 supports at least one of the following: AI model transmission, AI model update, air interface-based AI model transmission, air interface and 3GPP signaling-based AI model transmission.

[0330] The wireless communication apparatus 300 supports the first update manner.

[0331] The wireless communication apparatus 300 supports the first update manner and does not support the second update manner.

[0332] The wireless communication apparatus 300 supports the second update manner.

[0333] The wireless communication apparatus 300 supports the second update manner and does not support the first update manner.

[0334] The wireless communication apparatus 300 supports the first update manner and the second update manner.

[0335] In some embodiments, the target AI model comprises at least one of the following:

[0336] The AI model used by the wireless communication apparatus 300;

[0337] The AI model used by the second communication device;

[0338] The reference AI model of the AI model used by the wireless communication apparatus 300;

[0339] The reference AI model of the AI model used by the second communication device;

[0340] The AI model used by the wireless communication apparatus 300 in testing;

[0341] The AI model used by the second communication device in testing;

[0342] The AI model used by the testing device in testing;

[0343] The reference AI model of the AI model used by the wireless communication apparatus 300 in testing;

[0344] a reference AI model of an AI model used by the second communication device in the test;

[0345] a reference AI model of an AI model used by the test device in the test;

[0346] the wireless communication apparatus 300 is configured to match an AI model of an AI model used in the test;

[0347] the second communication device is configured to match an AI model of an AI model used in the test;

[0348] the test device is configured to match an AI model of an AI model used in the test.

[0349] Referring to FIG. 6, when the wireless communication apparatus is a second communication device or a component in the second communication device, the wireless communication apparatus 400 includes:

[0350] The sending module 401 is configured to send, to a first communication device, related information of a target artificial intelligence (AI) model; wherein the related information of the target AI model includes at least one of the following: model parameters of the target AI model, a model structure of the target AI model.

[0351] The receiving module 402 is configured to receive first information from the first communication device.

[0352] The first information includes at least one of the following:

[0353] an update time delay of the target AI model;

[0354] a timestamp at which the target AI model is updated;

[0355] a timestamp at which the target AI model can be used;

[0356] first indication information, wherein the first indication information is used to indicate that the target AI model has been updated, or the first indication information is used to indicate that the target AI model can be used;

[0357] The update manner of the target AI model is a first update manner or a second update manner.

[0358] The first update manner is that the first communication device processes the target AI model before or after the target AI model is updated or used; or the first update manner is that the first communication device directly updates or uses the target AI model.

[0359] The second updating manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used; or the second updating manner is that the first communication device does not directly update or use the target AI model.

[0360] In some embodiments, the time delay of the first updating manner is lower than the time delay of the second updating manner; and / or,

[0361] The time delay of the first updating manner is lower than or not higher than a first threshold; and / or,

[0362] The time delay of the second updating manner is higher than or not lower than a second threshold.

[0363] In some embodiments, the first information further comprises second indication information.

[0364] The second indication information is used to indicate that the first communication device updates the target AI model using the first updating manner, or the second indication information is used to indicate that the first communication device does not update the target AI model using the second updating manner, or the second indication information is used to indicate that the first communication device updates the target AI model using the second updating manner, and the second indication information is used to indicate that the first communication device does not update the target AI model using the first updating manner.

[0365] In some embodiments, the updating manner of the target AI model is determined based on model parameters of the target AI model; or,

[0366] The updating manner of the target AI model is determined based on a model structure of the target AI model; or,

[0367] The updating manner of the target AI model is the default updating manner used by the first communication device;

[0368] The model parameters of the target AI model comprise at least one of the following: a storage size of the target AI model, an operation complexity of the target AI model, an operation frequency of the target AI model, a time required for transmission of model parameters of the target AI model, and a number of data packets required for transmission of model parameters of the target AI model.

[0369] The model structure of the target AI model comprises at least one of the following: a number of layers of the target AI model, a number of neurons of each layer of the target AI model, a connection mode between each neuron of the target AI model, and an activation function of the target AI model.

[0370] In some embodiments, the updating manner of the target AI model is determined based on model parameters of the target AI model, including:

[0371] In a case where the model parameters of the target AI model are less than a third threshold, or in a case where the model parameters of the target AI model are less than or equal to the third threshold, the updating manner of the target AI model is the first updating manner.

[0372] and / or,

[0373] In a case where the model parameters of the target AI model are greater than the third threshold, or in a case where the model parameters of the target AI model are greater than or equal to the third threshold, the updating manner of the target AI model is the second updating manner.

[0374] In some embodiments, the updating manner of the target AI model is determined based on a model structure of the target AI model, including:

[0375] In a case where the model structure of the target AI model belongs to a first AI model structure set, the updating manner of the target AI model is the first updating manner; and / or,

[0376] In a case where the model structure of the target AI model belongs to a second AI model structure set, the updating manner of the target AI model is the second updating manner.

[0377] In some embodiments, before the wireless communication device 400 receives the first information from the first communication device, the sending module 401 is further configured to send second information or third information to the first communication device.

[0378] The second information is used to instruct the first communication device to update the target AI model using the first updating manner or the second updating manner.

[0379] The third information is used to instruct the first communication device to update the target AI model using the first updating manner or the second updating manner.

[0380] In some embodiments, the second information is determined based on an AI model updating capability of the first communication device; or the third information is determined based on the AI model updating capability of the first communication device.

[0381] In some embodiments, if the first communication device supports at least one of AI model transmission, AI model update, AI model transmission based on air interface, AI model transmission based on air interface and third generation partnership project (3GPP) signaling, the update mode of the target AI model is the first update mode used by the first communication device by default, or the update mode of the target AI model is the second update mode used by the first communication device by default, or the update mode of the target AI model is the first update mode or the first update mode used by the first communication device by itself, or the update mode of the target AI model is the first update mode or the second update mode used by the first communication device according to the indication of the wireless communication apparatus 400; or,

[0382] If the first communication device supports the first update mode, the update mode of the target AI model is the first update mode, or the update mode of the target AI model is the first update mode used by the first communication device by default, or the update mode of the target AI model is the first update mode or the first update mode used by the first communication device by itself, or the update mode of the target AI model is the first update mode or the second update mode used by the first communication device according to the indication of the wireless communication apparatus 400; or,

[0383] If the first communication device supports the first update mode and does not support the second update mode, the update mode of the target AI model is the first update mode; or,

[0384] If the first communication device supports the second update mode, the update mode of the target AI model is the second update mode, or the update mode of the target AI model is the second update mode used by the first communication device by default, or the update mode of the target AI model is the first update mode or the first update mode used by the first communication device by itself, or the update mode of the target AI model is the first update mode or the second update mode used by the first communication device according to the indication of the wireless communication apparatus 400; or,

[0385] If the first communication device supports the second update mode and does not support the first update mode, the update mode of the target AI model is the second update mode; or,

[0386] If the first communication device supports the first update manner and the second update manner, the update manner of the target AI model is the first update manner used by the first communication device by default, or the update manner of the target AI model is the second update manner used by the first communication device by default, or the update manner of the target AI model is the first update manner or the first update manner used by the first communication device by itself, or the update manner of the target AI model is the first update manner or the second update manner used by the first communication device according to the indication of the wireless communication apparatus 400.

[0387] In some embodiments, if the wireless communication apparatus 400 indicates to update the target AI model using the first update manner or the second update manner, the update manner of the target AI model is the update manner indicated by the wireless communication apparatus 400, and the first communication device does not feed back the used update manner to the wireless communication apparatus 400; or,

[0388] If the wireless communication apparatus 400 indicates to update the target AI model using the first update manner or the second update manner, the update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the wireless communication apparatus 400; or,

[0389] If the wireless communication apparatus 400 indicates that the first communication device uses the first update manner or the second update manner to update the target AI model by itself, the update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the wireless communication apparatus 400; or,

[0390] The update manner of the target AI model is the update manner used by the first communication device based on a protocol agreement, and the first communication device does not feed back the used update manner to the wireless communication apparatus 400; or,

[0391] If the protocol agrees to update the target AI model using the first update manner or the second update manner, the update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the wireless communication apparatus 400; or,

[0392] The update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the wireless communication apparatus 400.

[0393] In some embodiments, the receiving module 402 is further configured to receive capability information from the first communication device;

[0394] The capability information comprises at least one of:

[0395] The first communication device supports at least one of: AI model transmission, AI model update, air interface based AI model transmission, air interface and 3GPP signaling based AI model transmission;

[0396] The first communication device supports the first update mode;

[0397] The first communication device supports the first update mode and does not support the second update mode;

[0398] The first communication device supports the second update mode;

[0399] The first communication device supports the second update mode and does not support the first update mode;

[0400] The first communication device supports the first update mode and the second update mode.

[0401] In some embodiments, the target AI model comprises at least one of:

[0402] An AI model used by the first communication device;

[0403] An AI model used by the wireless communication apparatus 400;

[0404] A reference AI model of an AI model used by the first communication device;

[0405] A reference AI model of an AI model used by the wireless communication apparatus 400;

[0406] An AI model used by the first communication device in testing;

[0407] An AI model used by the wireless communication apparatus 400 in testing;

[0408] An AI model used by testing equipment in testing;

[0409] A reference AI model of an AI model used by the first communication device in testing;

[0410] A reference AI model of an AI model used by the wireless communication apparatus 400 in testing;

[0411] A reference AI model of an AI model used by testing equipment in testing;

[0412] The first communication device is configured to match the AI model used in the test.

[0413] The wireless communication device 400 is configured to match the AI model used in the test.

[0414] The test device is configured to match the AI model used in the test.

[0415] Therefore, in the embodiments of the present application, the first communication device updates the target AI model using a first update manner or a second update manner; the first update manner is that the first communication device processes the target AI model before or before using the target AI model; or the first update manner is that the first communication device directly updates or uses the target AI model; the second update manner is that the first communication device processes the target AI model through a third communication device before or before using the target AI model; or the second update manner is that the first communication device does not directly update or use the target AI model. Thus, the target AI model can be updated using a suitable update manner, and the target AI model can be prevented from being disabled due to the lack of timely updates.

[0416] The wireless communication device provided in the embodiments of the present application can implement each process implemented by the method embodiment of FIG. 4 and achieve the same technical effects. To avoid repetition, details are not described herein.

[0417] As shown in FIG. 7, the embodiments of the present application further provide a communication device 500, which includes a processor 501 and a memory 502, and the memory 502 stores programs or instructions executable on the processor 501.

[0418] For example, when the communication device 500 is a first communication device, the programs or instructions are executed by the processor 501 to implement each step performed by the first communication device in the wireless communication method embodiments, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0419] For another example, when the communication device 500 is a second communication device, the programs or instructions are executed by the processor 501 to implement each step performed by the second communication device in the wireless communication method embodiments, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0420] The embodiment of the present application further provides a terminal comprising a processor and a communication interface, the communication interface being coupled with the processor, and the processor being configured to run programs or instructions to implement the steps in the method embodiment shown in FIG. 4. The terminal embodiment corresponds to the first communication device or the second communication device side method embodiment, and each implementation process and implementation manner of the method embodiment can be applied to the terminal embodiment and achieve the same technical effects. The terminal can be the wireless communication device 300 shown in FIG. 5, or the terminal can be the wireless communication device 400 shown in FIG. 6. Specifically, FIG. 8 is a schematic diagram of the hardware structure of a terminal for implementing the embodiment of the present application.

[0421] The terminal 600 comprises, but is not limited to, at least part of the components such as a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, and a processor 610.

[0422] Those skilled in the art can understand that the terminal 600 can further comprise a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected with the processor 610 through a power management system, so as to realize the functions of power management, such as charging, discharging, and power consumption management, through the power management system. The terminal structure shown in FIG. 8 does not constitute a limitation on the terminal, and the terminal can comprise more or fewer components than those shown, or some components can be combined, or different components can be arranged, which will not be described here.

[0423] It should be understood that in the embodiment of the present application, the input unit 604 can comprise a graphic processor 6041 and a microphone 6042, and the graphic processor 6041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 606 can comprise a display panel 6061, which can be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 607 comprises at least one of a touch panel 6071 and other input devices 6072. The touch panel 6071 is also called a touch screen. The touch panel 6071 can comprise a touch detection device and a touch controller. The other input devices 6072 can comprise, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), a trackball, a mouse, a joystick, etc., which will not be described here.

[0424] In the embodiment of the present application, the radio frequency unit 601 can transmit downlink data from a network side device to the processor 610 for processing, and can send uplink data to the network side device. Generally, the radio frequency unit 601 comprises, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0425] The memory 609 can be used to store software programs or instructions and various data. The memory 609 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 609 can include a volatile memory or a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 609 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0426] The processor 610 can include one or more processing units; optionally, the processor 610 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 610.

[0427] In some embodiments, the terminal is a first communication device;

[0428] The radio frequency unit 601 is configured to receive, from a second communication device, information related to a target artificial intelligence (AI) model; wherein the information related to the target AI model includes at least one of the following: model parameters of the target AI model, a model structure of the target AI model;

[0429] The processor 610 is configured to update the target AI model using a first update manner or a second update manner.

[0430] The first update manner is that the first communication device processes the target AI model before the target AI model is updated or used, or the first update manner is that the first communication device directly updates or uses the target AI model.

[0431] The second update manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used, or the second update manner is that the first communication device does not directly update or use the target AI model.

[0432] In some embodiments, the terminal is a second communication device.

[0433] The radio frequency unit 601 is configured to send, to a first communication device, related information of a target artificial intelligence (AI) model. The related information of the target AI model includes at least one of the following: model parameters of the target AI model, and a model structure of the target AI model.

[0434] The radio frequency unit 601 is further configured to receive, from the first communication device, first information.

[0435] The first information includes at least one of the following:

[0436] An update time delay of the target AI model;

[0437] A timestamp at which the target AI model is updated to be completed;

[0438] A timestamp at which the target AI model can be used;

[0439] First indication information, where the first indication information is used to indicate that the target AI model has been updated, or the first indication information is used to indicate that the target AI model can be used.

[0440] The update manner of the target AI model is a first update manner or a second update manner.

[0441] The first update manner is that the first communication device processes the target AI model before the target AI model is updated or used, or the first update manner is that the first communication device directly updates or uses the target AI model.

[0442] The second updating manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used, or the second updating manner is that the first communication device does not directly update or use the target AI model.

[0443] Therefore, in the embodiments of the present application, the first communication device updates the target AI model using the first updating manner or the second updating manner. The first updating manner is that the first communication device processes the target AI model before the target AI model is updated or used, or the first updating manner is that the first communication device directly updates or uses the target AI model. The second updating manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used, or the second updating manner is that the first communication device does not directly update or use the target AI model. Thus, the target AI model can be updated using a suitable updating manner, and the target AI model can be prevented from being disabled due to not being updated in time.

[0444] It can be understood that the implementation processes of the implementation manners mentioned in the embodiments can refer to the related descriptions of the method embodiments and achieve the same or corresponding technical effects. To avoid repetition, they will not be described here again.

[0445] The embodiments of the present application also provide a network side device, which includes a processor and a communication interface. The communication interface is coupled with the processor. The processor is used to run programs or instructions to implement the steps of the method embodiments shown in FIG. 4. The network side device embodiments correspond to the method embodiments performed by the first communication device or the second communication device. The implementation processes and implementation manners of the above method embodiments can be applied to the network side device embodiments and achieve the same technical effects.

[0446] Specifically, the embodiments of the present application also provide a network side device. The network side device can be the wireless communication apparatus 300 shown in FIG. 5, or the network side device can be the wireless communication apparatus 400 shown in FIG. 6. As shown in FIG. 9, the network side device 700 includes an antenna 71, a radio frequency device 72, a baseband device 73, a processor 74 and a memory 75. The antenna 71 is connected with the radio frequency device 72. In the uplink direction, the radio frequency device 72 receives information through the antenna 71 and sends the received information to the baseband device 73 for processing. In the downlink direction, the baseband device 73 processes the information to be sent and sends it to the radio frequency device 72. The radio frequency device 72 processes the received information and sends it out through the antenna 71.

[0447] The method performed by the first communication device or the second communication device in the above embodiments can be implemented in the baseband device 73, which includes a baseband processor.

[0448] The baseband device 73 can include at least one baseband board on which a plurality of chips are disposed, as shown in FIG. 9. One of the chips is, for example, a baseband processor, which is connected with the memory 75 through a bus interface to invoke programs in the memory 75 and perform operations performed by the first communication device or the second communication device in the above method embodiments.

[0449] The network-side device can further include a network interface 76, which is, for example, a common public radio interface (CPRI).

[0450] Specifically, the network-side device 700 of the embodiments of the present application further includes instructions or programs stored in the memory 75 and executable on the processor 74, which invokes the instructions or programs in the memory 75 to perform the method performed by the modules shown in FIG. 5 or FIG. 6 and achieve the same technical effects. To avoid repetition, details are not described herein.

[0451] Specifically, the embodiments of the present application further provide a network-side device. As shown in FIG. 10, the network-side device 800 includes a processor 801, a network interface 802 and a memory 803. The network-side device can be the wireless communication device 300 shown in FIG. 5, or the network-side device can be the wireless communication device 400 shown in FIG. 6. The network interface 802 is, for example, a common public radio interface (CPRI).

[0452] Specifically, the network-side device 800 of the embodiments of the present application further includes instructions or programs stored in the memory 803 and executable on the processor 801, which invokes the instructions or programs in the memory 803 to perform the method performed by the modules shown in FIG. 5 or FIG. 6 and achieve the same technical effects. To avoid repetition, details are not described herein.

[0453] The embodiments of the present application further provide a readable storage medium, which stores programs or instructions. When the programs or instructions are executed by a processor, each process of the above wireless communication method embodiments is implemented, and the same technical effects are achieved. To avoid repetition, details are not described herein.

[0454] The processor is the processor in the first communication device or the second communication device in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[0455] The embodiment of the present application further provides a chip, which comprises a processor and a communication interface, the communication interface is coupled with the processor, the processor is used for running programs or instructions, realizes various processes of the wireless communication method embodiment, and can achieve the same technical effects. To avoid repetition, details are not repeated here.

[0456] It should be understood that the chip mentioned in the embodiment of the present application can also be referred to as a system chip, a system chip, a chip system or a system on chip, etc.

[0457] The embodiment of the present application further provides a computer program / program product stored in a storage medium, which is executed by at least one processor to realize various processes of the wireless communication method embodiment and achieve the same technical effects. To avoid repetition, details are not repeated here.

[0458] The embodiment of the present application further provides a wireless communication system, which comprises a first communication device and a second communication device. The first communication device can be used to execute the steps performed by the first communication device in the wireless communication method described above. The second communication device can be used to execute the steps performed by the second communication device in the wireless communication method described above.

[0459] It should be noted that in this paper, the term "including", "containing" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the present application is not limited to the order of functions shown or discussed, but also includes functions performed in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method can be performed in a different order from the described order, and various steps can also be added, omitted or combined. In addition, the features described with reference to some examples can be combined in other examples.

[0460] From the above description of the embodiments, those skilled in the art can clearly understand that the above embodiment method can be realized by means of computer software product and general hardware platform, of course, it can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.), which includes a plurality of instructions for making terminal or network side equipment execute the method described in various embodiments of the present application.

[0461] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms of embodiments under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these embodiments all belong to the protection of the present application.

Claims

1. A method of wireless communication, comprising: receiving, by a first communication device, related information of a target artificial intelligence (AI) model from a second communication device, wherein the related information of the target AI model comprises at least one of: model parameters of the target AI model, or a model structure of the target AI model; updating, by the first communication device, the target AI model using a first update manner or a second update manner; wherein the first update manner is that the first communication device processes the target AI model before the target AI model is updated or used; or the first update manner is that the first communication device directly updates or uses the target AI model; wherein the second update manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used; or the second update manner is that the first communication device does not directly update or use the target AI model. 2.The method of claim 1, wherein: a latency of the first update manner is lower than a latency of the second update manner; and / or the latency of the first update manner is lower than or not higher than a first threshold; and / or the latency of the second update manner is higher than or not lower than a second threshold. The method further comprises: sending, by the first communication device, first information to the second communication device; wherein the first information comprises at least one of: an update latency of the target AI model; a time stamp at which the target AI model is updated; a time stamp at which the target AI model can be used; or first indication information, wherein the first indication information indicates that the target AI model has been updated, or the first indication information indicates that the target AI model can be used. 4.The method of claim 3, wherein: the first information further comprises second indication information; wherein the second indication information indicates that the first communication device updates the target AI model using the first update manner, or the second indication information indicates that the first communication device does not update the target AI model using the second update manner, or the second indication information indicates that the first communication device updates the target AI model using the second update manner, and the second indication information indicates that the first communication device does not update the target AI model using the first update manner. The first communication device updates the target AI model using the first update manner or the second update manner comprises: the first communication device updates the target AI model using the first update manner or the second update manner according to the model parameters of the target AI model; or the first communication device updates the target AI model using the first update manner or the second update manner according to the model structure of the target AI model; or the first communication device updates the target AI model using the first update manner or the second update manner by default. ​ ​ ​ ​ 3. The method of claim 1 or 2, wherein, ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 5. The method of any one of claims 1 to 4, wherein, ​ ​ ​ ​ The model parameters of the target AI model include at least one of a storage size of the target AI model, a computational complexity of the target AI model, a number of operations of the target AI model, a time required for transmission of model parameters of the target AI model, and a number of data packets required for transmission of model parameters of the target AI model. The model structure of the target AI model includes at least one of a number of layers of the target AI model, a number of neurons of each layer of the target AI model, a connection mode between each neuron of the target AI model, and an activation function of the target AI model.

6. The method of claim 5, wherein, The first communication device updates the target AI model using the first update mode or the second update mode according to the model parameters of the target AI model, including: In a case where the model parameters of the target AI model are less than a third threshold, or in a case where the model parameters of the target AI model are less than or equal to the third threshold, the first communication device updates the target AI model using the first update mode; and / or, In a case where the model parameters of the target AI model are greater than the third threshold, or in a case where the model parameters of the target AI model are greater than or equal to the third threshold, the first communication device updates the target AI model using the second update mode.

7. The method of claim 5, wherein, The first communication device updates the target AI model using the first update mode or the second update mode according to the model structure of the target AI model, including: In a case where the model structure of the target AI model belongs to a first AI model structure set, the first communication device updates the target AI model using the first update mode; and / or, In a case where the model structure of the target AI model belongs to a second AI model structure set, the first communication device updates the target AI model using the second update mode.

8. The method of any one of claims 1 to 4, wherein, Before the first communication device updates the target AI model using the first update mode or the second update mode, the method further includes: The first communication device receives second information or third information from the second communication device; The second information is used to instruct the first communication device to update the target AI model using the first update mode or the second update mode; The third information is used to instruct the first communication device to autonomously update the target AI model using the first update mode or the second update mode.

9. The method of claim 8, wherein, The second information is determined based on an AI model update capability of the first communication device; or The third information is determined based on the AI model update capability of the first communication device.

10. The method of any one of claims 1 to 4, wherein, The first communication device updates the target AI model using a first update mode or a second update mode, including: If the first communication device supports at least one of AI model transmission, AI model update, AI model transmission based on air interface, AI model transmission based on air interface and 3rd Generation Partnership Project (3GPP) signaling, the first communication device updates the target AI model using the first update mode by default, or the first communication device updates the target AI model using the second update mode by default, or the first communication device updates the target AI model using the first update mode or the first update mode by itself, or the first communication device updates the target AI model using the first update mode or the second update mode according to an indication of the second communication device; or If the first communication device supports the first update mode, the first communication device updates the target AI model using the first update mode, or the first communication device updates the target AI model using the first update mode by default, or the first communication device updates the target AI model using the first update mode or the first update mode by itself, or the first communication device updates the target AI model using the first update mode or the second update mode according to an indication of the second communication device; or If the first communication device supports the first update mode and does not support the second update mode, the first communication device updates the target AI model using the first update mode; or If the first communication device supports the second update mode, the first communication device updates the target AI model using the second update mode, or the first communication device updates the target AI model using the second update mode by default, or the first communication device updates the target AI model using the first update mode or the first update mode by itself, or the first communication device updates the target AI model using the first update mode or the second update mode according to an indication of the second communication device; or If the first communication device supports the second update mode and does not support the first update mode, the first communication device updates the target AI model using the second update mode; or If the first communication device supports the first update mode and the second update mode, the first communication device updates the target AI model using the first update mode by default, or the first communication device updates the target AI model using the second update mode by default, or the first communication device updates the target AI model using the first update mode or the first update mode by itself, or the first communication device updates the target AI model using the first update mode or the second update mode according to an indication of the second communication device.

11. The method of any one of claims 1 to 3, wherein, The first communication device updates the target AI model using a first update manner or a second update manner, including: If the second communication device indicates to update the target AI model using the first update manner or the second update manner, the first communication device updates the target AI model using the update manner indicated by the second communication device, and the first communication device does not feed back the used update manner to the second communication device; or, If the second communication device indicates to update the target AI model using the first update manner or the second update manner, the first communication device updates the target AI model using the first update manner or the second update manner by itself, and the first communication device feeds back the used update manner to the second communication device; or, If the second communication device indicates that the first communication device updates the target AI model using the first update manner or the second update manner by itself, the first communication device updates the target AI model using the first update manner or the second update manner by itself, and the first communication device feeds back the used update manner to the second communication device; or, The first communication device updates the target AI model using the first update manner or the second update manner based on a protocol agreement, and the first communication device does not feed back the used update manner to the second communication device; or, If the protocol agrees to update the target AI model using the first update manner or the second update manner, the first communication device updates the target AI model using the first update manner or the second update manner by itself, and the first communication device feeds back the used update manner to the second communication device; or, The first communication device updates the target AI model using the first update manner or the second update manner by itself, and the first communication device feeds back the used update manner to the second communication device.

12. The method of any one of claims 1 to 11, wherein, The method further includes: The first communication device sends capability information to the second communication device; The capability information includes at least one of the following: The first communication device supports at least one of the following: AI model transmission, AI model update, AI model transmission based on air interface, AI model transmission based on air interface and 3GPP signaling; The first communication device supports the first update manner; The first communication device supports the first update manner and does not support the second update manner; The first communication device supports the second update manner; The first communication device supports the second update manner and does not support the first update manner; The first communication device supports the first update manner and the second update manner.

13. The method of any one of claims 1-12, wherein: The target AI model includes at least one of the following: An AI model used by the first communication device; An AI model used by the second communication device; a reference AI model of an AI model used by the first communication device; a reference AI model of an AI model used by the second communication device; an AI model used by the first communication device in the test; an AI model used by the second communication device in the test; an AI model used by the test device in the test; a reference AI model of an AI model used by the first communication device in the test; a reference AI model of an AI model used by the second communication device in the test; a reference AI model of an AI model used by the test device in the test; an AI model used by the first communication device to match the AI model used in the test; an AI model used by the second communication device to match the AI model used in the test; an AI model used by the test device to match the AI model used in the test.

14. A wireless communication method comprising: sending, by a second communication device, related information of a target artificial intelligence (AI) model to a first communication device; wherein the related information of the target AI model comprises at least one of: model parameters of the target AI model, a model structure of the target AI model; receiving, by the second communication device, first information from the first communication device; wherein the first information comprises at least one of: an update time delay of the target AI model; a time stamp at which the target AI model is updated; a time stamp at which the target AI model can be used; first indication information, wherein the first indication information is used to indicate that the target AI model has been updated, or the first indication information is used to indicate that the target AI model can be used; wherein an update manner of the target AI model is a first update manner or a second update manner; wherein the first update manner is that the first communication device processes the target AI model before the target AI model is updated or used, or the first update manner is that the first communication device directly updates or uses the target AI model; wherein the second update manner is that the first communication device processes the target AI model through a third communication device before the target AI model is updated or used, or the second update manner is that the first communication device does not directly update or use the target AI model.

15. The method of claim 14, wherein a time delay of the first update manner is lower than a time delay of the second update manner; and / or, the time delay of the first update manner is lower than or not higher than a first threshold; and / or, the time delay of the second update manner is higher than or not lower than a second threshold.

16. The method of claim 14 or 15, wherein the first information further comprises second indication information; The second indication information is used to indicate that the first communication device updates the target AI model using the first update manner, or the second indication information is used to indicate that the first communication device does not update the target AI model using the second update manner, or the second indication information is used to indicate that the first communication device updates the target AI model using the second update manner, and the second indication information is used to indicate that the first communication device does not update the target AI model using the first update manner.

17. The method of any one of claims 14-16, wherein The update manner of the target AI model is determined based on model parameters of the target AI model; or The update manner of the target AI model is determined based on a model structure of the target AI model; or The update manner of the target AI model is a default update manner used by the first communication device; The model parameters of the target AI model include at least one of the following: a storage size of the target AI model, a computational complexity of the target AI model, a number of operations of the target AI model, a time required for transmission of model parameters of the target AI model, and a number of data packets required for transmission of model parameters of the target AI model. The model structure of the target AI model includes at least one of the following: a number of layers of the target AI model, a number of neurons of each layer of the target AI model, a connection manner between each neuron of the target AI model, and an activation function of the target AI model.

18. The method of claim 17, wherein The update manner of the target AI model is determined based on model parameters of the target AI model, including: In a case where the model parameters of the target AI model are less than a third threshold value, or in a case where the model parameters of the target AI model are less than or equal to the third threshold value, the update manner of the target AI model is the first update manner; and / or In a case where the model parameters of the target AI model are greater than the third threshold value, or in a case where the model parameters of the target AI model are greater than or equal to the third threshold value, the update manner of the target AI model is the second update manner.

19. The method of claim 17, wherein The update manner of the target AI model is determined based on a model structure of the target AI model, including: In a case where the model structure of the target AI model belongs to a first AI model structure set, the update manner of the target AI model is the first update manner; and / or In a case where the model structure of the target AI model belongs to a second AI model structure set, the update manner of the target AI model is the second update manner.

20. The method of any one of claims 14-16, wherein Before the second communication device receives the first information from the first communication device, the method further includes: The second communication device sends second information or third information to the first communication device; ​ The second information is used to indicate that the first communication device uses the first update manner or the second update manner to update the target AI model. The third information is used to indicate that the first communication device autonomously uses the first update manner or the second update manner to update the target AI model.

21. The method of claim 20, wherein, The second information is determined based on an AI model update capability of the first communication device; or The third information is determined based on the AI model update capability of the first communication device.

22. The method of any one of claims 14-16, wherein, if the first communication device supports at least one of AI model transmission, AI model update, AI model transmission based on air interface, AI model transmission based on air interface and third generation partnership project (3GPP) signaling, the update manner of the target AI model is the first update manner used by the first communication device by default, or the update manner of the target AI model is the second update manner used by the first communication device by default, or the update manner of the target AI model is the first update manner used by the first communication device autonomously, or the update manner of the target AI model is the first update manner or the second update manner used by the first communication device according to an indication of the second communication device; or if the first communication device supports the first update manner, the update manner of the target AI model is the first update manner, or the update manner of the target AI model is the first update manner used by the first communication device by default, or the update manner of the target AI model is the first update manner used by the first communication device autonomously, or the update manner of the target AI model is the first update manner or the second update manner used by the first communication device according to the indication of the second communication device; or if the first communication device supports the first update manner and does not support the second update manner, the update manner of the target AI model is the first update manner; or if the first communication device supports the second update manner, the update manner of the target AI model is the second update manner, or the update manner of the target AI model is the second update manner used by the first communication device by default, or the update manner of the target AI model is the first update manner or the first update manner used by the first communication device autonomously, or the update manner of the target AI model is the first update manner or the second update manner used by the first communication device according to the indication of the second communication device; or if the first communication device supports the second update manner and does not support the first update manner, the update manner of the target AI model is the second update manner; or if the first communication device supports the second update manner and does not support the first update manner, the update manner of the target AI model is the second update manner; or If the first communication device supports the first update manner and the second update manner, the update manner of the target AI model is the first update manner used by the first communication device by default, or the update manner of the target AI model is the second update manner used by the first communication device by default, or the update manner of the target AI model is the first update manner or the first update manner used by the first communication device by itself, or the update manner of the target AI model is the first update manner or the second update manner used by the first communication device according to the indication of the second communication device.

23. The method of claim 14 or 15, wherein, If the second communication device indicates to update the target AI model using the first update manner or the second update manner, the update manner of the target AI model is the update manner indicated by the second communication device, and the first communication device does not feed back the used update manner to the second communication device; or, If the second communication device indicates to update the target AI model using the first update manner or the second update manner, the update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the second communication device; or, If the second communication device indicates that the first communication device uses the first update manner or the second update manner to update the target AI model by itself, the update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the second communication device; or, The update manner of the target AI model is the update manner used by the first communication device based on a protocol agreement, and the first communication device does not feed back the used update manner to the second communication device; or, If the protocol agrees to update the target AI model using the first update manner or the second update manner, the update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the second communication device; or, The update manner of the target AI model is the update manner used by the first communication device by itself, and the first communication device feeds back the used update manner to the second communication device.

24. The method of any one of claims 14 to 23, wherein, The method further comprises: The second communication device receives capability information from the first communication device; The capability information comprises at least one of the following: The first communication device supports at least one of the following: AI model transmission, AI model update, AI model transmission based on air interface, AI model transmission based on air interface and 3GPP signaling; The first communication device supports the first update manner; The first communication device supports the first update manner and does not support the second update manner; The first communication device supports the second update manner; The first communication device supports the second update mode and does not support the first update mode; The first communication device supports the first update mode and the second update mode.

25. The method of any one of claims 14-24, wherein, The target AI model comprises at least one of: An AI model used by the first communication device; An AI model used by the second communication device; A reference AI model of the AI model used by the first communication device; A reference AI model of the AI model used by the second communication device; An AI model used by the first communication device in testing; An AI model used by the second communication device in testing; An AI model used by a test device in testing; A reference AI model of the AI model used by the first communication device in testing; A reference AI model of the AI model used by the second communication device in testing; A reference AI model of the AI model used by a test device in testing; An AI model used by the first communication device to match the AI model used in testing; An AI model used by the second communication device to match the AI model used in testing; An AI model used by a test device to match the AI model used in testing.

26. A wireless communication apparatus comprising: a receiving module configured to receive, from a second communication device, related information of a target artificial intelligence (AI) model; wherein the related information of the target AI model comprises at least one of: model parameters of the target AI model, a model structure of the target AI model; a processing module configured to update the target AI model using a first update mode or a second update mode; wherein the first update mode is that the wireless communication apparatus processes the target AI model before the target AI model is updated or used; or the first update mode is that the wireless communication apparatus directly updates or uses the target AI model; wherein the second update mode is that the wireless communication apparatus processes the target AI model through a third communication device before the target AI model is updated or used; or the second update mode is that the wireless communication apparatus does not directly update or use the target AI model.

27. The apparatus of claim 26, wherein, The wireless communication apparatus further comprises: a sending module configured to send, to the second communication device, first information; wherein the first information comprises at least one of: an update latency of the target AI model; a time stamp at which the target AI model is updated to be completed; a time stamp at which the target AI model can be used; first indication information, wherein the first indication information is used to indicate that the target AI model has been updated, or the first indication information is used to indicate that the target AI model can be used.

28. The apparatus of claim 27, wherein, the first information further comprises second indication information; The second indication information is used for indicating that the wireless communication device updates the target AI model using the first update manner, or the second indication information is used for indicating that the wireless communication device does not update the target AI model using the second update manner, or the second indication information is used for indicating that the wireless communication device updates the target AI model using the second update manner, and the second indication information is used for indicating that the wireless communication device does not update the target AI model using the first update manner.

29. The apparatus of any one of claims 26-28, wherein, The processing module is specifically configured to: update the target AI model using the first update manner or the second update manner according to the model parameters of the target AI model; or update the target AI model using the first update manner or the second update manner according to the model structure of the target AI model; or update the target AI model using the first update manner or the second update manner by default; The model parameters of the target AI model include at least one of the following: a storage size of the target AI model, a computational complexity of the target AI model, a number of operations of the target AI model, a time required for transmission of model parameters of the target AI model, and a number of data packets required for transmission of model parameters of the target AI model. The model structure of the target AI model includes at least one of the following: a number of layers of the target AI model, a number of neurons of each layer of the target AI model, a connection mode between each neuron of the target AI model, and an activation function of the target AI model.

30. The apparatus of claim 29, wherein The processing module is specifically configured to: update the target AI model using the first update manner in a case where the model parameters of the target AI model are less than a third threshold value, or in a case where the model parameters of the target AI model are less than or equal to a third threshold value; and / or update the target AI model using the second update manner in a case where the model parameters of the target AI model are greater than a third threshold value, or in a case where the model parameters of the target AI model are greater than or equal to a third threshold value.

31. The apparatus of claim 29, wherein The processing module is specifically configured to: update the target AI model using the first update manner in a case where the model structure of the target AI model belongs to a first AI model structure set; and / or update the target AI model using the second update manner in a case where the model structure of the target AI model belongs to a second AI model structure set.

32. The apparatus of any one of claims 26 to 28, wherein The receiving module is further configured to receive second information or third information from the second communication device before the wireless communication device updates the target AI model using the first update manner or the second update manner. The second information is used to indicate that the wireless communication device uses the first update mode or the second update mode to update the target AI model. The third information is used to indicate that the wireless communication device autonomously determines the first update mode or the second update mode to update the target AI model.

33. The apparatus of any one of claims 26-28, wherein, The processing module is specifically configured to: If the wireless communication device supports at least one of AI model transmission, AI model update, AI model transmission based on air interface, and AI model transmission based on air interface and third generation partnership project (3GPP) signaling, the wireless communication device uses the first update mode to update the target AI model by default, or uses the second update mode to update the target AI model by default, or uses the first update mode or the first update mode to update the target AI model by itself, or uses the first update mode or the second update mode to update the target AI model according to an indication of the second communication device; or If the wireless communication device supports the first update mode, the wireless communication device uses the first update mode to update the target AI model, or uses the first update mode to update the target AI model by default, or uses the first update mode or the first update mode to update the target AI model by itself, or uses the first update mode or the second update mode to update the target AI model according to an indication of the second communication device; or If the wireless communication device supports the first update mode and does not support the second update mode, the wireless communication device uses the first update mode to update the target AI model; or If the wireless communication device supports the second update mode, the wireless communication device uses the second update mode to update the target AI model, or uses the second update mode to update the target AI model by default, or uses the first update mode or the first update mode to update the target AI model by itself, or uses the first update mode or the second update mode to update the target AI model according to an indication of the second communication device; or If the wireless communication device supports the second update mode and does not support the first update mode, the wireless communication device uses the second update mode to update the target AI model; or If the wireless communication device supports the first update mode and the second update mode, the wireless communication device uses the first update mode to update the target AI model by default, or uses the second update mode to update the target AI model by default, or uses the first update mode or the first update mode to update the target AI model by itself, or uses the first update mode or the second update mode to update the target AI model according to an indication of the second communication device.

34. The apparatus of claim 26 or 27, wherein, The processing module is specifically configured to: if the second communication device indicates to use the first update manner or the second update manner to update the target AI model, using the update manner indicated by the second communication device to update the target AI model, and the wireless communication apparatus does not feed back the used update manner to the second communication device; or, if the second communication device indicates to use the first update manner or the second update manner to update the target AI model, using the first update manner or the second update manner to update the target AI model by itself, and the wireless communication apparatus feeds back the used update manner to the second communication device; or, if the second communication device indicates that the wireless communication apparatus uses the first update manner or the second update manner to update the target AI model by itself, using the first update manner or the second update manner to update the target AI model by itself, and the wireless communication apparatus feeds back the used update manner to the second communication device; or, using the first update manner or the second update manner to update the target AI model based on a protocol agreement, and the wireless communication apparatus does not feed back the used update manner to the second communication device; or, if the protocol agrees to use the first update manner or the second update manner to update the target AI model, using the first update manner or the second update manner to update the target AI model by itself, and the wireless communication apparatus feeds back the used update manner to the second communication device; or, using the first update manner or the second update manner to update the target AI model by itself, and the wireless communication apparatus feeds back the used update manner to the second communication device.

35. The apparatus of any one of claims 26-34, wherein, the wireless communication apparatus further comprises: a sending module configured to send capability information to the second communication device; wherein the capability information comprises at least one of: the wireless communication apparatus supports at least one of: AI model transmission, AI model update, AI model transmission based on air interface, AI model transmission based on air interface and 3GPP signaling; the wireless communication apparatus supports the first update manner; the wireless communication apparatus supports the first update manner and does not support the second update manner; the wireless communication apparatus supports the second update manner; the wireless communication apparatus supports the second update manner and does not support the first update manner; the wireless communication apparatus supports the first update manner and the second update manner.

36. A wireless communication apparatus, comprising: a sending module configured to send information related to a target artificial intelligence (AI) model to a first communication device; wherein the information related to the target AI model comprises at least one of: model parameters of the target AI model, model structure of the target AI model; a receiving module configured to receive first information from the first communication device; wherein the first information comprises at least one of: an update time delay of the target AI model; a timestamp of completion of the target AI model update; a timestamp of availability of the target AI model; first indication information, wherein the first indication information indicates that the target AI model has completed update, or the first indication information indicates that the target AI model is available for use; wherein the update manner of the target AI model is a first update manner or a second update manner; wherein the first update manner is that the first communication device processes the target AI model before or after the target AI model is updated or used; or the first update manner is that the first communication device directly updates or uses the target AI model; wherein the second update manner is that the first communication device processes the target AI model through a third communication device before or after the target AI model is updated or used; or the second update manner is that the first communication device does not directly update or use the target AI model.

37. The apparatus of claim 36, wherein, the first information further comprises second indication information; wherein the second indication information indicates that the first communication device updates the target AI model using the first update manner, or the second indication information indicates that the first communication device does not update the target AI model using the second update manner, or the second indication information indicates that the first communication device updates the target AI model using the second update manner, and the second indication information indicates that the first communication device does not update the target AI model using the first update manner.

38. The apparatus of claim 36 or 37, wherein, the update manner of the target AI model is determined based on model parameters of the target AI model; or the update manner of the target AI model is determined based on a model structure of the target AI model; or the update manner of the target AI model is a default update manner used by the first communication device; wherein the model parameters of the target AI model comprise at least one of the following: a storage size of the target AI model, a computational complexity of the target AI model, a number of operations of the target AI model, a time required for transmission of model parameters of the target AI model, and a number of data packets required for transmission of model parameters of the target AI model; wherein the model structure of the target AI model comprises at least one of the following: a number of layers of the target AI model, a number of neurons of each layer of the target AI model, a connection manner between each neuron of the target AI model, and an activation function of the target AI model.

39. The apparatus of claim 36 or 37, wherein, before the wireless communication device receives the first information from the first communication device, the sending module is further configured to send second information or third information to the first communication device; wherein the second information indicates that the first communication device updates the target AI model using the first update manner or the second update manner. The third information is used to indicate that the first communication device autonomously uses the first update manner or the second update manner to update the target AI model.

40. The apparatus of any one of claims 36-39, wherein, The receiving module is further configured to receive capability information from the first communication device. The capability information includes at least one of the following: The first communication device supports at least one of the following: AI model transmission, AI model update, air interface-based AI model transmission, and air interface and 3GPP signaling-based AI model transmission. The first communication device supports the first update manner. The first communication device supports the first update manner and does not support the second update manner. The first communication device supports the second update manner. The first communication device supports the second update manner and does not support the first update manner. The first communication device supports the first update manner and the second update manner. 41.A first communication device, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement steps of the wireless communication method according to any one of claims 1 to 13. 42.A second communication device, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement steps of the wireless communication method according to any one of claims 14 to 25. 43.A readable storage medium, the readable storage medium storing programs or instructions, and the programs or instructions, when executed by a processor, implement steps of the wireless communication method according to any one of claims 1 to 13, or implement steps of the wireless communication method according to any one of claims 14 to 25.

Images